| ; 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 |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1 |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512DQ |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW |
| |
| ; |
| ; 128-bit vector comparisons |
| ; |
| |
| define <2 x i1> @test_cmp_v2f64(<2 x double> %a0, <2 x double> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v2f64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltpd %xmm0, %xmm1 |
| ; SSE-NEXT: movapd %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v2f64: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vcmpltpd %xmm0, %xmm1, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = fcmp ogt <2 x double> %a0, %a1 |
| ret <2 x i1> %1 |
| } |
| |
| define <4 x i1> @test_cmp_v4f32(<4 x float> %a0, <4 x float> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v4f32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltps %xmm0, %xmm1 |
| ; SSE-NEXT: movaps %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v4f32: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vcmpltps %xmm0, %xmm1, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = fcmp ogt <4 x float> %a0, %a1 |
| ret <4 x i1> %1 |
| } |
| |
| define <2 x i1> @test_cmp_v2i64(<2 x i64> %a0, <2 x i64> %a1) nounwind { |
| ; SSE2-LABEL: test_cmp_v2i64: |
| ; SSE2: # %bb.0: |
| ; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648] |
| ; SSE2-NEXT: pxor %xmm2, %xmm1 |
| ; SSE2-NEXT: pxor %xmm2, %xmm0 |
| ; SSE2-NEXT: movdqa %xmm0, %xmm2 |
| ; SSE2-NEXT: pcmpgtd %xmm1, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm1, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm3, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm0 |
| ; SSE2-NEXT: retq |
| ; |
| ; SSE42-LABEL: test_cmp_v2i64: |
| ; SSE42: # %bb.0: |
| ; SSE42-NEXT: pcmpgtq %xmm1, %xmm0 |
| ; SSE42-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v2i64: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = icmp sgt <2 x i64> %a0, %a1 |
| ret <2 x i1> %1 |
| } |
| |
| define <4 x i1> @test_cmp_v4i32(<4 x i32> %a0, <4 x i32> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v4i32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtd %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v4i32: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = icmp sgt <4 x i32> %a0, %a1 |
| ret <4 x i1> %1 |
| } |
| |
| define <8 x i1> @test_cmp_v8i16(<8 x i16> %a0, <8 x i16> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v8i16: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtw %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v8i16: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = icmp sgt <8 x i16> %a0, %a1 |
| ret <8 x i1> %1 |
| } |
| |
| define <16 x i1> @test_cmp_v16i8(<16 x i8> %a0, <16 x i8> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v16i8: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtb %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_cmp_v16i8: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0 |
| ; AVX-NEXT: retq |
| %1 = icmp sgt <16 x i8> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| ; |
| ; 256-bit vector comparisons |
| ; |
| |
| define <4 x i1> @test_cmp_v4f64(<4 x double> %a0, <4 x double> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v4f64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltpd %xmm1, %xmm3 |
| ; SSE-NEXT: cmpltpd %xmm0, %xmm2 |
| ; SSE-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE-NEXT: movdqa %xmm2, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v4f64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v4f64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0 |
| ; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512-LABEL: test_cmp_v4f64: |
| ; AVX512: # %bb.0: |
| ; AVX512-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0 |
| ; AVX512-NEXT: vpmovqd %zmm0, %ymm0 |
| ; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512-NEXT: vzeroupper |
| ; AVX512-NEXT: retq |
| %1 = fcmp ogt <4 x double> %a0, %a1 |
| ret <4 x i1> %1 |
| } |
| |
| define <8 x i1> @test_cmp_v8f32(<8 x float> %a0, <8 x float> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v8f32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltps %xmm1, %xmm3 |
| ; SSE-NEXT: cmpltps %xmm0, %xmm2 |
| ; SSE-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE-NEXT: movdqa %xmm2, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v8f32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltps %ymm0, %ymm1, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v8f32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltps %ymm0, %ymm1, %ymm0 |
| ; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512-LABEL: test_cmp_v8f32: |
| ; AVX512: # %bb.0: |
| ; AVX512-NEXT: vcmpltps %ymm0, %ymm1, %ymm0 |
| ; AVX512-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512-NEXT: vzeroupper |
| ; AVX512-NEXT: retq |
| %1 = fcmp ogt <8 x float> %a0, %a1 |
| ret <8 x i1> %1 |
| } |
| |
| define <4 x i1> @test_cmp_v4i64(<4 x i64> %a0, <4 x i64> %a1) nounwind { |
| ; SSE2-LABEL: test_cmp_v4i64: |
| ; SSE2: # %bb.0: |
| ; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648] |
| ; SSE2-NEXT: pxor %xmm4, %xmm3 |
| ; SSE2-NEXT: pxor %xmm4, %xmm1 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm5 |
| ; SSE2-NEXT: pcmpgtd %xmm3, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm3, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm6, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm3 |
| ; SSE2-NEXT: pxor %xmm4, %xmm2 |
| ; SSE2-NEXT: pxor %xmm4, %xmm0 |
| ; SSE2-NEXT: movdqa %xmm0, %xmm1 |
| ; SSE2-NEXT: pcmpgtd %xmm2, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm1[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm2, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm4, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: por %xmm2, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm3, %xmm0 |
| ; SSE2-NEXT: retq |
| ; |
| ; SSE42-LABEL: test_cmp_v4i64: |
| ; SSE42: # %bb.0: |
| ; SSE42-NEXT: pcmpgtq %xmm3, %xmm1 |
| ; SSE42-NEXT: pcmpgtq %xmm2, %xmm0 |
| ; SSE42-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE42-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v4i64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2 |
| ; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v4i64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512-LABEL: test_cmp_v4i64: |
| ; AVX512: # %bb.0: |
| ; AVX512-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0 |
| ; AVX512-NEXT: vpmovqd %zmm0, %ymm0 |
| ; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512-NEXT: vzeroupper |
| ; AVX512-NEXT: retq |
| %1 = icmp sgt <4 x i64> %a0, %a1 |
| ret <4 x i1> %1 |
| } |
| |
| define <8 x i1> @test_cmp_v8i32(<8 x i32> %a0, <8 x i32> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v8i32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtd %xmm3, %xmm1 |
| ; SSE-NEXT: pcmpgtd %xmm2, %xmm0 |
| ; SSE-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v8i32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2 |
| ; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v8i32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512-LABEL: test_cmp_v8i32: |
| ; AVX512: # %bb.0: |
| ; AVX512-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0 |
| ; AVX512-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512-NEXT: vzeroupper |
| ; AVX512-NEXT: retq |
| %1 = icmp sgt <8 x i32> %a0, %a1 |
| ret <8 x i1> %1 |
| } |
| |
| define <16 x i1> @test_cmp_v16i16(<16 x i16> %a0, <16 x i16> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v16i16: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtw %xmm3, %xmm1 |
| ; SSE-NEXT: pcmpgtw %xmm2, %xmm0 |
| ; SSE-NEXT: packsswb %xmm1, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v16i16: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpcmpgtw %xmm2, %xmm3, %xmm2 |
| ; AVX1-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v16i16: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v16i16: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v16i16: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v16i16: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0 |
| ; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <16 x i16> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| define <32 x i1> @test_cmp_v32i8(<32 x i8> %a0, <32 x i8> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v32i8: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtb %xmm2, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtb %xmm3, %xmm1 |
| ; SSE-NEXT: pmovmskb %xmm1, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: movl %edx, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32i8: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpcmpgtb %xmm2, %xmm3, %xmm2 |
| ; AVX1-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0 |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32i8: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtb %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512-LABEL: test_cmp_v32i8: |
| ; AVX512: # %bb.0: |
| ; AVX512-NEXT: vpcmpgtb %ymm1, %ymm0, %ymm0 |
| ; AVX512-NEXT: retq |
| %1 = icmp sgt <32 x i8> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
| |
| ; |
| ; 512-bit vector comparisons |
| ; |
| |
| define <8 x i1> @test_cmp_v8f64(<8 x double> %a0, <8 x double> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v8f64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltpd %xmm3, %xmm7 |
| ; SSE-NEXT: cmpltpd %xmm2, %xmm6 |
| ; SSE-NEXT: packssdw %xmm7, %xmm6 |
| ; SSE-NEXT: cmpltpd %xmm1, %xmm5 |
| ; SSE-NEXT: cmpltpd %xmm0, %xmm4 |
| ; SSE-NEXT: packssdw %xmm5, %xmm4 |
| ; SSE-NEXT: packssdw %xmm6, %xmm4 |
| ; SSE-NEXT: movdqa %xmm4, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v8f64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltpd %ymm1, %ymm3, %ymm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vcmpltpd %ymm0, %ymm2, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v8f64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltpd %ymm1, %ymm3, %ymm1 |
| ; AVX2-NEXT: vcmpltpd %ymm0, %ymm2, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v8f64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vcmpltpd %zmm0, %zmm1, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v8f64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vcmpltpd %zmm0, %zmm1, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v8f64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vcmpltpd %zmm0, %zmm1, %k0 |
| ; AVX512BW-NEXT: vpmovm2w %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = fcmp ogt <8 x double> %a0, %a1 |
| ret <8 x i1> %1 |
| } |
| |
| define <16 x i1> @test_cmp_v16f32(<16 x float> %a0, <16 x float> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v16f32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cmpltps %xmm3, %xmm7 |
| ; SSE-NEXT: cmpltps %xmm2, %xmm6 |
| ; SSE-NEXT: packssdw %xmm7, %xmm6 |
| ; SSE-NEXT: cmpltps %xmm1, %xmm5 |
| ; SSE-NEXT: cmpltps %xmm0, %xmm4 |
| ; SSE-NEXT: packssdw %xmm5, %xmm4 |
| ; SSE-NEXT: packsswb %xmm6, %xmm4 |
| ; SSE-NEXT: movdqa %xmm4, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v16f32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltps %ymm1, %ymm3, %ymm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vcmpltps %ymm0, %ymm2, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v16f32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltps %ymm1, %ymm3, %ymm1 |
| ; AVX2-NEXT: vcmpltps %ymm0, %ymm2, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v16f32: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vcmpltps %zmm0, %zmm1, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v16f32: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vcmpltps %zmm0, %zmm1, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v16f32: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vcmpltps %zmm0, %zmm1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = fcmp ogt <16 x float> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| define <8 x i1> @test_cmp_v8i64(<8 x i64> %a0, <8 x i64> %a1) nounwind { |
| ; SSE2-LABEL: test_cmp_v8i64: |
| ; SSE2: # %bb.0: |
| ; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648] |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm9 |
| ; SSE2-NEXT: pcmpgtd %xmm7, %xmm9 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm9[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm7, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm10, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm9[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm6 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa %xmm2, %xmm3 |
| ; SSE2-NEXT: pcmpgtd %xmm6, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm3[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm6, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm2[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm9, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: por %xmm6, %xmm2 |
| ; SSE2-NEXT: packssdw %xmm7, %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm3 |
| ; SSE2-NEXT: pcmpgtd %xmm5, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm3[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm5, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm6, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm4 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa %xmm0, %xmm1 |
| ; SSE2-NEXT: pcmpgtd %xmm4, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm1[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm4, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm4 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: por %xmm4, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm3, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE2-NEXT: retq |
| ; |
| ; SSE42-LABEL: test_cmp_v8i64: |
| ; SSE42: # %bb.0: |
| ; SSE42-NEXT: pcmpgtq %xmm7, %xmm3 |
| ; SSE42-NEXT: pcmpgtq %xmm6, %xmm2 |
| ; SSE42-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE42-NEXT: pcmpgtq %xmm5, %xmm1 |
| ; SSE42-NEXT: pcmpgtq %xmm4, %xmm0 |
| ; SSE42-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE42-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE42-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v8i64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq %xmm4, %xmm5, %xmm4 |
| ; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm4, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4 |
| ; AVX1-NEXT: vpcmpgtq %xmm3, %xmm4, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v8i64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtq %ymm3, %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v8i64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtq %zmm1, %zmm0, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v8i64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm1, %zmm0, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdw %zmm0, %ymm0 |
| ; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v8i64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtq %zmm1, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpmovm2w %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <8 x i64> %a0, %a1 |
| ret <8 x i1> %1 |
| } |
| |
| define <16 x i1> @test_cmp_v16i32(<16 x i32> %a0, <16 x i32> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v16i32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: pcmpgtd %xmm7, %xmm3 |
| ; SSE-NEXT: pcmpgtd %xmm6, %xmm2 |
| ; SSE-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE-NEXT: pcmpgtd %xmm5, %xmm1 |
| ; SSE-NEXT: pcmpgtd %xmm4, %xmm0 |
| ; SSE-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE-NEXT: packsswb %xmm2, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v16i32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5 |
| ; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4 |
| ; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm4, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4 |
| ; AVX1-NEXT: vpcmpgtd %xmm3, %xmm4, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v16i32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtd %ymm3, %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtd %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v16i32: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtd %zmm1, %zmm0, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v16i32: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtd %zmm1, %zmm0, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v16i32: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtd %zmm1, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <16 x i32> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| define <32 x i1> @test_cmp_v32i16(<32 x i16> %a0, <32 x i16> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v32i16: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtw %xmm5, %xmm1 |
