From d1498ed8df1b4c140898158540801c9838251976 Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Fri, 7 Dec 2018 18:20:56 +0000 Subject: [PATCH] [CostModel][X86] Fix overcounting arithmetic cost in illegal types in getArithmeticReductionCost/getMinMaxReductionCost We were overcounting the number of arithmetic operations needed at each level before we reach a legal type. We were using the full vector type for that level, but we are going to split the input vector at that level in half. So the effective arithmetic operation cost at that level is half the width. So for example on 8i32 on an sse target. Were were calculating the cost of an 8i32 op which is likely 2 for basic integer. Then after the loop we count 2 more v4i32 ops. For a total arith cost of 4. But if you look at the assembly there would only be 3 arithmetic ops. There are still more bugs in this code that I'm going to work on next. The non pairwise code shouldn't count extract subvectors in the loop. There are no extracts, the types are split in registers. For pairwise we need to use 2 two src permute shuffles. Differential Revision: https://reviews.llvm.org/D55397 llvm-svn: 348621 --- llvm/include/llvm/CodeGen/BasicTTIImpl.h | 9 +- .../CostModel/X86/reduce-add-widen.ll | 94 ++-- .../test/Analysis/CostModel/X86/reduce-add.ll | 94 ++-- .../CostModel/X86/reduce-and-widen.ll | 144 +++--- .../test/Analysis/CostModel/X86/reduce-and.ll | 144 +++--- .../CostModel/X86/reduce-mul-widen.ll | 120 ++--- .../test/Analysis/CostModel/X86/reduce-mul.ll | 124 ++--- .../Analysis/CostModel/X86/reduce-or-widen.ll | 144 +++--- llvm/test/Analysis/CostModel/X86/reduce-or.ll | 144 +++--- .../CostModel/X86/reduce-smax-widen.ll | 70 +-- .../Analysis/CostModel/X86/reduce-smax.ll | 70 +-- .../CostModel/X86/reduce-smin-widen.ll | 70 +-- .../Analysis/CostModel/X86/reduce-smin.ll | 70 +-- .../CostModel/X86/reduce-umax-widen.ll | 70 +-- .../Analysis/CostModel/X86/reduce-umax.ll | 70 +-- .../CostModel/X86/reduce-umin-widen.ll | 70 +-- .../Analysis/CostModel/X86/reduce-umin.ll | 70 +-- .../CostModel/X86/reduce-xor-widen.ll | 144 +++--- .../test/Analysis/CostModel/X86/reduce-xor.ll | 144 +++--- llvm/test/Analysis/CostModel/X86/reduction.ll | 130 ++---- .../SLPVectorizer/X86/horizontal-minmax.ll | 423 ++++-------------- .../SLPVectorizer/X86/reduction_unrolled.ll | 4 +- 22 files changed, 1053 insertions(+), 1369 deletions(-) diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h index ffd9b76da4dc..7b389f8fa440 100644 --- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h +++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h @@ -1431,7 +1431,7 @@ public: ShuffleCost += (IsPairwise + 1) * ConcreteTTI->getShuffleCost(TTI::SK_ExtractSubvector, Ty, NumVecElts, SubTy); - ArithCost += ConcreteTTI->getArithmeticInstrCost(Opcode, Ty); + ArithCost += ConcreteTTI->getArithmeticInstrCost(Opcode, SubTy); Ty = SubTy; ++LongVectorCount; } @@ -1476,16 +1476,17 @@ public: while (NumVecElts > MVTLen) { NumVecElts /= 2; Type *SubTy = VectorType::get(ScalarTy, NumVecElts); + CondTy = VectorType::get(ScalarCondTy, NumVecElts); + // Assume the pairwise shuffles add a cost. ShuffleCost += (IsPairwise + 1) * ConcreteTTI->getShuffleCost(TTI::SK_ExtractSubvector, Ty, NumVecElts, SubTy); MinMaxCost += - ConcreteTTI->getCmpSelInstrCost(CmpOpcode, Ty, CondTy, nullptr) + - ConcreteTTI->getCmpSelInstrCost(Instruction::Select, Ty, CondTy, + ConcreteTTI->getCmpSelInstrCost(CmpOpcode, SubTy, CondTy, nullptr) + + ConcreteTTI->getCmpSelInstrCost(Instruction::Select, SubTy, CondTy, nullptr); Ty = SubTy; - CondTy = VectorType::get(ScalarCondTy, NumVecElts); ++LongVectorCount; } // The minimal length of the vector is limited by the real length of vector diff --git a/llvm/test/Analysis/CostModel/X86/reduce-add-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-add-widen.ll index 35a492df626f..5230511b11ea 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-add-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-add-widen.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -46,7 +46,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) @@ -61,17 +61,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -95,7 +95,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) @@ -111,18 +111,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -139,8 +139,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -148,8 +148,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -157,8 +157,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -167,7 +167,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -175,8 +175,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) @@ -194,9 +194,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -204,9 +204,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -214,9 +214,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -225,8 +225,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 85 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -235,8 +235,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -245,8 +245,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -256,7 +256,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -265,8 +265,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-add.ll b/llvm/test/Analysis/CostModel/X86/reduce-add.ll index fedb0b31c3c0..bb7622333859 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-add.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-add.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -46,7 +46,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef) @@ -61,17 +61,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -95,7 +95,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef) @@ -111,18 +111,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -139,8 +139,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -148,8 +148,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -157,8 +157,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -167,7 +167,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -175,8 +175,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef) @@ -194,9 +194,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -204,9 +204,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -214,9 +214,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -225,8 +225,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 85 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -235,8 +235,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -245,8 +245,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -256,7 +256,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -265,8 +265,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-and-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-and-widen.ll index 320b43f19886..6f9db08b7076 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-and-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-and-widen.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-and.ll b/llvm/test/Analysis/CostModel/X86/reduce-and.ll index e86e126a1e9e..35caf489c004 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-and.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-and.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-mul-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-mul-widen.ll index d31781b3ca85..1331f78f0b4b 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-mul-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-mul-widen.