[llvm] 8da62b8 - [AArch64] Basic vector bswap costs

[David Green via llvm-commits]

Author: David Green
Date: 2023-07-21T08:48:53+01:00
New Revision: 8da62b865fe5bfe36af273954a29a63a78bfd7b9

URL: https://github.com/llvm/llvm-project/commit/8da62b865fe5bfe36af273954a29a63a78bfd7b9
DIFF: https://github.com/llvm/llvm-project/commit/8da62b865fe5bfe36af273954a29a63a78bfd7b9.diff

LOG: [AArch64] Basic vector bswap costs

This adds some basic vector bswap costs, providing the type is supported.

Differential Revision: https://reviews.llvm.org/D155806

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 19fa856bf76e8b..353e96856b8f36 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -437,6 +437,15 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       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);

diff  --git a/llvm/test/Analysis/CostModel/AArch64/bswap.ll b/llvm/test/Analysis/CostModel/AArch64/bswap.ll
index 8b387cf01adcd9..e5a1827e75a14d 100644
--- a/llvm/test/Analysis/CostModel/AArch64/bswap.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/bswap.ll
@@ -35,15 +35,15 @@ define void @scalar() {
 
 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
 ;