Index: lib/Target/X86/X86ISelLowering.cpp =================================================================== --- lib/Target/X86/X86ISelLowering.cpp +++ lib/Target/X86/X86ISelLowering.cpp @@ -7156,8 +7156,7 @@ /// example. /// /// NB: We rely heavily on "undef" masks preserving the input lane. -static SDValue getV4X86ShuffleImm8ForMask(ArrayRef Mask, const SDLoc &DL, - SelectionDAG &DAG) { +static unsigned getV4X86ShuffleImm(ArrayRef Mask) { assert(Mask.size() == 4 && "Only 4-lane shuffle masks"); assert(Mask[0] >= -1 && Mask[0] < 4 && "Out of bound mask element!"); assert(Mask[1] >= -1 && Mask[1] < 4 && "Out of bound mask element!"); @@ -7169,7 +7168,12 @@ Imm |= (Mask[1] == -1 ? 1 : Mask[1]) << 2; Imm |= (Mask[2] == -1 ? 2 : Mask[2]) << 4; Imm |= (Mask[3] == -1 ? 3 : Mask[3]) << 6; - return DAG.getConstant(Imm, DL, MVT::i8); + return Imm; +} + +static SDValue getV4X86ShuffleImm8ForMask(ArrayRef Mask, SDLoc DL, + SelectionDAG &DAG) { + return DAG.getConstant(getV4X86ShuffleImm(Mask), DL, MVT::i8); } /// \brief Compute whether each element of a shuffle is zeroable. @@ -24569,7 +24573,8 @@ static bool matchUnaryVectorShuffle(MVT SrcVT, ArrayRef Mask, const X86Subtarget &Subtarget, unsigned &Shuffle, MVT &ShuffleVT) { - bool FloatDomain = SrcVT.isFloatingPoint(); + bool FloatDomain = SrcVT.isFloatingPoint() || + (!Subtarget.hasAVX2() && SrcVT.is256BitVector()); // Match a 128-bit integer vector against a VZEXT_MOVL (MOVQ) instruction. if (!FloatDomain && SrcVT.is128BitVector() && @@ -24647,6 +24652,83 @@ return false; } +// Attempt to match a combined shuffle mask against supported unary immediate +// permute instructions. +// TODO: Investigate sharing more of this with shuffle lowering. +static bool matchPermuteVectorShuffle(MVT SrcVT, ArrayRef Mask, + const X86Subtarget &Subtarget, + unsigned &Shuffle, MVT &ShuffleVT, + unsigned &PermuteImm) { + // Ensure we don't contain any zero elements. + for (int M : Mask) { + if (M == SM_SentinelZero) + return false; + assert(SM_SentinelUndef <= M && M < Mask.size() && + "Expected unary shuffle"); + } + + // We only support permutation of 32/64 bit elements. + // TODO - support PSHUFLW/PSHUFHW. + unsigned MaskScalarSizeInBits = SrcVT.getSizeInBits() / Mask.size(); + if (MaskScalarSizeInBits != 32 && MaskScalarSizeInBits != 64) + return false; + MVT MaskEltVT = MVT::getIntegerVT(MaskScalarSizeInBits); + + // AVX introduced the VPERMILPD/VPERMILPS float permutes, before then we + // had to use 2-input SHUFPD/SHUFPS shuffles (not handled here). + bool FloatDomain = SrcVT.isFloatingPoint(); + if (FloatDomain && !Subtarget.hasAVX()) + return false; + + // Pre-AVX2 we must use float shuffles on 256-bit vectors. + if (SrcVT.is256BitVector() && !Subtarget.hasAVX2()) + FloatDomain = true; + + // TODO - support LaneCrossing for AVX2 PERMQ/PERMPD + if (is128BitLaneCrossingShuffleMask(MaskEltVT, Mask)) + return false; + + // VPERMILPD can permute with a non-repeating shuffle. + if (FloatDomain && MaskScalarSizeInBits == 64) { + Shuffle = X86ISD::VPERMILPI; + ShuffleVT = MVT::getVectorVT(MVT::f64, Mask.size()); + PermuteImm = 0; + for (int i = 0, e = Mask.size(); i != e; ++i) { + int M = Mask[i]; + if (M == SM_SentinelUndef) + continue; + assert(((M / 2) == (i / 2)) && "Out of range shuffle mask index"); + PermuteImm |= (M & 1) << i; + } + return true; + } + + // We need a repeating shuffle mask for VPERMILPS/PSHUFD. + SmallVector RepeatedMask; + if (!is128BitLaneRepeatedShuffleMask(MaskEltVT, Mask, RepeatedMask)) + return false; + + // Narrow the repeated mask for 32-bit element permutes. + SmallVector WordMask = RepeatedMask; + if (MaskScalarSizeInBits == 64) { + WordMask.clear(); + for (int M : Mask) { + if (M == SM_SentinelUndef) { + WordMask.append(2, SM_SentinelUndef); + continue; + } + WordMask.push_back((M * 2) + 0); + WordMask.push_back((M * 2) + 1); + } + } + + Shuffle = (FloatDomain ? X86ISD::VPERMILPI : X86ISD::PSHUFD); + ShuffleVT = (FloatDomain ? MVT::f32 : MVT::i32); + ShuffleVT = MVT::getVectorVT(ShuffleVT, SrcVT.getSizeInBits() / 32); + PermuteImm = getV4X86ShuffleImm(WordMask); + return true; +} + // Attempt to match a combined unary shuffle mask against supported binary // shuffle instructions. // TODO: Investigate sharing more of this with shuffle lowering. @@ -24748,7 +24830,7 @@ // Attempt to match the mask against known shuffle patterns. MVT ShuffleVT; - unsigned