From c89b3af0e3e970820ed35798ab2516459a8d829d Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Sun, 20 Sep 2020 13:52:04 -0700 Subject: [PATCH] [X86] Pre-commit test cases for D87863. NFC --- llvm/test/CodeGen/X86/masked_load.ll | 115 ++++++- llvm/test/CodeGen/X86/masked_store.ll | 450 ++++++++++++++++---------- 2 files changed, 384 insertions(+), 181 deletions(-) diff --git a/llvm/test/CodeGen/X86/masked_load.ll b/llvm/test/CodeGen/X86/masked_load.ll index 2d2fb44cdfbd..44938d029aed 100644 --- a/llvm/test/CodeGen/X86/masked_load.ll +++ b/llvm/test/CodeGen/X86/masked_load.ll @@ -7175,36 +7175,138 @@ define <8 x double> @load_one_mask_bit_set5(<8 x double>* %addr, <8 x double> %v ret <8 x double> %res } +define <16 x i64> @load_one_mask_bit_set6(<16 x i64>* %addr, <16 x i64> %val) { +; SSE2-LABEL: load_one_mask_bit_set6: +; SSE2: ## %bb.0: +; SSE2-NEXT: movq %rdi, %rax +; SSE2-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3] +; SSE2-NEXT: movlps {{.*#+}} xmm5 = mem[0,1],xmm5[2,3] +; SSE2-NEXT: movsd {{.*#+}} xmm8 = mem[0],zero +; SSE2-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm8[0] +; SSE2-NEXT: movaps %xmm7, 112(%rdi) +; SSE2-NEXT: movaps %xmm4, 64(%rdi) +; SSE2-NEXT: movaps %xmm3, 48(%rdi) +; SSE2-NEXT: movaps %xmm2, 32(%rdi) +; SSE2-NEXT: movaps %xmm0, (%rdi) +; SSE2-NEXT: movaps %xmm5, 80(%rdi) +; SSE2-NEXT: movaps %xmm1, 16(%rdi) +; SSE2-NEXT: movaps %xmm6, 96(%rdi) +; SSE2-NEXT: retq +; +; SSE42-LABEL: load_one_mask_bit_set6: +; SSE42: ## %bb.0: +; SSE42-NEXT: movq %rdi, %rax +; SSE42-NEXT: pinsrq $0, 16(%rsi), %xmm1 +; SSE42-NEXT: pinsrq $0, 80(%rsi), %xmm5 +; SSE42-NEXT: pinsrq $1, 104(%rsi), %xmm6 +; SSE42-NEXT: movaps %xmm7, 112(%rdi) +; SSE42-NEXT: movaps %xmm4, 64(%rdi) +; SSE42-NEXT: movaps %xmm3, 48(%rdi) +; SSE42-NEXT: movaps %xmm2, 32(%rdi) +; SSE42-NEXT: movaps %xmm0, (%rdi) +; SSE42-NEXT: movdqa %xmm6, 96(%rdi) +; SSE42-NEXT: movdqa %xmm5, 80(%rdi) +; SSE42-NEXT: movdqa %xmm1, 16(%rdi) +; SSE42-NEXT: retq +; +; AVX1-LABEL: load_one_mask_bit_set6: +; AVX1: ## %bb.0: +; AVX1-NEXT: vmovapd {{.*#+}} ymm4 = [0,0,18446744073709551615,0] +; AVX1-NEXT: vmaskmovpd (%rdi), %ymm4, %ymm5 +; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm5[2],ymm0[3] +; AVX1-NEXT: vmaskmovpd 64(%rdi), %ymm4, %ymm4 +; AVX1-NEXT: vblendpd {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3] +; AVX1-NEXT: vmovapd {{.*#+}} ymm4 = [0,18446744073709551615,0,0] +; AVX1-NEXT: vmaskmovpd 96(%rdi), %ymm4, %ymm4 +; AVX1-NEXT: vblendpd {{.*#+}} ymm3 = ymm3[0],ymm4[1],ymm3[2,3] +; AVX1-NEXT: retq +; +; AVX2-LABEL: load_one_mask_bit_set6: +; AVX2: ## %bb.0: +; AVX2-NEXT: vmovdqa {{.*#+}} ymm4 = [0,0,18446744073709551615,0] +; AVX2-NEXT: vpmaskmovq (%rdi), %ymm4, %ymm5 +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm5[4,5],ymm0[6,7] +; AVX2-NEXT: vpmaskmovq 64(%rdi), %ymm4, %ymm4 +; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0,1,2,3],ymm4[4,5],ymm2[6,7] +; AVX2-NEXT: vmovdqa {{.*#+}} ymm4 = [0,18446744073709551615,0,0] +; AVX2-NEXT: vpmaskmovq 96(%rdi), %ymm4, %ymm4 +; AVX2-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2,3],ymm3[4,5,6,7] +; AVX2-NEXT: retq +; +; AVX512F-LABEL: load_one_mask_bit_set6: +; AVX512F: ## %bb.0: +; AVX512F-NEXT: movb $4, %al +; AVX512F-NEXT: kmovw %eax, %k1 +; AVX512F-NEXT: vmovdqu64 (%rdi), %zmm0 {%k1} +; AVX512F-NEXT: movb $36, %al +; AVX512F-NEXT: kmovw %eax, %k1 +; AVX512F-NEXT: vmovdqu64 64(%rdi), %zmm1 {%k1} +; AVX512F-NEXT: retq +; +; AVX512VLDQ-LABEL: load_one_mask_bit_set6: +; AVX512VLDQ: ## %bb.0: +; AVX512VLDQ-NEXT: movb $4, %al +; AVX512VLDQ-NEXT: kmovw %eax, %k1 +; AVX512VLDQ-NEXT: vmovdqu64 (%rdi), %zmm0 {%k1} +; AVX512VLDQ-NEXT: movb $36, %al +; AVX512VLDQ-NEXT: kmovw %eax, %k1 +; AVX512VLDQ-NEXT: vmovdqu64 64(%rdi), %zmm1 {%k1} +; AVX512VLDQ-NEXT: retq +; +; AVX512VLBW-LABEL: load_one_mask_bit_set6: +; AVX512VLBW: ## %bb.0: +; AVX512VLBW-NEXT: movb $4, %al +; AVX512VLBW-NEXT: kmovd %eax, %k1 +; AVX512VLBW-NEXT: vmovdqu64 (%rdi), %zmm0 {%k1} +; AVX512VLBW-NEXT: movb $36, %al +; AVX512VLBW-NEXT: kmovd %eax, %k1 +; AVX512VLBW-NEXT: vmovdqu64 64(%rdi), %zmm1 {%k1} +; AVX512VLBW-NEXT: retq +; +; X86-AVX512-LABEL: load_one_mask_bit_set6: +; X86-AVX512: ## %bb.0: +; X86-AVX512-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-AVX512-NEXT: movb $4, %cl +; X86-AVX512-NEXT: kmovd %ecx, %k1 +; X86-AVX512-NEXT: vmovdqu64 (%eax), %zmm0 {%k1} +; X86-AVX512-NEXT: movb $36, %cl +; X86-AVX512-NEXT: kmovd %ecx, %k1 +; X86-AVX512-NEXT: vmovdqu64 64(%eax), %zmm1 {%k1} +; X86-AVX512-NEXT: retl + %res = call <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>* %addr, i32 4, <16 x i1> , <16 x i64> %val) + ret <16 x i64> %res +} + define i32 @pr38986(i1 %c, i32* %p) { ; SSE-LABEL: pr38986: ; SSE: ## %bb.0: ; SSE-NEXT: testb $1, %dil ; SSE-NEXT: ## implicit-def: $eax -; SSE-NEXT: je LBB44_2 +; SSE-NEXT: je LBB45_2 ; SSE-NEXT: ## %bb.1: ## %cond.load ; SSE-NEXT: movl (%rsi), %eax -; SSE-NEXT: LBB44_2: ## %else +; SSE-NEXT: LBB45_2: ## %else ; SSE-NEXT: retq ; ; AVX-LABEL: pr38986: ; AVX: ## %bb.0: ; AVX-NEXT: testb $1, %dil ; AVX-NEXT: ## implicit-def: $eax -; AVX-NEXT: je LBB44_2 +; AVX-NEXT: je LBB45_2 ; AVX-NEXT: ## %bb.1: ## %cond.load ; AVX-NEXT: movl (%rsi), %eax -; AVX-NEXT: LBB44_2: ## %else +; AVX-NEXT: LBB45_2: ## %else ; AVX-NEXT: retq ; ; X86-AVX512-LABEL: pr38986: ; X86-AVX512: ## %bb.0: ; X86-AVX512-NEXT: testb $1, {{[0-9]+}}(%esp) ; X86-AVX512-NEXT: ## implicit-def: $eax -; X86-AVX512-NEXT: je LBB44_2 +; X86-AVX512-NEXT: je LBB45_2 ; X86-AVX512-NEXT: ## %bb.1: ## %cond.load ; X86-AVX512-NEXT: movl {{[0-9]+}}(%esp), %eax ; X86-AVX512-NEXT: movl (%eax), %eax -; X86-AVX512-NEXT: LBB44_2: ## %else +; X86-AVX512-NEXT: LBB45_2: ## %else ; X86-AVX512-NEXT: retl %vc = insertelement <1 x i1> undef, i1 %c, i32 0 %vp = bitcast i32* %p to <1 x i32>* @@ -7240,6 +7342,7 @@ declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>) declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>) +declare <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>*, i32, <16 x i1>, <16 x i64>) declare <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>*, i32, <8 x i1>, <8 x i64>) declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>) declare <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>*, i32, <2 x i1>, <2 x i64>) diff --git a/llvm/test/CodeGen/X86/masked_store.ll b/llvm/test/CodeGen/X86/masked_store.ll index 417463226063..319d946794b7 100644 --- a/llvm/test/CodeGen/X86/masked_store.ll +++ b/llvm/test/CodeGen/X86/masked_store.ll @@ -4660,100 +4660,118 @@ define void @mstore_constmask_v4i32_v4i32(<4 x i32> %trigger, <4 x i32>* %addr, ; Make sure we are able to detect all ones constant mask after type legalization ; to avoid masked stores. -define void @mstore_constmask_allones_split(<16 x i32> %trigger, <16 x i32>* %addr, <16 x i32> %val) { +define void @mstore_constmask_allones_split(<16 x i64> %trigger, <16 x i64>* %addr, <16 x i64> %val) { ; SSE2-LABEL: mstore_constmask_allones_split: ; SSE2: ## %bb.0: -; SSE2-NEXT: movd %xmm4, (%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,1,1] -; SSE2-NEXT: movd %xmm0, 4(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[3,3,3,3] -; SSE2-NEXT: movd %xmm0, 12(%rdi) -; SSE2-NEXT: movd %xmm5, 16(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm5[2,3,2,3] -; SSE2-NEXT: movd %xmm0, 24(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm5[3,3,3,3] -; SSE2-NEXT: movd %xmm0, 28(%rdi) -; SSE2-NEXT: movd %xmm6, 32(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[1,1,1,1] -; SSE2-NEXT: movd %xmm0, 36(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[2,3,2,3] -; SSE2-NEXT: movd %xmm0, 40(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[3,3,3,3] -; SSE2-NEXT: movd %xmm0, 44(%rdi) -; SSE2-NEXT: movd %xmm7, 