From 3538ee763d13a26515a224ddeb3a51a5af143e38 Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Sun, 26 Sep 2021 13:43:46 +0100 Subject: [PATCH] [CostModel][X86] Improve AVX1/AVX2 v16i32->v16i16/v16i8 truncation costs (PR51972) Based off worst case btver2 (AVX1) and haswell (AVX2) llvm-mca reports --- .../lib/Target/X86/X86TargetTransformInfo.cpp | 4 +++ llvm/test/Analysis/CostModel/X86/arith-fix.ll | 24 +++++++-------- .../Analysis/CostModel/X86/arith-overflow.ll | 24 +++++++-------- llvm/test/Analysis/CostModel/X86/cast.ll | 8 ++--- .../CostModel/X86/min-legal-vector-width.ll | 4 +-- llvm/test/Analysis/CostModel/X86/trunc.ll | 30 +++++++++---------- 6 files changed, 49 insertions(+), 45 deletions(-) diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index 52e8238771eb..8b40df5dff3d 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -1940,6 +1940,8 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, { ISD::TRUNCATE, MVT::v8i1, MVT::v8i32, 2 }, + { ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, 4 }, + { ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 4 }, { ISD::TRUNCATE, MVT::v16i8, MVT::v8i16, 1 }, { ISD::TRUNCATE, MVT::v16i8, MVT::v4i32, 1 }, { ISD::TRUNCATE, MVT::v16i8, MVT::v2i64, 1 }, @@ -2015,6 +2017,8 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, { ISD::TRUNCATE, MVT::v8i1, MVT::v8i64, 9 }, { ISD::TRUNCATE, MVT::v16i1, MVT::v16i64, 11 }, + { ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, 6 }, + { ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 6 }, { ISD::TRUNCATE, MVT::v16i8, MVT::v16i16, 2 }, // and+extract+packuswb { ISD::TRUNCATE, MVT::v16i8, MVT::v8i32, 5 }, { ISD::TRUNCATE, MVT::v8i16, MVT::v8i32, 5 }, diff --git a/llvm/test/Analysis/CostModel/X86/arith-fix.ll b/llvm/test/Analysis/CostModel/X86/arith-fix.ll index fcb2b90de81c..f9aaa427751a 100644 --- a/llvm/test/Analysis/CostModel/X86/arith-fix.ll +++ b/llvm/test/Analysis/CostModel/X86/arith-fix.ll @@ -81,8 +81,8 @@ define i32 @smul(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; AVX1-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) @@ -100,8 +100,8 @@ define i32 @smul(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) @@ -214,8 +214,8 @@ define i32 @smul(i32 %arg) { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.smul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.smul.fix.i16(i16 undef, i16 undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.smul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.smul.fix.i8(i8 undef, i8 undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) @@ -315,8 +315,8 @@ define i32 @umul(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; AVX1-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; AVX1-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; AVX1-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) @@ -334,8 +334,8 @@ define i32 @umul(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; AVX2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) @@ -448,8 +448,8 @@ define i32 @umul(i32 %arg) { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 114 for instruction: %V16I32 = call <16 x i32> @llvm.umul.fix.v16i32(<16 x i32> undef, <16 x i32> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call i16 @llvm.umul.fix.i16(i16 undef, i16 undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.umul.fix.v8i16(<8 x i16> undef, <8 x i16> undef, i32 3) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 106 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V16I16 = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> undef, <16 x i16> undef, i32 3) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V32I16 = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> undef, <32 x i16> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call i8 @llvm.umul.fix.i8(i8 undef, i8 undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> undef, <16 x i8> undef, i32 3) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V32I8 = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> undef, <32 x i8> undef, i32 3) diff --git a/llvm/test/Analysis/CostModel/X86/arith-overflow.ll b/llvm/test/Analysis/CostModel/X86/arith-overflow.ll index 280a672bb3ac..b5cdd7d4ecf6 100644 --- a/llvm/test/Analysis/CostModel/X86/arith-overflow.ll +++ b/llvm/test/Analysis/CostModel/X86/arith-overflow.ll @@ -1037,8 +1037,8 @@ define i32 @smul(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) @@ -1056,8 +1056,8 @@ define i32 @smul(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) @@ -1170,8 +1170,8 @@ define i32 @smul(i32 %arg) { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) @@ -1275,8 +1275,8 @@ define i32 @umul(i32 %arg) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; AVX1-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; AVX1-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; AVX1-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) @@ -1294,8 +1294,8 @@ define i32 @umul(i32 %arg) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; AVX2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; AVX2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; AVX2-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) @@ -1408,8 +1408,8 @@ define i32 @umul(i32 %arg) { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; BTVER2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; BTVER2-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; BTVER2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) diff --git a/llvm/test/Analysis/CostModel/X86/cast.ll b/llvm/test/Analysis/CostModel/X86/cast.ll index 