diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp --- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp +++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp @@ -1279,6 +1279,10 @@ { TTI::SK_Reverse, MVT::nxv8bf16, 1 }, { TTI::SK_Reverse, MVT::nxv4f32, 1 }, { TTI::SK_Reverse, MVT::nxv2f64, 1 }, + { TTI::SK_Reverse, MVT::nxv16i1, 1 }, + { TTI::SK_Reverse, MVT::nxv8i1, 1 }, + { TTI::SK_Reverse, MVT::nxv4i1, 1 }, + { TTI::SK_Reverse, MVT::nxv2i1, 1 }, }; std::pair LT = TLI->getTypeLegalizationCost(DL, Tp); if (const auto *Entry = CostTableLookup(ShuffleTbl, Kind, LT.second)) diff --git a/llvm/test/Analysis/CostModel/AArch64/getIntrinsicInstrCost-vector-reverse.ll b/llvm/test/Analysis/CostModel/AArch64/getIntrinsicInstrCost-vector-reverse.ll deleted file mode 100644 --- a/llvm/test/Analysis/CostModel/AArch64/getIntrinsicInstrCost-vector-reverse.ll +++ /dev/null @@ -1,65 +0,0 @@ -; Check getIntrinsicInstrCost in BasicTTIImpl.h for vector.reverse - -; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s - -; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t - -; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it. -; WARN-NOT: warning - -define void @vector_reverse() #0{ -; CHECK-LABEL: 'vector_reverse': -; CHECK-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %1 = call <16 x i8> @llvm.experimental.vector.reverse.v16i8(<16 x i8> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 180 for instruction: %2 = call <32 x i8> @llvm.experimental.vector.reverse.v32i8(<32 x i8> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %3 = call <8 x i16> @llvm.experimental.vector.reverse.v8i16(<8 x i16> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %4 = call <16 x i16> @llvm.experimental.vector.reverse.v16i16(<16 x i16> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %5 = call <4 x i32> @llvm.experimental.vector.reverse.v4i32(<4 x i32> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %6 = call <8 x i32> @llvm.experimental.vector.reverse.v8i32(<8 x i32> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %7 = call <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %8 = call <4 x i64> @llvm.experimental.vector.reverse.v4i64(<4 x i64> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <8 x half> @llvm.experimental.vector.reverse.v8f16(<8 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %10 = call <16 x half> @llvm.experimental.vector.reverse.v16f16(<16 x half> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %11 = call <4 x float> @llvm.experimental.vector.reverse.v4f32(<4 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %12 = call <8 x float> @llvm.experimental.vector.reverse.v8f32(<8 x float> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %13 = call <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %14 = call <4 x double> @llvm.experimental.vector.reverse.v4f64(<4 x double> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %15 = call <8 x bfloat> @llvm.experimental.vector.reverse.v8bf16(<8 x bfloat> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %16 = call <16 x bfloat> @llvm.experimental.vector.reverse.v16bf16(<16 x bfloat> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void - - call <16 x i8> @llvm.experimental.vector.reverse.v16i8(<16 x i8> undef) - call <32 x i8> @llvm.experimental.vector.reverse.v32i8(<32 x i8> undef) - call <8 x i16> @llvm.experimental.vector.reverse.v8i16(<8 x i16> undef) - call <16 x i16> @llvm.experimental.vector.reverse.v16i16(<16 x i16> undef) - call <4 x i32> @llvm.experimental.vector.reverse.v4i32(<4 x i32> undef) - call <8 x i32> @llvm.experimental.vector.reverse.v8i32(<8 x i32> undef) - call <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64> undef) - call <4 x i64> @llvm.experimental.vector.reverse.v4i64(<4 x i64> undef) - call <8 x half> @llvm.experimental.vector.reverse.v8f16(<8 x half> undef) - call <16 x half> @llvm.experimental.vector.reverse.v16f16(<16 x half> undef) - call <4 x float> @llvm.experimental.vector.reverse.v4f32(<4 x float> undef) - call <8 x float> @llvm.experimental.vector.reverse.v8f32(<8 x float> undef) - call <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double> undef) - call <4 x double> @llvm.experimental.vector.reverse.v4f64(<4 x double> undef) - call <8 x bfloat> @llvm.experimental.vector.reverse.v8bf16(<8 x bfloat> undef) - call <16 x bfloat> @llvm.experimental.vector.reverse.v16bf16(<16 x bfloat> undef) - ret void -} - -attributes #0 = { "target-features"="+sve,+bf16" } -declare <16 x i8> @llvm.experimental.vector.reverse.v16i8(<16 x i8>) -declare <32 x i8> @llvm.experimental.vector.reverse.v32i8(<32 x i8>) -declare <8 x i16> @llvm.experimental.vector.reverse.v8i16(<8 x i16>) -declare <16 x i16> @llvm.experimental.vector.reverse.v16i16(<16 x i16>) -declare <4 x i32> @llvm.experimental.vector.reverse.v4i32(<4 x i32>) -declare <8 x i32> @llvm.experimental.vector.reverse.v8i32(<8 x i32>) -declare <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64>) -declare <4 x i64> @llvm.experimental.vector.reverse.v4i64(<4 x i64>) -declare <8 x half> @llvm.experimental.vector.reverse.v8f16(<8 x half>) -declare <16 x half> @llvm.experimental.vector.reverse.v16f16(<16 x half>) -declare <4 x float> @llvm.experimental.vector.reverse.v4f32(<4 x float>) -declare <8 x float> @llvm.experimental.vector.reverse.v8f32(<8 x float>) -declare <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double>) -declare <4 x double> @llvm.experimental.vector.reverse.v4f64(<4 x double>) -declare <8 x bfloat> @llvm.experimental.vector.reverse.v8bf16(<8 x bfloat>) -declare <16 x bfloat> @llvm.experimental.vector.reverse.v16bf16(<16 x bfloat>) diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll --- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll +++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll @@ -133,6 +133,11 @@ ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4f64 = call @llvm.experimental.vector.reverse.nxv4f64( undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8bf16 = call @llvm.experimental.vector.reverse.nxv8bf16( undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16bf16 = call @llvm.experimental.vector.reverse.nxv16bf16( undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i1 = call @llvm.experimental.vector.reverse.nxv16i1( undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i1 = call @llvm.experimental.vector.reverse.nxv8i1( undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i1 = call @llvm.experimental.vector.reverse.nxv4i1( undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i1 = call @llvm.experimental.vector.reverse.nxv2i1( undef) + %reverse_nxv16i8 = call @llvm.experimental.vector.reverse.nxv16i8( undef) %reverse_nxv32i8 = call @llvm.experimental.vector.reverse.nxv32i8( undef) %reverse_nxv8i16 = call @llvm.experimental.vector.reverse.nxv8i16( undef) @@ -149,6 +154,10 @@ %reverse_nxv4f64 = call @llvm.experimental.vector.reverse.nxv4f64( undef) %reverse_nxv8bf16 = call @llvm.experimental.vector.reverse.nxv8bf16( undef) %reverse_nxv16bf16 = call @llvm.experimental.vector.reverse.nxv16bf16( undef) + %reverse_nxv16i1 = call @llvm.experimental.vector.reverse.nxv16i1( undef) + %reverse_nxv8i1 = call @llvm.experimental.vector.reverse.nxv8i1( undef) + %reverse_nxv4i1 = call @llvm.experimental.vector.reverse.nxv4i1( undef) + %reverse_nxv2i1 = call @llvm.experimental.vector.reverse.nxv2i1( undef) ret void } declare @llvm.experimental.vector.reverse.nxv16i8() @@ -167,5 +176,9 @@ declare @llvm.experimental.vector.reverse.nxv4f64() declare @llvm.experimental.vector.reverse.nxv8bf16() declare @llvm.experimental.vector.reverse.nxv16bf16() +declare @llvm.experimental.vector.reverse.nxv16i1() +declare @llvm.experimental.vector.reverse.nxv8i1() +declare @llvm.experimental.vector.reverse.nxv4i1() +declare @llvm.experimental.vector.reverse.nxv2i1() attributes #0 = { "target-features"="+sve,+bf16" }