[PATCH] D155806: [AArch64] Basic vector bswap costs

[Dave Green via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG8da62b865fe5: [AArch64] Basic vector bswap costs (authored by dmgreen).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155806/new/

https://reviews.llvm.org/D155806

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Analysis/CostModel/AArch64/bswap.ll


Index: llvm/test/Analysis/CostModel/AArch64/bswap.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/bswap.ll
+++ llvm/test/Analysis/CostModel/AArch64/bswap.ll
@@ -35,15 +35,15 @@
 
 define void @neon() {
 ; CHECK-LABEL: 'neon'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v4i48 = call <4 x i48> @llvm.bswap.v4i48(<4 x i48> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -437,6 +437,15 @@
       return LT.first;
     break;
   }
+  case Intrinsic::bswap: {
+    static const auto ValidAbsTys = {MVT::v4i16, MVT::v8i16, MVT::v2i32,
+                                     MVT::v4i32, MVT::v2i64};
+    auto LT = getTypeLegalizationCost(RetTy);
+    if (any_of(ValidAbsTys, [&LT](MVT M) { return M == LT.second; }) &&
+        LT.second.getScalarSizeInBits() == RetTy->getScalarSizeInBits())
+      return LT.first;
+    break;
+  }
   case Intrinsic::experimental_stepvector: {
     InstructionCost Cost = 1; // Cost of the `index' instruction
     auto LT = getTypeLegalizationCost(RetTy);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D155806.542788.patch
Type: text/x-patch
Size: 3786 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230721/871b2601/attachment.bin>