Page MenuHomePhabricator

Please use GitHub pull requests for new patches. Avoid migrating existing patches. Phabricator shutdown timeline

Differential D35844 Diff 108098 test/CodeGen/X86/masked_gather_scatter.ll

Changeset View

Standalone View

View Options

test/CodeGen/X86/masked_gather_scatter.ll

Show First 20 Lines • Show All 1,758 Lines • ▼ Show 20 Lines
; KNL_32-NEXT: vmovdqa64 8(%ebp), %zmm1 ; KNL_32-NEXT: vmovdqa64 8(%ebp), %zmm1
; KNL_32-NEXT: kshiftrw $8, %k1, %k2 ; KNL_32-NEXT: kshiftrw $8, %k1, %k2
; KNL_32-NEXT: vpgatherdq (,%ymm0), %zmm2 {%k1} ; KNL_32-NEXT: vpgatherdq (,%ymm0), %zmm2 {%k1}
; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0 ; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT: vpgatherdq (,%ymm0), %zmm1 {%k2} ; KNL_32-NEXT: vpgatherdq (,%ymm0), %zmm1 {%k2}
; KNL_32-NEXT: vmovdqa64 %zmm2, %zmm0 ; KNL_32-NEXT: vmovdqa64 %zmm2, %zmm0
; KNL_32-NEXT: movl %ebp, %esp ; KNL_32-NEXT: movl %ebp, %esp
; KNL_32-NEXT: popl %ebp ; KNL_32-NEXT: popl %ebp
; KNL_32-NEXT: .Lcfi3:
; KNL_32-NEXT: .cfi_def_cfa %esp, 4
; KNL_32-NEXT: retl ; KNL_32-NEXT: retl
; ;
; SKX-LABEL: test_gather_16i64: ; SKX-LABEL: test_gather_16i64:
; SKX: # BB#0: ; SKX: # BB#0:
; SKX-NEXT: vpmovsxbd %xmm2, %zmm2 ; SKX-NEXT: vpmovsxbd %xmm2, %zmm2
; SKX-NEXT: vpslld $31, %zmm2, %zmm2 ; SKX-NEXT: vpslld $31, %zmm2, %zmm2
; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1 ; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1
; SKX-NEXT: kshiftrw $8, %k1, %k2 ; SKX-NEXT: kshiftrw $8, %k1, %k2
; SKX-NEXT: vpgatherqq (,%zmm0), %zmm3 {%k1} ; SKX-NEXT: vpgatherqq (,%zmm0), %zmm3 {%k1}
; SKX-NEXT: vpgatherqq (,%zmm1), %zmm4 {%k2} ; SKX-NEXT: vpgatherqq (,%zmm1), %zmm4 {%k2}
; SKX-NEXT: vmovdqa64 %zmm3, %zmm0 ; SKX-NEXT: vmovdqa64 %zmm3, %zmm0
; SKX-NEXT: vmovdqa64 %zmm4, %zmm1 ; SKX-NEXT: vmovdqa64 %zmm4, %zmm1
; SKX-NEXT: retq ; SKX-NEXT: retq
; ;
; SKX_32-LABEL: test_gather_16i64: ; SKX_32-LABEL: test_gather_16i64:
; SKX_32: # BB#0: ; SKX_32: # BB#0:
; SKX_32-NEXT: pushl %ebp ; SKX_32-NEXT: pushl %ebp
; SKX_32-NEXT: .Lcfi1:
; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi2: ; SKX_32-NEXT: .Lcfi2:
; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi3:
; SKX_32-NEXT: .cfi_offset %ebp, -8 ; SKX_32-NEXT: .cfi_offset %ebp, -8
; SKX_32-NEXT: movl %esp, %ebp ; SKX_32-NEXT: movl %esp, %ebp
; SKX_32-NEXT: .Lcfi3: ; SKX_32-NEXT: .Lcfi4:
; SKX_32-NEXT: .cfi_def_cfa_register %ebp ; SKX_32-NEXT: .cfi_def_cfa_register %ebp
; SKX_32-NEXT: andl $-64, %esp ; SKX_32-NEXT: andl $-64, %esp
; SKX_32-NEXT: subl $64, %esp ; SKX_32-NEXT: subl $64, %esp
; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1
; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1 ; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; SKX_32-NEXT: vmovdqa64 8(%ebp), %zmm1 ; SKX_32-NEXT: vmovdqa64 8(%ebp), %zmm1
; SKX_32-NEXT: kshiftrw $8, %k1, %k2 ; SKX_32-NEXT: kshiftrw $8, %k1, %k2
; SKX_32-NEXT: vpgatherdq (,%ymm0), %zmm2 {%k1} ; SKX_32-NEXT: vpgatherdq (,%ymm0), %zmm2 {%k1}
; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0 ; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0
; SKX_32-NEXT: vpgatherdq (,%ymm0), %zmm1 {%k2} ; SKX_32-NEXT: vpgatherdq (,%ymm0), %zmm1 {%k2}
; SKX_32-NEXT: vmovdqa64 %zmm2, %zmm0 ; SKX_32-NEXT: vmovdqa64 %zmm2, %zmm0
; SKX_32-NEXT: movl %ebp, %esp ; SKX_32-NEXT: movl %ebp, %esp
; SKX_32-NEXT: popl %ebp ; SKX_32-NEXT: popl %ebp
; SKX_32-NEXT: .Lcfi5:
; SKX_32-NEXT: .cfi_def_cfa %esp, 4
; SKX_32-NEXT: retl ; SKX_32-NEXT: retl
%res = call <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0) %res = call <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0)
ret <16 x i64> %res ret <16 x i64> %res
} }
declare <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32, <16 x i1> %mask, <16 x i64> %src0) declare <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32, <16 x i1> %mask, <16 x i64> %src0)
define <16 x float> @test_gather_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0) { define <16 x float> @test_gather_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0) {
; KNL_64-LABEL: test_gather_16f32: ; KNL_64-LABEL: test_gather_16f32:
; KNL_64: # BB#0: ; KNL_64: # BB#0:
▲ Show 20 Lines • Show All 50 Lines • ▼ Show 20 Lines
; KNL_64-NEXT: vgatherqpd (,%zmm1), %zmm4 {%k2} ; KNL_64-NEXT: vgatherqpd (,%zmm1), %zmm4 {%k2}
; KNL_64-NEXT: vmovapd %zmm3, %zmm0 ; KNL_64-NEXT: vmovapd %zmm3, %zmm0
; KNL_64-NEXT: vmovapd %zmm4, %zmm1 ; KNL_64-NEXT: vmovapd %zmm4, %zmm1
; KNL_64-NEXT: retq ; KNL_64-NEXT: retq
; ;
; KNL_32-LABEL: test_gather_16f64: ; KNL_32-LABEL: test_gather_16f64:
; KNL_32: # BB#0: ; KNL_32: # BB#0:
; KNL_32-NEXT: pushl %ebp ; KNL_32-NEXT: pushl %ebp
; KNL_32-NEXT: .Lcfi3:
; KNL_32-NEXT: .cfi_def_cfa_offset 8
; KNL_32-NEXT: .Lcfi4: ; KNL_32-NEXT: .Lcfi4:
; KNL_32-NEXT: .cfi_def_cfa_offset 8
; KNL_32-NEXT: .Lcfi5:
; KNL_32-NEXT: .cfi_offset %ebp, -8 ; KNL_32-NEXT: .cfi_offset %ebp, -8
; KNL_32-NEXT: movl %esp, %ebp ; KNL_32-NEXT: movl %esp, %ebp
; KNL_32-NEXT: .Lcfi5: ; KNL_32-NEXT: .Lcfi6:
; KNL_32-NEXT: .cfi_def_cfa_register %ebp ; KNL_32-NEXT: .cfi_def_cfa_register %ebp
; KNL_32-NEXT: andl $-64, %esp ; KNL_32-NEXT: andl $-64, %esp
; KNL_32-NEXT: subl $64, %esp ; KNL_32-NEXT: subl $64, %esp
; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1
; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1 ; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT: vmovapd 8(%ebp), %zmm1 ; KNL_32-NEXT: vmovapd 8(%ebp), %zmm1
; KNL_32-NEXT: kshiftrw $8, %k1, %k2 ; KNL_32-NEXT: kshiftrw $8, %k1, %k2
; KNL_32-NEXT: vgatherdpd (,%ymm0), %zmm2 {%k1} ; KNL_32-NEXT: vgatherdpd (,%ymm0), %zmm2 {%k1}
; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0 ; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT: vgatherdpd (,%ymm0), %zmm1 {%k2} ; KNL_32-NEXT: vgatherdpd (,%ymm0), %zmm1 {%k2}
; KNL_32-NEXT: vmovapd %zmm2, %zmm0 ; KNL_32-NEXT: vmovapd %zmm2, %zmm0
; KNL_32-NEXT: movl %ebp, %esp ; KNL_32-NEXT: movl %ebp, %esp
; KNL_32-NEXT: popl %ebp ; KNL_32-NEXT: popl %ebp