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 122 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 149 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 95 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i64' @@ -46,7 +46,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i64' @@ -54,7 +54,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) @@ -69,41 +69,41 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' ; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -111,7 +111,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) @@ -127,27 +127,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -164,8 +164,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -173,8 +173,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -191,8 +191,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 113 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 161 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 257 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 101 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 173 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 171 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 223 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 327 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 197 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 249 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -251,8 +251,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 123 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 157 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -261,8 +261,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 115 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -281,8 +281,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-mul.ll b/llvm/test/Analysis/CostModel/X86/reduce-mul.ll index d1d40d35fec8..68f94cdfec99 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-mul.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-mul.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 122 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 149 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 95 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 67 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i64' @@ -46,7 +46,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i64' @@ -54,7 +54,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef) @@ -69,41 +69,41 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i32' @@ -111,7 +111,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i32' @@ -119,7 +119,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i32' @@ -127,7 +127,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef) @@ -143,27 +143,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -171,8 +171,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -180,8 +180,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -189,8 +189,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -199,7 +199,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -207,8 +207,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef) @@ -226,9 +226,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 113 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 161 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 257 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 101 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 173 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -236,9 +236,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -246,9 +246,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -257,8 +257,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 171 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 223 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 327 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 197 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 249 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -267,8 +267,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 123 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 157 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -277,8 +277,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -288,7 +288,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 115 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -297,8 +297,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-or-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-or-widen.ll index 48aa3a4d533f..8cdef17e438a 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-or-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-or-widen.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-or.ll b/llvm/test/Analysis/CostModel/X86/reduce-or.ll index 0752a5ed638f..ed0ef620482c 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-or.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-or.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-smax-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-smax-widen.ll index bc5b5e6392ab..602ee12d9951 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-smax-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-smax-widen.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smax.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smax.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smax.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smax.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smax.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smax.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-smax.ll b/llvm/test/Analysis/CostModel/X86/reduce-smax.ll index 1d48e1b9189d..6e5fc7bea7a9 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-smax.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-smax.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smax.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smax.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smax.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smax.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smax.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smax.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smax.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smax.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smax.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smax.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smax.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smax.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smax.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smax.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smax.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smax.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smax.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smax.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smax.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smax.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smax.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smax.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smax.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smax.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smax.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-smin-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-smin-widen.ll index 7f2057e2190c..67fba3f1ce7f 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-smin-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-smin-widen.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smin.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smin.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smin.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smin.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -126,17 +126,17 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-LABEL: 'reduce_i16' ; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -151,8 +151,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -176,7 +176,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -201,9 +201,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -211,9 +211,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -221,9 +221,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -232,8 +232,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -263,7 +263,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-smin.ll b/llvm/test/Analysis/CostModel/X86/reduce-smin.ll index be8d7fc9a353..86e557a750ac 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-smin.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-smin.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.smin.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.smin.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.smin.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.smin.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.smin.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smin.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smin.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.smin.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.smin.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.smin.