[X86] Add some cost model entries for sext/zext for avx512bw

This fixes some of scalarization costs reported for sext/zext using avx512bw. This does not fix all scalarization costs being reported. Just the worst.

I've restricted this only to combinations of types that are legal with avx512bw like v32i1/v64i1/v32i16/v64i8 and conversions between vXi1 and vXi8/vXi16 with legal vXi8/vXi16 result types.

Differential Revision: https://reviews.llvm.org/D54979

llvm-svn: 347785

1 files changed, 27 insertions, 0 deletions

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index bb40d0bf73e..a77d8e04451 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1224,6 +1224,27 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
   // FIXME: Need a better design of the cost table to handle non-simple types of
   // potential massive combinations (elem_num x src_type x dst_type).
 
+  static const TypeConversionCostTblEntry AVX512BWConversionTbl[] {
+    { ISD::SIGN_EXTEND, MVT::v32i16, MVT::v32i8, 1 },
+    { ISD::ZERO_EXTEND, MVT::v32i16, MVT::v32i8, 1 },
+
+    // Mask sign extend has an instruction.
+    { ISD::SIGN_EXTEND, MVT::v8i16,  MVT::v8i1,  1 },
+    { ISD::SIGN_EXTEND, MVT::v16i8,  MVT::v16i1, 1 },
+    { ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i1, 1 },
+    { ISD::SIGN_EXTEND, MVT::v32i8,  MVT::v32i1, 1 },
+    { ISD::SIGN_EXTEND, MVT::v32i16, MVT::v32i1, 1 },
+    { ISD::SIGN_EXTEND, MVT::v64i8,  MVT::v64i1, 1 },
+
+    // Mask zero extend is a load + broadcast.
+    { ISD::ZERO_EXTEND, MVT::v8i16,  MVT::v8i1,  2 },
+    { ISD::ZERO_EXTEND, MVT::v16i8,  MVT::v16i1, 2 },
+    { ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i1, 2 },
+    { ISD::ZERO_EXTEND, MVT::v32i8,  MVT::v32i1, 2 },
+    { ISD::ZERO_EXTEND, MVT::v32i16, MVT::v32i1, 2 },
+    { ISD::ZERO_EXTEND, MVT::v64i8,  MVT::v64i1, 2 },
+  };
+
   static const TypeConversionCostTblEntry AVX512DQConversionTbl[] = {
     { ISD::SINT_TO_FP,  MVT::v2f32,  MVT::v2i64,  1 },
     { ISD::SINT_TO_FP,  MVT::v2f64,  MVT::v2i64,  1 },
@@ -1549,6 +1570,12 @@ int X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
   if (!SrcTy.isSimple() || !DstTy.isSimple())
     return BaseT::getCastInstrCost(Opcode, Dst, Src);
 
+  if (ST->hasBWI())
+    if (const auto *Entry = ConvertCostTableLookup(AVX512BWConversionTbl, ISD,
+                                                   DstTy.getSimpleVT(),
+                                                   SrcTy.getSimpleVT()))
+      return Entry->Cost;
+
   if (ST->hasDQI())
     if (const auto *Entry = ConvertCostTableLookup(AVX512DQConversionTbl, ISD,
                                                    DstTy.getSimpleVT(),