; KNL_32-NEXT: .Lcfi7:
; KNL_32-NEXT: .cfi_def_cfa %esp, 4
; KNL_32-NEXT: retl ; KNL_32-NEXT: retl
; ;
; SKX-LABEL: test_gather_16f64: ; SKX-LABEL: test_gather_16f64:
; SKX: # BB#0: ; SKX: # BB#0:
; SKX-NEXT: vpmovsxbd %xmm2, %zmm2 ; SKX-NEXT: vpmovsxbd %xmm2, %zmm2
; SKX-NEXT: vpslld $31, %zmm2, %zmm2 ; SKX-NEXT: vpslld $31, %zmm2, %zmm2
; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1 ; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1
; SKX-NEXT: kshiftrw $8, %k1, %k2 ; SKX-NEXT: kshiftrw $8, %k1, %k2
; SKX-NEXT: vgatherqpd (,%zmm0), %zmm3 {%k1} ; SKX-NEXT: vgatherqpd (,%zmm0), %zmm3 {%k1}
; SKX-NEXT: vgatherqpd (,%zmm1), %zmm4 {%k2} ; SKX-NEXT: vgatherqpd (,%zmm1), %zmm4 {%k2}
; SKX-NEXT: vmovapd %zmm3, %zmm0 ; SKX-NEXT: vmovapd %zmm3, %zmm0
; SKX-NEXT: vmovapd %zmm4, %zmm1 ; SKX-NEXT: vmovapd %zmm4, %zmm1
; SKX-NEXT: retq ; SKX-NEXT: retq
; ;
; SKX_32-LABEL: test_gather_16f64: ; SKX_32-LABEL: test_gather_16f64:
; SKX_32: # BB#0: ; SKX_32: # BB#0:
; SKX_32-NEXT: pushl %ebp ; SKX_32-NEXT: pushl %ebp
; SKX_32-NEXT: .Lcfi4: ; SKX_32-NEXT: .Lcfi6:
; SKX_32-NEXT: .cfi_def_cfa_offset 8 ; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi5: ; SKX_32-NEXT: .Lcfi7:
; SKX_32-NEXT: .cfi_offset %ebp, -8 ; SKX_32-NEXT: .cfi_offset %ebp, -8
; SKX_32-NEXT: movl %esp, %ebp ; SKX_32-NEXT: movl %esp, %ebp
; SKX_32-NEXT: .Lcfi6: ; SKX_32-NEXT: .Lcfi8:
; SKX_32-NEXT: .cfi_def_cfa_register %ebp ; SKX_32-NEXT: .cfi_def_cfa_register %ebp
; SKX_32-NEXT: andl $-64, %esp ; SKX_32-NEXT: andl $-64, %esp
; SKX_32-NEXT: subl $64, %esp ; SKX_32-NEXT: subl $64, %esp
; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1
; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1 ; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; SKX_32-NEXT: vmovapd 8(%ebp), %zmm1 ; SKX_32-NEXT: vmovapd 8(%ebp), %zmm1
; SKX_32-NEXT: kshiftrw $8, %k1, %k2 ; SKX_32-NEXT: kshiftrw $8, %k1, %k2
; SKX_32-NEXT: vgatherdpd (,%ymm0), %zmm2 {%k1} ; SKX_32-NEXT: vgatherdpd (,%ymm0), %zmm2 {%k1}
; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0 ; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0
; SKX_32-NEXT: vgatherdpd (,%ymm0), %zmm1 {%k2} ; SKX_32-NEXT: vgatherdpd (,%ymm0), %zmm1 {%k2}
; SKX_32-NEXT: vmovapd %zmm2, %zmm0 ; SKX_32-NEXT: vmovapd %zmm2, %zmm0
; SKX_32-NEXT: movl %ebp, %esp ; SKX_32-NEXT: movl %ebp, %esp
; SKX_32-NEXT: popl %ebp ; SKX_32-NEXT: popl %ebp
; SKX_32-NEXT: .Lcfi9:
; SKX_32-NEXT: .cfi_def_cfa %esp, 4
; SKX_32-NEXT: retl ; SKX_32-NEXT: retl
%res = call <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0) %res = call <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0)
ret <16 x double> %res ret <16 x double> %res
} }
declare <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32, <16 x i1> %mask, <16 x double> %src0) declare <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32, <16 x i1> %mask, <16 x double> %src0)
