[llvm] 77c5e6b - [Analysis] Fix getOrderedReductionCost to call target's getArithmeticInstrCost implementation
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 26 09:16:00 PDT 2021
Author: Simon Pilgrim
Date: 2021-07-26T17:15:43+01:00
New Revision: 77c5e6ba900a167909873d2364d55b6a19df8994
URL: https://github.com/llvm/llvm-project/commit/77c5e6ba900a167909873d2364d55b6a19df8994
DIFF: https://github.com/llvm/llvm-project/commit/77c5e6ba900a167909873d2364d55b6a19df8994.diff
LOG: [Analysis] Fix getOrderedReductionCost to call target's getArithmeticInstrCost implementation
The getOrderedReductionCost implementation introduced in D105432 calls the CRTP base version getArithmeticInstrCost instead of the redirecting to the target version.
Differential Revision: https://reviews.llvm.org/D106795
Added:
Modified:
llvm/include/llvm/CodeGen/BasicTTIImpl.h
llvm/test/Analysis/CostModel/X86/reduce-fadd.ll
llvm/test/Analysis/CostModel/X86/reduce-fmul.ll
Removed:
################################################################################
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 3fd6be5dc8b3f..e3b834ec42c3c 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -2091,8 +2091,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
auto *VTy = cast<FixedVectorType>(Ty);
InstructionCost ExtractCost =
getScalarizationOverhead(VTy, /*Insert=*/false, /*Extract=*/true);
- InstructionCost ArithCost =
- getArithmeticInstrCost(Opcode, VTy->getElementType(), CostKind);
+ InstructionCost ArithCost = thisT()->getArithmeticInstrCost(
+ Opcode, VTy->getElementType(), CostKind);
ArithCost *= VTy->getNumElements();
return ExtractCost + ArithCost;
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-fadd.ll b/llvm/test/Analysis/CostModel/X86/reduce-fadd.ll
index 50ee1a5abb94e..3b811e82018d1 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-fadd.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-fadd.ll
@@ -11,59 +11,59 @@
define void @reduce_f64(double %arg) {
; SSE2-LABEL: 'reduce_f64'
-; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSSE3-LABEL: 'reduce_f64'
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE41-LABEL: 'reduce_f64'
-; SSE41-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; SSE41-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'reduce_f64'
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'reduce_f64'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'reduce_f64'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'reduce_f64'
-; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fadd.v2f64(double %arg, <2 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fadd.v4f64(double %arg, <4 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V1 = call double @llvm.vector.reduce.fadd.v1f64(double %arg, <1 x double> undef)
@@ -76,66 +76,66 @@ define void @reduce_f64(double %arg) {
define void @reduce_f32(float %arg) {
; SSE2-LABEL: 'reduce_f32'
-; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; SSE2-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSSE3-LABEL: 'reduce_f32'
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; SSSE3-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE41-LABEL: 'reduce_f32'
-; SSE41-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; SSE41-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; SSE41-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; SSE41-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'reduce_f32'
-; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'reduce_f32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'reduce_f32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'reduce_f32'
-; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fadd.v2f32(float %arg, <2 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fadd.v4f32(float %arg, <4 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fadd.v8f32(float %arg, <8 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V32 = call float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V1 = call float @llvm.vector.reduce.fadd.v1f32(float %arg, <1 x float> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/reduce-fmul.ll b/llvm/test/Analysis/CostModel/X86/reduce-fmul.ll
index f27cdbf5f42dd..c18bc41469659 100644
--- a/llvm/test/Analysis/CostModel/X86/reduce-fmul.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduce-fmul.ll
@@ -35,11 +35,11 @@ define void @reduce_f64(double %arg) {
; SSE41-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'reduce_f64'
-; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'reduce_f64'
@@ -51,19 +51,19 @@ define void @reduce_f64(double %arg) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'reduce_f64'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'reduce_f64'
-; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call double @llvm.vector.reduce.fmul.v2f64(double %arg, <2 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call double @llvm.vector.reduce.fmul.v4f64(double %arg, <4 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V1 = call double @llvm.vector.reduce.fmul.v1f64(double %arg, <1 x double> undef)
@@ -103,39 +103,39 @@ define void @reduce_f32(float %arg) {
; SSE41-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'reduce_f32'
-; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
-; SSE42-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'reduce_f32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
-; AVX1-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'reduce_f32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
-; AVX2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'reduce_f32'
-; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
-; AVX512-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call float @llvm.vector.reduce.fmul.v2f32(float %arg, <2 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4 = call float @llvm.vector.reduce.fmul.v4f32(float %arg, <4 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8 = call float @llvm.vector.reduce.fmul.v8f32(float %arg, <8 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16 = call float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %V32 = call float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V1 = call float @llvm.vector.reduce.fmul.v1f32(float %arg, <1 x float> undef)
More information about the llvm-commits
mailing list