48(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm7[1,1,1,1] -; SSE2-NEXT: movd %xmm0, 52(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm7[2,3,2,3] -; SSE2-NEXT: movd %xmm0, 56(%rdi) -; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm7[3,3,3,3] -; SSE2-NEXT: movd %xmm0, 60(%rdi) +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0 +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm4 +; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 +; SSE2-NEXT: movq %xmm5, (%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[2,3,2,3] +; SSE2-NEXT: movq %xmm5, 8(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm5 = mem[2,3,2,3] +; SSE2-NEXT: movq %xmm5, 24(%rdi) +; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rax +; SSE2-NEXT: movq %rax, 32(%rdi) +; SSE2-NEXT: movq %xmm4, 48(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,2,3] +; SSE2-NEXT: movq %xmm4, 56(%rdi) +; SSE2-NEXT: movq %xmm3, 64(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,2,3] +; SSE2-NEXT: movq %xmm3, 72(%rdi) +; SSE2-NEXT: movq %xmm2, 80(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,2,3] +; SSE2-NEXT: movq %xmm2, 88(%rdi) +; SSE2-NEXT: movq %xmm1, 96(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3] +; SSE2-NEXT: movq %xmm1, 104(%rdi) +; SSE2-NEXT: movq %xmm0, 112(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3] +; SSE2-NEXT: movq %xmm0, 120(%rdi) ; SSE2-NEXT: retq ; ; SSE4-LABEL: mstore_constmask_allones_split: ; SSE4: ## %bb.0: -; SSE4-NEXT: movss %xmm4, (%rdi) -; SSE4-NEXT: extractps $1, %xmm4, 4(%rdi) -; SSE4-NEXT: extractps $3, %xmm4, 12(%rdi) -; SSE4-NEXT: movd %xmm5, 16(%rdi) -; SSE4-NEXT: movdqa %xmm7, %xmm0 -; SSE4-NEXT: palignr {{.*#+}} xmm0 = xmm6[8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7] -; SSE4-NEXT: palignr {{.*#+}} xmm6 = xmm5[8,9,10,11,12,13,14,15],xmm6[0,1,2,3,4,5,6,7] -; SSE4-NEXT: movdqu %xmm6, 24(%rdi) -; SSE4-NEXT: movdqu %xmm0, 40(%rdi) -; SSE4-NEXT: pextrd $2, %xmm7, 56(%rdi) -; SSE4-NEXT: pextrd $3, %xmm7, 60(%rdi) +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm0 +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1 +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm2 +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm3 +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm4 +; SSE4-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 +; SSE4-NEXT: movaps {{[0-9]+}}(%rsp), %xmm6 +; SSE4-NEXT: movups %xmm6, (%rdi) +; SSE4-NEXT: palignr {{.*#+}} xmm5 = mem[8,9,10,11,12,13,14,15],xmm5[0,1,2,3,4,5,6,7] +; SSE4-NEXT: movdqu %xmm5, 24(%rdi) +; SSE4-NEXT: movups %xmm4, 48(%rdi) +; SSE4-NEXT: movups %xmm3, 64(%rdi) +; SSE4-NEXT: movups %xmm2, 80(%rdi) +; SSE4-NEXT: movups %xmm1, 96(%rdi) +; SSE4-NEXT: movups %xmm0, 112(%rdi) ; SSE4-NEXT: retq ; ; AVX1-LABEL: mstore_constmask_allones_split: ; AVX1: ## %bb.0: -; AVX1-NEXT: vmovaps {{.*#+}} ymm0 = [4294967295,4294967295,0,4294967295,4294967295,0,4294967295,4294967295] -; AVX1-NEXT: vmaskmovps %ymm2, %ymm0, (%rdi) -; AVX1-NEXT: vmovups %ymm3, 32(%rdi) +; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [18446744073709551615,0,18446744073709551615,18446744073709551615] +; AVX1-NEXT: vmaskmovpd %ymm5, %ymm0, 32(%rdi) +; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [18446744073709551615,18446744073709551615,0,18446744073709551615] +; AVX1-NEXT: vmaskmovpd %ymm4, %ymm0, (%rdi) +; AVX1-NEXT: vmovups %ymm7, 96(%rdi) +; AVX1-NEXT: vmovups %ymm6, 64(%rdi) ; AVX1-NEXT: vzeroupper ; AVX1-NEXT: retq ; ; AVX2-LABEL: mstore_constmask_allones_split: ; AVX2: ## %bb.0: -; AVX2-NEXT: vmovdqa {{.*#+}} ymm0 = [4294967295,4294967295,0,4294967295,4294967295,0,4294967295,4294967295] -; AVX2-NEXT: vpmaskmovd %ymm2, %ymm0, (%rdi) -; AVX2-NEXT: vmovups %ymm3, 32(%rdi) +; AVX2-NEXT: vmovdqa {{.*#+}} ymm0 = [18446744073709551615,0,18446744073709551615,18446744073709551615] +; AVX2-NEXT: vpmaskmovq %ymm5, %ymm0, 32(%rdi) +; AVX2-NEXT: vmovdqa {{.