define void @test_scatter_16i32(<16 x i32*> %ptrs, <16 x i1> %mask, <16 x i32> %src0) { define void @test_scatter_16i32(<16 x i32*> %ptrs, <16 x i1> %mask, <16 x i32> %src0) {
; KNL_64-LABEL: test_scatter_16i32: ; KNL_64-LABEL: test_scatter_16i32:
; KNL_64: # BB#0: ; KNL_64: # BB#0:
▲ Show 20 Lines • Show All 49 Lines • ▼ Show 20 Lines
; KNL_64-NEXT: vpscatterqq %zmm3, (,%zmm0) {%k1} ; KNL_64-NEXT: vpscatterqq %zmm3, (,%zmm0) {%k1}
; KNL_64-NEXT: vpscatterqq %zmm4, (,%zmm1) {%k2} ; KNL_64-NEXT: vpscatterqq %zmm4, (,%zmm1) {%k2}
; KNL_64-NEXT: vzeroupper ; KNL_64-NEXT: vzeroupper
; KNL_64-NEXT: retq ; KNL_64-NEXT: retq
; ;
; KNL_32-LABEL: test_scatter_16i64: ; KNL_32-LABEL: test_scatter_16i64:
; KNL_32: # BB#0: ; KNL_32: # BB#0:
; KNL_32-NEXT: pushl %ebp ; KNL_32-NEXT: pushl %ebp
; KNL_32-NEXT: .Lcfi6: ; KNL_32-NEXT: .Lcfi8:
; KNL_32-NEXT: .cfi_def_cfa_offset 8 ; KNL_32-NEXT: .cfi_def_cfa_offset 8
; KNL_32-NEXT: .Lcfi7: ; KNL_32-NEXT: .Lcfi9:
; KNL_32-NEXT: .cfi_offset %ebp, -8 ; KNL_32-NEXT: .cfi_offset %ebp, -8
; KNL_32-NEXT: movl %esp, %ebp ; KNL_32-NEXT: movl %esp, %ebp
; KNL_32-NEXT: .Lcfi8: ; KNL_32-NEXT: .Lcfi10:
; KNL_32-NEXT: .cfi_def_cfa_register %ebp ; KNL_32-NEXT: .cfi_def_cfa_register %ebp
; KNL_32-NEXT: andl $-64, %esp ; KNL_32-NEXT: andl $-64, %esp
; KNL_32-NEXT: subl $64, %esp ; KNL_32-NEXT: subl $64, %esp
; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1
; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1 ; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT: vmovdqa64 8(%ebp), %zmm1 ; KNL_32-NEXT: vmovdqa64 8(%ebp), %zmm1
; KNL_32-NEXT: kshiftrw $8, %k1, %k2 ; KNL_32-NEXT: kshiftrw $8, %k1, %k2
; KNL_32-NEXT: vpscatterdq %zmm2, (,%ymm0) {%k1} ; KNL_32-NEXT: vpscatterdq %zmm2, (,%ymm0) {%k1}
; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0 ; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT: vpscatterdq %zmm1, (,%ymm0) {%k2} ; KNL_32-NEXT: vpscatterdq %zmm1, (,%ymm0) {%k2}
; KNL_32-NEXT: movl %ebp, %esp ; KNL_32-NEXT: movl %ebp, %esp
; KNL_32-NEXT: popl %ebp ; KNL_32-NEXT: popl %ebp
; KNL_32-NEXT: .Lcfi11:
; KNL_32-NEXT: .cfi_def_cfa %esp, 4
; KNL_32-NEXT: vzeroupper ; KNL_32-NEXT: vzeroupper
; KNL_32-NEXT: retl ; KNL_32-NEXT: retl
; ;
; SKX-LABEL: test_scatter_16i64: ; SKX-LABEL: test_scatter_16i64:
; SKX: # BB#0: ; SKX: # BB#0:
; SKX-NEXT: vpmovsxbd %xmm2, %zmm2 ; SKX-NEXT: vpmovsxbd %xmm2, %zmm2
; SKX-NEXT: vpslld $31, %zmm2, %zmm2 ; SKX-NEXT: vpslld $31, %zmm2, %zmm2
; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1 ; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1
; SKX-NEXT: kshiftrw $8, %k1, %k2 ; SKX-NEXT: kshiftrw $8, %k1, %k2
; SKX-NEXT: vpscatterqq %zmm3, (,%zmm0) {%k1} ; SKX-NEXT: vpscatterqq %zmm3, (,%zmm0) {%k1}
; SKX-NEXT: vpscatterqq %zmm4, (,%zmm1) {%k2} ; SKX-NEXT: vpscatterqq %zmm4, (,%zmm1) {%k2}
; SKX-NEXT: vzeroupper ; SKX-NEXT: vzeroupper
; SKX-NEXT: retq ; SKX-NEXT: retq
; ;
; SKX_32-LABEL: test_scatter_16i64: ; SKX_32-LABEL: test_scatter_16i64:
; SKX_32: # BB#0: ; SKX_32: # BB#0:
; SKX_32-NEXT: pushl %ebp ; SKX_32-NEXT: pushl %ebp