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.smin.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.smin.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smin.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.smin.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.smin.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.smin.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.smin.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.smin.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.smin.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.smin.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.smin.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.smin.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.smin.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.smin.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.smin.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-umax-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-umax-widen.ll index 3d5547370ca7..d95c4a48e232 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-umax-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-umax-widen.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umax.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umax.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umax.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umax.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umax.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umax.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-umax.ll b/llvm/test/Analysis/CostModel/X86/reduce-umax.ll index e3147e1db1fc..a6889000f3aa 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-umax.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-umax.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umax.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umax.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umax.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umax.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umax.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umax.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umax.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umax.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umax.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umax.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umax.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umax.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umax.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umax.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umax.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umax.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umax.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umax.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umax.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umax.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umax.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umax.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umax.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-umin-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-umin-widen.ll index ea5884f23114..85715113fddb 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-umin-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-umin-widen.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umin.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umin.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umin.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umin.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umin.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umin.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-umin.ll b/llvm/test/Analysis/CostModel/X86/reduce-umin.ll index afd00c08f186..22a063ac5d33 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-umin.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-umin.ll @@ -12,17 +12,17 @@ define i32 @reduce_i64(i32 %arg) { ; SSE2-LABEL: 'reduce_i64' ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i64' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i64' @@ -37,8 +37,8 @@ define i32 @reduce_i64(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.umin.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.umin.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.umin.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.umin.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.umin.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' @@ -69,17 +69,17 @@ define i32 @reduce_i32(i32 %arg) { ; SSE2-LABEL: 'reduce_i32' ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umin.i32.v2i32(<2 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umin.i32.v4i32(<4 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i32' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.umin.i32.v2i32(<2 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.umin.i32.v4i32(<4 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.umin.i32.v8i32(<8 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.umin.i32.v16i32(<16 x i32> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.umin.i32.v32i32(<32 x i32> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i32' @@ -127,18 +127,18 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umin.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.umin.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 41 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' @@ -155,8 +155,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.umin.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 86 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 71 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -183,7 +183,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.umin.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.umin.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.umin.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.umin.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -210,9 +210,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -220,9 +220,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -230,9 +230,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.umin.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -241,8 +241,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.umin.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 99 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -272,7 +272,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.umin.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.umin.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.umin.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.umin.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' diff --git a/llvm/test/Analysis/CostModel/X86/reduce-xor-widen.ll b/llvm/test/Analysis/CostModel/X86/reduce-xor-widen.ll index 2f0b222e1a2d..ff0d276c2213 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-xor-widen.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-xor-widen.