[X86] Use a more realisitic cost for truncate v16i64->v16i8 with avx512f.

Still not great and we could probably codegen this better, but
11 was clearly ridiculous.

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index da776be..c7df5ae 100644 (file)
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1356,6 +1356,7 @@ 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
 
     // v16i1 -> v16i32 - load + broadcast
     { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i1,  2 },

diff --git a/llvm/test/Analysis/CostModel/X86/trunc.ll b/llvm/test/Analysis/CostModel/X86/trunc.ll
index 792310f..9b8b762 100644 (file)
--- a/llvm/test/Analysis/CostModel/X86/trunc.ll
+++ b/llvm/test/Analysis/CostModel/X86/trunc.ll
@@ -283,7 +283,7 @@ 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 11 for instruction: %V16i64 = trunc <16 x i64> undef to <16 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 0 for instruction: %V32i64 = trunc <32 x i64> undef to <32 x i8>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 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>
@@ -304,7 +304,7 @@ 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 11 for instruction: %V16i64 = trunc <16 x i64> undef to <16 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 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>