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

[X86] Improve accuracy of cost for v16i64->v16i8 truncate with avx512. 

The 2 vpmovqds are only 1 uop each.
This commit is contained in:
Craig Topper 2020-04-24 18:56:33 -07:00
parent 485cf19651
commit 7664a0d282
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86TargetTransformInfo.cpp
View File

@ -1406,7 +1406,7 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
{ ISD::TRUNCATE, MVT::v8i8, MVT::v8i64, 2 },
{ ISD::TRUNCATE, MVT::v8i16, MVT::v8i64, 1 },
{ ISD::TRUNCATE, MVT::v8i32, MVT::v8i64, 1 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i64, 7 },// 2*vpmovqd+concat+vpmovdb
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i64, 5 },// 2*vpmovqd+concat+vpmovdb
{ ISD::TRUNCATE, MVT::v32i8, MVT::v32i16, 9 }, // FIXME

4
llvm/test/Analysis/CostModel/X86/trunc.ll
View File

@ -270,7 +270,7 @@ define i32 @trunc_vXi8() {
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = trunc <2 x i64> undef to <2 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = trunc <4 x i64> undef to <4 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i64 = trunc <8 x i64> undef to <8 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i64 = trunc <16 x i64> undef to <16 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16i64 = trunc <16 x i64> undef to <16 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V32i64 = trunc <32 x i64> undef to <32 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64i64 = trunc <64 x i64> undef to <64 x i8>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8>
@ -291,7 +291,7 @@ define i32 @trunc_vXi8() {
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = trunc <2 x i64> undef to <2 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = trunc <4 x i64> undef to <4 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i64 = trunc <8 x i64> undef to <8 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i64 = trunc <16 x i64> undef to <16 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16i64 = trunc <16 x i64> undef to <16 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V32i64 = trunc <32 x i64> undef to <32 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64i64 = trunc <64 x i64> undef to <64 x i8>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2i32 = trunc <2 x i32> undef to <2 x i8>