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduce-xor.ll b/llvm/test/Analysis/CostModel/X86/reduce-xor.ll index 39f280f5c8f2..8f7dfdd02fb6 100644 --- a/llvm/test/Analysis/CostModel/X86/reduce-xor.ll +++ b/llvm/test/Analysis/CostModel/X86/reduce-xor.ll @@ -12,25 +12,25 @@ define i32 @reduce_i64(i32 %arg) { ; SSE-LABEL: 'reduce_i64' ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i64' @@ -38,7 +38,7 @@ define i32 @reduce_i64(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef) @@ -53,25 +53,25 @@ define i32 @reduce_i32(i32 %arg) { ; SSE-LABEL: 'reduce_i32' ; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; SSE-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'reduce_i32' @@ -79,7 +79,7 @@ define i32 @reduce_i32(i32 %arg) { ; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef) -; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) +; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef) ; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef) @@ -95,27 +95,27 @@ define i32 @reduce_i16(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i16' @@ -123,8 +123,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i16' @@ -132,8 +132,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i16' @@ -141,8 +141,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i16' @@ -151,7 +151,7 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i16' @@ -159,8 +159,8 @@ define i32 @reduce_i16(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef) @@ -178,9 +178,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i8' @@ -188,9 +188,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i8' @@ -198,9 +198,9 @@ define i32 @reduce_i8(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i8' @@ -209,8 +209,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i8' @@ -219,8 +219,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i8' @@ -229,8 +229,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i8' @@ -240,7 +240,7 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i8' @@ -249,8 +249,8 @@ define i32 @reduce_i8(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef) @@ -270,9 +270,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSE2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSSE3-LABEL: 'reduce_i1' @@ -281,9 +281,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSSE3-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; SSE42-LABEL: 'reduce_i1' @@ -292,9 +292,9 @@ define i32 @reduce_i1(i32 %arg) { ; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX1-LABEL: 'reduce_i1' @@ -304,8 +304,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'reduce_i1' @@ -315,8 +315,8 @@ define i32 @reduce_i1(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'reduce_i1' @@ -325,9 +325,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512F-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512F-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX512F-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512BW-LABEL: 'reduce_i1' @@ -338,7 +338,7 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512BW-NEXT: Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512BW-NEXT: Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512DQ-LABEL: 'reduce_i1' @@ -347,9 +347,9 @@ define i32 @reduce_i1(i32 %arg) { ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) -; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef) +; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef) ; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef) diff --git a/llvm/test/Analysis/CostModel/X86/reduction.ll b/llvm/test/Analysis/CostModel/X86/reduction.ll index f379714509d5..59a1acc04a84 100644 --- a/llvm/test/Analysis/CostModel/X86/reduction.ll +++ b/llvm/test/Analysis/CostModel/X86/reduction.ll @@ -52,35 +52,15 @@ define fastcc float @reduction_cost_float(<4 x float> %rdx) { } define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) { -; SSE2-LABEL: 'reduction_cost_int' -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 -; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 -; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r -; -; SSSE3-LABEL: 'reduction_cost_int' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r -; -; SSE42-LABEL: 'reduction_cost_int' -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 -; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 -; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; SSE-LABEL: 'reduction_cost_int' +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 +; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; AVX1-LABEL: 'reduction_cost_int' ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> @@ -376,7 +356,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1 ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf ; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 -; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSSE3-LABEL: 'no_pairwise_reduction4double' @@ -384,7 +364,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf ; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSE42-LABEL: 'no_pairwise_reduction4double' @@ -428,7 +408,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 -; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSSE3-LABEL: 'no_pairwise_reduction8float' @@ -438,7 +418,7 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSE42-LABEL: 'no_pairwise_reduction8float' @@ -557,29 +537,13 @@ define fastcc i32 @no_pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) { } define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { -; SSE2-LABEL: 'no_pairwise_reduction4i64' -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 -; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 -; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r -; -; SSSE3-LABEL: 'no_pairwise_reduction4i64' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r -; -; SSE42-LABEL: 'no_pairwise_reduction4i64' -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 -; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r +; SSE-LABEL: 'no_pairwise_reduction4i64' +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 +; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; ; AVX1-LABEL: 'no_pairwise_reduction4i64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> @@ -659,35 +623,15 @@ define fastcc i16 @no_pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) { } define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { -; SSE2-LABEL: 'no_pairwise_reduction8i32' -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 -; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 -; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r -; -; SSSE3-LABEL: 'no_pairwise_reduction8i32' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r -; -; SSE42-LABEL: 'no_pairwise_reduction8i32' -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 -; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 -; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; SSE-LABEL: 'no_pairwise_reduction8i32' +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 +; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; AVX1-LABEL: 'no_pairwise_reduction8i32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> @@ -817,7 +761,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 -; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSSE3-LABEL: 'pairwise_reduction4double' @@ -827,7 +771,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSE42-LABEL: 'pairwise_reduction4double' @@ -882,7 +826,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 -; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSSE3-LABEL: 'pairwise_reduction8float' @@ -895,7 +839,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSE42-LABEL: 'pairwise_reduction8float' @@ -1048,7 +992,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 -; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; ; SSSE3-LABEL: 'pairwise_reduction4i64' @@ -1058,7 +1002,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; ; SSE42-LABEL: 'pairwise_reduction4i64' @@ -1180,7 +1124,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1 -; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 +; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; SSSE3-LABEL: 'pairwise_reduction8i32' @@ -1193,7 +1137,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; SSE42-LABEL: 'pairwise_reduction8i32' diff --git a/llvm/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll b/llvm/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll index 84bc85f8e985..2bdb10136497 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll @@ -716,348 +716,87 @@ define float @maxf16(float) { } define float @maxf32(float) { -; SSE-LABEL: @maxf32( -; SSE-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16 -; SSE-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4 -; SSE-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]] -; SSE-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]] -; SSE-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8 -; SSE-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]] -; SSE-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]] -; SSE-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4 -; SSE-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]] -; SSE-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]] -; SSE-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16 -; SSE-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]] -; SSE-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]] -; SSE-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4 -; SSE-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]] -; SSE-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]] -; SSE-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8 -; SSE-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]] -; SSE-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]] -; SSE-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4 -; SSE-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]] -; SSE-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]] -; SSE-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16 -; SSE-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]] -; SSE-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]] -; SSE-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4 -; SSE-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]] -; SSE-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]] -; SSE-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8 -; SSE-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]] -; SSE-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]] -; SSE-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4 -; SSE-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]] -; SSE-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]] -; SSE-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16 -; SSE-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]] -; SSE-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]] -; SSE-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4 -; SSE-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]] -; SSE-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]] -; SSE-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8 -; SSE-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]] -; SSE-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]] -; SSE-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4 -; SSE-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]] -; SSE-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]] -; SSE-NEXT: [[TMP48:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16 -; SSE-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP47]], [[TMP48]] -; SSE-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP47]], float [[TMP48]] -; SSE-NEXT: [[TMP51:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4 -; SSE-NEXT: [[TMP52:%.*]] = fcmp fast ogt float [[TMP50]], [[TMP51]] -; SSE-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], float [[TMP50]], float [[TMP51]] -; SSE-NEXT: [[TMP54:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8 -; SSE-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP53]], [[TMP54]] -; SSE-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP53]], float [[TMP54]] -; SSE-NEXT: [[TMP57:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4 -; SSE-NEXT: [[TMP58:%.*]] = fcmp fast ogt float [[TMP56]], [[TMP57]] -; SSE-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], float [[TMP56]], float [[TMP57]] -; SSE-NEXT: [[TMP60:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16 -; SSE-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP59]], [[TMP60]] -; SSE-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP59]], float [[TMP60]] -; SSE-NEXT: [[TMP63:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4 -; SSE-NEXT: [[TMP64:%.*]] = fcmp fast ogt float [[TMP62]], [[TMP63]] -; SSE-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], float [[TMP62]], float [[TMP63]] -; SSE-NEXT: [[TMP66:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8 -; SSE-NEXT: [[TMP67:%.*]] = fcmp fast ogt float [[TMP65]], [[TMP66]] -; SSE-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], float [[TMP65]], float [[TMP66]] -; SSE-NEXT: [[TMP69:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4 -; SSE-NEXT: [[TMP70:%.*]] = fcmp fast ogt float [[TMP68]], [[TMP69]] -; SSE-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], float [[TMP68]], float [[TMP69]] -; SSE-NEXT: [[TMP72:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16 -; SSE-NEXT: [[TMP73:%.*]] = fcmp fast ogt float [[TMP71]], [[TMP72]] -; SSE-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], float [[TMP71]], float [[TMP72]] -; SSE-NEXT: [[TMP75:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4 -; SSE-NEXT: [[TMP76:%.*]] = fcmp fast ogt float [[TMP74]], [[TMP75]] -; SSE-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], float [[TMP74]], float [[TMP75]] -; SSE-NEXT: [[TMP78:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8 -; SSE-NEXT: [[TMP79:%.*]] = fcmp fast ogt float [[TMP77]], [[TMP78]] -; SSE-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], float [[TMP77]], float [[TMP78]] -; SSE-NEXT: [[TMP81:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4 -; SSE-NEXT: [[TMP82:%.*]] = fcmp fast ogt float [[TMP80]], [[TMP81]] -; SSE-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], float [[TMP80]], float [[TMP81]] -; SSE-NEXT: [[TMP84:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16 -; SSE-NEXT: [[TMP85:%.*]] = fcmp fast ogt float [[TMP83]], [[TMP84]] -; SSE-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], float [[TMP83]], float [[TMP84]] -; SSE-NEXT: [[TMP87:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4 -; SSE-NEXT: [[TMP88:%.*]] = fcmp fast ogt float [[TMP86]], [[TMP87]] -; SSE-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], float [[TMP86]], float [[TMP87]] -; SSE-NEXT: [[TMP90:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8 -; SSE-NEXT: [[TMP91:%.*]] = fcmp fast ogt float [[TMP89]], [[TMP90]] -; SSE-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], float [[TMP89]], float [[TMP90]] -; SSE-NEXT: [[TMP93:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4 -; SSE-NEXT: [[TMP94:%.*]] = fcmp fast ogt float [[TMP92]], [[TMP93]] -; SSE-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], float [[TMP92]], float [[TMP93]] -; SSE-NEXT: ret float [[TMP95]] -; -; AVX-LABEL: @maxf32( -; AVX-NEXT: [[TMP2:%.*]] = load <32 x float>, <32 x float>* bitcast ([32 x float]* @arr1 to <32 x float>*), align 16 -; AVX-NEXT: [[TMP3:%.*]] = fcmp fast ogt float undef, undef -; AVX-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], float undef, float undef -; AVX-NEXT: [[TMP5:%.*]] = fcmp fast ogt float [[TMP4]], undef -; AVX-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float undef -; AVX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP6]], undef -; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP6]], float undef -; AVX-NEXT: [[TMP9:%.*]] = fcmp fast ogt float [[TMP8]], undef -; AVX-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP8]], float undef -; AVX-NEXT: [[TMP11:%.*]] = fcmp fast ogt float [[TMP10]], undef -; AVX-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], float [[TMP10]], float undef -; AVX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP12]], undef -; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP12]], float undef -; AVX-NEXT: [[TMP15:%.*]] = fcmp fast ogt float [[TMP14]], undef -; AVX-NEXT: [[TMP16:%.*]] = select i1 [[TMP15]], float [[TMP14]], float undef -; AVX-NEXT: [[TMP17:%.*]] = fcmp fast ogt float [[TMP16]], undef -; AVX-NEXT: [[TMP18:%.*]] = select i1 [[TMP17]], float [[TMP16]], float undef -; AVX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP18]], undef -; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP18]], float undef -; AVX-NEXT: [[TMP21:%.*]] = fcmp fast ogt float [[TMP20]], undef -; AVX-NEXT: [[TMP22:%.*]] = select i1 [[TMP21]], float [[TMP20]], float undef -; AVX-NEXT: [[TMP23:%.*]] = fcmp fast ogt float [[TMP22]], undef -; AVX-NEXT: [[TMP24:%.*]] = select i1 [[TMP23]], float [[TMP22]], float undef -; AVX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP24]], undef -; AVX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP24]], float undef -; AVX-NEXT: [[TMP27:%.*]] = fcmp fast ogt float [[TMP26]], undef -; AVX-NEXT: [[TMP28:%.*]] = select i1 [[TMP27]], float [[TMP26]], float undef -; AVX-NEXT: [[TMP29:%.*]] = fcmp fast ogt float [[TMP28]], undef -; AVX-NEXT: [[TMP30:%.*]] = select i1 [[TMP29]], float [[TMP28]], float undef -; AVX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP30]], undef -; AVX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP30]], float undef -; AVX-NEXT: [[TMP33:%.