| ; SSE-NEXT: pcmpgtw %xmm4, %xmm0 |
| ; SSE-NEXT: packsswb %xmm1, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtw %xmm7, %xmm3 |
| ; SSE-NEXT: pcmpgtw %xmm6, %xmm2 |
| ; SSE-NEXT: packsswb %xmm3, %xmm2 |
| ; SSE-NEXT: pmovmskb %xmm2, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: movl %edx, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32i16: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5 |
| ; AVX1-NEXT: vpcmpgtw %xmm4, %xmm5, %xmm4 |
| ; AVX1-NEXT: vpcmpgtw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpacksswb %xmm4, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4 |
| ; AVX1-NEXT: vpcmpgtw %xmm3, %xmm4, %xmm3 |
| ; AVX1-NEXT: vpcmpgtw %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32i16: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtw %ymm3, %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtw %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpacksswb %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v32i16: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtw %ymm2, %ymm0, %ymm0 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpcmpgtw %ymm3, %ymm1, %ymm1 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v32i16: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm2, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm3, %ymm1, %ymm1 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v32i16: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtw %zmm1, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <32 x i16> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
| |
| define <64 x i1> @test_cmp_v64i8(<64 x i8> %a0, <64 x i8> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v64i8: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtb %xmm4, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtb %xmm5, %xmm1 |
| ; SSE-NEXT: pmovmskb %xmm1, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: pcmpgtb %xmm6, %xmm2 |
| ; SSE-NEXT: pmovmskb %xmm2, %ecx |
| ; SSE-NEXT: pcmpgtb %xmm7, %xmm3 |
| ; SSE-NEXT: pmovmskb %xmm3, %esi |
| ; SSE-NEXT: shll $16, %esi |
| ; SSE-NEXT: orl %ecx, %esi |
| ; SSE-NEXT: shlq $32, %rsi |
| ; SSE-NEXT: orq %rdx, %rsi |
| ; SSE-NEXT: movq %rsi, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v64i8: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: movq %rdi, %rax |
| ; AVX1-NEXT: vpcmpgtb %xmm2, %xmm0, %xmm4 |
| ; AVX1-NEXT: vpmovmskb %xmm4, %ecx |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 |
| ; AVX1-NEXT: vpcmpgtb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edx |
| ; AVX1-NEXT: shll $16, %edx |
| ; AVX1-NEXT: orl %ecx, %edx |
| ; AVX1-NEXT: vpcmpgtb %xmm3, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %ecx |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1 |
| ; AVX1-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %esi |
| ; AVX1-NEXT: shll $16, %esi |
| ; AVX1-NEXT: orl %ecx, %esi |
| ; AVX1-NEXT: shlq $32, %rsi |
| ; AVX1-NEXT: orq %rdx, %rsi |
| ; AVX1-NEXT: movq %rsi, (%rdi) |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v64i8: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: movq %rdi, %rax |
| ; AVX2-NEXT: vpcmpgtb %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %ecx |
| ; AVX2-NEXT: vpcmpgtb %ymm3, %ymm1, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %edx |
| ; AVX2-NEXT: shlq $32, %rdx |
| ; AVX2-NEXT: orq %rcx, %rdx |
| ; AVX2-NEXT: movq %rdx, (%rdi) |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v64i8: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtb %ymm2, %ymm0, %ymm0 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm4 |
| ; AVX512F-NEXT: vpcmpgtb %ymm3, %ymm1, %ymm2 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm2, %xmm3 |
| ; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512F-NEXT: vmovdqa %xmm4, %xmm1 |
| ; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 killed $ymm2 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v64i8: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm2, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm0, %xmm4 |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm3, %ymm1, %ymm2 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm2, %xmm3 |
| ; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0 |
| ; AVX512DQ-NEXT: vmovdqa %xmm4, %xmm1 |
| ; AVX512DQ-NEXT: # kill: def $xmm2 killed $xmm2 killed $ymm2 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v64i8: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtb %zmm1, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <64 x i8> %a0, %a1 |
| ret <64 x i1> %1 |
| } |
| |
| ; |
| ; 1024-bit vector comparisons |
| ; |
| |
| define <16 x i1> @test_cmp_v16f64(<16 x double> %a0, <16 x double> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v16f64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movapd %xmm0, %xmm8 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm11 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm10 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm12 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm13 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm14 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm15 |
| ; SSE-NEXT: cmpltpd %xmm7, %xmm15 |
| ; SSE-NEXT: cmpltpd %xmm6, %xmm14 |
| ; SSE-NEXT: packssdw %xmm15, %xmm14 |
| ; SSE-NEXT: cmpltpd %xmm5, %xmm13 |
| ; SSE-NEXT: cmpltpd %xmm4, %xmm9 |
| ; SSE-NEXT: packssdw %xmm13, %xmm9 |
| ; SSE-NEXT: packssdw %xmm14, %xmm9 |
| ; SSE-NEXT: cmpltpd %xmm3, %xmm12 |
| ; SSE-NEXT: cmpltpd %xmm2, %xmm10 |
| ; SSE-NEXT: packssdw %xmm12, %xmm10 |
| ; SSE-NEXT: cmpltpd %xmm1, %xmm11 |
| ; SSE-NEXT: cmpltpd %xmm8, %xmm0 |
| ; SSE-NEXT: packssdw %xmm11, %xmm0 |
| ; SSE-NEXT: packssdw %xmm10, %xmm0 |
| ; SSE-NEXT: packsswb %xmm9, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v16f64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltpd %ymm3, %ymm7, %ymm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vcmpltpd %ymm2, %ymm6, %ymm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm6 |
| ; AVX1-NEXT: vpackssdw %xmm6, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vcmpltpd %ymm1, %ymm5, %ymm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vcmpltpd %ymm0, %ymm4, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v16f64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltpd %ymm3, %ymm7, %ymm3 |
| ; AVX2-NEXT: vcmpltpd %ymm2, %ymm6, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vcmpltpd %ymm1, %ymm5, %ymm1 |
| ; AVX2-NEXT: vcmpltpd %ymm0, %ymm4, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v16f64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vcmpltpd %zmm0, %zmm2, %k0 |
| ; AVX512F-NEXT: vcmpltpd %zmm1, %zmm3, %k1 |
| ; AVX512F-NEXT: kunpckbw %k0, %k1, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v16f64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vcmpltpd %zmm0, %zmm2, %k0 |
| ; AVX512DQ-NEXT: vcmpltpd %zmm1, %zmm3, %k1 |
| ; AVX512DQ-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v16f64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vcmpltpd %zmm0, %zmm2, %k0 |
| ; AVX512BW-NEXT: vcmpltpd %zmm1, %zmm3, %k1 |
| ; AVX512BW-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = fcmp ogt <16 x double> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| define <32 x i1> @test_cmp_v32f32(<32 x float> %a0, <32 x float> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v32f32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm10 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm11 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm12 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm13 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm14 |
| ; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm15 |
| ; SSE-NEXT: cmpltps %xmm3, %xmm15 |
| ; SSE-NEXT: cmpltps %xmm2, %xmm14 |
| ; SSE-NEXT: packssdw %xmm15, %xmm14 |
| ; SSE-NEXT: cmpltps %xmm1, %xmm13 |
| ; SSE-NEXT: cmpltps %xmm0, %xmm12 |