; SKX_32-NEXT: .Lcfi7: ; SKX_32-NEXT: .Lcfi10:
; SKX_32-NEXT: .cfi_def_cfa_offset 8 ; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi8: ; SKX_32-NEXT: .Lcfi11:
; SKX_32-NEXT: .cfi_offset %ebp, -8 ; SKX_32-NEXT: .cfi_offset %ebp, -8
; SKX_32-NEXT: movl %esp, %ebp ; SKX_32-NEXT: movl %esp, %ebp
; SKX_32-NEXT: .Lcfi9: ; SKX_32-NEXT: .Lcfi12:
; SKX_32-NEXT: .cfi_def_cfa_register %ebp ; SKX_32-NEXT: .cfi_def_cfa_register %ebp
; SKX_32-NEXT: andl $-64, %esp ; SKX_32-NEXT: andl $-64, %esp
; SKX_32-NEXT: subl $64, %esp ; SKX_32-NEXT: subl $64, %esp
; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1
; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1 ; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; SKX_32-NEXT: vmovdqa64 8(%ebp), %zmm1 ; SKX_32-NEXT: vmovdqa64 8(%ebp), %zmm1
; SKX_32-NEXT: kshiftrw $8, %k1, %k2 ; SKX_32-NEXT: kshiftrw $8, %k1, %k2
; SKX_32-NEXT: vpscatterdq %zmm2, (,%ymm0) {%k1} ; SKX_32-NEXT: vpscatterdq %zmm2, (,%ymm0) {%k1}
; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0 ; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0
; SKX_32-NEXT: vpscatterdq %zmm1, (,%ymm0) {%k2} ; SKX_32-NEXT: vpscatterdq %zmm1, (,%ymm0) {%k2}
; SKX_32-NEXT: movl %ebp, %esp ; SKX_32-NEXT: movl %ebp, %esp
; SKX_32-NEXT: popl %ebp ; SKX_32-NEXT: popl %ebp
; SKX_32-NEXT: .Lcfi13:
; SKX_32-NEXT: .cfi_def_cfa %esp, 4
; SKX_32-NEXT: vzeroupper ; SKX_32-NEXT: vzeroupper
; SKX_32-NEXT: retl ; SKX_32-NEXT: retl
call void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32 4, <16 x i1> %mask) call void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32 4, <16 x i1> %mask)
ret void ret void
} }
declare void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32, <16 x i1> %mask) declare void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32, <16 x i1> %mask)
define void @test_scatter_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0) { define void @test_scatter_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0) {
; KNL_64-LABEL: test_scatter_16f32: ; KNL_64-LABEL: test_scatter_16f32:
▲ Show 20 Lines • Show All 51 Lines • ▼ Show 20 Lines
; KNL_64-NEXT: vscatterqpd %zmm3, (,%zmm0) {%k1} ; KNL_64-NEXT: vscatterqpd %zmm3, (,%zmm0) {%k1}
; KNL_64-NEXT: vscatterqpd %zmm4, (,%zmm1) {%k2} ; KNL_64-NEXT: vscatterqpd %zmm4, (,%zmm1) {%k2}
; KNL_64-NEXT: vzeroupper ; KNL_64-NEXT: vzeroupper
; KNL_64-NEXT: retq ; KNL_64-NEXT: retq
; ;
; KNL_32-LABEL: test_scatter_16f64: ; KNL_32-LABEL: test_scatter_16f64:
; KNL_32: # BB#0: ; KNL_32: # BB#0:
; KNL_32-NEXT: pushl %ebp ; KNL_32-NEXT: pushl %ebp
; KNL_32-NEXT: .Lcfi9: ; KNL_32-NEXT: .Lcfi12:
; KNL_32-NEXT: .cfi_def_cfa_offset 8 ; KNL_32-NEXT: .cfi_def_cfa_offset 8
; KNL_32-NEXT: .Lcfi10: ; KNL_32-NEXT: .Lcfi13:
; KNL_32-NEXT: .cfi_offset %ebp, -8 ; KNL_32-NEXT: .cfi_offset %ebp, -8
; KNL_32-NEXT: movl %esp, %ebp ; KNL_32-NEXT: movl %esp, %ebp
; KNL_32-NEXT: .Lcfi11: ; KNL_32-NEXT: .Lcfi14:
; KNL_32-NEXT: .cfi_def_cfa_register %ebp ; KNL_32-NEXT: .cfi_def_cfa_register %ebp
