diff options
Diffstat (limited to 'llvm/test/CodeGen')
5 files changed, 47 insertions, 56 deletions
diff --git a/llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll index 20327658a7b..a526518c3fe 100644 --- a/llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll +++ b/llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll @@ -29,11 +29,10 @@ define i16 @unpckbw_test(i16 %a0, i16 %a1) { define <16 x i32>@test_int_x86_avx512_mask_pbroadcastd_gpr_512(i32 %x0, <16 x i32> %x1, i16 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcastd_gpr_512: ; X86: ## %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax ## encoding: [0x8b,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastd %eax, %zmm1 ## encoding: [0x62,0xf2,0x7d,0x48,0x7c,0xc8] +; X86-NEXT: vpbroadcastd {{[0-9]+}}(%esp), %zmm1 ## encoding: [0x62,0xf2,0x7d,0x48,0x58,0x4c,0x24,0x01] ; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 ## encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastd %eax, %zmm0 {%k1} ## encoding: [0x62,0xf2,0x7d,0x49,0x7c,0xc0] -; X86-NEXT: vpbroadcastd %eax, %zmm2 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xc9,0x7c,0xd0] +; X86-NEXT: vmovdqa32 %zmm1, %zmm0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x49,0x6f,0xc1] +; X86-NEXT: vmovdqa32 %zmm1, %zmm2 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xc9,0x6f,0xd1] ; X86-NEXT: vpaddd %zmm2, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7d,0x48,0xfe,0xc2] ; X86-NEXT: vpaddd %zmm0, %zmm1, %zmm0 ## encoding: [0x62,0xf1,0x75,0x48,0xfe,0xc0] ; X86-NEXT: retl ## encoding: [0xc3] diff --git a/llvm/test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll index beea392fc17..0ca1f7be885 100644 --- a/llvm/test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll +++ b/llvm/test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll @@ -49,11 +49,10 @@ declare <64 x i8> @llvm.x86.avx512.mask.pbroadcast.b.gpr.512(i8, <64 x i8>, i64) define <64 x i8>@test_int_x86_avx512_mask_pbroadcast_b_gpr_512(i8 %x0, <64 x i8> %x1, i64 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_b_gpr_512: ; X86: # %bb.0: -; X86-NEXT: movb {{[0-9]+}}(%esp), %al # encoding: [0x8a,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastb %eax, %zmm1 # encoding: [0x62,0xf2,0x7d,0x48,0x7a,0xc8] +; X86-NEXT: vpbroadcastb {{[0-9]+}}(%esp), %zmm1 # encoding: [0x62,0xf2,0x7d,0x48,0x78,0x4c,0x24,0x04] ; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastb %eax, %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x7a,0xc0] -; X86-NEXT: vpbroadcastb %eax, %zmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x7a,0xd0] +; X86-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1} # encoding: [0x62,0xf1,0x7f,0x49,0x6f,0xc1] +; X86-NEXT: vmovdqu8 %zmm1, %zmm2 {%k1} {z} # encoding: [0x62,0xf1,0x7f,0xc9,0x6f,0xd1] ; X86-NEXT: vpaddb %zmm2, %zmm0, %zmm0 # encoding: [0x62,0xf1,0x7d,0x48,0xfc,0xc2] ; X86-NEXT: vpaddb %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0x75,0x48,0xfc,0xc0] ; X86-NEXT: retl # encoding: [0xc3] @@ -79,11 +78,10 @@ declare <32 x i16> @llvm.x86.avx512.mask.pbroadcast.w.gpr.512(i16, <32 x i16>, i define <32 x i16>@test_int_x86_avx512_mask_pbroadcast_w_gpr_512(i16 %x0, <32 x i16> %x1, i32 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_w_gpr_512: ; X86: # %bb.0: -; X86-NEXT: movzwl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb7,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastw %eax, %zmm1 # encoding: [0x62,0xf2,0x7d,0x48,0x7b,0xc8] +; X86-NEXT: vpbroadcastw {{[0-9]+}}(%esp), %zmm1 # encoding: [0x62,0xf2,0x7d,0x48,0x79,0x4c,0x24,0x02] ; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastw %eax, %zmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0x7b,0xc0] -; X86-NEXT: vpbroadcastw %eax, %zmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0x7b,0xd0] +; X86-NEXT: vmovdqu16 %zmm1, %zmm0 {%k1} # encoding: [0x62,0xf1,0xff,0x49,0x6f,0xc1] +; X86-NEXT: vmovdqu16 %zmm1, %zmm2 {%k1} {z} # encoding: [0x62,0xf1,0xff,0xc9,0x6f,0xd1] ; X86-NEXT: vpaddw %zmm2, %zmm0, %zmm0 # encoding: [0x62,0xf1,0x7d,0x48,0xfd,0xc2] ; X86-NEXT: vpaddw %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0x75,0x48,0xfd,0xc0] ; X86-NEXT: retl # encoding: [0xc3] diff --git a/llvm/test/CodeGen/X86/avx512bwvl-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512bwvl-intrinsics-upgrade.ll index bd7969e9969..8907578cd33 100644 --- a/llvm/test/CodeGen/X86/avx512bwvl-intrinsics-upgrade.ll +++ b/llvm/test/CodeGen/X86/avx512bwvl-intrinsics-upgrade.ll @@ -7,11 +7,10 @@ declare <16 x i8> @llvm.x86.avx512.mask.pbroadcast.b.gpr.128(i8, <16 x i8>, i16) define <16 x i8>@test_int_x86_avx512_mask_pbroadcast_b_gpr_128(i8 %x0, <16 x i8> %x1, i16 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_b_gpr_128: ; X86: # %bb.0: -; X86-NEXT: movb {{[0-9]+}}(%esp), %al # encoding: [0x8a,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastb %eax, %xmm1 # encoding: [0x62,0xf2,0x7d,0x08,0x7a,0xc8] +; X86-NEXT: vpbroadcastb {{[0-9]+}}(%esp), %xmm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x78,0x4c,0x24,0x04] ; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastb %eax, %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x7a,0xc0] -; X86-NEXT: vpbroadcastb %eax, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x7a,0xd0] +; X86-NEXT: vmovdqu8 %xmm1, %xmm0 {%k1} # encoding: [0x62,0xf1,0x7f,0x09,0x6f,0xc1] +; X86-NEXT: vmovdqu8 %xmm1, %xmm2 {%k1} {z} # encoding: [0x62,0xf1,0x7f,0x89,0x6f,0xd1] ; X86-NEXT: vpaddb %xmm2, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc2] ; X86-NEXT: vpaddb %xmm0, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xc0] ; X86-NEXT: retl # encoding: [0xc3] @@ -39,12 +38,11 @@ declare <8 x i16> @llvm.x86.avx512.mask.pbroadcast.w.gpr.128(i16, <8 x i16>, i8) define <8 x i16>@test_int_x86_avx512_mask_pbroadcast_w_gpr_128(i16 %x0, <8 x i16> %x1, i8 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_w_gpr_128: ; X86: # %bb.0: -; X86-NEXT: movzwl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb7,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastw %eax, %xmm1 # encoding: [0x62,0xf2,0x7d,0x08,0x7b,0xc8] -; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08] -; X86-NEXT: kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9] -; X86-NEXT: vpbroadcastw %eax, %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x7b,0xc0] -; X86-NEXT: vpbroadcastw %eax, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x7b,0xd0] +; X86-NEXT: vpbroadcastw {{[0-9]+}}(%esp), %xmm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x79,0x4c,0x24,0x04] +; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08] +; X86-NEXT: kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8] +; X86-NEXT: vmovdqu16 %xmm1, %xmm0 {%k1} # encoding: [0x62,0xf1,0xff,0x09,0x6f,0xc1] +; X86-NEXT: vmovdqu16 %xmm1, %xmm2 {%k1} {z} # encoding: [0x62,0xf1,0xff,0x89,0x6f,0xd1] ; X86-NEXT: vpaddw %xmm2, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc2] ; X86-NEXT: vpaddw %xmm0, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc0] ; X86-NEXT: retl # encoding: [0xc3] @@ -72,11 +70,10 @@ define <8 x i16>@test_int_x86_avx512_mask_pbroadcast_w_gpr_128(i16 %x0, <8 x i16 define <32 x i8>@test_int_x86_avx512_mask_pbroadcast_b_gpr_256(i8 %x0, <32 x i8> %x1, i32 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_b_gpr_256: ; X86: # %bb.0: -; X86-NEXT: movb {{[0-9]+}}(%esp), %al # encoding: [0x8a,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastb %eax, %ymm1 # encoding: [0x62,0xf2,0x7d,0x28,0x7a,0xc8] +; X86-NEXT: vpbroadcastb {{[0-9]+}}(%esp), %ymm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x78,0x4c,0x24,0x04] ; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastb %eax, %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x7a,0xc0] -; X86-NEXT: vpbroadcastb %eax, %ymm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x7a,0xd0] +; X86-NEXT: vmovdqu8 %ymm1, %ymm0 {%k1} # encoding: [0x62,0xf1,0x7f,0x29,0x6f,0xc1] +; X86-NEXT: vmovdqu8 %ymm1, %ymm2 {%k1} {z} # encoding: [0x62,0xf1,0x7f,0xa9,0x6f,0xd1] ; X86-NEXT: vpaddb %ymm2, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfc,0xc2] ; X86-NEXT: vpaddb %ymm0, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfc,0xc0] ; X86-NEXT: retl # encoding: [0xc3] @@ -105,11 +102,10 @@ declare <16 x i16> @llvm.x86.avx512.mask.pbroadcast.w.gpr.256(i16, <16 x i16>, i define <16 x i16>@test_int_x86_avx512_mask_pbroadcast_w_gpr_256(i16 %x0, <16 x i16> %x1, i16 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_w_gpr_256: ; X86: # %bb.0: -; X86-NEXT: movzwl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb7,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastw %eax, %ymm1 # encoding: [0x62,0xf2,0x7d,0x28,0x7b,0xc8] +; X86-NEXT: vpbroadcastw {{[0-9]+}}(%esp), %ymm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x79,0x4c,0x24,0x04] ; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08] -; X86-NEXT: vpbroadcastw %eax, %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x7b,0xc0] -; X86-NEXT: vpbroadcastw %eax, %ymm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x7b,0xd0] +; X86-NEXT: vmovdqu16 %ymm1, %ymm0 {%k1} # encoding: [0x62,0xf1,0xff,0x29,0x6f,0xc1] +; X86-NEXT: vmovdqu16 %ymm1, %ymm2 {%k1} {z} # encoding: [0x62,0xf1,0xff,0xa9,0x6f,0xd1] ; X86-NEXT: vpaddw %ymm2, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc2] ; X86-NEXT: vpaddw %ymm0, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc0] ; X86-NEXT: retl # encoding: [0xc3] diff --git a/llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll b/llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll index 022ec6c6855..8684d1f568f 100644 --- a/llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll +++ b/llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll @@ -7,12 +7,11 @@ declare <4 x i32> @llvm.x86.avx512.mask.pbroadcast.d.gpr.128(i32, <4 x i32>, i8) define <4 x i32>@test_int_x86_avx512_mask_pbroadcast_d_gpr_128(i32 %x0, <4 x i32> %x1, i8 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_d_gpr_128: ; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastd %eax, %xmm1 # encoding: [0x62,0xf2,0x7d,0x08,0x7c,0xc8] -; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08] -; X86-NEXT: kmovw %ecx, %k1 # encoding: [0xc5,0xf8,0x92,0xc9] -; X86-NEXT: vpbroadcastd %eax, %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x7c,0xc0] -; X86-NEXT: vpbroadcastd %eax, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x7c,0xd0] +; X86-NEXT: vpbroadcastd {{[0-9]+}}(%esp), %xmm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x58,0x4c,0x24,0x04] +; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08] +; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8] +; X86-NEXT: vmovdqa32 %xmm1, %xmm0 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x6f,0xc1] +; X86-NEXT: vmovdqa32 %xmm1, %xmm2 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x6f,0xd1] ; X86-NEXT: vpaddd %xmm2, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfe,0xc2] ; X86-NEXT: vpaddd %xmm0, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfe,0xc0] ; X86-NEXT: retl # encoding: [0xc3] @@ -72,12 +71,11 @@ define <2 x