*]] = fcmp fast ogt float [[TMP32]], undef -; AVX-NEXT: [[TMP34:%.*]] = select i1 [[TMP33]], float [[TMP32]], float undef -; AVX-NEXT: [[TMP35:%.*]] = fcmp fast ogt float [[TMP34]], undef -; AVX-NEXT: [[TMP36:%.*]] = select i1 [[TMP35]], float [[TMP34]], float undef -; AVX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP36]], undef -; AVX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP36]], float undef -; AVX-NEXT: [[TMP39:%.*]] = fcmp fast ogt float [[TMP38]], undef -; AVX-NEXT: [[TMP40:%.*]] = select i1 [[TMP39]], float [[TMP38]], float undef -; AVX-NEXT: [[TMP41:%.*]] = fcmp fast ogt float [[TMP40]], undef -; AVX-NEXT: [[TMP42:%.*]] = select i1 [[TMP41]], float [[TMP40]], float undef -; AVX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP42]], undef -; AVX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP42]], float undef -; AVX-NEXT: [[TMP45:%.*]] = fcmp fast ogt float [[TMP44]], undef -; AVX-NEXT: [[TMP46:%.*]] = select i1 [[TMP45]], float [[TMP44]], float undef -; AVX-NEXT: [[TMP47:%.*]] = fcmp fast ogt float [[TMP46]], undef -; AVX-NEXT: [[TMP48:%.*]] = select i1 [[TMP47]], float [[TMP46]], float undef -; AVX-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP48]], undef -; AVX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP48]], float undef -; AVX-NEXT: [[TMP51:%.*]] = fcmp fast ogt float [[TMP50]], undef -; AVX-NEXT: [[TMP52:%.*]] = select i1 [[TMP51]], float [[TMP50]], float undef -; AVX-NEXT: [[TMP53:%.*]] = fcmp fast ogt float [[TMP52]], undef -; AVX-NEXT: [[TMP54:%.*]] = select i1 [[TMP53]], float [[TMP52]], float undef -; AVX-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP54]], undef -; AVX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP54]], float undef -; AVX-NEXT: [[TMP57:%.*]] = fcmp fast ogt float [[TMP56]], undef -; AVX-NEXT: [[TMP58:%.*]] = select i1 [[TMP57]], float [[TMP56]], float undef -; AVX-NEXT: [[TMP59:%.*]] = fcmp fast ogt float [[TMP58]], undef -; AVX-NEXT: [[TMP60:%.*]] = select i1 [[TMP59]], float [[TMP58]], float undef -; AVX-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP60]], undef -; AVX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP60]], float undef -; AVX-NEXT: [[TMP63:%.*]] = fcmp fast ogt float [[TMP62]], undef -; AVX-NEXT: [[RDX_SHUF:%.*]] = shufflevector <32 x float> [[TMP2]], <32 x float> undef, <32 x i32> -; AVX-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast ogt <32 x float> [[TMP2]], [[RDX_SHUF]] -; AVX-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP]], <32 x float> [[TMP2]], <32 x float> [[RDX_SHUF]] -; AVX-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> undef, <32 x i32> -; AVX-NEXT: [[RDX_MINMAX_CMP2:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT]], [[RDX_SHUF1]] -; AVX-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP2]], <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> [[RDX_SHUF1]] -; AVX-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> undef, <32 x i32> -; AVX-NEXT: [[RDX_MINMAX_CMP5:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT3]], [[RDX_SHUF4]] -; AVX-NEXT: [[RDX_MINMAX_SELECT6:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP5]], <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> [[RDX_SHUF4]] -; AVX-NEXT: [[RDX_SHUF7:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> undef, <32 x i32> -; AVX-NEXT: [[RDX_MINMAX_CMP8:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT6]], [[RDX_SHUF7]] -; AVX-NEXT: [[RDX_MINMAX_SELECT9:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP8]], <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> [[RDX_SHUF7]] -; AVX-NEXT: [[RDX_SHUF10:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> undef, <32 x i32> -; AVX-NEXT: [[RDX_MINMAX_CMP11:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT9]], [[RDX_SHUF10]] -; AVX-NEXT: [[RDX_MINMAX_SELECT12:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP11]], <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> [[RDX_SHUF10]] -; AVX-NEXT: [[TMP64:%.*]] = extractelement <32 x float> [[RDX_MINMAX_SELECT12]], i32 0 -; AVX-NEXT: [[TMP65:%.*]] = select i1 [[TMP63]], float [[TMP62]], float undef -; AVX-NEXT: ret float [[TMP64]] -; -; AVX2-LABEL: @maxf32( -; AVX2-NEXT: [[TMP2:%.*]] = load <32 x float>, <32 x float>* bitcast ([32 x float]* @arr1 to <32 x float>*), align 16 -; AVX2-NEXT: [[TMP3:%.*]] = fcmp fast ogt float undef, undef -; AVX2-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], float undef, float undef -; AVX2-NEXT: [[TMP5:%.*]] = fcmp fast ogt float [[TMP4]], undef -; AVX2-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float undef -; AVX2-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP6]], undef -; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP6]], float undef -; AVX2-NEXT: [[TMP9:%.*]] = fcmp fast ogt float [[TMP8]], undef -; AVX2-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP8]], float undef -; AVX2-NEXT: [[TMP11:%.*]] = fcmp fast ogt float [[TMP10]], undef -; AVX2-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], float [[TMP10]], float undef -; AVX2-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP12]], undef -; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP12]], float undef -; AVX2-NEXT: [[TMP15:%.*]] = fcmp fast ogt float [[TMP14]], undef -; AVX2-NEXT: [[TMP16:%.*]] = select i1 [[TMP15]], float [[TMP14]], float undef -; AVX2-NEXT: [[TMP17:%.*]] = fcmp fast ogt float [[TMP16]], undef -; AVX2-NEXT: [[TMP18:%.*]] = select i1 [[TMP17]], float [[TMP16]], float undef -; AVX2-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP18]], undef -; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP18]], float undef -; AVX2-NEXT: [[TMP21:%.*]] = fcmp fast ogt float [[TMP20]], undef -; AVX2-NEXT: [[TMP22:%.*]] = select i1 [[TMP21]], float [[TMP20]], float undef -; AVX2-NEXT: [[TMP23:%.*]] = fcmp fast ogt float [[TMP22]], undef -; AVX2-NEXT: [[TMP24:%.*]] = select i1 [[TMP23]], float [[TMP22]], float undef -; AVX2-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP24]], undef -; AVX2-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP24]], float undef -; AVX2-NEXT: [[TMP27:%.*]] = fcmp fast ogt float [[TMP26]], undef -; AVX2-NEXT: [[TMP28:%.*]] = select i1 [[TMP27]], float [[TMP26]], float undef -; AVX2-NEXT: [[TMP29:%.*]] = fcmp fast ogt float [[TMP28]], undef -; AVX2-NEXT: [[TMP30:%.*]] = select i1 [[TMP29]], float [[TMP28]], float undef -; AVX2-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP30]], undef -; AVX2-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP30]], float undef -; AVX2-NEXT: [[TMP33:%.*]] = fcmp fast ogt float [[TMP32]], undef -; AVX2-NEXT: [[TMP34:%.*]] = select i1 [[TMP33]], float [[TMP32]], float undef -; AVX2-NEXT: [[TMP35:%.*]] = fcmp fast ogt float [[TMP34]], undef -; AVX2-NEXT: [[TMP36:%.*]] = select i1 [[TMP35]], float [[TMP34]], float undef -; AVX2-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP36]], undef -; AVX2-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP36]], float undef -; AVX2-NEXT: [[TMP39:%.*]] = fcmp fast ogt float [[TMP38]], undef -; AVX2-NEXT: [[TMP40:%.*]] = select i1 [[TMP39]], float [[TMP38]], float undef -; AVX2-NEXT: [[TMP41:%.*]] = fcmp fast ogt float [[TMP40]], undef -; AVX2-NEXT: [[TMP42:%.*]] = select i1 [[TMP41]], float [[TMP40]], float undef -; AVX2-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP42]], undef -; AVX2-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP42]], float undef -; AVX2-NEXT: [[TMP45:%.*]] = fcmp fast ogt float [[TMP44]], undef -; AVX2-NEXT: [[TMP46:%.*]] = select i1 [[TMP45]], float [[TMP44]], float undef -; AVX2-NEXT: [[TMP47:%.*]] = fcmp fast ogt float [[TMP46]], undef -; AVX2-NEXT: [[TMP48:%.*]] = select i1 [[TMP47]], float [[TMP46]], float undef -; AVX2-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP48]], undef -; AVX2-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP48]], float undef -; AVX2-NEXT: [[TMP51:%.*]] = fcmp fast ogt float [[TMP50]], undef -; AVX2-NEXT: [[TMP52:%.*]] = select i1 [[TMP51]], float [[TMP50]], float undef -; AVX2-NEXT: [[TMP53:%.*]] = fcmp fast ogt float [[TMP52]], undef -; AVX2-NEXT: [[TMP54:%.*]] = select i1 [[TMP53]], float [[TMP52]], float undef -; AVX2-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP54]], undef -; AVX2-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP54]], float undef -; AVX2-NEXT: [[TMP57:%.