; KNL_32-NEXT: andl $-64, %esp ; KNL_32-NEXT: andl $-64, %esp
; KNL_32-NEXT: subl $64, %esp ; KNL_32-NEXT: subl $64, %esp
; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; KNL_32-NEXT: vpmovsxbd %xmm1, %zmm1
; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1 ; KNL_32-NEXT: vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; KNL_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT: vmovapd 8(%ebp), %zmm1 ; KNL_32-NEXT: vmovapd 8(%ebp), %zmm1
; KNL_32-NEXT: kshiftrw $8, %k1, %k2 ; KNL_32-NEXT: kshiftrw $8, %k1, %k2
; KNL_32-NEXT: vscatterdpd %zmm2, (,%ymm0) {%k1} ; KNL_32-NEXT: vscatterdpd %zmm2, (,%ymm0) {%k1}
; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0 ; KNL_32-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT: vscatterdpd %zmm1, (,%ymm0) {%k2} ; KNL_32-NEXT: vscatterdpd %zmm1, (,%ymm0) {%k2}
; KNL_32-NEXT: movl %ebp, %esp ; KNL_32-NEXT: movl %ebp, %esp
; KNL_32-NEXT: popl %ebp ; KNL_32-NEXT: popl %ebp
; KNL_32-NEXT: .Lcfi15:
; KNL_32-NEXT: .cfi_def_cfa %esp, 4
; KNL_32-NEXT: vzeroupper ; KNL_32-NEXT: vzeroupper
; KNL_32-NEXT: retl ; KNL_32-NEXT: retl
; ;
; SKX-LABEL: test_scatter_16f64: ; SKX-LABEL: test_scatter_16f64:
; SKX: # BB#0: ; SKX: # BB#0:
; SKX-NEXT: vpmovsxbd %xmm2, %zmm2 ; SKX-NEXT: vpmovsxbd %xmm2, %zmm2
; SKX-NEXT: vpslld $31, %zmm2, %zmm2 ; SKX-NEXT: vpslld $31, %zmm2, %zmm2
; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1 ; SKX-NEXT: vptestmd %zmm2, %zmm2, %k1
; SKX-NEXT: kshiftrw $8, %k1, %k2 ; SKX-NEXT: kshiftrw $8, %k1, %k2
; SKX-NEXT: vscatterqpd %zmm3, (,%zmm0) {%k1} ; SKX-NEXT: vscatterqpd %zmm3, (,%zmm0) {%k1}
; SKX-NEXT: vscatterqpd %zmm4, (,%zmm1) {%k2} ; SKX-NEXT: vscatterqpd %zmm4, (,%zmm1) {%k2}
; SKX-NEXT: vzeroupper ; SKX-NEXT: vzeroupper
; SKX-NEXT: retq ; SKX-NEXT: retq
; ;
; SKX_32-LABEL: test_scatter_16f64: ; SKX_32-LABEL: test_scatter_16f64:
; SKX_32: # BB#0: ; SKX_32: # BB#0:
; SKX_32-NEXT: pushl %ebp ; SKX_32-NEXT: pushl %ebp
; SKX_32-NEXT: .Lcfi10: ; SKX_32-NEXT: .Lcfi14:
; SKX_32-NEXT: .cfi_def_cfa_offset 8 ; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi11: ; SKX_32-NEXT: .Lcfi15:
; SKX_32-NEXT: .cfi_offset %ebp, -8 ; SKX_32-NEXT: .cfi_offset %ebp, -8
; SKX_32-NEXT: movl %esp, %ebp ; SKX_32-NEXT: movl %esp, %ebp
; SKX_32-NEXT: .Lcfi12: ; SKX_32-NEXT: .Lcfi16:
; SKX_32-NEXT: .cfi_def_cfa_register %ebp ; SKX_32-NEXT: .cfi_def_cfa_register %ebp
; SKX_32-NEXT: andl $-64, %esp ; SKX_32-NEXT: andl $-64, %esp
; SKX_32-NEXT: subl $64, %esp ; SKX_32-NEXT: subl $64, %esp
; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1 ; SKX_32-NEXT: vpmovsxbd %xmm1, %zmm1
; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1 ; SKX_32-NEXT: vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1 ; SKX_32-NEXT: vptestmd %zmm1, %zmm1, %k1
; SKX_32-NEXT: vmovapd 8(%ebp), %zmm1 ; SKX_32-NEXT: vmovapd 8(%ebp), %zmm1
; SKX_32-NEXT: kshiftrw $8, %k1, %k2 ; SKX_32-NEXT: kshiftrw $8, %k1, %k2
; SKX_32-NEXT: vscatterdpd %zmm2, (,%ymm0) {%k1} ; SKX_32-NEXT: vscatterdpd %zmm2, (,%ymm0) {%k1}
; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0 ; SKX_32-NEXT: vextracti32x8 $1, %zmm0, %ymm0
; SKX_32-NEXT: vscatterdpd %zmm1, (,%ymm0) {%k2} ; SKX_32-NEXT: vscatterdpd %zmm1, (,%ymm0) {%k2}
; SKX_32-NEXT: movl %ebp, %esp ; SKX_32-NEXT: movl %ebp, %esp
; SKX_32-NEXT: popl %ebp ; SKX_32-NEXT: popl %ebp
; SKX_32-NEXT: .Lcfi17:
; SKX_32-NEXT: .cfi_def_cfa %esp, 4
; SKX_32-NEXT: vzeroupper ; SKX_32-NEXT: vzeroupper
; SKX_32-NEXT: retl ; SKX_32-NEXT: retl
call void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32 4, <16 x i1> %mask) call void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32 4, <16 x i1> %mask)
ret void ret void
} }
declare void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32, <16 x i1> %mask) declare void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32, <16 x i1> %mask)
define <4 x i64> @test_pr28312(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i64> %d) { define <4 x i64> @test_pr28312(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i64> %d) {
Show All 10 Lines
; KNL_64-NEXT: vpgatherqq (,%zmm0), %zmm1 {%k1} ; KNL_64-NEXT: vpgatherqq (,%zmm0), %zmm1 {%k1}
; KNL_64-NEXT: vpaddq %ymm1, %ymm1, %ymm0 ; KNL_64-NEXT: vpaddq %ymm1, %ymm1, %ymm0
; KNL_64-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ; KNL_64-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; KNL_64-NEXT: retq ; KNL_64-NEXT: retq
; ;
; KNL_32-LABEL: test_pr28312: ; KNL_32-LABEL: test_pr28312:
; KNL_32: # BB#0: ; KNL_32: # BB#0:
; KNL_32-NEXT: pushl %ebp ; KNL_32-NEXT: pushl %ebp
; KNL_32-NEXT: .Lcfi12: ; KNL_32-NEXT: .Lcfi16:
; KNL_32-NEXT: .cfi_def_cfa_offset 8 ; KNL_32-NEXT: .cfi_def_cfa_offset 8
; KNL_32-NEXT: .Lcfi13: ; KNL_32-NEXT: .Lcfi17:
; KNL_32-NEXT: .cfi_offset %ebp, -8 ; KNL_32-NEXT: .cfi_offset %ebp, -8
; KNL_32-NEXT: movl %esp, %ebp ; KNL_32-NEXT: movl %esp, %ebp
; KNL_32-NEXT: .Lcfi14: ; KNL_32-NEXT: .Lcfi18:
; KNL_32-NEXT: .cfi_def_cfa_register %ebp ; KNL_32-NEXT: .cfi_def_cfa_register %ebp
; KNL_32-NEXT: andl $-32, %esp ; KNL_32-NEXT: andl $-32, %esp
; KNL_32-NEXT: subl $32, %esp ; KNL_32-NEXT: subl $32, %esp
; KNL_32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def> ; KNL_32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<def>
; KNL_32-NEXT: vpslld $31, %xmm1, %xmm1 ; KNL_32-NEXT: vpslld $31, %xmm1, %xmm1
; KNL_32-NEXT: vpsrad $31, %xmm1, %xmm1 ; KNL_32-NEXT: vpsrad $31, %xmm1, %xmm1
; KNL_32-NEXT: vpmovsxdq %xmm1, %ymm1 ; KNL_32-NEXT: vpmovsxdq %xmm1, %ymm1
; KNL_32-NEXT: vpxord %zmm2, %zmm2, %zmm2 ; KNL_32-NEXT: vpxord %zmm2, %zmm2, %zmm2
; KNL_32-NEXT: vinserti64x4 $0, %ymm1, %zmm2, %zmm1 ; KNL_32-NEXT: vinserti64x4 $0, %ymm1, %zmm2, %zmm1
; KNL_32-NEXT: vpmovsxdq %ymm0, %zmm0 ; KNL_32-NEXT: vpmovsxdq %ymm0, %zmm0
; KNL_32-NEXT: vpsllq $63, %zmm1, %zmm1 ; KNL_32-NEXT: vpsllq $63, %zmm1, %zmm1
; KNL_32-NEXT: vptestmq %zmm1, %zmm1, %k1 ; KNL_32-NEXT: vptestmq %zmm1, %zmm1, %k1
; KNL_32-NEXT: vpgatherqq (,%zmm0), %zmm1 {%k1} ; KNL_32-NEXT: vpgatherqq (,%zmm0), %zmm1 {%k1}