Shuffle; + unsigned Shuffle, PermuteImm; if (matchUnaryVectorShuffle(VT, Mask, Subtarget, Shuffle, ShuffleVT)) { if (Depth == 1 && Root.getOpcode() == Shuffle) @@ -24762,6 +24844,20 @@ return true; } + if (matchPermuteVectorShuffle(VT, Mask, Subtarget, Shuffle, ShuffleVT, + PermuteImm)) { + if (Depth == 1 && Root.getOpcode() == Shuffle) + return false; // Nothing to do! + Res = DAG.getBitcast(ShuffleVT, Input); + DCI.AddToWorklist(Res.getNode()); + Res = DAG.getNode(Shuffle, DL, ShuffleVT, Res, + DAG.getConstant(PermuteImm, DL, MVT::i8)); + DCI.AddToWorklist(Res.getNode()); + DCI.CombineTo(Root.getNode(), DAG.getBitcast(RootVT, Res), + /*AddTo*/ true); + return true; + } + if (matchBinaryVectorShuffle(VT, Mask, Shuffle, ShuffleVT)) { if (Depth == 1 && Root.getOpcode() == Shuffle) return false; // Nothing to do! Index: test/CodeGen/X86/2012-01-12-extract-sv.ll =================================================================== --- test/CodeGen/X86/2012-01-12-extract-sv.ll +++ test/CodeGen/X86/2012-01-12-extract-sv.ll @@ -6,7 +6,7 @@ ; CHECK-NEXT: vmovaps (%eax), %ymm0 ; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0 ; CHECK-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1] -; CHECK-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0] +; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1] ; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1 ; CHECK-NEXT: vxorps %ymm2, %ymm2, %ymm2 ; CHECK-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3,4,5,6],ymm1[7] Index: test/CodeGen/X86/2012-04-26-sdglue.ll =================================================================== --- test/CodeGen/X86/2012-04-26-sdglue.ll +++ test/CodeGen/X86/2012-04-26-sdglue.ll @@ -10,9 +10,9 @@ ; CHECK-NEXT: vmovups 0, %xmm0 ; CHECK-NEXT: vxorps %ymm1, %ymm1, %ymm1 ; CHECK-NEXT: vblendps {{.*#+}} ymm2 = ymm0[0,1,2,3],ymm1[4,5,6,7] -; CHECK-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,2,3,3] -; CHECK-NEXT: vpbroadcastd 32, %xmm3 -; CHECK-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm0 +; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,2,3,3] +; CHECK-NEXT: vbroadcastss 32, %xmm3 +; CHECK-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0 ; CHECK-NEXT: vmulps %ymm0, %ymm2, %ymm2 ; CHECK-NEXT: vmulps %ymm0, %ymm0, %ymm0 ; CHECK-NEXT: vaddps %ymm0, %ymm2, %ymm0 Index: test/CodeGen/X86/avx-intrinsics-fast-isel.ll =================================================================== --- test/CodeGen/X86/avx-intrinsics-fast-isel.ll +++ test/CodeGen/X86/avx-intrinsics-fast-isel.ll @@ -2385,14 +2385,14 @@ ; X32-LABEL: test_mm256_set1_epi32: ; X32: # BB#0: ; X32-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero -; X32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0] +; X32-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] ; X32-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: test_mm256_set1_epi32: ; X64: # BB#0: ; X64-NEXT: vmovd %edi, %xmm0 -; X64-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0] +; X64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] ; X64-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X64-NEXT: retq %res0 = insertelement <8 x i32> undef, i32 %a0, i32 0 @@ -2422,7 +2422,7 @@ ; X64-LABEL: test_mm256_set1_epi64x: ; X64: # BB#0: ; X64-NEXT: vmovq %rdi, %xmm0 -; X64-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; X64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1] ; X64-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X64-NEXT: retq %res0 = insertelement <4 x i64> undef, i64 %a0, i32 0 Index: test/CodeGen/X86/avx-intrinsics-x86.ll =================================================================== --- test/CodeGen/X86/avx-intrinsics-x86.ll +++ test/CodeGen/X86/avx-intrinsics-x86.ll @@ -4036,7 +4036,7 @@ ; ; AVX512VL-LABEL: test_x86_avx_vpermilvar_pd_256_2: ; AVX512VL: ## BB#0: -; AVX512VL-NEXT: vpermilpd LCPI227_0, %ymm0, %ymm0 +; AVX512VL-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3] ; AVX512VL-NEXT: retl %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> ) ; <<4 x double>> [#uses=1] ret <4 x double> %res Index: test/CodeGen/X86/avx-splat.ll =================================================================== --- test/CodeGen/X86/avx-splat.ll +++ test/CodeGen/X86/avx-splat.ll @@ -28,7 +28,7 @@ ; CHECK-LABEL: funcC: ; CHECK: ## BB#0: ## %entry ; CHECK-NEXT: vmovq %rdi, %xmm0 -; CHECK-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; CHECK-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1] ; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; CHECK-NEXT: retq entry: Index: test/CodeGen/X86/avx-vbroadcast.ll =================================================================== --- test/CodeGen/X86/avx-vbroadcast.ll +++ test/CodeGen/X86/avx-vbroadcast.ll @@ -173,13 +173,13 @@ ; X32-LABEL: load_splat_8i32_4i32_33333333: ; X32: ## BB#0: ## %entry ; X32-NEXT: movl {{[0-9]+}}(%esp), %eax -; X32-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,3,3,3] +; X32-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,3,3,3] ; X32-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: load_splat_8i32_4i32_33333333: ; X64: ## BB#0: ## %entry -; X64-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,3,3,3] +; X64-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,3,3,3] ; X64-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X64-NEXT: retq entry: @@ -277,15 +277,13 @@ ; X32-LABEL: load_splat_4i64_2i64_1111: ; X32: ## BB#0: ## %entry ; X32-NEXT: movl {{[0-9]+}}(%esp), %eax -; X32-NEXT: vmovaps (%eax), %xmm0 -; X32-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; X32-NEXT: vpshufd {{.*#+}} xmm0 = mem[2,3,2,3] ; X32-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X32-NEXT: retl ; ; X64-LABEL: load_splat_4i64_2i64_1111: ; X64: ## BB#0: ## %entry -; X64-NEXT: vmovaps (%rdi), %xmm0 -; X64-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; X64-NEXT: vpshufd {{.*#+}} xmm0 = mem[2,3,2,3] ; X64-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; X64-NEXT: retq entry: Index: test/CodeGen/X86/merge-consecutive-loads-128.ll =================================================================== --- test/CodeGen/X86/merge-consecutive-loads-128.ll +++ test/CodeGen/X86/merge-consecutive-loads-128.ll @@ -760,7 +760,7 @@ ; AVX: # BB#0: ; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero -; AVX-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0,0,1,1] +; AVX-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,1,1] ; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0] ; AVX-NEXT: retq ; Index: test/CodeGen/X86/pshufb-mask-comments.ll =================================================================== --- test/CodeGen/X86/pshufb-mask-comments.ll +++ test/CodeGen/X86/pshufb-mask-comments.ll @@ -39,9 +39,9 @@ define <16 x i8> @test4(<16 x i8> %V, <2 x i64>* %P) { ; CHECK-LABEL: test4: ; CHECK: # BB#0: -; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [1084818905618843912,506097522914230528] -; CHECK-NEXT: movdqa %xmm1, (%rdi) -; CHECK-NEXT: pshufb %xmm1, %xmm0 +; CHECK-NEXT: movaps {{.*#+}} xmm1 = [1084818905618843912,506097522914230528] +; CHECK-NEXT: movaps %xmm1, (%rdi) +; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1] ; CHECK-NEXT: retq %1 = insertelement <2 x i64> undef, i64 1084818905618843912, i32 0 %2 = insertelement <2 x i64> %1, i64 506097522914230528, i32 1 Index: test/CodeGen/X86/sse3.ll =================================================================== --- test/CodeGen/X86/sse3.ll +++ test/CodeGen/X86/sse3.ll @@ -140,7 +140,7 @@ ; X64-LABEL: t9: ; X64: ## BB#0: ; X64-NEXT: movapd (%rdi), %xmm0 -; X64-NEXT: movhpd (%rsi), %xmm0 +; X64-NEXT: movhpd {{.*#+}} xmm0 = xmm0[0],mem[0] ; X64-NEXT: movapd %xmm0, (%rdi) ; X64-NEXT: retq %tmp = load <4 x float>, <4 x float>* %r @@ -207,7 +207,7 @@ ; X64: ## BB#0: ## %entry ; X64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3] ; X64-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7] -; X64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,6,7] +; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,3,3] ; X64-NEXT: retq entry: %tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 0, i32 1, i32 undef, i32 undef, i32 3, i32 11, i32 undef , i32 undef > @@ -220,7 +220,7 @@ ; X64: ## BB#0: ## %entry ; X64-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] ; X64-NEXT: pshuflw {{.