| ; SSE-NEXT: packssdw %xmm13, %xmm12 |
| ; SSE-NEXT: packsswb %xmm14, %xmm12 |
| ; SSE-NEXT: pmovmskb %xmm12, %ecx |
| ; SSE-NEXT: cmpltps %xmm7, %xmm11 |
| ; SSE-NEXT: cmpltps %xmm6, %xmm9 |
| ; SSE-NEXT: packssdw %xmm11, %xmm9 |
| ; SSE-NEXT: cmpltps %xmm5, %xmm10 |
| ; SSE-NEXT: cmpltps %xmm4, %xmm8 |
| ; SSE-NEXT: packssdw %xmm10, %xmm8 |
| ; SSE-NEXT: packsswb %xmm9, %xmm8 |
| ; SSE-NEXT: pmovmskb %xmm8, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: movl %edx, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32f32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vcmpltps %ymm3, %ymm7, %ymm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vcmpltps %ymm2, %ymm6, %ymm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm6 |
| ; AVX1-NEXT: vpackssdw %xmm6, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpacksswb %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vcmpltps %ymm1, %ymm5, %ymm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vcmpltps %ymm0, %ymm4, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0 |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32f32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vcmpltps %ymm3, %ymm7, %ymm3 |
| ; AVX2-NEXT: vcmpltps %ymm2, %ymm6, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vcmpltps %ymm1, %ymm5, %ymm1 |
| ; AVX2-NEXT: vcmpltps %ymm0, %ymm4, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpacksswb %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v32f32: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vcmpltps %zmm1, %zmm3, %k1 |
| ; AVX512F-NEXT: vcmpltps %zmm0, %zmm2, %k2 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v32f32: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vcmpltps %zmm1, %zmm3, %k0 |
| ; AVX512DQ-NEXT: vcmpltps %zmm0, %zmm2, %k1 |
| ; AVX512DQ-NEXT: vpmovm2d %k1, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v32f32: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vcmpltps %zmm0, %zmm2, %k0 |
| ; AVX512BW-NEXT: vcmpltps %zmm1, %zmm3, %k1 |
| ; AVX512BW-NEXT: kunpckwd %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = fcmp ogt <32 x float> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
| |
| define <16 x i1> @test_cmp_v16i64(<16 x i64> %a0, <16 x i64> %a1) nounwind { |
| ; SSE2-LABEL: test_cmp_v16i64: |
| ; SSE2: # %bb.0: |
| ; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648] |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE2-NEXT: pxor %xmm8, %xmm9 |
| ; SSE2-NEXT: movdqa %xmm7, %xmm10 |
| ; SSE2-NEXT: pcmpgtd %xmm9, %xmm10 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm10[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm7, %xmm9 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm9[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm11, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm10[1,1,3,3] |
| ; SSE2-NEXT: por %xmm7, %xmm9 |
| ; SSE2-NEXT: pxor %xmm8, %xmm6 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa %xmm6, %xmm10 |
| ; SSE2-NEXT: pcmpgtd %xmm7, %xmm10 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm10[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm6, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm11, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm10[1,1,3,3] |
| ; SSE2-NEXT: por %xmm7, %xmm10 |
| ; SSE2-NEXT: packssdw %xmm9, %xmm10 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa %xmm5, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm7, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm5, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm9, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm5, %xmm6 |
| ; SSE2-NEXT: pxor %xmm8, %xmm4 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa %xmm4, %xmm7 |
| ; SSE2-NEXT: pcmpgtd %xmm5, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm7[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm4, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm9, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: por %xmm5, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm6, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm10, %xmm4 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm5, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm3, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm7, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm2, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm3, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm2, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm7, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm2 |
| ; SSE2-NEXT: packssdw %xmm5, %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm5 |
| ; SSE2-NEXT: pcmpgtd %xmm3, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm1, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm6, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: pxor {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE2-NEXT: movdqa %xmm0, %xmm1 |
| ; SSE2-NEXT: pcmpgtd %xmm8, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm1[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm8 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm8[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: por %xmm6, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm3, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE2-NEXT: packsswb %xmm4, %xmm0 |
| ; SSE2-NEXT: retq |
| ; |
| ; SSE42-LABEL: test_cmp_v16i64: |
| ; SSE42: # %bb.0: |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE42-NEXT: packssdw %xmm7, %xmm6 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE42-NEXT: packssdw %xmm5, %xmm4 |
| ; SSE42-NEXT: packssdw %xmm6, %xmm4 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE42-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE42-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE42-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE42-NEXT: packsswb %xmm4, %xmm0 |
| ; SSE42-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v16i64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm9 |
| ; AVX1-NEXT: vpcmpgtq %xmm8, %xmm9, %xmm8 |
| ; AVX1-NEXT: vpcmpgtq %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm8, %xmm3, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm6, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm8, %xmm2, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm6 |
| ; AVX1-NEXT: vpcmpgtq %xmm3, %xmm6, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm5, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq %xmm3, %xmm5, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq %xmm4, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v16i64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtq %ymm7, %ymm3, %ymm3 |
| ; AVX2-NEXT: vpcmpgtq %ymm6, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vpcmpgtq %ymm5, %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtq %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v16i64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtq %zmm2, %zmm0, %k0 |
| ; AVX512F-NEXT: vpcmpgtq %zmm3, %zmm1, %k1 |
| ; AVX512F-NEXT: kunpckbw %k0, %k1, %k1 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v16i64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm2, %zmm0, %k0 |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm3, %zmm1, %k1 |
| ; AVX512DQ-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v16i64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtq %zmm2, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpcmpgtq %zmm3, %zmm1, %k1 |
| ; AVX512BW-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0 |
| ; AVX512BW-NEXT: vzeroupper |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <16 x i64> %a0, %a1 |
| ret <16 x i1> %1 |
| } |
| |
| define <32 x i1> @test_cmp_v32i32(<32 x i32> %a0, <32 x i32> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v32i32: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE-NEXT: packsswb %xmm2, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE-NEXT: packssdw %xmm7, %xmm6 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE-NEXT: packssdw %xmm5, %xmm4 |
| ; SSE-NEXT: packsswb %xmm6, %xmm4 |
| ; SSE-NEXT: pmovmskb %xmm4, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: movl %edx, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32i32: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm9 |