; KNL_32-NEXT: vpaddq %ymm1, %ymm1, %ymm0 ; KNL_32-NEXT: vpaddq %ymm1, %ymm1, %ymm0
; KNL_32-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ; KNL_32-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; KNL_32-NEXT: movl %ebp, %esp ; KNL_32-NEXT: movl %ebp, %esp
; KNL_32-NEXT: popl %ebp ; KNL_32-NEXT: popl %ebp
; KNL_32-NEXT: .Lcfi19:
; KNL_32-NEXT: .cfi_def_cfa %esp, 4
; KNL_32-NEXT: retl ; KNL_32-NEXT: retl
; ;
; SKX-LABEL: test_pr28312: ; SKX-LABEL: test_pr28312:
; SKX: # BB#0: ; SKX: # BB#0:
; SKX-NEXT: vpslld $31, %xmm1, %xmm1 ; SKX-NEXT: vpslld $31, %xmm1, %xmm1
; SKX-NEXT: vptestmd %xmm1, %xmm1, %k1 ; SKX-NEXT: vptestmd %xmm1, %xmm1, %k1
; SKX-NEXT: vpgatherqq (,%ymm0), %ymm1 {%k1} ; SKX-NEXT: vpgatherqq (,%ymm0), %ymm1 {%k1}
; SKX-NEXT: vpaddq %ymm1, %ymm1, %ymm0 ; SKX-NEXT: vpaddq %ymm1, %ymm1, %ymm0
; SKX-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ; SKX-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; SKX-NEXT: retq ; SKX-NEXT: retq
; ;
; SKX_32-LABEL: test_pr28312: ; SKX_32-LABEL: test_pr28312:
; SKX_32: # BB#0: ; SKX_32: # BB#0:
; SKX_32-NEXT: pushl %ebp ; SKX_32-NEXT: pushl %ebp
; SKX_32-NEXT: .Lcfi13: ; SKX_32-NEXT: .Lcfi18:
; SKX_32-NEXT: .cfi_def_cfa_offset 8 ; SKX_32-NEXT: .cfi_def_cfa_offset 8
; SKX_32-NEXT: .Lcfi14: ; SKX_32-NEXT: .Lcfi19:
; SKX_32-NEXT: .cfi_offset %ebp, -8 ; SKX_32-NEXT: .cfi_offset %ebp, -8
; SKX_32-NEXT: movl %esp, %ebp ; SKX_32-NEXT: movl %esp, %ebp
; SKX_32-NEXT: .Lcfi15: ; SKX_32-NEXT: .Lcfi20:
; SKX_32-NEXT: .cfi_def_cfa_register %ebp ; SKX_32-NEXT: .cfi_def_cfa_register %ebp
; SKX_32-NEXT: andl $-32, %esp ; SKX_32-NEXT: andl $-32, %esp
; SKX_32-NEXT: subl $32, %esp ; SKX_32-NEXT: subl $32, %esp
; SKX_32-NEXT: vpslld $31, %xmm1, %xmm1 ; SKX_32-NEXT: vpslld $31, %xmm1, %xmm1
; SKX_32-NEXT: vptestmd %xmm1, %xmm1, %k1 ; SKX_32-NEXT: vptestmd %xmm1, %xmm1, %k1
; SKX_32-NEXT: vpgatherdq (,%xmm0), %ymm1 {%k1} ; SKX_32-NEXT: vpgatherdq (,%xmm0), %ymm1 {%k1}
; SKX_32-NEXT: vpaddq %ymm1, %ymm1, %ymm0 ; SKX_32-NEXT: vpaddq %ymm1, %ymm1, %ymm0
; SKX_32-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ; SKX_32-NEXT: vpaddq %ymm0, %ymm1, %ymm0
; SKX_32-NEXT: movl %ebp, %esp ; SKX_32-NEXT: movl %ebp, %esp
; SKX_32-NEXT: popl %ebp ; SKX_32-NEXT: popl %ebp
; SKX_32-NEXT: .Lcfi21:
; SKX_32-NEXT: .cfi_def_cfa %esp, 4
; SKX_32-NEXT: retl ; SKX_32-NEXT: retl
%g1 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef) %g1 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
%g2 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef) %g2 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
%g3 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef) %g3 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
%a = add <4 x i64> %g1, %g2 %a = add <4 x i64> %g1, %g2
%b = add <4 x i64> %a, %g3 %b = add <4 x i64> %a, %g3
ret <4 x i64> %b ret <4 x i64> %b
} }
declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>) declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)