diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -5092,6 +5092,8 @@ {3, MVT::v16i8, 11}, // (load 48i8 and) deinterleave into 3 x 16i8 {3, MVT::v32i8, 14}, // (load 96i8 and) deinterleave into 3 x 32i8 + {3, MVT::v2i16, 5}, // (load 6i16 and) deinterleave into 3 x 2i16 + {3, MVT::v8i32, 17}, // (load 24i32 and) deinterleave into 3 x 8i32 {4, MVT::v2i8, 4}, // (load 8i8 and) deinterleave into 4 x 2i8 @@ -5144,6 +5146,8 @@ {3, MVT::v16i8, 11}, // interleave 3 x 16i8 into 48i8 (and store) {3, MVT::v32i8, 13}, // interleave 3 x 32i8 into 96i8 (and store) + {3, MVT::v2i16, 4}, // interleave 3 x 2i16 into 6i16 (and store) + {4, MVT::v2i8, 4}, // interleave 4 x 2i8 into 8i8 (and store) {4, MVT::v4i8, 4}, // interleave 4 x 4i8 into 16i8 (and store) {4, MVT::v8i8, 4}, // interleave 4 x 8i8 into 32i8 (and store) diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll @@ -26,7 +26,7 @@ ; AVX1: LV: Found an estimated cost of 258 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2 ; ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 -; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 +; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 ; AVX2: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2 ; AVX2: LV: Found an estimated cost of 58 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2 ; AVX2: LV: Found an estimated cost of 129 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll @@ -26,7 +26,7 @@ ; AVX1: LV: Found an estimated cost of 258 for VF 32 For instruction: store i16 %v2, i16* %out2, align 2 ; ; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v2, i16* %out2, align 2 -; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: store i16 %v2, i16* %out2, align 2 +; AVX2: LV: Found an estimated cost of 7 for VF 2 For instruction: store i16 %v2, i16* %out2, align 2 ; AVX2: LV: Found an estimated cost of 30 for VF 4 For instruction: store i16 %v2, i16* %out2, align 2 ; AVX2: LV: Found an estimated cost of 53 for VF 8 For instruction: store i16 %v2, i16* %out2, align 2 ; AVX2: LV: Found an estimated cost of 129 for VF 16 For instruction: store i16 %v2, i16* %out2, align 2