| ; AVX1-NEXT: vpcmpgtd %xmm8, %xmm9, %xmm8 |
| ; AVX1-NEXT: vpcmpgtd %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm8, %xmm3, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm7, %xmm3, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm6, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpacksswb %xmm8, %xmm2, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm6 |
| ; AVX1-NEXT: vpcmpgtd %xmm3, %xmm6, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm5, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5 |
| ; AVX1-NEXT: vpcmpgtd %xmm3, %xmm5, %xmm3 |
| ; AVX1-NEXT: vpcmpgtd %xmm4, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0 |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32i32: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: vpcmpgtd %ymm7, %ymm3, %ymm3 |
| ; AVX2-NEXT: vpcmpgtd %ymm6, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vpcmpgtd %ymm5, %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtd %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpacksswb %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v32i32: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtd %zmm3, %zmm1, %k1 |
| ; AVX512F-NEXT: vpcmpgtd %zmm2, %zmm0, %k2 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v32i32: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtd %zmm3, %zmm1, %k0 |
| ; AVX512DQ-NEXT: vpcmpgtd %zmm2, %zmm0, %k1 |
| ; AVX512DQ-NEXT: vpmovm2d %k1, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v32i32: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtd %zmm2, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpcmpgtd %zmm3, %zmm1, %k1 |
| ; AVX512BW-NEXT: kunpckwd %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <32 x i32> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
| |
| define <64 x i1> @test_cmp_v64i16(<64 x i16> %a0, <64 x i16> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v64i16: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: packsswb %xmm1, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: packsswb %xmm3, %xmm2 |
| ; SSE-NEXT: pmovmskb %xmm2, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE-NEXT: packsswb %xmm5, %xmm4 |
| ; SSE-NEXT: pmovmskb %xmm4, %ecx |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE-NEXT: packsswb %xmm7, %xmm6 |
| ; SSE-NEXT: pmovmskb %xmm6, %esi |
| ; SSE-NEXT: shll $16, %esi |
| ; SSE-NEXT: orl %ecx, %esi |
| ; SSE-NEXT: shlq $32, %rsi |
| ; SSE-NEXT: orq %rdx, %rsi |
| ; SSE-NEXT: movq %rsi, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v64i16: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: movq %rdi, %rax |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm9 |
| ; AVX1-NEXT: vpcmpgtw %xmm8, %xmm9, %xmm8 |
| ; AVX1-NEXT: vpcmpgtw %xmm4, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm8, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %ecx |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4 |
| ; AVX1-NEXT: vpcmpgtw %xmm0, %xmm4, %xmm0 |
| ; AVX1-NEXT: vpcmpgtw %xmm5, %xmm1, %xmm1 |
| ; AVX1-NEXT: vpacksswb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edx |
| ; AVX1-NEXT: shll $16, %edx |
| ; AVX1-NEXT: orl %ecx, %edx |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm1 |
| ; AVX1-NEXT: vpcmpgtw %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpcmpgtw %xmm6, %xmm2, %xmm1 |
| ; AVX1-NEXT: vpacksswb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %ecx |
| ; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm1 |
| ; AVX1-NEXT: vpcmpgtw %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpcmpgtw %xmm7, %xmm3, %xmm1 |
| ; AVX1-NEXT: vpacksswb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %esi |
| ; AVX1-NEXT: shll $16, %esi |
| ; AVX1-NEXT: orl %ecx, %esi |
| ; AVX1-NEXT: shlq $32, %rsi |
| ; AVX1-NEXT: orq %rdx, %rsi |
| ; AVX1-NEXT: movq %rsi, (%rdi) |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v64i16: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: movq %rdi, %rax |
| ; AVX2-NEXT: vpcmpgtw %ymm5, %ymm1, %ymm1 |
| ; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm5 |
| ; AVX2-NEXT: vpacksswb %xmm5, %xmm1, %xmm1 |
| ; AVX2-NEXT: vpcmpgtw %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm4 |
| ; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm0 |
| ; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %ecx |
| ; AVX2-NEXT: vpcmpgtw %ymm7, %ymm3, %ymm0 |
| ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 |
| ; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 |
| ; AVX2-NEXT: vpcmpgtw %ymm6, %ymm2, %ymm1 |
| ; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2 |
| ; AVX2-NEXT: vpacksswb %xmm2, %xmm1, %xmm1 |
| ; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %edx |
| ; AVX2-NEXT: shlq $32, %rdx |
| ; AVX2-NEXT: orq %rcx, %rdx |
| ; AVX2-NEXT: movq %rdx, (%rdi) |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v64i16: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtw %ymm7, %ymm3, %ymm3 |
| ; AVX512F-NEXT: vpcmpgtw %ymm6, %ymm2, %ymm2 |
| ; AVX512F-NEXT: vpcmpgtw %ymm5, %ymm1, %ymm1 |
| ; AVX512F-NEXT: vpcmpgtw %ymm4, %ymm0, %ymm0 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero,ymm2[8],zero,ymm2[9],zero,ymm2[10],zero,ymm2[11],zero,ymm2[12],zero,ymm2[13],zero,ymm2[14],zero,ymm2[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm2, %xmm2 |
| ; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm3[0],zero,ymm3[1],zero,ymm3[2],zero,ymm3[3],zero,ymm3[4],zero,ymm3[5],zero,ymm3[6],zero,ymm3[7],zero,ymm3[8],zero,ymm3[9],zero,ymm3[10],zero,ymm3[11],zero,ymm3[12],zero,ymm3[13],zero,ymm3[14],zero,ymm3[15],zero |
| ; AVX512F-NEXT: vpmovdb %zmm3, %xmm3 |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v64i16: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm7, %ymm3, %ymm3 |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm6, %ymm2, %ymm2 |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm5, %ymm1, %ymm1 |
| ; AVX512DQ-NEXT: vpcmpgtw %ymm4, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero,ymm2[8],zero,ymm2[9],zero,ymm2[10],zero,ymm2[11],zero,ymm2[12],zero,ymm2[13],zero,ymm2[14],zero,ymm2[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm2, %xmm2 |
| ; AVX512DQ-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm3[0],zero,ymm3[1],zero,ymm3[2],zero,ymm3[3],zero,ymm3[4],zero,ymm3[5],zero,ymm3[6],zero,ymm3[7],zero,ymm3[8],zero,ymm3[9],zero,ymm3[10],zero,ymm3[11],zero,ymm3[12],zero,ymm3[13],zero,ymm3[14],zero,ymm3[15],zero |
| ; AVX512DQ-NEXT: vpmovdb %zmm3, %xmm3 |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v64i16: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtw %zmm2, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpcmpgtw %zmm3, %zmm1, %k1 |
| ; AVX512BW-NEXT: kunpckdq %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <64 x i16> %a0, %a1 |
| ret <64 x i1> %1 |
| } |
| |
| define <128 x i1> @test_cmp_v128i8(<128 x i8> %a0, <128 x i8> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v128i8: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: pmovmskb %xmm1, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: pmovmskb %xmm2, %esi |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: pmovmskb %xmm3, %ecx |
| ; SSE-NEXT: shll $16, %ecx |
| ; SSE-NEXT: orl %esi, %ecx |
| ; SSE-NEXT: shlq $32, %rcx |
| ; SSE-NEXT: orq %rdx, %rcx |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE-NEXT: pmovmskb %xmm4, %edx |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE-NEXT: pmovmskb %xmm5, %esi |
| ; SSE-NEXT: shll $16, %esi |
| ; SSE-NEXT: orl %edx, %esi |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE-NEXT: pmovmskb %xmm6, %edx |
| ; SSE-NEXT: pcmpgtb {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE-NEXT: pmovmskb %xmm7, %edi |
| ; SSE-NEXT: shll $16, %edi |
| ; SSE-NEXT: orl %edx, %edi |
| ; SSE-NEXT: shlq $32, %rdi |
| ; SSE-NEXT: orq %rsi, %rdi |
| ; SSE-NEXT: movq %rdi, 8(%rax) |
| ; SSE-NEXT: movq %rcx, (%rax) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v128i8: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: movq %rdi, %rax |
| ; AVX1-NEXT: vpcmpgtb %xmm4, %xmm0, %xmm8 |
| ; AVX1-NEXT: vpmovmskb %xmm8, %ecx |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0 |
| ; AVX1-NEXT: vpcmpgtb %xmm4, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edx |