087fef47db6b..ae66aaaa2807 100644 --- a/llvm/test/Analysis/CostModel/X86/cast.ll +++ b/llvm/test/Analysis/CostModel/X86/cast.ll @@ -167,8 +167,8 @@ define i32 @zext_sext(<8 x i1> %in) { ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %G = trunc <8 x i64> undef to <8 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16> -; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8> +; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16> +; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'zext_sext' @@ -197,8 +197,8 @@ define i32 @zext_sext(<8 x i1> %in) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %G = trunc <8 x i64> undef to <8 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16> -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512F-LABEL: 'zext_sext' diff --git a/llvm/test/Analysis/CostModel/X86/min-legal-vector-width.ll b/llvm/test/Analysis/CostModel/X86/min-legal-vector-width.ll index 46293ab0634e..9b7f37493d62 100644 --- a/llvm/test/Analysis/CostModel/X86/min-legal-vector-width.ll +++ b/llvm/test/Analysis/CostModel/X86/min-legal-vector-width.ll @@ -218,8 +218,8 @@ define void @trunc256() "min-legal-vector-width"="256" { ; VEC256-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %A = trunc <8 x i64> undef to <8 x i32> ; VEC256-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %B = trunc <8 x i64> undef to <8 x i16> ; VEC256-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C = trunc <8 x i64> undef to <8 x i8> -; VEC256-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %D = trunc <16 x i32> undef to <16 x i16> -; VEC256-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %E = trunc <16 x i32> undef to <16 x i8> +; VEC256-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D = trunc <16 x i32> undef to <16 x i16> +; VEC256-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %E = trunc <16 x i32> undef to <16 x i8> ; VEC256-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %F = trunc <32 x i16> undef to <32 x i8> ; VEC256-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; diff --git a/llvm/test/Analysis/CostModel/X86/trunc.ll b/llvm/test/Analysis/CostModel/X86/trunc.ll index b169e9a9ed1b..a49bd3bb29c0 100644 --- a/llvm/test/Analysis/CostModel/X86/trunc.ll +++ b/llvm/test/Analysis/CostModel/X86/trunc.ll @@ -117,8 +117,8 @@ define i32 @trunc_vXi16() { ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16> ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16> ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16> -; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> -; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> +; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> +; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX2-LABEL: 'trunc_vXi16' @@ -132,8 +132,8 @@ define i32 @trunc_vXi16() { ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16> ; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16> -; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> -; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; AVX512-LABEL: 'trunc_vXi16' @@ -162,8 +162,8 @@ define i32 @trunc_vXi16() { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i16> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i16> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i16> -; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> -; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> +; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i16> +; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i16> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; %i64 = trunc i64 undef to i16 @@ -267,9 +267,9 @@ define i32 @trunc_vXi8() { ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8> -; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> -; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> -; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> +; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> +; AVX1-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> +; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8 ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8> ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8> @@ -291,9 +291,9 @@ define i32 @trunc_vXi8() { ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8> -; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> -; AVX2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> -; AVX2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> +; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> +; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8 ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8> @@ -363,9 +363,9 @@ define i32 @trunc_vXi8() { ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = trunc <4 x i32> undef to <4 x i8> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8i32 = trunc <8 x i32> undef to <8 x i8> -; BTVER2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> -; BTVER2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> -; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> +; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16i32 = trunc <16 x i32> undef to <16 x i8> +; BTVER2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32i32 = trunc <32 x i32> undef to <32 x i8> +; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V64i32 = trunc <64 x i32> undef to <64 x i8> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %i16 = trunc i16 undef to i8 ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = trunc <2 x i16> undef to <2 x i8> ; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = trunc <4 x i16> undef to <4 x i8>