[ARM] sext of a load is free

[dmgreen]

Summary

This teaches the cost model that the sext or zext of a load is going to be free.

[samparker]

Huh, surprised this was missing. Add i64 before committing?

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

int ARMTTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
   }
 
   EVT SrcTy = TLI->getValueType(DL, Src);
   EVT DstTy = TLI->getValueType(DL, Dst);
 
   if (!SrcTy.isSimple() || !DstTy.isSimple())
     return BaseT::getCastInstrCost(Opcode, Dst, Src);
 
+  // The extend of a load is free
+  if (I && isa<LoadInst>(I->getOperand(0))) {
+    static const TypeConversionCostTblEntry LoadConversionTbl[] = {
+        {ISD::SIGN_EXTEND, MVT::i32, MVT::i16, 0},
+        {ISD::ZERO_EXTEND, MVT::i32, MVT::i16, 0},
+        {ISD::SIGN_EXTEND, MVT::i32, MVT::i8, 0},
+        {ISD::ZERO_EXTEND, MVT::i32, MVT::i8, 0},
+        {ISD::SIGN_EXTEND, MVT::i16, MVT::i8, 0},
+        {ISD::ZERO_EXTEND, MVT::i16, MVT::i8, 0},
+    };
+    if (const auto *Entry = ConvertCostTableLookup(
+            LoadConversionTbl, 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 },
     { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i32, 1 },
     { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i32, 1 },

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

 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi16 = load i16, i16* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi32 = load i32, i32* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i8 = load <2 x i8>, <2 x i8>* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv4i8 = load <4 x i8>, <4 x i8>* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv8i8 = load <8 x i8>, <8 x i8>* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i16 = load <2 x i16>, <2 x i16>* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv4i16 = load <4 x i16>, <4 x i16>* undef
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i32 = load <2 x i32>, <2 x i32>* undef
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r0 = sext i8 %loadi8 to i16
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r1 = zext i8 %loadi8 to i16
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r2 = sext i8 %loadi8 to i32
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r3 = zext i8 %loadi8 to i32
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r0 = sext i8 %loadi8 to i16
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r1 = zext i8 %loadi8 to i16
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r2 = sext i8 %loadi8 to i32
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r3 = zext i8 %loadi8 to i32
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i8 %loadi8 to i64
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r5 = zext i8 %loadi8 to i64
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r6 = sext i16 %loadi16 to i32
-; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r7 = zext i16 %loadi16 to i32
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r6 = sext i16 %loadi16 to i32
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r7 = zext i16 %loadi16 to i32
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r8 = sext i16 %loadi16 to i64
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %loadi16 to i64
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r11 = zext i32 %loadi32 to i64
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>

 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi16 = load i16, i16* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi32 = load i32, i32* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i8 = load <2 x i8>, <2 x i8>* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv4i8 = load <4 x i8>, <4 x i8>* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv8i8 = load <8 x i8>, <8 x i8>* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i16 = load <2 x i16>, <2 x i16>* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv4i16 = load <4 x i16>, <4 x i16>* undef
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i32 = load <2 x i32>, <2 x i32>* undef
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r0 = sext i8 %loadi8 to i16
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r1 = zext i8 %loadi8 to i16
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r2 = sext i8 %loadi8 to i32
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r3 = zext i8 %loadi8 to i32
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r0 = sext i8 %loadi8 to i16
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r1 = zext i8 %loadi8 to i16
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r2 = sext i8 %loadi8 to i32
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r3 = zext i8 %loadi8 to i32
 ; 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 1 for instruction: %r6 = sext i16 %loadi16 to i32
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r7 = zext i16 %loadi16 to i32
+; 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 2 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 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>