*#+}} ymm0 = [18446744073709551615,18446744073709551615,0,18446744073709551615] +; AVX2-NEXT: vpmaskmovq %ymm4, %ymm0, (%rdi) +; AVX2-NEXT: vmovups %ymm7, 96(%rdi) +; AVX2-NEXT: vmovups %ymm6, 64(%rdi) ; AVX2-NEXT: vzeroupper ; AVX2-NEXT: retq ; ; AVX512F-LABEL: mstore_constmask_allones_split: ; AVX512F: ## %bb.0: -; AVX512F-NEXT: movw $-37, %ax +; AVX512F-NEXT: movb $-37, %al ; AVX512F-NEXT: kmovw %eax, %k1 -; AVX512F-NEXT: vmovdqu32 %zmm1, (%rdi) {%k1} +; AVX512F-NEXT: vmovdqu64 %zmm2, (%rdi) {%k1} +; AVX512F-NEXT: vmovups %zmm3, 64(%rdi) ; AVX512F-NEXT: vzeroupper ; AVX512F-NEXT: retq ; ; AVX512VLDQ-LABEL: mstore_constmask_allones_split: ; AVX512VLDQ: ## %bb.0: -; AVX512VLDQ-NEXT: movw $-37, %ax +; AVX512VLDQ-NEXT: movb $-37, %al ; AVX512VLDQ-NEXT: kmovw %eax, %k1 -; AVX512VLDQ-NEXT: vmovdqu32 %zmm1, (%rdi) {%k1} +; AVX512VLDQ-NEXT: vmovdqu64 %zmm2, (%rdi) {%k1} +; AVX512VLDQ-NEXT: vmovups %zmm3, 64(%rdi) ; AVX512VLDQ-NEXT: vzeroupper ; AVX512VLDQ-NEXT: retq ; ; AVX512VLBW-LABEL: mstore_constmask_allones_split: ; AVX512VLBW: ## %bb.0: -; AVX512VLBW-NEXT: movw $-37, %ax +; AVX512VLBW-NEXT: movb $-37, %al ; AVX512VLBW-NEXT: kmovd %eax, %k1 -; AVX512VLBW-NEXT: vmovdqu32 %zmm1, (%rdi) {%k1} +; AVX512VLBW-NEXT: vmovdqu64 %zmm2, (%rdi) {%k1} +; AVX512VLBW-NEXT: vmovups %zmm3, 64(%rdi) ; AVX512VLBW-NEXT: vzeroupper ; AVX512VLBW-NEXT: retq ; ; X86-AVX512-LABEL: mstore_constmask_allones_split: ; X86-AVX512: ## %bb.0: ; X86-AVX512-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-AVX512-NEXT: movw $-37, %cx +; X86-AVX512-NEXT: movb $-37, %cl ; X86-AVX512-NEXT: kmovd %ecx, %k1 -; X86-AVX512-NEXT: vmovdqu32 %zmm1, (%eax) {%k1} +; X86-AVX512-NEXT: vmovdqu64 %zmm2, (%eax) {%k1} +; X86-AVX512-NEXT: vmovups %zmm3, 64(%eax) ; X86-AVX512-NEXT: vzeroupper ; X86-AVX512-NEXT: retl - %mask = icmp eq <16 x i32> %trigger, zeroinitializer - call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> %val, <16 x i32>* %addr, i32 4, <16 x i1>) + %mask = icmp eq <16 x i64> %trigger, zeroinitializer + call void @llvm.masked.store.v16i64.p0v16i64(<16 x i64> %val, <16 x i64>* %addr, i32 4, <16 x i1>) ret void } @@ -4892,6 +4910,87 @@ define void @one_mask_bit_set5(<8 x double>* %addr, <8 x double> %val) { ret void } +; Try one elt in each half of a vector that needs to split +define void @one_mask_bit_set6(<16 x i64>* %addr, <16 x i64> %val) { +; SSE2-LABEL: one_mask_bit_set6: +; SSE2: ## %bb.0: +; SSE2-NEXT: movlps %xmm3, 48(%rdi) +; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm5[2,3,2,3] +; SSE2-NEXT: movq %xmm0, 88(%rdi) +; SSE2-NEXT: retq +; +; SSE4-LABEL: one_mask_bit_set6: +; SSE4: ## %bb.0: +; SSE4-NEXT: movlps %xmm3, 48(%rdi) +; SSE4-NEXT: pextrq $1, %xmm5, 88(%rdi) +; SSE4-NEXT: retq +; +; AVX1-LABEL: one_mask_bit_set6: +; AVX1: ## %bb.0: +; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [0,0,0,18446744073709551615] +; AVX1-NEXT: vmaskmovpd %ymm2, %ymm0, 64(%rdi) +; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [0,0,18446744073709551615,0] +; AVX1-NEXT: vmaskmovpd %ymm1, %ymm0, 32(%rdi) +; AVX1-NEXT: vzeroupper +; AVX1-NEXT: retq +; +; AVX2-LABEL: one_mask_bit_set6: +; AVX2: ## %bb.0: +; AVX2-NEXT: vmovdqa {{.*#+}} ymm0 = [0,0,0,18446744073709551615] +; AVX2-NEXT: vpmaskmovq %ymm2, %ymm0, 64(%rdi) +; AVX2-NEXT: vmovdqa {{.*#+}} ymm0 = [0,0,18446744073709551615,0] +; AVX2-NEXT: vpmaskmovq %ymm1, %ymm0, 32(%rdi) +; AVX2-NEXT: vzeroupper +; AVX2-NEXT: retq +; +; AVX512F-LABEL: one_mask_bit_set6: +; AVX512F: ## %bb.0: +; AVX512F-NEXT: movb $8, %al +; AVX512F-NEXT: kmovw %eax, %k1 +; AVX512F-NEXT: vmovdqu64 %zmm1, 64(%rdi) {%k1} +; AVX512F-NEXT: movb $64, %al +; AVX512F-NEXT: kmovw %eax, %k1 +; AVX512F-NEXT: vmovdqu64 %zmm0, (%rdi) {%k1} +; AVX512F-NEXT: vzeroupper +; AVX512F-NEXT: retq +; +; AVX512VLDQ-LABEL: one_mask_bit_set6: +; AVX512VLDQ: ## %bb.0: +; AVX512VLDQ-NEXT: movb $8, %al +; AVX512VLDQ-NEXT: kmovw %eax, %k1 +; AVX512VLDQ-NEXT: vmovdqu64 %zmm1, 