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 @@ -5089,6 +5089,7 @@ {4, MVT::v4i16, 17}, // (load 16i16 and) deinterleave into 4 x 4i16 {4, MVT::v8i16, 33}, // (load 32i16 and) deinterleave into 4 x 8i16 {4, MVT::v16i16, 75}, // (load 64i16 and) deinterleave into 4 x 16i16 + {4, MVT::v32i16, 150}, // (load 128i16 and) deinterleave into 4 x 32i16 {8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32 }; @@ -5118,6 +5119,7 @@ {4, MVT::v4i16, 6}, // interleave 4 x 4i16 into 16i16 (and store) {4, MVT::v8i16, 10}, // interleave 4 x 8i16 into 32i16 (and store) {4, MVT::v16i16, 32}, // interleave 4 x 16i16 into 64i16 (and store) + {4, MVT::v32i16, 64}, // interleave 4 x 32i16 into 128i16 (and store) }; if (Opcode == Instruction::Load) { diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll @@ -13,7 +13,7 @@ ; CHECK: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK: LV: Found an estimated cost of 79 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2 -; CHECK: LV: Found an estimated cost of 456 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2 +; CHECK: LV: Found an estimated cost of 158 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2 define void @test() { diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll @@ -13,7 +13,7 @@ ; CHECK: LV: Found an estimated cost of 7 for VF 4 For instruction: store i16 %v3, i16* %out3, align 2 ; CHECK: LV: Found an estimated cost of 12 for VF 8 For instruction: store i16 %v3, i16* %out3, align 2 ; CHECK: LV: Found an estimated cost of 36 for VF 16 For instruction: store i16 %v3, i16* %out3, align 2 -; CHECK: LV: Found an estimated cost of 456 for VF 32 For instruction: store i16 %v3, i16* %out3, align 2 +; CHECK: LV: Found an estimated cost of 72 for VF 32 For instruction: store i16 %v3, i16* %out3, align 2 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: store i16 %v3, i16* %out3, align 2 define void @test() {