*]] = fcmp fast ogt float [[TMP56]], undef -; AVX2-NEXT: [[TMP58:%.*]] = select i1 [[TMP57]], float [[TMP56]], float undef -; AVX2-NEXT: [[TMP59:%.*]] = fcmp fast ogt float [[TMP58]], undef -; AVX2-NEXT: [[TMP60:%.*]] = select i1 [[TMP59]], float [[TMP58]], float undef -; AVX2-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP60]], undef -; AVX2-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP60]], float undef -; AVX2-NEXT: [[TMP63:%.*]] = fcmp fast ogt float [[TMP62]], undef -; AVX2-NEXT: [[RDX_SHUF:%.*]] = shufflevector <32 x float> [[TMP2]], <32 x float> undef, <32 x i32> -; AVX2-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast ogt <32 x float> [[TMP2]], [[RDX_SHUF]] -; AVX2-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP]], <32 x float> [[TMP2]], <32 x float> [[RDX_SHUF]] -; AVX2-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> undef, <32 x i32> -; AVX2-NEXT: [[RDX_MINMAX_CMP2:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT]], [[RDX_SHUF1]] -; AVX2-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP2]], <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> [[RDX_SHUF1]] -; AVX2-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> undef, <32 x i32> -; AVX2-NEXT: [[RDX_MINMAX_CMP5:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT3]], [[RDX_SHUF4]] -; AVX2-NEXT: [[RDX_MINMAX_SELECT6:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP5]], <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> [[RDX_SHUF4]] -; AVX2-NEXT: [[RDX_SHUF7:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> undef, <32 x i32> -; AVX2-NEXT: [[RDX_MINMAX_CMP8:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT6]], [[RDX_SHUF7]] -; AVX2-NEXT: [[RDX_MINMAX_SELECT9:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP8]], <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> [[RDX_SHUF7]] -; AVX2-NEXT: [[RDX_SHUF10:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> undef, <32 x i32> -; AVX2-NEXT: [[RDX_MINMAX_CMP11:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT9]], [[RDX_SHUF10]] -; AVX2-NEXT: [[RDX_MINMAX_SELECT12:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP11]], <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> [[RDX_SHUF10]] -; AVX2-NEXT: [[TMP64:%.*]] = extractelement <32 x float> [[RDX_MINMAX_SELECT12]], i32 0 -; AVX2-NEXT: [[TMP65:%.*]] = select i1 [[TMP63]], float [[TMP62]], float undef -; AVX2-NEXT: ret float [[TMP64]] -; -; SKX-LABEL: @maxf32( -; SKX-NEXT: [[TMP2:%.*]] = load <32 x float>, <32 x float>* bitcast ([32 x float]* @arr1 to <32 x float>*), align 16 -; SKX-NEXT: [[TMP3:%.*]] = fcmp fast ogt float undef, undef -; SKX-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], float undef, float undef -; SKX-NEXT: [[TMP5:%.*]] = fcmp fast ogt float [[TMP4]], undef -; SKX-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float undef -; SKX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP6]], undef -; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP6]], float undef -; SKX-NEXT: [[TMP9:%.*]] = fcmp fast ogt float [[TMP8]], undef -; SKX-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP8]], float undef -; SKX-NEXT: [[TMP11:%.*]] = fcmp fast ogt float [[TMP10]], undef -; SKX-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], float [[TMP10]], float undef -; SKX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP12]], undef -; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP12]], float undef -; SKX-NEXT: [[TMP15:%.*]] = fcmp fast ogt float [[TMP14]], undef -; SKX-NEXT: [[TMP16:%.*]] = select i1 [[TMP15]], float [[TMP14]], float undef -; SKX-NEXT: [[TMP17:%.*]] = fcmp fast ogt float [[TMP16]], undef -; SKX-NEXT: [[TMP18:%.*]] = select i1 [[TMP17]], float [[TMP16]], float undef -; SKX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP18]], undef -; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP18]], float undef -; SKX-NEXT: [[TMP21:%.*]] = fcmp fast ogt float [[TMP20]], undef -; SKX-NEXT: [[TMP22:%.*]] = select i1 [[TMP21]], float [[TMP20]], float undef -; SKX-NEXT: [[TMP23:%.*]] = fcmp fast ogt float [[TMP22]], undef -; SKX-NEXT: [[TMP24:%.*]] = select i1 [[TMP23]], float [[TMP22]], float undef -; SKX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP24]], undef -; SKX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP24]], float undef -; SKX-NEXT: [[TMP27:%.*]] = fcmp fast ogt float [[TMP26]], undef -; SKX-NEXT: [[TMP28:%.*]] = select i1 [[TMP27]], float [[TMP26]], float undef -; SKX-NEXT: [[TMP29:%.*]] = fcmp fast ogt float [[TMP28]], undef -; SKX-NEXT: [[TMP30:%.*]] = select i1 [[TMP29]], float [[TMP28]], float undef -; SKX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP30]], undef -; SKX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP30]], float undef -; SKX-NEXT: [[TMP33:%.*]] = fcmp fast ogt float [[TMP32]], undef -; SKX-NEXT: [[TMP34:%.*]] = select i1 [[TMP33]], float [[TMP32]], float undef -; SKX-NEXT: [[TMP35:%.*]] = fcmp fast ogt float [[TMP34]], undef -; SKX-NEXT: [[TMP36:%.*]] = select i1 [[TMP35]], float [[TMP34]], float undef -; SKX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP36]], undef -; SKX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP36]], float undef -; SKX-NEXT: [[TMP39:%.*]] = fcmp fast ogt float [[TMP38]], undef -; SKX-NEXT: [[TMP40:%.*]] = select i1 [[TMP39]], float [[TMP38]], float undef -; SKX-NEXT: [[TMP41:%.*]] = fcmp fast ogt float [[TMP40]], undef -; SKX-NEXT: [[TMP42:%.*]] = select i1 [[TMP41]], float [[TMP40]], float undef -; SKX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP42]], undef -; SKX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP42]], float undef -; SKX-NEXT: [[TMP45:%.*]] = fcmp fast ogt float [[TMP44]], undef -; SKX-NEXT: [[TMP46:%.*]] = select i1 [[TMP45]], float [[TMP44]], float undef -; SKX-NEXT: [[TMP47:%.*]] = fcmp fast ogt float [[TMP46]], undef -; SKX-NEXT: [[TMP48:%.*]] = select i1 [[TMP47]], float [[TMP46]], float undef -; SKX-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP48]], undef -; SKX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP48]], float undef -; SKX-NEXT: [[TMP51:%.*]] = fcmp fast ogt float [[TMP50]], undef -; SKX-NEXT: [[TMP52:%.*]] = select i1 [[TMP51]], float [[TMP50]], float undef -; SKX-NEXT: [[TMP53:%.*]] = fcmp fast ogt float [[TMP52]], undef -; SKX-NEXT: [[TMP54:%.*]] = select i1 [[TMP53]], float [[TMP52]], float undef -; SKX-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP54]], undef -; SKX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP54]], float undef -; SKX-NEXT: [[TMP57:%.*]] = fcmp fast ogt float [[TMP56]], undef -; SKX-NEXT: [[TMP58:%.*]] = select i1 [[TMP57]], float [[TMP56]], float undef -; SKX-NEXT: [[TMP59:%.*]] = fcmp fast ogt float [[TMP58]], undef -; SKX-NEXT: [[TMP60:%.*]] = select i1 [[TMP59]], float [[TMP58]], float undef -; SKX-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP60]], undef -; SKX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP60]], float undef -; SKX-NEXT: [[TMP63:%.*]] = fcmp fast ogt float [[TMP62]], undef -; SKX-NEXT: [[RDX_SHUF:%.*]] = shufflevector <32 x float> [[TMP2]], <32 x float> undef, <32 x i32> -; SKX-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast ogt <32 x float> [[TMP2]], [[RDX_SHUF]] -; SKX-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP]], <32 x float> [[TMP2]], <32 x float> [[RDX_SHUF]] -; SKX-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> undef, <32 x i32> -; SKX-NEXT: [[RDX_MINMAX_CMP2:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT]], [[RDX_SHUF1]] -; SKX-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP2]], <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> [[RDX_SHUF1]] -; SKX-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> undef, <32 x i32> -; SKX-NEXT: [[RDX_MINMAX_CMP5:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT3]], [[RDX_SHUF4]] -; SKX-NEXT: [[RDX_MINMAX_SELECT6:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP5]], <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> [[RDX_SHUF4]] -; SKX-NEXT: [[RDX_SHUF7:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> undef, <32 x i32> -; SKX-NEXT: [[RDX_MINMAX_CMP8:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT6]], [[RDX_SHUF7]] -; SKX-NEXT: [[RDX_MINMAX_SELECT9:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP8]], <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> [[RDX_SHUF7]] -; SKX-NEXT: [[RDX_SHUF10:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> undef, <32 x i32> -; SKX-NEXT: [[RDX_MINMAX_CMP11:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT9]], [[RDX_SHUF10]] -; SKX-NEXT: [[RDX_MINMAX_SELECT12:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP11]], <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> [[RDX_SHUF10]] -; SKX-NEXT: [[TMP64:%.