[llvm] 7664a0d - [X86] Improve accuracy of cost for v16i64->v16i8 truncate with avx512.

[Craig Topper via llvm-commits]

Author: Craig Topper
Date: 2020-04-24T19:13:55-07:00
New Revision: 7664a0d28285ee3d51f05fa0bf5891bf193087b3

URL: https://github.com/llvm/llvm-project/commit/7664a0d28285ee3d51f05fa0bf5891bf193087b3
DIFF: https://github.com/llvm/llvm-project/commit/7664a0d28285ee3d51f05fa0bf5891bf193087b3.diff

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

The 2 vpmovqds are only 1 uop each.

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/X86/trunc.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 868e88914460..0e077623e129 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -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
 

diff  --git a/llvm/test/Analysis/CostModel/X86/trunc.ll b/llvm/test/Analysis/CostModel/X86/trunc.ll
index 02a5e043679b..c90a93e25a8f 100644
--- a/llvm/test/Analysis/CostModel/X86/trunc.ll
+++ b/llvm/test/Analysis/CostModel/X86/trunc.ll
@@ -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>