| ; AVX1-NEXT: shll $16, %edx |
| ; AVX1-NEXT: orl %ecx, %edx |
| ; AVX1-NEXT: vpcmpgtb %xmm5, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %esi |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1 |
| ; AVX1-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %ecx |
| ; AVX1-NEXT: shll $16, %ecx |
| ; AVX1-NEXT: orl %esi, %ecx |
| ; AVX1-NEXT: shlq $32, %rcx |
| ; AVX1-NEXT: orq %rdx, %rcx |
| ; AVX1-NEXT: vpcmpgtb %xmm6, %xmm2, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edx |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm1 |
| ; AVX1-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %esi |
| ; AVX1-NEXT: shll $16, %esi |
| ; AVX1-NEXT: orl %edx, %esi |
| ; AVX1-NEXT: vpcmpgtb %xmm7, %xmm3, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edx |
| ; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm1 |
| ; AVX1-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0 |
| ; AVX1-NEXT: vpmovmskb %xmm0, %edi |
| ; AVX1-NEXT: shll $16, %edi |
| ; AVX1-NEXT: orl %edx, %edi |
| ; AVX1-NEXT: shlq $32, %rdi |
| ; AVX1-NEXT: orq %rsi, %rdi |
| ; AVX1-NEXT: movq %rdi, 8(%rax) |
| ; AVX1-NEXT: movq %rcx, (%rax) |
| ; AVX1-NEXT: vzeroupper |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v128i8: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: movq %rdi, %rax |
| ; AVX2-NEXT: vpcmpgtb %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %ecx |
| ; AVX2-NEXT: vpcmpgtb %ymm5, %ymm1, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %edx |
| ; AVX2-NEXT: shlq $32, %rdx |
| ; AVX2-NEXT: orq %rcx, %rdx |
| ; AVX2-NEXT: vpcmpgtb %ymm6, %ymm2, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %ecx |
| ; AVX2-NEXT: vpcmpgtb %ymm7, %ymm3, %ymm0 |
| ; AVX2-NEXT: vpmovmskb %ymm0, %esi |
| ; AVX2-NEXT: shlq $32, %rsi |
| ; AVX2-NEXT: orq %rcx, %rsi |
| ; AVX2-NEXT: movq %rsi, 8(%rdi) |
| ; AVX2-NEXT: movq %rdx, (%rdi) |
| ; AVX2-NEXT: vzeroupper |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v128i8: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: movq %rdi, %rax |
| ; AVX512F-NEXT: vpcmpgtb %ymm4, %ymm0, %ymm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm4 |
| ; AVX512F-NEXT: vptestmd %zmm4, %zmm4, %k0 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1 |
| ; AVX512F-NEXT: vpcmpgtb %ymm5, %ymm1, %ymm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k2 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k3 |
| ; AVX512F-NEXT: vpcmpgtb %ymm6, %ymm2, %ymm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k4 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k5 |
| ; AVX512F-NEXT: vpcmpgtb %ymm7, %ymm3, %ymm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k6 |
| ; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k7 |
| ; AVX512F-NEXT: kmovw %k7, 14(%rdi) |
| ; AVX512F-NEXT: kmovw %k6, 12(%rdi) |
| ; AVX512F-NEXT: kmovw %k5, 10(%rdi) |
| ; AVX512F-NEXT: kmovw %k4, 8(%rdi) |
| ; AVX512F-NEXT: kmovw %k3, 6(%rdi) |
| ; AVX512F-NEXT: kmovw %k2, 4(%rdi) |
| ; AVX512F-NEXT: kmovw %k1, 2(%rdi) |
| ; AVX512F-NEXT: kmovw %k0, (%rdi) |
| ; AVX512F-NEXT: vzeroupper |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v128i8: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: movq %rdi, %rax |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm4, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm4 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm4, %k0 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm0, %k1 |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm5, %ymm1, %ymm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm1, %k2 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm0, %k3 |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm6, %ymm2, %ymm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm1, %k4 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm0, %k5 |
| ; AVX512DQ-NEXT: vpcmpgtb %ymm7, %ymm3, %ymm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm1, %k6 |
| ; AVX512DQ-NEXT: vextracti128 $1, %ymm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovsxbd %xmm0, %zmm0 |
| ; AVX512DQ-NEXT: vpmovd2m %zmm0, %k7 |
| ; AVX512DQ-NEXT: kmovw %k7, 14(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k6, 12(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k5, 10(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k4, 8(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k3, 6(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k2, 4(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k1, 2(%rdi) |
| ; AVX512DQ-NEXT: kmovw %k0, (%rdi) |
| ; AVX512DQ-NEXT: vzeroupper |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v128i8: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtb %zmm3, %zmm1, %k0 |
| ; AVX512BW-NEXT: vpcmpgtb %zmm2, %zmm0, %k1 |
| ; AVX512BW-NEXT: vpmovm2b %k1, %zmm0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm1 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <128 x i8> %a0, %a1 |
| ret <128 x i1> %1 |
| } |
| |
| ; |
| ; 2048-bit vector comparisons |
| ; |
| |
| define <32 x i1> @test_cmp_v32f64(<32 x double> %a0, <32 x double> %a1) nounwind { |
| ; SSE-LABEL: test_cmp_v32f64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: movq %rdi, %rax |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE-NEXT: cmpltpd %xmm7, %xmm8 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE-NEXT: cmpltpd %xmm6, %xmm7 |
| ; SSE-NEXT: packssdw %xmm8, %xmm7 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE-NEXT: cmpltpd %xmm5, %xmm6 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE-NEXT: cmpltpd %xmm4, %xmm5 |
| ; SSE-NEXT: packssdw %xmm6, %xmm5 |
| ; SSE-NEXT: packssdw %xmm7, %xmm5 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE-NEXT: cmpltpd %xmm3, %xmm4 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: cmpltpd %xmm2, %xmm3 |
| ; SSE-NEXT: packssdw %xmm4, %xmm3 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: cmpltpd %xmm1, %xmm2 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: cmpltpd %xmm0, %xmm1 |
| ; SSE-NEXT: packssdw %xmm2, %xmm1 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: packssdw %xmm3, %xmm1 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: packsswb %xmm5, %xmm1 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: pmovmskb %xmm1, %ecx |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: packssdw %xmm1, %xmm3 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE-NEXT: packssdw %xmm1, %xmm2 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE-NEXT: packssdw %xmm3, %xmm1 |
| ; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE-NEXT: packssdw %xmm3, %xmm0 |
| ; SSE-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE-NEXT: packsswb %xmm2, %xmm0 |
| ; SSE-NEXT: pmovmskb %xmm0, %edx |
| ; SSE-NEXT: shll $16, %edx |
| ; SSE-NEXT: orl %ecx, %edx |
| ; SSE-NEXT: movl %edx, (%rdi) |
| ; SSE-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32f64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: pushq %rbp |
| ; AVX1-NEXT: movq %rsp, %rbp |
| ; AVX1-NEXT: andq $-32, %rsp |
| ; AVX1-NEXT: subq $32, %rsp |
| ; AVX1-NEXT: vmovapd 16(%rbp), %ymm8 |
| ; AVX1-NEXT: vmovapd 48(%rbp), %ymm9 |
| ; AVX1-NEXT: vmovapd 80(%rbp), %ymm10 |
| ; AVX1-NEXT: vmovapd 112(%rbp), %ymm11 |
| ; AVX1-NEXT: vmovapd 144(%rbp), %ymm12 |
| ; AVX1-NEXT: vmovapd 176(%rbp), %ymm13 |
| ; AVX1-NEXT: vmovapd 208(%rbp), %ymm14 |
| ; AVX1-NEXT: vmovapd 240(%rbp), %ymm15 |
| ; AVX1-NEXT: vcmpltpd %ymm7, %ymm15, %ymm15 |
| ; AVX1-NEXT: vextractf128 $1, %ymm15, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm15, %xmm15 |
| ; AVX1-NEXT: vcmpltpd %ymm6, %ymm14, %ymm6 |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm6, %xmm6 |
| ; AVX1-NEXT: vpackssdw %xmm15, %xmm6, %xmm6 |
| ; AVX1-NEXT: vcmpltpd %ymm5, %ymm13, %ymm5 |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm5, %xmm5 |
| ; AVX1-NEXT: vcmpltpd %ymm4, %ymm12, %ymm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm4, %xmm4 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm4, %xmm4 |
| ; AVX1-NEXT: vpacksswb %xmm6, %xmm4, %xmm4 |
| ; AVX1-NEXT: vcmpltpd %ymm3, %ymm11, %ymm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm5 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm3, %xmm3 |