*]] = extractelement <32 x float> [[RDX_MINMAX_SELECT12]], i32 0 -; SKX-NEXT: [[TMP65:%.*]] = select i1 [[TMP63]], float [[TMP62]], float undef -; SKX-NEXT: ret float [[TMP64]] +; CHECK-LABEL: @maxf32( +; CHECK-NEXT: [[TMP2:%.*]] = load <32 x float>, <32 x float>* bitcast ([32 x float]* @arr1 to <32 x float>*), align 16 +; CHECK-NEXT: [[TMP3:%.*]] = fcmp fast ogt float undef, undef +; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], float undef, float undef +; CHECK-NEXT: [[TMP5:%.*]] = fcmp fast ogt float [[TMP4]], undef +; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], float [[TMP4]], float undef +; CHECK-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP6]], undef +; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP6]], float undef +; CHECK-NEXT: [[TMP9:%.*]] = fcmp fast ogt float [[TMP8]], undef +; CHECK-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP8]], float undef +; CHECK-NEXT: [[TMP11:%.*]] = fcmp fast ogt float [[TMP10]], undef +; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], float [[TMP10]], float undef +; CHECK-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP12]], undef +; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP12]], float undef +; CHECK-NEXT: [[TMP15:%.*]] = fcmp fast ogt float [[TMP14]], undef +; CHECK-NEXT: [[TMP16:%.*]] = select i1 [[TMP15]], float [[TMP14]], float undef +; CHECK-NEXT: [[TMP17:%.*]] = fcmp fast ogt float [[TMP16]], undef +; CHECK-NEXT: [[TMP18:%.*]] = select i1 [[TMP17]], float [[TMP16]], float undef +; CHECK-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP18]], undef +; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP18]], float undef +; CHECK-NEXT: [[TMP21:%.*]] = fcmp fast ogt float [[TMP20]], undef +; CHECK-NEXT: [[TMP22:%.*]] = select i1 [[TMP21]], float [[TMP20]], float undef +; CHECK-NEXT: [[TMP23:%.*]] = fcmp fast ogt float [[TMP22]], undef +; CHECK-NEXT: [[TMP24:%.*]] = select i1 [[TMP23]], float [[TMP22]], float undef +; CHECK-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP24]], undef +; CHECK-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP24]], float undef +; CHECK-NEXT: [[TMP27:%.*]] = fcmp fast ogt float [[TMP26]], undef +; CHECK-NEXT: [[TMP28:%.*]] = select i1 [[TMP27]], float [[TMP26]], float undef +; CHECK-NEXT: [[TMP29:%.*]] = fcmp fast ogt float [[TMP28]], undef +; CHECK-NEXT: [[TMP30:%.*]] = select i1 [[TMP29]], float [[TMP28]], float undef +; CHECK-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP30]], undef +; CHECK-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP30]], float undef +; CHECK-NEXT: [[TMP33:%.*]] = fcmp fast ogt float [[TMP32]], undef +; CHECK-NEXT: [[TMP34:%.*]] = select i1 [[TMP33]], float [[TMP32]], float undef +; CHECK-NEXT: [[TMP35:%.*]] = fcmp fast ogt float [[TMP34]], undef +; CHECK-NEXT: [[TMP36:%.*]] = select i1 [[TMP35]], float [[TMP34]], float undef +; CHECK-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP36]], undef +; CHECK-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP36]], float undef +; CHECK-NEXT: [[TMP39:%.*]] = fcmp fast ogt float [[TMP38]], undef +; CHECK-NEXT: [[TMP40:%.*]] = select i1 [[TMP39]], float [[TMP38]], float undef +; CHECK-NEXT: [[TMP41:%.*]] = fcmp fast ogt float [[TMP40]], undef +; CHECK-NEXT: [[TMP42:%.*]] = select i1 [[TMP41]], float [[TMP40]], float undef +; CHECK-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP42]], undef +; CHECK-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP42]], float undef +; CHECK-NEXT: [[TMP45:%.*]] = fcmp fast ogt float [[TMP44]], undef +; CHECK-NEXT: [[TMP46:%.*]] = select i1 [[TMP45]], float [[TMP44]], float undef +; CHECK-NEXT: [[TMP47:%.*]] = fcmp fast ogt float [[TMP46]], undef +; CHECK-NEXT: [[TMP48:%.*]] = select i1 [[TMP47]], float [[TMP46]], float undef +; CHECK-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP48]], undef +; CHECK-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP48]], float undef +; CHECK-NEXT: [[TMP51:%.*]] = fcmp fast ogt float [[TMP50]], undef +; CHECK-NEXT: [[TMP52:%.*]] = select i1 [[TMP51]], float [[TMP50]], float undef +; CHECK-NEXT: [[TMP53:%.*]] = fcmp fast ogt float [[TMP52]], undef +; CHECK-NEXT: [[TMP54:%.*]] = select i1 [[TMP53]], float [[TMP52]], float undef +; CHECK-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP54]], undef +; CHECK-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP54]], float undef +; CHECK-NEXT: [[TMP57:%.*]] = fcmp fast ogt float [[TMP56]], undef +; CHECK-NEXT: [[TMP58:%.*]] = select i1 [[TMP57]], float [[TMP56]], float undef +; CHECK-NEXT: [[TMP59:%.*]] = fcmp fast ogt float [[TMP58]], undef +; CHECK-NEXT: [[TMP60:%.*]] = select i1 [[TMP59]], float [[TMP58]], float undef +; CHECK-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP60]], undef +; CHECK-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP60]], float undef +; CHECK-NEXT: [[TMP63:%.*]] = fcmp fast ogt float [[TMP62]], undef +; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <32 x float> [[TMP2]], <32 x float> undef, <32 x i32> +; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast ogt <32 x float> [[TMP2]], [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP]], <32 x float> [[TMP2]], <32 x float> [[RDX_SHUF]] +; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> undef, <32 x i32> +; CHECK-NEXT: [[RDX_MINMAX_CMP2:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT]], [[RDX_SHUF1]] +; CHECK-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP2]], <32 x float> [[RDX_MINMAX_SELECT]], <32 x float> [[RDX_SHUF1]] +; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> undef, <32 x i32> +; CHECK-NEXT: [[RDX_MINMAX_CMP5:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT3]], [[RDX_SHUF4]] +; CHECK-NEXT: [[RDX_MINMAX_SELECT6:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP5]], <32 x float> [[RDX_MINMAX_SELECT3]], <32 x float> [[RDX_SHUF4]] +; CHECK-NEXT: [[RDX_SHUF7:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> undef, <32 x i32> +; CHECK-NEXT: [[RDX_MINMAX_CMP8:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT6]], [[RDX_SHUF7]] +; CHECK-NEXT: [[RDX_MINMAX_SELECT9:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP8]], <32 x float> [[RDX_MINMAX_SELECT6]], <32 x float> [[RDX_SHUF7]] +; CHECK-NEXT: [[RDX_SHUF10:%.*]] = shufflevector <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> undef, <32 x i32> +; CHECK-NEXT: [[RDX_MINMAX_CMP11:%.*]] = fcmp fast ogt <32 x float> [[RDX_MINMAX_SELECT9]], [[RDX_SHUF10]] +; CHECK-NEXT: [[RDX_MINMAX_SELECT12:%.*]] = select <32 x i1> [[RDX_MINMAX_CMP11]], <32 x float> [[RDX_MINMAX_SELECT9]], <32 x float> [[RDX_SHUF10]] +; CHECK-NEXT: [[TMP64:%.*]] = extractelement <32 x float> [[RDX_MINMAX_SELECT12]], i32 0 +; CHECK-NEXT: [[TMP65:%.*]] = select i1 [[TMP63]], float [[TMP62]], float undef +; CHECK-NEXT: ret float [[TMP64]] ; %2 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16 %3 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4 diff --git a/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll b/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll index d40515fb709a..4dd40876a70a 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll @@ -12,8 +12,8 @@ ; Vector cost is 5, Scalar cost is 7 ; AVX: Adding cost -2 for reduction that starts with %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction) -; Vector cost is 7, Scalar cost is 7 -; SSE: Adding cost 0 for reduction that starts with %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction) +; Vector cost is 6, Scalar cost is 7 +; SSE: Adding cost -1 for reduction that starts with %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction) define i32 @test_add(i32* nocapture readonly %p) { ; CHECK-LABEL: @test_add( ; CHECK-NEXT: entry: