[X86] Lower the cost of v2i32->v2f64 sint_to_fp under vector widening legalization.

I don't really understand the costs we're using for fp_to_sint,
but prior to widening legalization we used 20 as the cost for this
via the v2i64->v2f64 entry. That number seems better than the 40
we got with widening legalization. So now we need either a
v2i32->v2f64 entry or a v4i32->v2f64 entry depending on whether
AVX is enabled or not since we skip the first SSE2 table look up
under AVX.

llvm-svn: 369628

1 files changed, 18 insertions, 0 deletions

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 1181181a3c5..1e8f1b31214 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1568,6 +1568,11 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
     { ISD::UINT_TO_FP,  MVT::f64,    MVT::i64,    4 },
   };
 
+  static const TypeConversionCostTblEntry SSE2ConversionTblWide[] = {
+    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v4i32, 2*10 },
+    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i32, 2*10 },
+  };
+
   static const TypeConversionCostTblEntry SSE2ConversionTbl[] = {
     // These are somewhat magic numbers justified by looking at the output of
     // Intel's IACA, running some kernels and making sure when we take
@@ -1633,6 +1638,13 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
   std::pair<int, MVT> LTSrc = TLI->getTypeLegalizationCost(DL, Src);
   std::pair<int, MVT> LTDest = TLI->getTypeLegalizationCost(DL, Dst);
 
+  if (ST->hasSSE2() && !ST->hasAVX() &&
+      ExperimentalVectorWideningLegalization) {
+    if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTblWide, ISD,
+                                                   LTDest.second, LTSrc.second))
+      return LTSrc.first * Entry->Cost;
+  }
+
   if (ST->hasSSE2() && !ST->hasAVX()) {
     if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTbl, ISD,
                                                    LTDest.second, LTSrc.second))
@@ -1705,6 +1717,12 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
       return Entry->Cost;
   }
 
+  if (ST->hasSSE2() && ExperimentalVectorWideningLegalization) {
+    if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTblWide, ISD,
+                                                   SimpleDstTy, SimpleSrcTy))
+      return Entry->Cost;
+  }
+
   if (ST->hasSSE2()) {
     if (const auto *Entry = ConvertCostTableLookup(SSE2ConversionTbl, ISD,
                                                    SimpleDstTy, SimpleSrcTy))