summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/X86/avx512-intrinsics.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/X86/avx512-intrinsics.ll')
-rw-r--r--llvm/test/CodeGen/X86/avx512-intrinsics.ll94
1 files changed, 46 insertions, 48 deletions
diff --git a/llvm/test/CodeGen/X86/avx512-intrinsics.ll b/llvm/test/CodeGen/X86/avx512-intrinsics.ll
index ddd059ecf55..c134fc386b4 100644
--- a/llvm/test/CodeGen/X86/avx512-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx512-intrinsics.ll
@@ -4707,15 +4707,15 @@ define <2 x double>@test_int_x86_avx512_mask_vfmadd_sd(<2 x double> %x0, <2 x do
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm0, %xmm3
-; CHECK-NEXT: vfmadd132sd %xmm1, %xmm2, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vfmadd213sd %xmm2, %xmm1, %xmm3 {%k1}
+; CHECK-NEXT: vmovaps %xmm0, %xmm4
+; CHECK-NEXT: vfmadd213sd %xmm2, %xmm1, %xmm4
; CHECK-NEXT: vmovaps %xmm0, %xmm5
-; CHECK-NEXT: vfmadd132sd {rz-sae}, %xmm1, %xmm2, %xmm5 {%k1}
-; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1
-; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
-; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm1, %xmm5 {%k1}
+; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm1, %xmm0
+; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm1
+; CHECK-NEXT: vaddpd %xmm5, %xmm0, %xmm0
+; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
@@ -4735,15 +4735,15 @@ define <4 x float>@test_int_x86_avx512_mask_vfmadd_ss(<4 x float> %x0, <4 x floa
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm0, %xmm3
-; CHECK-NEXT: vfmadd132ss %xmm1, %xmm2, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vfmadd213ss %xmm2, %xmm1, %xmm3 {%k1}
+; CHECK-NEXT: vmovaps %xmm0, %xmm4
+; CHECK-NEXT: vfmadd213ss %xmm2, %xmm1, %xmm4
; CHECK-NEXT: vmovaps %xmm0, %xmm5
-; CHECK-NEXT: vfmadd132ss {rz-sae}, %xmm1, %xmm2, %xmm5 {%k1}
-; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm0, %xmm1
-; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
-; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm1, %xmm5 {%k1}
+; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm1, %xmm0
+; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm1
+; CHECK-NEXT: vaddps %xmm5, %xmm0, %xmm0
+; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
@@ -4762,10 +4762,10 @@ define <2 x double>@test_int_x86_avx512_maskz_vfmadd_sd(<2 x double> %x0, <2 x d
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
-; CHECK-NEXT: vmovaps %xmm1, %xmm3
-; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm3 {%k1} {z}
-; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1 {%k1} {z}
-; CHECK-NEXT: vaddpd %xmm1, %xmm3, %xmm0
+; CHECK-NEXT: vmovaps %xmm0, %xmm3
+; CHECK-NEXT: vfmadd213sd %xmm2, %xmm1, %xmm3 {%k1} {z}
+; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm1, %xmm0 {%k1} {z}
+; CHECK-NEXT: vaddpd %xmm0, %xmm3, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
@@ -4780,8 +4780,7 @@ define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss(<4 x float> %x0, <4 x flo
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
-; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm1 {%k1} {z}
-; CHECK-NEXT: vmovaps %xmm1, %xmm0
+; CHECK-NEXT: vfmadd213ss %xmm2, %xmm1, %xmm0 {%k1} {z}
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
@@ -4797,13 +4796,13 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmadd_sd(<2 x double> %x0, <2 x d
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfmadd231sd %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfmadd231sd %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfmadd231sd {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfmadd231sd {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddpd %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
@@ -4825,13 +4824,13 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss(<4 x float> %x0, <4 x flo
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfmadd231ss %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfmadd231ss %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfmadd231ss {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfmadd231ss {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddps %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
@@ -4853,13 +4852,13 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmsub_sd(<2 x double> %x0, <2 x d
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfmsub231sd %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmsub213sd %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfmsub231sd %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfmsub231sd {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfmsub213sd {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfmsub231sd {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddpd %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
@@ -4881,13 +4880,13 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmsub_ss(<4 x float> %x0, <4 x flo
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfmsub231ss %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfmsub213ss %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfmsub231ss %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfmsub231ss {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfmsub213ss {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfmsub231ss {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddps %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
@@ -4909,13 +4908,13 @@ define <2 x double>@test_int_x86_avx512_mask3_vfnmsub_sd(<2 x double> %x0, <2 x
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfnmsub231sd %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfnmsub213sd %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfnmsub231sd %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfnmsub231sd {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfnmsub213sd {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfnmsub231sd {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddpd %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
@@ -4937,13 +4936,13 @@ define <4 x float>@test_int_x86_avx512_mask3_vfnmsub_ss(<4 x float> %x0, <4 x fl
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovaps %xmm2, %xmm3
; CHECK-NEXT: vfnmsub231ss %xmm1, %xmm0, %xmm3 {%k1}
-; CHECK-NEXT: vmovaps %xmm1, %xmm4
-; CHECK-NEXT: vfnmsub213ss %xmm2, %xmm0, %xmm4
+; CHECK-NEXT: vmovaps %xmm2, %xmm4
+; CHECK-NEXT: vfnmsub231ss %xmm1, %xmm0, %xmm4
; CHECK-NEXT: vmovaps %xmm2, %xmm5
; CHECK-NEXT: vfnmsub231ss {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
-; CHECK-NEXT: vfnmsub213ss {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT: vfnmsub231ss {rz-sae}, %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
-; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
+; CHECK-NEXT: vaddps %xmm5, %xmm2, %xmm1
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
@@ -4988,8 +4987,7 @@ define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss_rm(<4 x float> %x0, <4 x
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_ss_rm:
; CHECK: ## BB#0:
; CHECK-NEXT: kxorw %k0, %k0, %k1
-; CHECK-NEXT: vfmadd213ss (%rdi), %xmm0, %xmm1 {%k1} {z}
-; CHECK-NEXT: vmovaps %xmm1, %xmm0
+; CHECK-NEXT: vfmadd213ss (%rdi), %xmm1, %xmm0 {%k1} {z}
; CHECK-NEXT: retq
%q = load float, float* %ptr_b
%vecinit.i = insertelement <4 x float> undef, float %q, i32 0
OpenPOWER on IntegriCloud