*#+}} xmm0 = xmm1[0,2,2,3,4,5,6,7] -; X64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,6,7] +; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,3,3] ; X64-NEXT: retq entry: %tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 11, i32 3, i32 undef , i32 undef > Index: test/CodeGen/X86/vector-compare-results.ll =================================================================== --- test/CodeGen/X86/vector-compare-results.ll +++ test/CodeGen/X86/vector-compare-results.ll @@ -1,4 +1,3 @@ -; NOTE: Assertions have been autogenerated by update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE42 @@ -147,7 +146,7 @@ ; AVX2-LABEL: test_cmp_v4f64: ; AVX2: # BB#0: ; AVX2-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0 -; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3] ; AVX2-NEXT: vzeroupper ; AVX2-NEXT: retq @@ -684,10 +683,10 @@ ; AVX2-LABEL: test_cmp_v8f64: ; AVX2: # BB#0: ; AVX2-NEXT: vcmpltpd %ymm0, %ymm2, %ymm0 -; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3] ; AVX2-NEXT: vcmpltpd %ymm1, %ymm3, %ymm1 -; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,3,2,3] ; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 ; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero,ymm0[16,17,20,21,24,25,28,29],zero,zero,zero,zero,zero,zero,zero,zero @@ -2143,10 +2142,10 @@ ; AVX2-LABEL: test_cmp_v16f64: ; AVX2: # BB#0: ; AVX2-NEXT: vcmpltpd %ymm2, %ymm6, %ymm2 -; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm2 = ymm2[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,3,2,3] ; AVX2-NEXT: vcmpltpd %ymm3, %ymm7, %ymm3 -; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm3 = ymm3[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,3,2,3] ; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2 ; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128,0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128] @@ -2155,10 +2154,10 @@ ; AVX2-NEXT: vmovdqa {{.*#+}} xmm6 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u> ; AVX2-NEXT: vpshufb %xmm6, %xmm2, %xmm2 ; AVX2-NEXT: vcmpltpd %ymm0, %ymm4, %ymm0 -; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,3,2,3] ; AVX2-NEXT: vcmpltpd %ymm1, %ymm5, %ymm1 -; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6] +; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,2,0,2,4,6,4,6] ; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,3,2,3] ; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 ; AVX2-NEXT: vpshufb %ymm3, %ymm0, %ymm0 Index: test/CodeGen/X86/vector-shuffle-128-v16.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-128-v16.ll +++ test/CodeGen/X86/vector-shuffle-128-v16.ll @@ -925,7 +925,7 @@ ; SSE2: # BB#0: ; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7] ; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3] -; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0,0,1,1] +; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3] ; SSE2-NEXT: retq ; ; SSSE3-LABEL: shuffle_v16i8_00_uu_uu_uu_uu_uu_uu_uu_01_uu_uu_uu_uu_uu_uu_uu: Index: test/CodeGen/X86/vector-shuffle-128-v2.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-128-v2.ll +++ test/CodeGen/X86/vector-shuffle-128-v2.ll @@ -1,4 +1,3 @@ -; NOTE: Assertions have been autogenerated by update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3 @@ -160,7 +159,7 @@ ; ; AVX-LABEL: shuffle_v2f64_11: ; AVX: # BB#0: -; AVX-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,1] ; AVX-NEXT: retq %shuffle = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> ret <2 x double> %shuffle @@ -218,7 +217,7 @@ ; ; AVX-LABEL: shuffle_v2f64_33: ; AVX: # BB#0: -; AVX-NEXT: vmovhlps {{.*#+}} xmm0 = xmm1[1,1] +; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm1[1,1] ; AVX-NEXT: retq %shuffle = shufflevector <2 x double> %a, <2 x double> %b, <2 x i32> ret <2 x double> %shuffle Index: test/CodeGen/X86/vector-shuffle-128-v4.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-128-v4.ll +++ test/CodeGen/X86/vector-shuffle-128-v4.ll @@ -227,7 +227,7 @@ ; ; AVX-LABEL: shuffle_v4f32_0011: ; AVX: # BB#0: -; AVX-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0,0,1,1] +; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1] ; AVX-NEXT: retq %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> ret <4 x float> %shuffle @@ -240,7 +240,7 @@ ; ; AVX-LABEL: shuffle_v4f32_2233: ; AVX: # BB#0: -; AVX-NEXT: vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3] +; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3] ; AVX-NEXT: retq %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> ret <4 x float> %shuffle Index: test/CodeGen/X86/vector-shuffle-256-v16.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-256-v16.ll +++ test/CodeGen/X86/vector-shuffle-256-v16.ll @@ -1443,7 +1443,7 @@ ; AVX1: # BB#0: ; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1 ; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7] -; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v16i16_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_zz: Index: test/CodeGen/X86/vector-shuffle-256-v4.