| ; AVX1-NEXT: vcmpltpd %ymm2, %ymm10, %ymm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vcmpltpd %ymm1, %ymm9, %ymm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vcmpltpd %ymm0, %ymm8, %ymm0 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0 |
| ; AVX1-NEXT: movq %rbp, %rsp |
| ; AVX1-NEXT: popq %rbp |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32f64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: pushq %rbp |
| ; AVX2-NEXT: movq %rsp, %rbp |
| ; AVX2-NEXT: andq $-32, %rsp |
| ; AVX2-NEXT: subq $32, %rsp |
| ; AVX2-NEXT: vmovapd 16(%rbp), %ymm8 |
| ; AVX2-NEXT: vmovapd 48(%rbp), %ymm9 |
| ; AVX2-NEXT: vmovapd 80(%rbp), %ymm10 |
| ; AVX2-NEXT: vmovapd 112(%rbp), %ymm11 |
| ; AVX2-NEXT: vmovapd 144(%rbp), %ymm12 |
| ; AVX2-NEXT: vmovapd 176(%rbp), %ymm13 |
| ; AVX2-NEXT: vmovapd 208(%rbp), %ymm14 |
| ; AVX2-NEXT: vmovapd 240(%rbp), %ymm15 |
| ; AVX2-NEXT: vcmpltpd %ymm7, %ymm15, %ymm7 |
| ; AVX2-NEXT: vcmpltpd %ymm6, %ymm14, %ymm6 |
| ; AVX2-NEXT: vpackssdw %ymm7, %ymm6, %ymm6 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm6 = ymm6[0,2,1,3] |
| ; AVX2-NEXT: vcmpltpd %ymm5, %ymm13, %ymm5 |
| ; AVX2-NEXT: vcmpltpd %ymm4, %ymm12, %ymm4 |
| ; AVX2-NEXT: vpackssdw %ymm5, %ymm4, %ymm4 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm6, %ymm4, %ymm4 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,2,1,3] |
| ; AVX2-NEXT: vcmpltpd %ymm3, %ymm11, %ymm3 |
| ; AVX2-NEXT: vcmpltpd %ymm2, %ymm10, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vcmpltpd %ymm1, %ymm9, %ymm1 |
| ; AVX2-NEXT: vcmpltpd %ymm0, %ymm8, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpacksswb %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: movq %rbp, %rsp |
| ; AVX2-NEXT: popq %rbp |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v32f64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vcmpltpd %zmm2, %zmm6, %k0 |
| ; AVX512F-NEXT: vcmpltpd %zmm3, %zmm7, %k1 |
| ; AVX512F-NEXT: kunpckbw %k0, %k1, %k1 |
| ; AVX512F-NEXT: vcmpltpd %zmm0, %zmm4, %k0 |
| ; AVX512F-NEXT: vcmpltpd %zmm1, %zmm5, %k2 |
| ; AVX512F-NEXT: kunpckbw %k0, %k2, %k2 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v32f64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vcmpltpd %zmm2, %zmm6, %k0 |
| ; AVX512DQ-NEXT: vcmpltpd %zmm3, %zmm7, %k1 |
| ; AVX512DQ-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512DQ-NEXT: vcmpltpd %zmm0, %zmm4, %k1 |
| ; AVX512DQ-NEXT: vcmpltpd %zmm1, %zmm5, %k2 |
| ; AVX512DQ-NEXT: kunpckbw %k1, %k2, %k1 |
| ; AVX512DQ-NEXT: vpmovm2d %k1, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v32f64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vcmpltpd %zmm0, %zmm4, %k0 |
| ; AVX512BW-NEXT: vcmpltpd %zmm1, %zmm5, %k1 |
| ; AVX512BW-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vcmpltpd %zmm2, %zmm6, %k1 |
| ; AVX512BW-NEXT: vcmpltpd %zmm3, %zmm7, %k2 |
| ; AVX512BW-NEXT: kunpckbw %k1, %k2, %k1 |
| ; AVX512BW-NEXT: kunpckwd %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = fcmp ogt <32 x double> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
| |
| define <32 x i1> @test_cmp_v32i64(<32 x i64> %a0, <32 x i64> %a1) nounwind { |
| ; SSE2-LABEL: test_cmp_v32i64: |
| ; SSE2: # %bb.0: |
| ; SSE2-NEXT: movq %rdi, %rax |
| ; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648] |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE2-NEXT: pxor %xmm8, %xmm9 |
| ; SSE2-NEXT: movdqa %xmm7, %xmm10 |
| ; SSE2-NEXT: pcmpgtd %xmm9, %xmm10 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm10[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm7, %xmm9 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm9[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm11, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm10[1,1,3,3] |
| ; SSE2-NEXT: por %xmm7, %xmm9 |
| ; SSE2-NEXT: pxor %xmm8, %xmm6 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa %xmm6, %xmm10 |
| ; SSE2-NEXT: pcmpgtd %xmm7, %xmm10 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm10[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm6, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm11, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm10[1,1,3,3] |
| ; SSE2-NEXT: por %xmm7, %xmm10 |
| ; SSE2-NEXT: packssdw %xmm9, %xmm10 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE2-NEXT: pxor %xmm8, %xmm7 |
| ; SSE2-NEXT: movdqa %xmm5, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm7, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm5, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm9, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm5, %xmm6 |
| ; SSE2-NEXT: pxor %xmm8, %xmm4 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa %xmm4, %xmm7 |
| ; SSE2-NEXT: pcmpgtd %xmm5, %xmm7 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm7[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm4, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm9, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3] |
| ; SSE2-NEXT: por %xmm5, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm6, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm10, %xmm4 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm5 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm5, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm3, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm7, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm5 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm2, %xmm6 |
| ; SSE2-NEXT: pcmpgtd %xmm3, %xmm6 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm2, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm7, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm6[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm2 |
| ; SSE2-NEXT: packssdw %xmm5, %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm5 |
| ; SSE2-NEXT: pcmpgtd %xmm3, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm1, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm6, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa %xmm0, %xmm5 |
| ; SSE2-NEXT: pcmpgtd %xmm1, %xmm5 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm6, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm5[1,1,3,3] |
| ; SSE2-NEXT: por %xmm0, %xmm1 |
| ; SSE2-NEXT: packssdw %xmm3, %xmm1 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm1 |
| ; SSE2-NEXT: packsswb %xmm4, %xmm1 |
| ; SSE2-NEXT: pmovmskb %xmm1, %ecx |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm2 |
| ; SSE2-NEXT: pcmpgtd %xmm0, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm3, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3] |
| ; SSE2-NEXT: por %xmm0, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa %xmm1, %xmm3 |
| ; SSE2-NEXT: pcmpgtd %xmm0, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm4, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: por %xmm0, %xmm1 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa %xmm2, %xmm3 |
| ; SSE2-NEXT: pcmpgtd %xmm0, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm4, %xmm0 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: por %xmm0, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE2-NEXT: pxor %xmm8, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm4 |
| ; SSE2-NEXT: pcmpgtd %xmm0, %xmm4 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm0, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE2-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa %xmm2, %xmm3 |
| ; SSE2-NEXT: pcmpgtd %xmm1, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm1, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm4, %xmm1 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: por %xmm1, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE2-NEXT: pxor %xmm8, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm4 |
| ; SSE2-NEXT: pcmpgtd %xmm1, %xmm4 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm1, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm4[1,1,3,3] |
| ; SSE2-NEXT: por %xmm3, %xmm1 |
| ; SSE2-NEXT: packssdw %xmm2, %xmm1 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE2-NEXT: pxor %xmm8, %xmm3 |
| ; SSE2-NEXT: movdqa %xmm3, %xmm4 |
| ; SSE2-NEXT: pcmpgtd %xmm2, %xmm4 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm2, %xmm3 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3] |
| ; SSE2-NEXT: por %xmm2, %xmm3 |
| ; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE2-NEXT: pxor %xmm8, %xmm2 |
