[ARM] MVE sext of a load is also free.

[dmgreen]

Summary

MVE also has some sext of loads, which will be free.

[ostannard]

LGTM

llvm/trunk/lib/Target/ARM/ARMTargetTransformInfo.cpp

static const TypeConversionCostTblEntry LoadConversionTbl[] = {
         {ISD::SIGN_EXTEND, MVT::i64, MVT::i16, 1},
         {ISD::ZERO_EXTEND, MVT::i64, MVT::i16, 1},
         {ISD::SIGN_EXTEND, MVT::i64, MVT::i8, 1},
         {ISD::ZERO_EXTEND, MVT::i64, MVT::i8, 1},
     };
     if (const auto *Entry = ConvertCostTableLookup(
             LoadConversionTbl, ISD, DstTy.getSimpleVT(), SrcTy.getSimpleVT()))
       return Entry->Cost;
+
+    static const TypeConversionCostTblEntry MVELoadConversionTbl[] = {
+        {ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 0},
+        {ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 0},
+        {ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i8, 0},
+        {ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i8, 0},
+        {ISD::SIGN_EXTEND, MVT::v8i16, MVT::v8i8, 0},
+        {ISD::ZERO_EXTEND, MVT::v8i16, MVT::v8i8, 0},
+    };
+    if (SrcTy.isVector() && ST->hasMVEIntegerOps()) {
+      if (const auto *Entry =
+              ConvertCostTableLookup(MVELoadConversionTbl, ISD,
+                                     DstTy.getSimpleVT(), SrcTy.getSimpleVT()))
+        return Entry->Cost;
+    }
   }
 
   // Some arithmetic, load and store operations have specific instructions
   // to cast up/down their types automatically at no extra cost.
   // TODO: Get these tables to know at least what the related operations are.
   static const TypeConversionCostTblEntry NEONVectorConversionTbl[] = {
     { ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 0 },
     { ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 0 },

llvm/trunk/test/Analysis/CostModel/ARM/cast.ll

 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i8 %loadi8 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r5 = zext i8 %loadi8 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r6 = sext i16 %loadi16 to i32
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r7 = zext i16 %loadi16 to i32
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r8 = sext i16 %loadi16 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %loadi16 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r11 = zext i32 %loadi32 to i64
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 
   %loadi8 = load i8, i8* undef