%res5 = add <8 x i32> %res3, %res4
ret <8 x i32> %res5
}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psrl.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psrl_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_q_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlq %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsrlq %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsrlq %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm0, %xmm2, %xmm0
+; CHECK-NEXT: vpaddq %xmm3, %xmm0, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psrl.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psrl.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psrl.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> zeroinitializer, i8 %x3)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res3, %res2
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psrl.q.256(<4 x i64>, <2 x i64>, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psrl_q_256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_q_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlq %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsrlq %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsrlq %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0
+; CHECK-NEXT: vpaddq %ymm3, %ymm0, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psrl.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psrl.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 -1)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psrl.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> zeroinitializer, i8 %x3)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psrl.qi.128(<2 x i64>, i8, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psrl_qi_128(<2 x i64> %x0, i8 %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_qi_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlq $255, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpsrlq $255, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpsrlq $255, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: vpaddq %xmm0, %xmm2, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psrl.qi.128(<2 x i64> %x0, i8 255, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psrl.qi.128(<2 x i64> %x0, i8 255, <2 x i64> %x2, i8 -1)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psrl.qi.128(<2 x i64> %x0, i8 255, <2 x i64> zeroinitializer, i8 %x3)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res2, %res3
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psrl.qi.256(<4 x i64>, i8, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psrl_qi_256(<4 x i64> %x0, i8 %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_qi_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlq $255, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpsrlq $255, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpsrlq $255, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psrl.qi.256(<4 x i64> %x0, i8 255, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psrl.qi.256(<4 x i64> %x0, i8 255, <4 x i64> %x2, i8 -1)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psrl.qi.256(<4 x i64> %x0, i8 255, <4 x i64> zeroinitializer, i8 %x3)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res2, %res3
+ ret <4 x i64> %res4
+}
+declare <4 x i32> @llvm.x86.avx512.mask.psrl.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
+define <4 x i32>@test_int_x86_avx512_mask_psrl_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_d_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrld %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsrld %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsrld %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
+; CHECK-NEXT: vpaddd %xmm3, %xmm0, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psrl.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psrl.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psrl.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %x3)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psrl.d.256(<8 x i32>, <4 x i32>, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psrl_d_256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_d_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrld %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsrld %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsrld %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm0, %ymm2, %ymm0
+; CHECK-NEXT: vpaddd %ymm0, %ymm3, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psrl.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psrl.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 -1)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psrl.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> zeroinitializer, i8 %x3)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res2, %res3
+ ret <8 x i32> %res4
+}
+
+declare <4 x i32> @llvm.x86.avx512.mask.psrl.di.128(<4 x i32>, i8, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psrl_di_128(<4 x i32> %x0, i8 %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_di_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrld $255, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpsrld $255, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpsrld $255, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psrl.di.128(<4 x i32> %x0, i8 255, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psrl.di.128(<4 x i32> %x0, i8 255, <4 x i32> %x2, i8 -1)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psrl.di.128(<4 x i32> %x0, i8 255, <4 x i32> zeroinitializer, i8 %x3)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res2, %res3
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psrl.di.256(<8 x i32>, i8, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psrl_di_256(<8 x i32> %x0, i8 %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_di_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrld $255, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpsrld $255, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpsrld $255, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: vpaddd %ymm0, %ymm2, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psrl.di.256(<8 x i32> %x0, i8 255, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psrl.di.256(<8 x i32> %x0, i8 255, <8 x i32> %x2, i8 -1)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psrl.di.256(<8 x i32> %x0, i8 255, <8 x i32> zeroinitializer, i8 %x3)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res2, %res3
+ ret <8 x i32> %res4
+}
+
+declare <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32>, i8, <16 x i32>, i16)
+
+define <16 x i32>@test_int_x86_avx512_mask_psrl_di_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrl_di_512:
+; CHECK: ## BB#0:
+; CHECK-NEXT: kmovw %esi, %k1
+; CHECK-NEXT: vpsrld $255, %zmm0, %zmm1 {%k1}
+; CHECK-NEXT: vpsrld $255, %zmm0, %zmm2 {%k1} {z}
+; CHECK-NEXT: vpsrld $255, %zmm0, %zmm0
+; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
+; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
+; CHECK-NEXT: retq
+ %res = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> %x2, i16 %x3)
+ %res1 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> %x2, i16 -1)
+ %res2 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i8 255, <16 x i32> zeroinitializer, i16 %x3)
+ %res3 = add <16 x i32> %res, %res1
+ %res4 = add <16 x i32> %res2, %res3
+ ret <16 x i32> %res4
+}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psrlv2.di(<2 x i64>, <2 x i64>, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psrlv2_di(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrlv2_di:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlvq %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsrlvq %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsrlvq %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm1
+; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psrlv2.di(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psrlv2.di(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psrlv2.di(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res3, %res2
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psrlv4.di(<4 x i64>, <4 x i64>, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psrlv4_di(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrlv4_di:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlvq %ymm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsrlvq %ymm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsrlvq %ymm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psrlv4.di(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psrlv4.di(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psrlv4.di(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 -1)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}
+
+declare <4 x i32> @llvm.x86.avx512.mask.psrlv4.si(<4 x i32>, <4 x i32>, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psrlv4_si(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrlv4_si:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlvd %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsrlvd %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm1
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psrlv4.si(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psrlv4.si(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psrlv4.si(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psrlv8.si(<8 x i32>, <8 x i32>, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psrlv8_si(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psrlv8_si:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrlvd %ymm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsrlvd %ymm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsrlvd %ymm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psrlv8.si(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psrlv8.si(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psrlv8.si(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res3, %res2
+ ret <8 x i32> %res4
+}
+
+declare <4 x i32> @llvm.x86.avx512.mask.psra.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psra_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_d_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrad %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsrad %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsrad %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm1
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psra.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psra.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psra.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psra.d.256(<8 x i32>, <4 x i32>, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psra_d_256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_d_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrad %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsrad %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsrad %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psra.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psra.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psra.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 -1)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res3, %res2
+ ret <8 x i32> %res4
+}
+
+declare <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32>, i8, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psra_di_128(<4 x i32> %x0, i8 %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrad $3, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpsrad $3, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpsrad $3, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm2, %xmm1, %xmm1
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32> %x0, i8 3, <4 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 -1)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32>, i8, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psra_di_256(<8 x i32> %x0, i8 %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsrad $3, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpsrad $3, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpsrad $3, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm2, %ymm1, %ymm1
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32> %x0, i8 3, <8 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 -1)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res3, %res2
+ ret <8 x i32> %res4
+}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psra.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psra_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_q_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsraq %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpsraq %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpsraq %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm1
+; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psra.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psra.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psra.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res3, %res2
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psra.q.256(<4 x i64>, <2 x i64>, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psra_q_256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_q_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsraq %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsraq %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsraq %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psra.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psra.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psra.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 -1)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64>, i8, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psra_qi_128(<2 x i64> %x0, i8 %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsraq $3, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpsraq $3, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpsraq $3, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm2, %xmm1, %xmm1
+; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64> %x0, i8 3, <2 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 -1)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res3, %res2
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64>, i8, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psra_qi_256(<4 x i64> %x0, i8 %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsraq $3, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpsraq $3, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpsraq $3, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm2, %ymm1, %ymm1
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64> %x0, i8 3, <4 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 -1)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}
+
+
+declare <4 x i32> @llvm.x86.avx512.mask.psll.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psll_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_d_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpslld %xmm1, %xmm0, %xmm2 {%k1}
+; CHECK-NEXT: vpslld %xmm1, %xmm0, %xmm3 {%k1} {z}
+; CHECK-NEXT: vpslld %xmm1, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm1
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psll.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psll.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psll.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psll.d.256(<8 x i32>, <4 x i32>, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psll_d_256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_d_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpslld %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpslld %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpslld %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psll.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psll.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psll.d.256(<8 x i32> %x0, <4 x i32> %x1, <8 x i32> %x2, i8 -1)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res3, %res2
+ ret <8 x i32> %res4
+}
+
+declare <4 x i32> @llvm.x86.avx512.mask.psll.di.128(<4 x i32>, i8, <4 x i32>, i8)
+
+define <4 x i32>@test_int_x86_avx512_mask_psll_di_128(<4 x i32> %x0, i8 %x1, <4 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_di_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpslld $3, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpslld $3, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpslld $3, %xmm0, %xmm0
+; CHECK-NEXT: vpaddd %xmm2, %xmm1, %xmm1
+; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <4 x i32> @llvm.x86.avx512.mask.psll.di.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 %x3)
+ %res1 = call <4 x i32> @llvm.x86.avx512.mask.psll.di.128(<4 x i32> %x0, i8 3, <4 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i32> @llvm.x86.avx512.mask.psll.di.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 -1)
+ %res3 = add <4 x i32> %res, %res1
+ %res4 = add <4 x i32> %res3, %res2
+ ret <4 x i32> %res4
+}
+
+declare <8 x i32> @llvm.x86.avx512.mask.psll.di.256(<8 x i32>, i8, <8 x i32>, i8)
+
+define <8 x i32>@test_int_x86_avx512_mask_psll_di_256(<8 x i32> %x0, i8 %x1, <8 x i32> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_di_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpslld $3, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpslld $3, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpslld $3, %ymm0, %ymm0
+; CHECK-NEXT: vpaddd %ymm2, %ymm1, %ymm1
+; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <8 x i32> @llvm.x86.avx512.mask.psll.di.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 %x3)
+ %res1 = call <8 x i32> @llvm.x86.avx512.mask.psll.di.256(<8 x i32> %x0, i8 3, <8 x i32> zeroinitializer, i8 %x3)
+ %res2 = call <8 x i32> @llvm.x86.avx512.mask.psll.di.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 -1)
+ %res3 = add <8 x i32> %res, %res1
+ %res4 = add <8 x i32> %res3, %res2
+ ret <8 x i32> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psll.q.256(<4 x i64>, <2 x i64>, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psll_q_256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_q_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %dil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsllq %xmm1, %ymm0, %ymm2 {%k1}
+; CHECK-NEXT: vpsllq %xmm1, %ymm0, %ymm3 {%k1} {z}
+; CHECK-NEXT: vpsllq %xmm1, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm3, %ymm2, %ymm1
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psll.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psll.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psll.q.256(<4 x i64> %x0, <2 x i64> %x1, <4 x i64> %x2, i8 -1)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}
+
+declare <2 x i64> @llvm.x86.avx512.mask.psll.qi.128(<2 x i64>, i8, <2 x i64>, i8)
+
+define <2 x i64>@test_int_x86_avx512_mask_psll_qi_128(<2 x i64> %x0, i8 %x1, <2 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_qi_128:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsllq $3, %xmm0, %xmm1 {%k1}
+; CHECK-NEXT: vpsllq $3, %xmm0, %xmm2 {%k1} {z}
+; CHECK-NEXT: vpsllq $3, %xmm0, %xmm0
+; CHECK-NEXT: vpaddq %xmm2, %xmm1, %xmm1
+; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0
+; CHECK-NEXT: retq
+ %res = call <2 x i64> @llvm.x86.avx512.mask.psll.qi.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 %x3)
+ %res1 = call <2 x i64> @llvm.x86.avx512.mask.psll.qi.128(<2 x i64> %x0, i8 3, <2 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <2 x i64> @llvm.x86.avx512.mask.psll.qi.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 -1)
+ %res3 = add <2 x i64> %res, %res1
+ %res4 = add <2 x i64> %res3, %res2
+ ret <2 x i64> %res4
+}
+
+declare <4 x i64> @llvm.x86.avx512.mask.psll.qi.256(<4 x i64>, i8, <4 x i64>, i8)
+
+define <4 x i64>@test_int_x86_avx512_mask_psll_qi_256(<4 x i64> %x0, i8 %x1, <4 x i64> %x2, i8 %x3) {
+; CHECK-LABEL: test_int_x86_avx512_mask_psll_qi_256:
+; CHECK: ## BB#0:
+; CHECK-NEXT: movzbl %sil, %eax
+; CHECK-NEXT: kmovw %eax, %k1
+; CHECK-NEXT: vpsllq $3, %ymm0, %ymm1 {%k1}
+; CHECK-NEXT: vpsllq $3, %ymm0, %ymm2 {%k1} {z}
+; CHECK-NEXT: vpsllq $3, %ymm0, %ymm0
+; CHECK-NEXT: vpaddq %ymm2, %ymm1, %ymm1
+; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0
+; CHECK-NEXT: retq
+ %res = call <4 x i64> @llvm.x86.avx512.mask.psll.qi.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 %x3)
+ %res1 = call <4 x i64> @llvm.x86.avx512.mask.psll.qi.256(<4 x i64> %x0, i8 3, <4 x i64> zeroinitializer, i8 %x3)
+ %res2 = call <4 x i64> @llvm.x86.avx512.mask.psll.qi.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 -1)
+ %res3 = add <4 x i64> %res, %res1
+ %res4 = add <4 x i64> %res3, %res2
+ ret <4 x i64> %res4
+}