i64>@test_int_x86_avx512_mask_pbroadcast_q_gpr_128(i64 %x0, <2 x i64 define <8 x i32>@test_int_x86_avx512_mask_pbroadcast_d_gpr_256(i32 %x0, <8 x i32> %x1, i8 %mask) { ; X86-LABEL: test_int_x86_avx512_mask_pbroadcast_d_gpr_256: ; X86: # %bb.0: -; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04] -; X86-NEXT: vpbroadcastd %eax, %ymm1 # encoding: [0x62,0xf2,0x7d,0x28,0x7c,0xc8] -; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08] -; X86-NEXT: kmovw %ecx, %k1 # encoding: [0xc5,0xf8,0x92,0xc9] -; X86-NEXT: vpbroadcastd %eax, %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x7c,0xc0] -; X86-NEXT: vpbroadcastd %eax, %ymm2 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x7c,0xd0] +; X86-NEXT: vpbroadcastd {{[0-9]+}}(%esp), %ymm1 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x58,0x4c,0x24,0x04] +; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08] +; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8] +; X86-NEXT: vmovdqa32 %ymm1, %ymm0 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x6f,0xc1] +; X86-NEXT: vmovdqa32 %ymm1, %ymm2 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x6f,0xd1] ; X86-NEXT: vpaddd %ymm2, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfe,0xc2] ; X86-NEXT: vpaddd %ymm0, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfe,0xc0] ; X86-NEXT: retl # encoding: [0xc3] diff --git a/llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll b/llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll index 07e5f7a029c..af1abe71e2f 100644 --- a/llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll +++ b/llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll @@ -496,12 +496,12 @@ define <32 x i8> @ext_i32_32i8(i32 %a0) { ; AVX512F-NEXT: kmovw %edi, %k1 ; AVX512F-NEXT: shrl $16, %edi ; AVX512F-NEXT: kmovw %edi, %k2 -; AVX512F-NEXT: movl {{.*}}(%rip), %eax -; AVX512F-NEXT: vpbroadcastd %eax, %zmm0 {%k1} {z} -; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 -; AVX512F-NEXT: vpbroadcastd %eax, %zmm1 {%k2} {z} +; AVX512F-NEXT: vpbroadcastd {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm1 {%k1} {z} ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 -; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm0 {%k2} {z} +; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 +; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0 ; AVX512F-NEXT: retq ; ; AVX512VLBW-LABEL: ext_i32_32i8: @@ -898,18 +898,18 @@ define <64 x i8> @ext_i64_64i8(i64 %a0) { ; AVX512F-NEXT: kmovw %ecx, %k2 ; AVX512F-NEXT: kmovw %eax, %k3 ; AVX512F-NEXT: kmovw %edi, %k4 -; AVX512F-NEXT: movl {{.*}}(%rip), %eax -; AVX512F-NEXT: vpbroadcastd %eax, %zmm0 {%k4} {z} -; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 -; AVX512F-NEXT: vpbroadcastd %eax, %zmm1 {%k3} {z} -; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 -; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 -; AVX512F-NEXT: vpbroadcastd %eax, %zmm1 {%k1} {z} +; AVX512F-NEXT: vpbroadcastd {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm1 {%k4} {z} ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 -; AVX512F-NEXT: vpbroadcastd %eax, %zmm2 {%k2} {z} +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm2 {%k3} {z} ; AVX512F-NEXT: vpmovdb %zmm2, %xmm2 ; AVX512F-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1 -; AVX512F-NEXT: vinserti64x4 $1, %ymm0, %zmm1, %zmm0 +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm2 {%k1} {z} +; AVX512F-NEXT: vpmovdb %zmm2, %xmm2 +; AVX512F-NEXT: vmovdqa32 %zmm0, %zmm0 {%k2} {z} +; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 +; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm2, %ymm0 +; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0 ; AVX512F-NEXT: retq ; ; AVX512VLBW-LABEL: ext_i64_64i8: |
