RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[CostModel][X86] Improve v2f32 fadd reduction cost

Browse Source 
This was being reported as a similar cost to v4f32 when its a lot cheaper (just a shufps+addps).
This commit is contained in:
Simon Pilgrim 2021-04-23 16:55:59 +01:00
parent b71b6a828f
commit 982c79726f
2 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -3380,6 +3380,7 @@ X86TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
static const CostTblEntry SSE2CostTblNoPairWise[] = {
{ ISD::FADD, MVT::v2f64, 2 },
{ ISD::FADD, MVT::v2f32, 2 },
{ ISD::FADD, MVT::v4f32, 4 },
{ ISD::ADD, MVT::v2i64, 2 }, // The data reported by the IACA tool is "1.6".
{ ISD::ADD, MVT::v2i32, 2 }, // FIXME: chosen to be less than v4i32

14
test/Analysis/CostModel/X86/reduce-fadd.ll
View File

@ -77,7 +77,7 @@ 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 0 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 4 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 2 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 4 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 6 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 10 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -86,7 +86,7 @@ define void @reduce_f32(float %arg) {
;
; SSSE3-LABEL: 'reduce_f32'
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 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 4 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 2 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 4 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 6 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 10 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -95,7 +95,7 @@ define void @reduce_f32(float %arg) {
;
; SSE41-LABEL: 'reduce_f32'
; SSE41-NEXT: Cost Model: Found an estimated cost of 0 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 4 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 2 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 4 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 6 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 10 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -104,7 +104,7 @@ define void @reduce_f32(float %arg) {
;
; SSE42-LABEL: 'reduce_f32'
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 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 4 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 2 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 4 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 5 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 7 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -113,7 +113,7 @@ define void @reduce_f32(float %arg) {
;
; AVX1-LABEL: 'reduce_f32'
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 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 2 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 3 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 4 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 6 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -122,7 +122,7 @@ define void @reduce_f32(float %arg) {
;
; AVX2-LABEL: 'reduce_f32'
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 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 2 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 3 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 4 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 5 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
@ -131,7 +131,7 @@ define void @reduce_f32(float %arg) {
;
; AVX512-LABEL: 'reduce_f32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 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 2 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 3 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 4 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 8 for instruction: %V16 = call float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)