summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/X86/avx512bw-intrinsics.ll')
-rw-r--r--llvm/test/CodeGen/X86/avx512bw-intrinsics.ll252
1 files changed, 196 insertions, 56 deletions
diff --git a/llvm/test/CodeGen/X86/avx512bw-intrinsics.ll b/llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
index 3e7c0d949f2..c0125f3005b 100644
--- a/llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
@@ -214,31 +214,31 @@ define i64 @test_cmp_b_512(<64 x i8> %a0, <64 x i8> %a1) {
; AVX512F-32-NEXT: vpcmpltb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpleb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpunordb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpneqb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnltb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnleb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpordb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, (%esp)
; AVX512F-32-NEXT: addl (%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: addl $68, %esp
; AVX512F-32-NEXT: retl
%res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 -1)
@@ -303,31 +303,31 @@ define i64 @test_mask_cmp_b_512(<64 x i8> %a0, <64 x i8> %a1, i64 %mask) {
; AVX512F-32-NEXT: vpcmpltb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpleb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpunordb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpneqb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnltb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnleb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpordb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: addl $68, %esp
; AVX512F-32-NEXT: retl
%res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 %mask)
@@ -390,31 +390,31 @@ define i64 @test_ucmp_b_512(<64 x i8> %a0, <64 x i8> %a1) {
; AVX512F-32-NEXT: vpcmpltub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpleub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpunordub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnequb %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnltub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnleub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpordub %zmm1, %zmm0, %k0
; AVX512F-32-NEXT: kmovq %k0, (%esp)
; AVX512F-32-NEXT: addl (%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: addl $68, %esp
; AVX512F-32-NEXT: retl
%res0 = call i64 @llvm.x86.avx512.mask.ucmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 -1)
@@ -479,31 +479,31 @@ define i64 @test_mask_x86_avx512_ucmp_b_512(<64 x i8> %a0, <64 x i8> %a1, i64 %m
; AVX512F-32-NEXT: vpcmpltub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpleub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpunordub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnequb %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnltub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpnleub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: vpcmpordub %zmm1, %zmm0, %k0 {%k1}
; AVX512F-32-NEXT: kmovq %k0, {{[0-9]+}}(%esp)
; AVX512F-32-NEXT: addl {{[0-9]+}}(%esp), %eax
-; AVX512F-32-NEXT: adcl {{[0-9]+}}(%esp), %edx
+; AVX512F-32-NEXT: adcxl {{[0-9]+}}(%esp), %edx
; AVX512F-32-NEXT: addl $68, %esp
; AVX512F-32-NEXT: retl
%res0 = call i64 @llvm.x86.avx512.mask.ucmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 %mask)
@@ -2879,6 +2879,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psrl_w_512(<32 x i16> %x0, <8 x i16>
; AVX512BW-NEXT: vpaddw %zmm0, %zmm2, %zmm0
; AVX512BW-NEXT: vpaddw %zmm3, %zmm0, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psrl_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsrlw %xmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsrlw %xmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm2, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm0, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psrl.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psrl.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 -1)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psrl.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
@@ -2899,6 +2909,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psrl_wi_512(<32 x i16> %x0, i8 %x1, <
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: vpaddw %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psrl_wi_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsrlw $3, %zmm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpsrlw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpsrlw $3, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm0, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psrl.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psrl.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psrl.wi.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
@@ -2919,6 +2939,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psrlv32hi(<32 x i16> %x0, <32 x i16>
; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psrlv32hi:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsrlvw %zmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsrlvw %zmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsrlvw %zmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psrlv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psrlv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psrlv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 -1)
@@ -2939,6 +2969,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psra_w_512(<32 x i16> %x0, <8 x i16>
; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psra_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsraw %xmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsraw %xmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsraw %xmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psra.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 -1)
@@ -2959,6 +2999,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psra_wi_512(<32 x i16> %x0, i8 %x1, <
; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psra_wi_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsraw $3, %zmm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpsraw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpsraw $3, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
@@ -2979,6 +3029,16 @@ define <32 x i16>@test_int_x86_avx512_mask_pshufh_w_512(<32 x i16> %x0, i8 %x1,
; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_pshufh_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpshufhw $3, %zmm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpshufhw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpshufhw $3, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.pshufh.w.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.pshufh.w.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.pshufh.w.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
@@ -2992,13 +3052,23 @@ declare <32 x i16> @llvm.x86.avx512.mask.pshufl.w.512(<32 x i16>, i8, <32 x i16>
define <32 x i16>@test_int_x86_avx512_mask_pshufl_w_512(<32 x i16> %x0, i8 %x1, <32 x i16> %x2, i32 %x3) {
; AVX512BW-LABEL: test_int_x86_avx512_mask_pshufl_w_512:
; AVX512BW: ## BB#0:
-; AVX512BW-NEXT: kmovd %esi, %k1
-; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm1 {%k1}
-; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm2 {%k1} {z}
-; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm0
-; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
-; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
-; AVX512BW-NEXT: retq
+; AVX512BW-NEXT: kmovd %esi, %k1
+; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm1 {%k1}
+; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512BW-NEXT: vpshuflw $3, %zmm0, %zmm0
+; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_pshufl_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpshuflw $3, %zmm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpshuflw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpshuflw $3, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.pshufl.w.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.pshufl.w.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.pshufl.w.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
@@ -3019,6 +3089,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psrav32_hi(<32 x i16> %x0, <32 x i16>
; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psrav32_hi:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsravw %zmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsravw %zmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsravw %zmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psrav32.hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psrav32.hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psrav32.hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 -1)
@@ -3039,6 +3119,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psll_w_512(<32 x i16> %x0, <8 x i16>
; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psll_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsllw %xmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsllw %xmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsllw %xmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psll.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psll.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psll.w.512(<32 x i16> %x0, <8 x i16> %x1, <32 x i16> %x2, i32 -1)
@@ -3059,6 +3149,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psll_wi_512(<32 x i16> %x0, i8 %x1, <
; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psll_wi_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsllw $3, %zmm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpsllw $3, %zmm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpsllw $3, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psll.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psll.wi.512(<32 x i16> %x0, i8 3, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psll.wi.512(<32 x i16> %x0, i8 3, <32 x i16> %x2, i32 -1)
@@ -3079,6 +3179,16 @@ define <32 x i16>@test_int_x86_avx512_mask_psllv32hi(<32 x i16> %x0, <32 x i16>
; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_psllv32hi:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpsllvw %zmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpsllvw %zmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpsllvw %zmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.psllv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.psllv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.psllv32hi(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 -1)
@@ -3152,13 +3262,23 @@ declare <32 x i16> @llvm.x86.avx512.mask.pmovzxb.w.512(<32 x i8>, <32 x i16>, i3
define <32 x i16>@test_int_x86_avx512_mask_pmovzxb_w_512(<32 x i8> %x0, <32 x i16> %x1, i32 %x2) {
; AVX512BW-LABEL: test_int_x86_avx512_mask_pmovzxb_w_512:
; AVX512BW: ## BB#0:
-; AVX512BW-NEXT: kmovd %edi, %k1
-; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm1 {%k1}
-; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm2 {%k1} {z}
-; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm0
-; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
-; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
-; AVX512BW-NEXT: retq
+; AVX512BW-NEXT: kmovd %edi, %k1
+; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm1 {%k1}
+; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm2 {%k1} {z}
+; AVX512BW-NEXT: vpmovzxbw %ymm0, %zmm0
+; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_pmovzxb_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpmovzxbw %ymm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpmovzxbw %ymm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpmovzxbw %ymm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.pmovzxb.w.512(<32 x i8> %x0, <32 x i16> %x1, i32 %x2)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.pmovzxb.w.512(<32 x i8> %x0, <32 x i16> zeroinitializer, i32 %x2)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.pmovzxb.w.512(<32 x i8> %x0, <32 x i16> %x1, i32 -1)
@@ -3172,13 +3292,23 @@ declare <32 x i16> @llvm.x86.avx512.mask.pmovsxb.w.512(<32 x i8>, <32 x i16>, i3
define <32 x i16>@test_int_x86_avx512_mask_pmovsxb_w_512(<32 x i8> %x0, <32 x i16> %x1, i32 %x2) {
; AVX512BW-LABEL: test_int_x86_avx512_mask_pmovsxb_w_512:
; AVX512BW: ## BB#0:
-; AVX512BW-NEXT: kmovd %edi, %k1
-; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm1 {%k1}
-; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm2 {%k1} {z}
-; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
-; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
-; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
-; AVX512BW-NEXT: retq
+; AVX512BW-NEXT: kmovd %edi, %k1
+; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm1 {%k1}
+; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm2 {%k1} {z}
+; AVX512BW-NEXT: vpmovsxbw %ymm0, %zmm0
+; AVX512BW-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_pmovsxb_w_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpmovsxbw %ymm0, %zmm1 {%k1}
+; AVX512F-32-NEXT: vpmovsxbw %ymm0, %zmm2 {%k1} {z}
+; AVX512F-32-NEXT: vpmovsxbw %ymm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm2, %zmm1, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.pmovsxb.w.512(<32 x i8> %x0, <32 x i16> %x1, i32 %x2)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.pmovsxb.w.512(<32 x i8> %x0, <32 x i16> zeroinitializer, i32 %x2)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.pmovsxb.w.512(<32 x i8> %x0, <32 x i16> %x1, i32 -1)
@@ -3192,13 +3322,23 @@ declare <32 x i16> @llvm.x86.avx512.mask.permvar.hi.512(<32 x i16>, <32 x i16>,
define <32 x i16>@test_int_x86_avx512_mask_permvar_hi_512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 %x3) {
; AVX512BW-LABEL: test_int_x86_avx512_mask_permvar_hi_512:
; AVX512BW: ## BB#0:
-; AVX512BW-NEXT: kmovd %edi, %k1
-; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm2 {%k1}
-; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm3 {%k1} {z}
-; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm0
-; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
-; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
-; AVX512BW-NEXT: retq
+; AVX512BW-NEXT: kmovd %edi, %k1
+; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm2 {%k1}
+; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512BW-NEXT: vpermw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512BW-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT: retq
+;
+; AVX512F-32-LABEL: test_int_x86_avx512_mask_permvar_hi_512:
+; AVX512F-32: # BB#0:
+; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
+; AVX512F-32-NEXT: vpermw %zmm1, %zmm0, %zmm2 {%k1}
+; AVX512F-32-NEXT: vpermw %zmm1, %zmm0, %zmm3 {%k1} {z}
+; AVX512F-32-NEXT: vpermw %zmm1, %zmm0, %zmm0
+; AVX512F-32-NEXT: vpaddw %zmm3, %zmm2, %zmm1
+; AVX512F-32-NEXT: vpaddw %zmm0, %zmm1, %zmm0
+; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.permvar.hi.512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 %x3)
%res1 = call <32 x i16> @llvm.x86.avx512.mask.permvar.hi.512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> zeroinitializer, i32 %x3)
%res2 = call <32 x i16> @llvm.x86.avx512.mask.permvar.hi.512(<32 x i16> %x0, <32 x i16> %x1, <32 x i16> %x2, i32 -1)
OpenPOWER on IntegriCloud