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-256-v4.ll +++ test/CodeGen/X86/vector-shuffle-256-v4.ll @@ -488,7 +488,7 @@ define <4 x double> @shuffle_v4f64_11uu(<4 x double> %a, <4 x double> %b) { ; ALL-LABEL: shuffle_v4f64_11uu: ; ALL: # BB#0: -; ALL-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; ALL-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,1] ; ALL-NEXT: retq %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> ret <4 x double> %shuffle @@ -557,7 +557,7 @@ define <4 x i64> @shuffle_v4i64_0001(<4 x i64> %a, <4 x i64> %b) { ; AVX1-LABEL: shuffle_v4i64_0001: ; AVX1: # BB#0: -; AVX1-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -579,7 +579,7 @@ ; AVX1: # BB#0: ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1 ; AVX1-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0] -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1] ; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 ; AVX1-NEXT: retq ; @@ -641,8 +641,8 @@ define <4 x i64> @shuffle_v4i64_1000(<4 x i64> %a, <4 x i64> %b) { ; AVX1-LABEL: shuffle_v4i64_1000: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -800,7 +800,7 @@ ; AVX1: # BB#0: ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2 ; AVX1-NEXT: vshufpd {{.*#+}} xmm2 = xmm0[1],xmm2[0] -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1] ; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0 ; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3] ; AVX1-NEXT: retq @@ -1320,7 +1320,7 @@ define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) { ; AVX1-LABEL: splat_mem_v4i64_from_v2i64: ; AVX1: # BB#0: -; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = mem[0,1,0,1] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; AVX1-NEXT: retq ; Index: test/CodeGen/X86/vector-shuffle-256-v8.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-256-v8.ll +++ test/CodeGen/X86/vector-shuffle-256-v8.ll @@ -152,8 +152,8 @@ define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) { ; AVX1-LABEL: shuffle_v8f32_00112233: ; AVX1: # BB#0: -; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm0[0,0,1,1] -; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3] +; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1] +; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -196,7 +196,7 @@ ; AVX1-LABEL: shuffle_v8f32_08080808: ; AVX1: # BB#0: ; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0] -; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3] +; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; AVX1-NEXT: retq ; @@ -213,7 +213,7 @@ ; ALL-LABEL: shuffle_v8f32_08084c4c: ; ALL: # BB#0: ; ALL-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4] -; ALL-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] +; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] ; ALL-NEXT: retq %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> ret <8 x float> %shuffle @@ -907,8 +907,8 @@ define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_00000010: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,0] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -924,8 +924,8 @@ define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_00000200: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,0,0] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -941,8 +941,8 @@ define <8 x i32> @shuffle_v8i32_00003000(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_00003000: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,0,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,0,0,0] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -1042,8 +1042,8 @@ define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_00112233: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,1,1] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -1059,8 +1059,8 @@ define <8 x i32> @shuffle_v8i32_00001111(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_00001111: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1] +; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,1,1] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; AVX1-NEXT: retq ; @@ -1091,7 +1091,7 @@ ; AVX1-LABEL: shuffle_v8i32_08080808: ; AVX1: # BB#0: ; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0] -; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2,1,3] +; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 ; AVX1-NEXT: retq ; @@ -1108,7 +1108,7 @@ ; AVX1-LABEL: shuffle_v8i32_08084c4c: ; AVX1: # BB#0: ; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4] -; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_08084c4c: @@ -1239,8 +1239,8 @@ define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_091b2d3f: ; AVX1: # BB#0: -; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3] -; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3] +; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[0,1,1,3] +; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,1,3,3] ; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0 ; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7] ; AVX1-NEXT: retq @@ -1257,7 +1257,7 @@ define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) { ; AVX1-LABEL: shuffle_v8i32_09ab1def: ; AVX1: # BB#0: -; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3] +; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,3,3] ; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0 ; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7] ; AVX1-NEXT: retq @@ -2050,7 +2050,7 @@ ; AVX1: # BB#0: ; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1 ; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6] -; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5] +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_z0U2zUz6: @@ -2066,7 +2066,7 @@ ; AVX1: # BB#0: ; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1 ; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7] -; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] +; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] ; AVX1-NEXT: retq ; ; AVX2-LABEL: shuffle_v8i32_1U3z5zUU: Index: test/CodeGen/X86/vector-shuffle-combining-avx.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-combining-avx.ll +++ test/CodeGen/X86/vector-shuffle-combining-avx.ll @@ -67,7 +67,7 @@ define <4 x float> @combine_vpermilvar_4f32_unpckh(<4 x float> %a0) { ; ALL-LABEL: combine_vpermilvar_4f32_unpckh: ; ALL: # BB#0: -; ALL-NEXT: vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3] +; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3] ; ALL-NEXT: retq %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> ) ret <4 x float> %1 @@ -76,7 +76,7 @@ define <4 x float> @combine_vpermilvar_4f32_unpckl(<4 x float> %a0) { ; ALL-LABEL: combine_vpermilvar_4f32_unpckl: ; ALL: # BB#0: -; ALL-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0,0,1,1] +; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1] ; ALL-NEXT: retq %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> ) ret <4 x float> %1 @@ -167,7 +167,7 @@ define <4 x float> @combine_vpermilvar_4f32_4stage(<4 x float> %a0) { ; ALL-LABEL: combine_vpermilvar_4f32_4stage: ; ALL: # BB#0: -; ALL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7] +; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,0,3,1] ; ALL-NEXT: retq %1 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> ) %2 = tail call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %1, <4 x i32> ) @@ -177,24 +177,10 @@ } define <8 x float> @combine_vpermilvar_8f32_4stage(<8 x float> %a0) { -; AVX1-LABEL: combine_vpermilvar_8f32_4stage: -; AVX1: # BB#0: -; AVX1-NEXT: vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0] -; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0 -; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5] -; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7] -; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0 -; AVX1-NEXT: retq -; -; AVX2-LABEL: combine_vpermilvar_8f32_4stage: -; AVX2: # BB#0: -; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7,24,25,26,27,16,17,18,19,28,29,30,31,20,21,22,23] -; AVX2-NEXT: retq -; -; AVX512F-LABEL: combine_vpermilvar_8f32_4stage: -; AVX512F: # BB#0: -; AVX512F-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,0,1,2,3,12,13,14,15,4,5,6,7,24,25,26,27,16,17,18,19,28,29,30,31,20,21,22,23] -; AVX512F-NEXT: retq +; ALL-LABEL: combine_vpermilvar_8f32_4stage: +; ALL: # BB#0: +; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5] +; ALL-NEXT: retq %1 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> ) %2 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %1, <8 x i32> ) %3 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %2, <8 x i32> ) Index: test/CodeGen/X86/vector-shuffle-combining-avx2.