Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp =================================================================== --- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp +++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp @@ -2001,13 +2001,20 @@ { TTI::SK_Select, MVT::v4f32, 2 }, // rev+trn (or similar). { TTI::SK_Select, MVT::v2f64, 1 }, // mov. // PermuteSingleSrc shuffle kinds. - // TODO: handle vXi8/vXi16. { TTI::SK_PermuteSingleSrc, MVT::v2i32, 1 }, // mov. { TTI::SK_PermuteSingleSrc, MVT::v4i32, 3 }, // perfectshuffle worst case. { TTI::SK_PermuteSingleSrc, MVT::v2i64, 1 }, // mov. { TTI::SK_PermuteSingleSrc, MVT::v2f32, 1 }, // mov. { TTI::SK_PermuteSingleSrc, MVT::v4f32, 3 }, // perfectshuffle worst case. { TTI::SK_PermuteSingleSrc, MVT::v2f64, 1 }, // mov. + { TTI::SK_PermuteSingleSrc, MVT::v4i16, 3 }, // perfectshuffle worst case. + { TTI::SK_PermuteSingleSrc, MVT::v4f16, 3 }, // perfectshuffle worst case. + { TTI::SK_PermuteSingleSrc, MVT::v4bf16, 3 }, // perfectshuffle worst case. + { TTI::SK_PermuteSingleSrc, MVT::v8i16, 8 }, // constpool + load + tbl + { TTI::SK_PermuteSingleSrc, MVT::v8f16, 8 }, // constpool + load + tbl + { TTI::SK_PermuteSingleSrc, MVT::v8bf16, 8 }, // constpool + load + tbl + { TTI::SK_PermuteSingleSrc, MVT::v8i8, 8 }, // constpool + load + tbl + { TTI::SK_PermuteSingleSrc, MVT::v16i8, 8 }, // constpool + load + tbl // Reverse can be lowered with `rev`. { TTI::SK_Reverse, MVT::v2i32, 1 }, // mov. { TTI::SK_Reverse, MVT::v4i32, 2 }, // REV64; EXT Index: llvm/test/Analysis/CostModel/AArch64/reduce-and.ll =================================================================== --- llvm/test/Analysis/CostModel/AArch64/reduce-and.ll +++ llvm/test/Analysis/CostModel/AArch64/reduce-and.ll @@ -12,7 +12,7 @@ ; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V3i8 = call i8 @llvm.vector.reduce.and.v3i8(<3 x i8> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.and.v3i8(<3 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i8 = call i8 @llvm.vector.reduce.and.v8i8(<8 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16i8 = call i8 @llvm.vector.reduce.and.v16i8(<16 x i8> undef) Index: llvm/test/Analysis/CostModel/AArch64/reduce-or.ll =================================================================== --- llvm/test/Analysis/CostModel/AArch64/reduce-or.ll +++ llvm/test/Analysis/CostModel/AArch64/reduce-or.ll @@ -12,7 +12,7 @@ ; CHECK-NEXT: Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.or.v1i8(<1 x i8> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V3i8 = call i8 @llvm.vector.reduce.or.v3i8(<3 x i8> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.or.v3i8(<3 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i8 = call i8 @llvm.vector.reduce.or.v8i8(<8 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16i8 = call i8 @llvm.vector.reduce.or.v16i8(<16 x i8> undef) Index: llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll =================================================================== --- llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll +++ llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll @@ -5,14 +5,14 @@ ; CHECK-LABEL: 'reduce' ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.xor.v1i1(<1 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.xor.v2i1(<2 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V4 = call i1 @llvm.vector.reduce.xor.v4i1(<4 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 129 for instruction: %V8 = call i1 @llvm.vector.reduce.xor.v8i1(<8 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 364 for instruction: %V16 = call i1 @llvm.vector.reduce.xor.v16i1(<16 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 455 for instruction: %V32 = call i1 @llvm.vector.reduce.xor.v32i1(<32 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 637 for instruction: %V64 = call i1 @llvm.vector.reduce.xor.v64i1(<64 x i1> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 1001 for instruction: %V128 = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.vector.reduce.xor.v4i1(<4 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i1 @llvm.vector.reduce.xor.v8i1(<8 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i1 @llvm.vector.reduce.xor.v16i1(<16 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 127 for instruction: %V32 = call i1 @llvm.vector.reduce.xor.v32i1(<32 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 309 for instruction: %V64 = call i1 @llvm.vector.reduce.xor.v64i1(<64 x i1> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 673 for instruction: %V128 = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.xor.v1i8(<1 x i8> undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V3i8 = call i8 @llvm.vector.reduce.xor.v3i8(<3 x i8> undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.xor.v3i8(<3 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i8 = call i8 @llvm.vector.reduce.xor.v8i8(<8 x i8> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16i8 = call i8 @llvm.vector.reduce.xor.v16i8(<16 x i8> undef) Index: llvm/test/Analysis/CostModel/AArch64/shuffle-other.ll =================================================================== --- llvm/test/Analysis/CostModel/AArch64/shuffle-other.ll +++ llvm/test/Analysis/CostModel/AArch64/shuffle-other.ll @@ -4,12 +4,12 @@ define void @shuffle() { ; CHECK-LABEL: 'shuffle' ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v7 = shufflevector <2 x i8> undef, <2 x i8> undef, <2 x i32> -; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> -; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %v9 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> -; CHECK-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %v10 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v9 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v10 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v11 = shufflevector <2 x i16> undef, <2 x i16> undef, <2 x i32> -; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %v12 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> -; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %v13 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> +; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v12 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> +; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v13 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v14 = shufflevector <2 x i32> undef, <2 x i32> undef, <2 x i32> ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v15 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16 = shufflevector <2 x float> undef, <2 x float> undef, <2 x i32>