64(%rdi) {%k1} +; AVX512VLDQ-NEXT: movb $64, %al +; AVX512VLDQ-NEXT: kmovw %eax, %k1 +; AVX512VLDQ-NEXT: vmovdqu64 %zmm0, (%rdi) {%k1} +; AVX512VLDQ-NEXT: vzeroupper +; AVX512VLDQ-NEXT: retq +; +; AVX512VLBW-LABEL: one_mask_bit_set6: +; AVX512VLBW: ## %bb.0: +; AVX512VLBW-NEXT: movb $8, %al +; AVX512VLBW-NEXT: kmovd %eax, %k1 +; AVX512VLBW-NEXT: vmovdqu64 %zmm1, 64(%rdi) {%k1} +; AVX512VLBW-NEXT: movb $64, %al +; AVX512VLBW-NEXT: kmovd %eax, %k1 +; AVX512VLBW-NEXT: vmovdqu64 %zmm0, (%rdi) {%k1} +; AVX512VLBW-NEXT: vzeroupper +; AVX512VLBW-NEXT: retq +; +; X86-AVX512-LABEL: one_mask_bit_set6: +; X86-AVX512: ## %bb.0: +; X86-AVX512-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-AVX512-NEXT: movb $8, %cl +; X86-AVX512-NEXT: kmovd %ecx, %k1 +; X86-AVX512-NEXT: vmovdqu64 %zmm1, 64(%eax) {%k1} +; X86-AVX512-NEXT: movb $64, %cl +; X86-AVX512-NEXT: kmovd %ecx, %k1 +; X86-AVX512-NEXT: vmovdqu64 %zmm0, (%eax) {%k1} +; X86-AVX512-NEXT: vzeroupper +; X86-AVX512-NEXT: retl + call void @llvm.masked.store.v16i64.p0v16i64(<16 x i64> %val, <16 x i64>* %addr, i32 4, <16 x i1>) + ret void +} + ; SimplifyDemandedBits eliminates an ashr here. define void @masked_store_bool_mask_demand_trunc_sext(<4 x double> %x, <4 x double>* %p, <4 x i32> %masksrc) { @@ -4900,31 +4999,31 @@ define void @masked_store_bool_mask_demand_trunc_sext(<4 x double> %x, <4 x doub ; SSE-NEXT: pslld $31, %xmm2 ; SSE-NEXT: movmskps %xmm2, %eax ; SSE-NEXT: testb $1, %al -; SSE-NEXT: jne LBB24_1 +; SSE-NEXT: jne LBB25_1 ; SSE-NEXT: ## %bb.2: ## %else ; SSE-NEXT: testb $2, %al -; SSE-NEXT: jne LBB24_3 -; SSE-NEXT: LBB24_4: ## %else2 +; SSE-NEXT: jne LBB25_3 +; SSE-NEXT: LBB25_4: ## %else2 ; SSE-NEXT: testb $4, %al -; SSE-NEXT: jne LBB24_5 -; SSE-NEXT: LBB24_6: ## %else4 +; SSE-NEXT: jne LBB25_5 +; SSE-NEXT: LBB25_6: ## %else4 ; SSE-NEXT: testb $8, %al -; SSE-NEXT: jne LBB24_7 -; SSE-NEXT: LBB24_8: ## %else6 +; SSE-NEXT: jne LBB25_7 +; SSE-NEXT: LBB25_8: ## %else6 ; SSE-NEXT: retq -; SSE-NEXT: LBB24_1: ## %cond.store +; SSE-NEXT: LBB25_1: ## %cond.store ; SSE-NEXT: movlps %xmm0, (%rdi) ; SSE-NEXT: testb $2, %al -; SSE-NEXT: je LBB24_4 -; SSE-NEXT: LBB24_3: ## %cond.store1 +; SSE-NEXT: je LBB25_4 +; SSE-NEXT: LBB25_3: ## %cond.store1 ; SSE-NEXT: movhps %xmm0, 8(%rdi) ; SSE-NEXT: testb $4, %al -; SSE-NEXT: je LBB24_6 -; SSE-NEXT: LBB24_5: ## %cond.store3 +; SSE-NEXT: je LBB25_6 +; SSE-NEXT: LBB25_5: ## %cond.store3 ; SSE-NEXT: movlps %xmm1, 16(%rdi) ; SSE-NEXT: testb $8, %al -; SSE-NEXT: je LBB24_8 -; SSE-NEXT: LBB24_7: ## %cond.store5 +; SSE-NEXT: je LBB25_8 +; SSE-NEXT: LBB25_7: ## %cond.store5 ; SSE-NEXT: movhps %xmm1, 24(%rdi) ; SSE-NEXT: retq ; @@ -4995,35 +5094,35 @@ define void @one_mask_bit_set1_variable(<4 x float>* %addr, <4 x float> %val, <4 ; SSE2: ## %bb.0: ; SSE2-NEXT: movmskps %xmm1, %eax ; SSE2-NEXT: testb $1, %al -; SSE2-NEXT: jne LBB25_1 +; SSE2-NEXT: jne LBB26_1 ; SSE2-NEXT: ## %bb.2: ## %else ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: jne LBB25_3 -; SSE2-NEXT: LBB25_4: ## %else2 +; SSE2-NEXT: jne LBB26_3 +; SSE2-NEXT: LBB26_4: ## %else2 ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: jne LBB25_5 -; SSE2-NEXT: LBB25_6: ## %else4 +; SSE2-NEXT: jne LBB26_5 +; SSE2-NEXT: LBB26_6: ## %else4 ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: jne LBB25_7 -; SSE2-NEXT: LBB25_8: ## %else6 +; SSE2-NEXT: jne LBB26_7 +; SSE2-NEXT: LBB26_8: ## %else6 ; SSE2-NEXT: retq -; SSE2-NEXT: LBB25_1: ## %cond.store +; SSE2-NEXT: LBB26_1: ## %cond.store ; SSE2-NEXT: movss %xmm0, (%rdi) ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: je LBB25_4 -; SSE2-NEXT: LBB25_3: ## %cond.store1 +; SSE2-NEXT: je LBB26_4 +; SSE2-NEXT: LBB26_3: ## %cond.store1 ; SSE2-NEXT: movaps %xmm0, %xmm1 ; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1],xmm0[1,1] ; SSE2-NEXT: movss %xmm1, 4(%rdi) ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: je LBB25_6 -; SSE2-NEXT: LBB25_5: ## %cond.store3 +; SSE2-NEXT: je LBB26_6 +; SSE2-NEXT: LBB26_5: ## %cond.store3 ; SSE2-NEXT: movaps %xmm0, %xmm1 ; SSE2-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1] ; SSE2-NEXT: movss %xmm1, 8(%rdi) ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: je LBB25_8 -; SSE2-NEXT: LBB25_7: ## %cond.store5 +; SSE2-NEXT: je LBB26_8 +; SSE2-NEXT: LBB26_7: ## %cond.store5 ; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3,3,3] ; SSE2-NEXT: movss %xmm0, 12(%rdi) ; SSE2-NEXT: retq @@ -5032,31 +5131,31 @@ define void @one_mask_bit_set1_variable(<4 x float>* %addr, <4 x float> %val, <4 ; SSE4: ## %bb.0: ; SSE4-NEXT: movmskps %xmm1, %eax ; SSE4-NEXT: testb $1, %al -; SSE4-NEXT: jne LBB25_1 +; SSE4-NEXT: jne LBB26_1 ; SSE4-NEXT: ## %bb.2: ## %else ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: jne LBB25_3 -; SSE4-NEXT: LBB25_4: ## %else2 +; SSE4-NEXT: jne LBB26_3 +; SSE4-NEXT: LBB26_4: ## %else2 ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: jne LBB25_5 -; SSE4-NEXT: LBB25_6: ## %else4 +; SSE4-NEXT: jne LBB26_5 +; SSE4-NEXT: LBB26_6: ## %else4 ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: jne LBB25_7 -; SSE4-NEXT: LBB25_8: ## %else6 +; SSE4-NEXT: jne LBB26_7 +; SSE4-NEXT: LBB26_8: ## %else6 ; SSE4-NEXT: retq -; SSE4-NEXT: LBB25_1: ## %cond.store +; SSE4-NEXT: LBB26_1: ## %cond.store ; SSE4-NEXT: movss %xmm0, (%rdi) ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: je LBB25_4 -; SSE4-NEXT: LBB25_3: ## %cond.store1 +; SSE4-NEXT: je LBB26_4 +; SSE4-NEXT: LBB26_3: ## %cond.store1 ; SSE4-NEXT: extractps $1, %xmm0, 4(%rdi) ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: je LBB25_6 -; SSE4-NEXT: LBB25_5: ## %cond.store3 +; SSE4-NEXT: je LBB26_6 +; SSE4-NEXT: LBB26_5: ## %cond.store3 ; SSE4-NEXT: extractps $2, %xmm0, 8(%rdi) ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: je LBB25_8 -; SSE4-NEXT: LBB25_7: ## %cond.store5 +; SSE4-NEXT: je LBB26_8 +; SSE4-NEXT: LBB26_7: ## %cond.store5 ; SSE4-NEXT: extractps $3, %xmm0, 12(%rdi) ; SSE4-NEXT: retq ; @@ -5085,7 +5184,7 @@ define void @one_mask_bit_set1_variable(<4 x float>* %addr, <4 x float> %val, <4 ; X86-AVX512-LABEL: one_mask_bit_set1_variable: ; X86-AVX512: ## %bb.0: ; X86-AVX512-NEXT: movl {{[0-9]+}}(%esp), %eax -; X86-AVX512-NEXT: vptestmd LCPI25_0{1to4}, %xmm1, %k1 +; X86-AVX512-NEXT: vptestmd LCPI26_0{1to4}, %xmm1, %k1 ; X86-AVX512-NEXT: vmovups %xmm0, (%eax) {%k1} ; X86-AVX512-NEXT: retl %mask_signbit = and <4 x i32> %mask, @@ -5108,25 +5207,25 @@ define void @widen_masked_store(<3 x i32> %v, <3 x i32>* %p, <3 x i1> %mask) { ; SSE2-NEXT: shlb $2, %cl ; SSE2-NEXT: orb %dl, %cl ; SSE2-NEXT: testb $1, %cl -; SSE2-NEXT: jne LBB26_1 +; SSE2-NEXT: jne LBB27_1 ; SSE2-NEXT: ## %bb.2: ## %else ; SSE2-NEXT: testb $2, %cl -; SSE2-NEXT: jne LBB26_3 -; SSE2-NEXT: LBB26_4: ## %else2 +; SSE2-NEXT: jne LBB27_3 +; SSE2-NEXT: LBB27_4: ## %else2 ; SSE2-NEXT: testb $4, %cl -; SSE2-NEXT: jne LBB26_5 -; SSE2-NEXT: LBB26_6: ## %else4 +; SSE2-NEXT: jne LBB27_5 +; SSE2-NEXT: LBB27_6: ## %else4 ; SSE2-NEXT: retq -; SSE2-NEXT: LBB26_1: ## %cond.store +; SSE2-NEXT: LBB27_1: ## %cond.store ; SSE2-NEXT: movd %xmm0, (%rdi) ; SSE2-NEXT: testb $2, %cl -; SSE2-NEXT: je LBB26_4 -; SSE2-NEXT: LBB26_3: ## %cond.store1 +; SSE2-NEXT: je LBB27_4 +; SSE2-NEXT: LBB27_3: ## %cond.store1 ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,1,1] ; SSE2-NEXT: movd %xmm1, 4(%rdi) ; SSE2-NEXT: testb $4, %cl -; SSE2-NEXT: je LBB26_6 -; SSE2-NEXT: LBB26_5: ## %cond.store3 +; SSE2-NEXT: je LBB27_6 +; SSE2-NEXT: LBB27_5: ## %cond.store3 ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3] ; SSE2-NEXT: movd %xmm0, 8(%rdi) ; SSE2-NEXT: retq @@ -5141,24 +5240,24 @@ define void @widen_masked_store(<3 x i32> %v, <3 x i32>* %p, <3 x i1> %mask) { ; SSE4-NEXT: shlb $2, %cl ; SSE4-NEXT: orb %dl, %cl ; SSE4-NEXT: testb $1, %cl -; SSE4-NEXT: jne LBB26_1 +; SSE4-NEXT: jne LBB27_1 ; SSE4-NEXT: ## %bb.2: ## %else ; SSE4-NEXT: testb $2, %cl -; SSE4-NEXT: jne LBB26_3 -; SSE4-NEXT: LBB26_4: ## %else2 +; SSE4-NEXT: jne LBB27_3 +; SSE4-NEXT: LBB27_4: ## %else2 ; SSE4-NEXT: testb $4, %cl -; SSE4-NEXT: jne LBB26_5 -; SSE4-NEXT: LBB26_6: ## %else4 +; SSE4-NEXT: jne LBB27_5 +; SSE4-NEXT: LBB27_6: ## %else4 ; SSE4-NEXT: retq -; SSE4-NEXT: LBB26_1: ## %cond.store +; SSE4-NEXT: LBB27_1: ## %cond.store ; SSE4-NEXT: movss %xmm0, (%rdi) ; SSE4-NEXT: testb $2, %cl -; SSE4-NEXT: je LBB26_4 -; SSE4-NEXT: LBB26_3: ## %cond.store1 +; SSE4-NEXT: je LBB27_4 +; SSE4-NEXT: LBB27_3: ## %cond.store1 ; SSE4-NEXT: extractps $1, %xmm0, 4(%rdi) ; SSE4-NEXT: testb $4, %cl -; SSE4-NEXT: je LBB26_6 -; SSE4-NEXT: LBB26_5: ## %cond.store3 +; SSE4-NEXT: je LBB27_6 +; SSE4-NEXT: LBB27_5: ## %cond.store3 ; SSE4-NEXT: extractps $2, %xmm0, 8(%rdi) ; SSE4-NEXT: retq ; @@ -5299,68 +5398,68 @@ define void @PR11210(<4 x float> %x, <4 x float>* %ptr, <4 x float> %y, <2 x i64 ; SSE2: ## %bb.0: ; SSE2-NEXT: movmskps %xmm2, %eax ; SSE2-NEXT: testb $1, %al -; SSE2-NEXT: jne LBB28_1 +; SSE2-NEXT: jne LBB29_1 ; SSE2-NEXT: ## %bb.2: ## %else ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: jne LBB28_3 -; SSE2-NEXT: LBB28_4: ## %else2 +; SSE2-NEXT: jne LBB29_3 +; SSE2-NEXT: LBB29_4: ## %else2 ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: jne LBB28_5 -; SSE2-NEXT: LBB28_6: ## %else4 +; SSE2-NEXT: jne LBB29_5 +; SSE2-NEXT: LBB29_6: ## %else4 ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: jne LBB28_7 -; SSE2-NEXT: LBB28_8: ## %else6 +; SSE2-NEXT: jne LBB29_7 +; SSE2-NEXT: LBB29_8: ## %else6 ; SSE2-NEXT: testb $1, %al -; SSE2-NEXT: jne LBB28_9 -; SSE2-NEXT: LBB28_10: ## %else9 +; SSE2-NEXT: jne LBB29_9 +; SSE2-NEXT: LBB29_10: ## %else9 ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: jne LBB28_11 -; SSE2-NEXT: LBB28_12: ## %else11 +; SSE2-NEXT: jne LBB29_11 +; SSE2-NEXT: LBB29_12: ## %else11 ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: jne LBB28_13 -; SSE2-NEXT: LBB28_14: ## %else13 +; SSE2-NEXT: jne LBB29_13 +; SSE2-NEXT: LBB29_14: ## %else13 ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: jne LBB28_15 -; SSE2-NEXT: LBB28_16: ## %else15 +; SSE2-NEXT: jne LBB29_15 +; SSE2-NEXT: LBB29_16: ## %else15 ; SSE2-NEXT: retq -; SSE2-NEXT: LBB28_1: ## %cond.store +; SSE2-NEXT: LBB29_1: ## %cond.store ; SSE2-NEXT: movss %xmm0, (%rdi) ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: je LBB28_4 -; SSE2-NEXT: LBB28_3: ## %cond.store1 +; SSE2-NEXT: je LBB29_4 +; SSE2-NEXT: LBB29_3: ## %cond.store1 ; SSE2-NEXT: movaps %xmm0, %xmm2 ; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,1],xmm0[1,1] ; SSE2-NEXT: movss %xmm2, 4(%rdi) ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: je LBB28_6 -; SSE2-NEXT: LBB28_5: ## %cond.store3 +; SSE2-NEXT: je LBB29_6 +; SSE2-NEXT: LBB29_5: ## %cond.store3 ; SSE2-NEXT: movaps %xmm0, %xmm2 ; SSE2-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1] ; SSE2-NEXT: movss %xmm2, 8(%rdi) ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: je LBB28_8 -; SSE2-NEXT: LBB28_7: ## %cond.store5 +; SSE2-NEXT: je LBB29_8 +; SSE2-NEXT: LBB29_7: ## %cond.store5 ; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3,3,3] ; SSE2-NEXT: movss %xmm0, 12(%rdi) ; SSE2-NEXT: testb $1, %al -; SSE2-NEXT: je LBB28_10 -; SSE2-NEXT: LBB28_9: ## %cond.store8 +; SSE2-NEXT: je LBB29_10 +; SSE2-NEXT: LBB29_9: ## %cond.store8 ; SSE2-NEXT: movss %xmm1, (%rdi) ; SSE2-NEXT: testb $2, %al -; SSE2-NEXT: je LBB28_12 -; SSE2-NEXT: LBB28_11: ## %cond.store10 +; SSE2-NEXT: je LBB29_12 +; SSE2-NEXT: LBB29_11: ## %cond.store10 ; SSE2-NEXT: movaps %xmm1, %xmm0 ; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1],xmm1[1,1] ; SSE2-NEXT: movss %xmm0, 4(%rdi) ; SSE2-NEXT: testb $4, %al -; SSE2-NEXT: je LBB28_14 -; SSE2-NEXT: LBB28_13: ## %cond.store12 +; SSE2-NEXT: je LBB29_14 +; SSE2-NEXT: LBB29_13: ## %cond.store12 ; SSE2-NEXT: movaps %xmm1, %xmm0 ; SSE2-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1] ; SSE2-NEXT: movss %xmm0, 8(%rdi) ; SSE2-NEXT: testb $8, %al -; SSE2-NEXT: je LBB28_16 -; SSE2-NEXT: LBB28_15: ## %cond.store14 +; SSE2-NEXT: je LBB29_16 +; SSE2-NEXT: LBB29_15: ## %cond.store14 ; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,3,3,3] ; SSE2-NEXT: movss %xmm1, 12(%rdi) ; SSE2-NEXT: retq @@ -5369,59 +5468,59 @@ define void @PR11210(<4 x float> %x, <4 x float>* %ptr, <4 x float> %y, <2 x i64 ; SSE4: ## %bb.0: ; SSE4-NEXT: movmskps %xmm2, %eax ; SSE4-NEXT: testb $1, %al -; SSE4-NEXT: jne LBB28_1 +; SSE4-NEXT: jne LBB29_1 ; SSE4-NEXT: ## %bb.2: ## %else ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: jne LBB28_3 -; SSE4-NEXT: LBB28_4: ## %else2 +; SSE4-NEXT: jne LBB29_3 +; SSE4-NEXT: LBB29_4: ## %else2 ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: jne LBB28_5 -; SSE4-NEXT: LBB28_6: ## %else4 +; SSE4-NEXT: jne LBB29_5 +; SSE4-NEXT: LBB29_6: ## %else4 ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: jne LBB28_7 -; SSE4-NEXT: LBB28_8: ## %else6 +; SSE4-NEXT: jne LBB29_7 +; SSE4-NEXT: LBB29_8: ## %else6 ; SSE4-NEXT: testb $1, %al -; SSE4-NEXT: jne LBB28_9 -; SSE4-NEXT: LBB28_10: ## %else9 +; SSE4-NEXT: jne LBB29_9 +; SSE4-NEXT: LBB29_10: ## %else9 ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: jne LBB28_11 -; SSE4-NEXT: LBB28_12: ## %else11 +; SSE4-NEXT: jne LBB29_11 +; SSE4-NEXT: LBB29_12: ## %else11 ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: jne LBB28_13 -; SSE4-NEXT: LBB28_14: ## %else13 +; SSE4-NEXT: jne LBB29_13 +; SSE4-NEXT: LBB29_14: ## %else13 ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: jne LBB28_15 -; SSE4-NEXT: LBB28_16: ## %else15 +; SSE4-NEXT: jne LBB29_15 +; SSE4-NEXT: LBB29_16: ## %else15 ; SSE4-NEXT: retq -; SSE4-NEXT: LBB28_1: ## %cond.store +; SSE4-NEXT: LBB29_1: ## %cond.store ; SSE4-NEXT: movss %xmm0, (%rdi) ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: je LBB28_4 -; SSE4-NEXT: LBB28_3: ## %cond.store1 +; SSE4-NEXT: je LBB29_4 +; SSE4-NEXT: LBB29_3: ## %cond.store1 ; SSE4-NEXT: extractps $1, %xmm0, 4(%rdi) ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: je LBB28_6 -; SSE4-NEXT: LBB28_5: ## %cond.store3 +; SSE4-NEXT: je LBB29_6 +; SSE4-NEXT: LBB29_5: ## %cond.store3 ; SSE4-NEXT: extractps $2, %xmm0, 8(%rdi) ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: je LBB28_8 -; SSE4-NEXT: LBB28_7: ## %cond.store5 +; SSE4-NEXT: je LBB29_8 +; SSE4-NEXT: LBB29_7: ## %cond.store5 ; SSE4-NEXT: extractps $3, %xmm0, 12(%rdi) ; SSE4-NEXT: testb $1, %al -; SSE4-NEXT: je LBB28_10 -; SSE4-NEXT: LBB28_9: ## %cond.store8 +; SSE4-NEXT: je LBB29_10 +; SSE4-NEXT: LBB29_9: ## %cond.store8 ; SSE4-NEXT: movss %xmm1, (%rdi) ; SSE4-NEXT: testb $2, %al -; SSE4-NEXT: je LBB28_12 -; SSE4-NEXT: LBB28_11: ## %cond.store10 +; SSE4-NEXT: je LBB29_12 +; SSE4-NEXT: LBB29_11: ## %cond.store10 ; SSE4-NEXT: extractps $1, %xmm1, 4(%rdi) ; SSE4-NEXT: testb $4, %al -; SSE4-NEXT: je LBB28_14 -; SSE4-NEXT: LBB28_13: ## %cond.store12 +; SSE4-NEXT: je LBB29_14 +; SSE4-NEXT: LBB29_13: ## %cond.store12 ; SSE4-NEXT: extractps $2, %xmm1, 8(%rdi) ; SSE4-NEXT: testb $8, %al -; SSE4-NEXT: je LBB28_16 -; SSE4-NEXT: LBB28_15: ## %cond.store14 +; SSE4-NEXT: je LBB29_16 +; SSE4-NEXT: LBB29_15: ## %cond.store14 ; SSE4-NEXT: extractps $3, %xmm1, 12(%rdi) ; SSE4-NEXT: retq ; @@ -5484,6 +5583,7 @@ declare void @llvm.masked.store.v8f32.p0v8f32(<8 x float>, <8 x float>*, i32, <8 declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>) declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>) +declare void @llvm.masked.store.v16i64.p0v16i64(<16 x i64>, <16 x i64>*, i32, <16 x i1>) declare void @llvm.masked.store.v8i64.p0v8i64(<8 x i64>, <8 x i64>*, i32, <8 x i1>) declare void @llvm.masked.store.v4i64.p0v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>) declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)