| ; SSE2-NEXT: pxor {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE2-NEXT: movdqa %xmm8, %xmm4 |
| ; SSE2-NEXT: pcmpgtd %xmm2, %xmm4 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2] |
| ; SSE2-NEXT: pcmpeqd %xmm2, %xmm8 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm8[1,1,3,3] |
| ; SSE2-NEXT: pand %xmm5, %xmm2 |
| ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3] |
| ; SSE2-NEXT: por %xmm2, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm3, %xmm4 |
| ; SSE2-NEXT: packssdw %xmm1, %xmm4 |
| ; SSE2-NEXT: packsswb %xmm0, %xmm4 |
| ; SSE2-NEXT: pmovmskb %xmm4, %edx |
| ; SSE2-NEXT: shll $16, %edx |
| ; SSE2-NEXT: orl %ecx, %edx |
| ; SSE2-NEXT: movl %edx, (%rdi) |
| ; SSE2-NEXT: retq |
| ; |
| ; SSE42-LABEL: test_cmp_v32i64: |
| ; SSE42: # %bb.0: |
| ; SSE42-NEXT: movq %rdi, %rax |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm11 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm10 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm12 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm14 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm13 |
| ; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm15 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm7 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm6 |
| ; SSE42-NEXT: packssdw %xmm7, %xmm6 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm5 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm4 |
| ; SSE42-NEXT: packssdw %xmm5, %xmm4 |
| ; SSE42-NEXT: packssdw %xmm6, %xmm4 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm3 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm2 |
| ; SSE42-NEXT: packssdw %xmm3, %xmm2 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm1 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm0 |
| ; SSE42-NEXT: packssdw %xmm1, %xmm0 |
| ; SSE42-NEXT: packssdw %xmm2, %xmm0 |
| ; SSE42-NEXT: packsswb %xmm4, %xmm0 |
| ; SSE42-NEXT: pmovmskb %xmm0, %ecx |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm15 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm13 |
| ; SSE42-NEXT: packssdw %xmm15, %xmm13 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm14 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm9 |
| ; SSE42-NEXT: packssdw %xmm14, %xmm9 |
| ; SSE42-NEXT: packssdw %xmm13, %xmm9 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm12 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm10 |
| ; SSE42-NEXT: packssdw %xmm12, %xmm10 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm11 |
| ; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm8 |
| ; SSE42-NEXT: packssdw %xmm11, %xmm8 |
| ; SSE42-NEXT: packssdw %xmm10, %xmm8 |
| ; SSE42-NEXT: packsswb %xmm9, %xmm8 |
| ; SSE42-NEXT: pmovmskb %xmm8, %edx |
| ; SSE42-NEXT: shll $16, %edx |
| ; SSE42-NEXT: orl %ecx, %edx |
| ; SSE42-NEXT: movl %edx, (%rdi) |
| ; SSE42-NEXT: retq |
| ; |
| ; AVX1-LABEL: test_cmp_v32i64: |
| ; AVX1: # %bb.0: |
| ; AVX1-NEXT: pushq %rbp |
| ; AVX1-NEXT: movq %rsp, %rbp |
| ; AVX1-NEXT: andq $-32, %rsp |
| ; AVX1-NEXT: subq $32, %rsp |
| ; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm8 |
| ; AVX1-NEXT: vpcmpgtq 256(%rbp), %xmm8, %xmm8 |
| ; AVX1-NEXT: vpcmpgtq 240(%rbp), %xmm7, %xmm7 |
| ; AVX1-NEXT: vpackssdw %xmm8, %xmm7, %xmm8 |
| ; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 224(%rbp), %xmm7, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 208(%rbp), %xmm6, %xmm6 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm6, %xmm6 |
| ; AVX1-NEXT: vpackssdw %xmm8, %xmm6, %xmm6 |
| ; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 192(%rbp), %xmm7, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 176(%rbp), %xmm5, %xmm5 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm5, %xmm5 |
| ; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 160(%rbp), %xmm7, %xmm7 |
| ; AVX1-NEXT: vpcmpgtq 144(%rbp), %xmm4, %xmm4 |
| ; AVX1-NEXT: vpackssdw %xmm7, %xmm4, %xmm4 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm4, %xmm4 |
| ; AVX1-NEXT: vpacksswb %xmm6, %xmm4, %xmm4 |
| ; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq 128(%rbp), %xmm5, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq 112(%rbp), %xmm3, %xmm3 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm3, %xmm3 |
| ; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq 96(%rbp), %xmm5, %xmm5 |
| ; AVX1-NEXT: vpcmpgtq 80(%rbp), %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm5, %xmm2, %xmm2 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm2, %xmm2 |
| ; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq 64(%rbp), %xmm3, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq 48(%rbp), %xmm1, %xmm1 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm1, %xmm1 |
| ; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq 32(%rbp), %xmm3, %xmm3 |
| ; AVX1-NEXT: vpcmpgtq 16(%rbp), %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm3, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 |
| ; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0 |
| ; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0 |
| ; AVX1-NEXT: movq %rbp, %rsp |
| ; AVX1-NEXT: popq %rbp |
| ; AVX1-NEXT: retq |
| ; |
| ; AVX2-LABEL: test_cmp_v32i64: |
| ; AVX2: # %bb.0: |
| ; AVX2-NEXT: pushq %rbp |
| ; AVX2-NEXT: movq %rsp, %rbp |
| ; AVX2-NEXT: andq $-32, %rsp |
| ; AVX2-NEXT: subq $32, %rsp |
| ; AVX2-NEXT: vpcmpgtq 240(%rbp), %ymm7, %ymm7 |
| ; AVX2-NEXT: vpcmpgtq 208(%rbp), %ymm6, %ymm6 |
| ; AVX2-NEXT: vpackssdw %ymm7, %ymm6, %ymm6 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm6 = ymm6[0,2,1,3] |
| ; AVX2-NEXT: vpcmpgtq 176(%rbp), %ymm5, %ymm5 |
| ; AVX2-NEXT: vpcmpgtq 144(%rbp), %ymm4, %ymm4 |
| ; AVX2-NEXT: vpackssdw %ymm5, %ymm4, %ymm4 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm6, %ymm4, %ymm4 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,2,1,3] |
| ; AVX2-NEXT: vpcmpgtq 112(%rbp), %ymm3, %ymm3 |
| ; AVX2-NEXT: vpcmpgtq 80(%rbp), %ymm2, %ymm2 |
| ; AVX2-NEXT: vpackssdw %ymm3, %ymm2, %ymm2 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,1,3] |
| ; AVX2-NEXT: vpcmpgtq 48(%rbp), %ymm1, %ymm1 |
| ; AVX2-NEXT: vpcmpgtq 16(%rbp), %ymm0, %ymm0 |
| ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpackssdw %ymm2, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: vpacksswb %ymm4, %ymm0, %ymm0 |
| ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] |
| ; AVX2-NEXT: movq %rbp, %rsp |
| ; AVX2-NEXT: popq %rbp |
| ; AVX2-NEXT: retq |
| ; |
| ; AVX512F-LABEL: test_cmp_v32i64: |
| ; AVX512F: # %bb.0: |
| ; AVX512F-NEXT: vpcmpgtq %zmm6, %zmm2, %k0 |
| ; AVX512F-NEXT: vpcmpgtq %zmm7, %zmm3, %k1 |
| ; AVX512F-NEXT: kunpckbw %k0, %k1, %k1 |
| ; AVX512F-NEXT: vpcmpgtq %zmm4, %zmm0, %k0 |
| ; AVX512F-NEXT: vpcmpgtq %zmm5, %zmm1, %k2 |
| ; AVX512F-NEXT: kunpckbw %k0, %k2, %k2 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512F-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z} |
| ; AVX512F-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512F-NEXT: retq |
| ; |
| ; AVX512DQ-LABEL: test_cmp_v32i64: |
| ; AVX512DQ: # %bb.0: |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm6, %zmm2, %k0 |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm7, %zmm3, %k1 |
| ; AVX512DQ-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm4, %zmm0, %k1 |
| ; AVX512DQ-NEXT: vpcmpgtq %zmm5, %zmm1, %k2 |
| ; AVX512DQ-NEXT: kunpckbw %k1, %k2, %k1 |
| ; AVX512DQ-NEXT: vpmovm2d %k1, %zmm0 |
| ; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0 |
| ; AVX512DQ-NEXT: vpmovm2d %k0, %zmm1 |
| ; AVX512DQ-NEXT: vpmovdb %zmm1, %xmm1 |
| ; AVX512DQ-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0 |
| ; AVX512DQ-NEXT: retq |
| ; |
| ; AVX512BW-LABEL: test_cmp_v32i64: |
| ; AVX512BW: # %bb.0: |
| ; AVX512BW-NEXT: vpcmpgtq %zmm4, %zmm0, %k0 |
| ; AVX512BW-NEXT: vpcmpgtq %zmm5, %zmm1, %k1 |
| ; AVX512BW-NEXT: kunpckbw %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpcmpgtq %zmm6, %zmm2, %k1 |
| ; AVX512BW-NEXT: vpcmpgtq %zmm7, %zmm3, %k2 |
| ; AVX512BW-NEXT: kunpckbw %k1, %k2, %k1 |
| ; AVX512BW-NEXT: kunpckwd %k0, %k1, %k0 |
| ; AVX512BW-NEXT: vpmovm2b %k0, %zmm0 |
| ; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 killed $zmm0 |
| ; AVX512BW-NEXT: retq |
| %1 = icmp sgt <32 x i64> %a0, %a1 |
| ret <32 x i1> %1 |
| } |
