summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/X86
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Target/X86')
-rw-r--r--llvm/lib/Target/X86/X86TargetTransformInfo.cpp72
1 files changed, 61 insertions, 11 deletions
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index c648750b202..cf7a826ea85 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -528,17 +528,31 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
- static const TypeConversionCostTblEntry AVX512ConversionTbl[] = {
+ static const TypeConversionCostTblEntry AVX512DQConversionTbl[] = {
+ { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 1 },
+ { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i64, 1 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i64, 1 },
+ { ISD::UINT_TO_FP, MVT::v2f32, MVT::v2i64, 1 },
+ { ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i64, 1 },
+ { ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i64, 1 },
+
+ { ISD::FP_TO_UINT, MVT::v2i64, MVT::v2f64, 1 },
+ { ISD::FP_TO_UINT, MVT::v4i64, MVT::v4f64, 1 },
+ { ISD::FP_TO_UINT, MVT::v8i64, MVT::v8f64, 1 },
+ { ISD::FP_TO_UINT, MVT::v2i64, MVT::v2f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v4i64, MVT::v4f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v8i64, MVT::v8f32, 1 },
+ };
+
+ static const TypeConversionCostTblEntry AVX512FConversionTbl[] = {
{ ISD::FP_EXTEND, MVT::v8f64, MVT::v8f32, 1 },
{ ISD::FP_EXTEND, MVT::v8f64, MVT::v16f32, 3 },
{ ISD::FP_ROUND, MVT::v8f32, MVT::v8f64, 1 },
- { ISD::FP_ROUND, MVT::v16f32, MVT::v8f64, 3 },
{ ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 1 },
{ ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, 1 },
{ ISD::TRUNCATE, MVT::v8i16, MVT::v8i64, 1 },
{ ISD::TRUNCATE, MVT::v8i32, MVT::v8i64, 1 },
- { ISD::TRUNCATE, MVT::v16i32, MVT::v8i64, 4 },
// v16i1 -> v16i32 - load + broadcast
{ ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i1, 2 },
@@ -548,16 +562,46 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
{ ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, 1 },
{ ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i16, 1 },
{ ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i16, 1 },
- { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v16i32, 3 },
- { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v16i32, 3 },
+ { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i32, 1 },
+ { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i32, 1 },
+ { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i16, 1 },
+ { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i16, 1 },
{ ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i1, 3 },
{ ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i8, 2 },
{ ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i16, 2 },
{ ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i32, 1 },
{ ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i1, 4 },
+ { ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i8, 2 },
{ ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i16, 2 },
{ ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i32, 1 },
+
+ { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i1, 3 },
+ { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i8, 2 },
+ { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i16, 2 },
+ { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i32, 1 },
+ { ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i32, 1 },
+ { ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i32, 1 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i1, 4 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i16, 2 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i32, 1 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i8, 2 },
+ { ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i8, 2 },
+ { ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i16, 2 },
+ { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i8, 2 },
+ { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i16, 2 },
+ { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i32, 1 },
+ { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i8, 2 },
+ { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i16, 5 },
+ { ISD::UINT_TO_FP, MVT::v2f32, MVT::v2i32, 2 },
+ { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 5 },
+ { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i64, 12 },
+ { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i64, 26 },
+
+ { ISD::FP_TO_UINT, MVT::v2i32, MVT::v2f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v4i32, MVT::v4f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f32, 1 },
+ { ISD::FP_TO_UINT, MVT::v16i32, MVT::v16f32, 1 },
};
static const TypeConversionCostTblEntry AVX2ConversionTbl[] = {
@@ -693,12 +737,6 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
return LTSrc.first * Entry->Cost;
}
- if (ST->hasAVX512()) {
- if (const auto *Entry = ConvertCostTableLookup(AVX512ConversionTbl, ISD,
- LTDest.second, LTSrc.second))
- return Entry->Cost;
- }
-
EVT SrcTy = TLI->getValueType(DL, Src);
EVT DstTy = TLI->getValueType(DL, Dst);
@@ -706,6 +744,18 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
if (!SrcTy.isSimple() || !DstTy.isSimple())
return BaseT::getCastInstrCost(Opcode, Dst, Src);
+ if (ST->hasDQI())
+ if (const auto *Entry = ConvertCostTableLookup(AVX512DQConversionTbl, ISD,
+ DstTy.getSimpleVT(),
+ SrcTy.getSimpleVT()))
+ return Entry->Cost;
+
+ if (ST->hasAVX512())
+ if (const auto *Entry = ConvertCostTableLookup(AVX512FConversionTbl, ISD,
+ DstTy.getSimpleVT(),
+ SrcTy.getSimpleVT()))
+ return Entry->Cost;
+
if (ST->hasAVX2()) {
if (const auto *Entry = ConvertCostTableLookup(AVX2ConversionTbl, ISD,
DstTy.getSimpleVT(),
OpenPOWER on IntegriCloud