maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[Cost]Canonicalize the cost for logical or/and reductions. 

The generic cost of logical or/and reductions should be cost of bitcast
<ReduxWidth x i1> to iReduxWidth + cmp eq|ne iReduxWidth.

Differential Revision: https://reviews.llvm.org/D97961
This commit is contained in:
Alexey Bataev 2021-03-02 10:53:49 -08:00
parent 5737010a79
commit 14ae0cf0f5
14 changed files with 136 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/include/llvm/CodeGen/BasicTTIImpl.h
View File

@ -1895,6 +1895,22 @@ public:
TTI::TargetCostKind CostKind) {
Type *ScalarTy = Ty->getElementType();
unsigned NumVecElts = cast<FixedVectorType>(Ty)->getNumElements();
if ((Opcode == Instruction::Or || Opcode == Instruction::And) &&
ScalarTy == IntegerType::getInt1Ty(Ty->getContext()) &&
NumVecElts >= 2) {
// Or reduction for i1 is represented as:
// %val = bitcast <ReduxWidth x i1> to iReduxWidth
// %res = cmp ne iReduxWidth %val, 0
// And reduction for i1 is represented as:
// %val = bitcast <ReduxWidth x i1> to iReduxWidth
// %res = cmp eq iReduxWidth %val, 11111
Type *ValTy = IntegerType::get(Ty->getContext(), NumVecElts);
return thisT()->getCastInstrCost(Instruction::BitCast, ValTy, Ty,
TTI::CastContextHint::None, CostKind) +
thisT()->getCmpSelInstrCost(Instruction::ICmp, ValTy,
CmpInst::makeCmpResultType(ValTy),
CmpInst::BAD_ICMP_PREDICATE, CostKind);
}
unsigned NumReduxLevels = Log2_32(NumVecElts);
unsigned ArithCost = 0;
unsigned ShuffleCost = 0;

7
llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
View File

@ -750,8 +750,13 @@ int SystemZTTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
}
}
else if (ST->hasVector()) {
// Vector to scalar cast.
auto *SrcVecTy = cast<FixedVectorType>(Src);
auto *DstVecTy = cast<FixedVectorType>(Dst);
auto *DstVecTy = dyn_cast<FixedVectorType>(Dst);
if (!DstVecTy) {
// TODO: tune vector-to-scalar cast.
return BaseT::getCastInstrCost(Opcode, Dst, Src, CCH, CostKind, I);
}
unsigned VF = SrcVecTy->getNumElements();
unsigned NumDstVectors = getNumVectorRegs(Dst);
unsigned NumSrcVectors = getNumVectorRegs(Src);

12
llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
View File

@ -5,12 +5,12 @@ define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)

12
llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
View File

@ -5,12 +5,12 @@ define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/ARM/reduce-and.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 385 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/ARM/reduce-or.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 682 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1070 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 385 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/PowerPC/reduce-and.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 386 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/PowerPC/reduce-or.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 386 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)

35
llvm/test/Analysis/CostModel/RISCV/reduce-and.ll
View File

@ -1,18 +1,29 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s
; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s
; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV32
; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV64
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; RISCV32-LABEL: 'reduce_i1'
; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; RISCV64-LABEL: 'reduce_i1'
; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
%V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)

35
llvm/test/Analysis/CostModel/RISCV/reduce-or.ll
View File

@ -1,18 +1,29 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s
; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s
; RUN: opt < %s -mtriple=riscv32 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV32
; RUN: opt < %s -mtriple=riscv64 -cost-model -cost-kind=throughput -analyze | FileCheck %s --check-prefix=RISCV64
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 190 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 382 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
; RISCV32-LABEL: 'reduce_i1'
; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; RISCV32-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
; RISCV64-LABEL: 'reduce_i1'
; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; RISCV64-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
%V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)

14
llvm/test/Analysis/CostModel/SystemZ/reduce-and.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.and.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 258 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.and.v1i1(<1 x i1> undef)

14
llvm/test/Analysis/CostModel/SystemZ/reduce-or.ll
View File

@ -4,13 +4,13 @@
define i32 @reduce_i1(i32 %arg) {
; CHECK-LABEL: 'reduce_i1'
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 258 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)