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-combining-avx2.ll +++ test/CodeGen/X86/vector-shuffle-combining-avx2.ll @@ -51,7 +51,7 @@ ; CHECK-LABEL: combine_permq_pshufb: ; CHECK: # BB#0: ; CHECK-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0] -; CHECK-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7,24,25,26,27,28,29,30,31,16,17,18,19,20,21,22,23] +; CHECK-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5] ; CHECK-NEXT: retq %1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> %2 = bitcast <4 x i64> %1 to <32 x i8> Index: test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll +++ test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll @@ -212,6 +212,43 @@ ret <16 x float> %res0 } +define <16 x float> @combine_vpermt2var_16f32_vpermilps(<16 x float> %x0, <16 x float> %x1) { +; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps: +; CHECK: # BB#0: +; CHECK-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12] +; CHECK-NEXT: retq + %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> , <16 x float> %x0, <16 x float> %x1, i16 -1) + ret <16 x float> %res0 +} +define <16 x float> @combine_vpermt2var_16f32_vpermilps_load(<16 x float> *%p0, <16 x float> %x1) { +; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_load: +; CHECK: # BB#0: +; CHECK-NEXT: vpermilps {{.*#+}} zmm0 = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12] +; CHECK-NEXT: retq + %x0 = load <16 x float>, <16 x float> *%p0 + %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> , <16 x float> %x0, <16 x float> %x1, i16 -1) + ret <16 x float> %res0 +} +define <16 x float> @combine_vpermt2var_16f32_vpermilps_mask(<16 x float> %x0, <16 x float> %x1, i16 %m) { +; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_mask: +; CHECK: # BB#0: +; CHECK-NEXT: kmovw %edi, %k1 +; CHECK-NEXT: vpermilps {{.*#+}} zmm0 = zmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12] +; CHECK-NEXT: retq + %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> , <16 x float> %x0, <16 x float> %x1, i16 %m) + ret <16 x float> %res0 +} +define <16 x float> @combine_vpermt2var_16f32_vpermilps_mask_load(<16 x float> *%p0, <16 x float> %x1, i16 %m) { +; CHECK-LABEL: combine_vpermt2var_16f32_vpermilps_mask_load: +; CHECK: # BB#0: +; CHECK-NEXT: kmovw %esi, %k1 +; CHECK-NEXT: vpermilps {{.*#+}} zmm0 = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12] +; CHECK-NEXT: retq + %x0 = load <16 x float>, <16 x float> *%p0 + %res0 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> , <16 x float> %x0, <16 x float> %x1, i16 %m) + ret <16 x float> %res0 +} + define <16 x i32> @combine_vpermt2var_16i32_identity(<16 x i32> %x0, <16 x i32> %x1) { ; CHECK-LABEL: combine_vpermt2var_16i32_identity: ; CHECK: # BB#0: Index: test/CodeGen/X86/vector-shuffle-combining-ssse3.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-combining-ssse3.ll +++ test/CodeGen/X86/vector-shuffle-combining-ssse3.ll @@ -94,13 +94,12 @@ define <16 x i8> @combine_pshufb_palignr(<16 x i8> %a0, <16 x i8> %a1) { ; SSE-LABEL: combine_pshufb_palignr: ; SSE: # BB#0: -; SSE-NEXT: pshufb {{.*#+}} xmm1 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15] -; SSE-NEXT: movdqa %xmm1, %xmm0 +; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3] ; SSE-NEXT: retq ; ; AVX-LABEL: combine_pshufb_palignr: ; AVX: # BB#0: -; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15,8,9,10,11,12,13,14,15] +; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm1[2,3,2,3] ; AVX-NEXT: retq %1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> %2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> ) Index: test/CodeGen/X86/vector-shuffle-combining.ll =================================================================== --- test/CodeGen/X86/vector-shuffle-combining.ll +++ test/CodeGen/X86/vector-shuffle-combining.ll @@ -2440,7 +2440,7 @@ ; ; AVX-LABEL: combine_undef_input_test9: ; AVX: # BB#0: -; AVX-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,1] ; AVX-NEXT: retq %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> @@ -2631,7 +2631,7 @@ ; ; AVX-LABEL: combine_undef_input_test19: ; AVX: # BB#0: -; AVX-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1] +; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,1] ; AVX-NEXT: retq %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32>