[AVX512][PROLQ][PROLD] Change imm8 to int

[AsafBadouh]

LGTM

llvm/trunk/include/llvm/IR/IntrinsicsX86.td

def int_x86_avx512_mask_prorv_q_256 : GCCBuiltin<"__builtin_ia32_prorvq256_mask">,
               Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
                          llvm_v4i64_ty, llvm_v4i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prorv_q_512 : GCCBuiltin<"__builtin_ia32_prorvq512_mask">,
               Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty,
                          llvm_v8i64_ty, llvm_v8i64_ty, llvm_i8_ty], [IntrNoMem]>;
 
    def int_x86_avx512_mask_prol_d_128 : GCCBuiltin<"__builtin_ia32_prold128_mask">,
               Intrinsic<[llvm_v4i32_ty] , [llvm_v4i32_ty,
-                         llvm_i8_ty, llvm_v4i32_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v4i32_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prol_d_256 : GCCBuiltin<"__builtin_ia32_prold256_mask">,
               Intrinsic<[llvm_v8i32_ty] , [llvm_v8i32_ty,
-                         llvm_i8_ty, llvm_v8i32_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v8i32_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prol_d_512 : GCCBuiltin<"__builtin_ia32_prold512_mask">,
               Intrinsic<[llvm_v16i32_ty] , [llvm_v16i32_ty,
-                         llvm_i8_ty, llvm_v16i32_ty, llvm_i16_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v16i32_ty, llvm_i16_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prol_q_128 : GCCBuiltin<"__builtin_ia32_prolq128_mask">,
               Intrinsic<[llvm_v2i64_ty] , [llvm_v2i64_ty,
-                         llvm_i8_ty, llvm_v2i64_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v2i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prol_q_256 : GCCBuiltin<"__builtin_ia32_prolq256_mask">,
               Intrinsic<[llvm_v4i64_ty] , [llvm_v4i64_ty,
-                         llvm_i8_ty, llvm_v4i64_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v4i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prol_q_512 : GCCBuiltin<"__builtin_ia32_prolq512_mask">,
               Intrinsic<[llvm_v8i64_ty] , [llvm_v8i64_ty,
-                         llvm_i8_ty, llvm_v8i64_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v8i64_ty, llvm_i8_ty], [IntrNoMem]>;
 
 
   def int_x86_avx512_mask_prolv_d_128 : GCCBuiltin<"__builtin_ia32_prolvd128_mask">,
               Intrinsic<[llvm_v4i32_ty], [llvm_v4i32_ty,
                          llvm_v4i32_ty, llvm_v4i32_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_prolv_d_256 : GCCBuiltin<"__builtin_ia32_prolvd256_mask">,
               Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
                          llvm_v8i32_ty, llvm_v8i32_ty, llvm_i8_ty], [IntrNoMem]>;

llvm/trunk/lib/Target/X86/X86IntrinsicsInfo.h

   X86_INTRINSIC_DATA(avx512_mask_pmulu_dq_512, INTR_TYPE_2OP_MASK,
                      X86ISD::PMULUDQ, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_d_128, INTR_TYPE_2OP_MASK, ISD::OR, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_d_256, INTR_TYPE_2OP_MASK, ISD::OR, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_d_512, INTR_TYPE_2OP_MASK, ISD::OR, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_q_128, INTR_TYPE_2OP_MASK, ISD::OR, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_q_256, INTR_TYPE_2OP_MASK, ISD::OR, 0),
   X86_INTRINSIC_DATA(avx512_mask_por_q_512, INTR_TYPE_2OP_MASK, ISD::OR, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_d_128,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_d_256,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_d_512,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_q_128,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_q_256,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_prol_q_512,  INTR_TYPE_2OP_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_d_128,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_d_256,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_d_512,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_q_128,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_q_256,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_prol_q_512,  INTR_TYPE_2OP_IMM8_MASK, X86ISD::VROTLI, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_d_128, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_d_256, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_d_512, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_q_128, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_q_256, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_prolv_q_512, INTR_TYPE_2OP_MASK, ISD::ROTL, 0),
   X86_INTRINSIC_DATA(avx512_mask_pror_d_128,  INTR_TYPE_2OP_MASK, X86ISD::VROTRI, 0),
   X86_INTRINSIC_DATA(avx512_mask_pror_d_256,  INTR_TYPE_2OP_MASK, X86ISD::VROTRI, 0),

llvm/trunk/test/CodeGen/X86/avx512-intrinsics.ll

 ; CHECK-NEXT:    retq
   %res = call <8 x i64> @llvm.x86.avx512.mask.loadu.q.512(i8* %ptr, <8 x i64> zeroinitializer, i8 -1)
   %res1 = call <8 x i64> @llvm.x86.avx512.mask.loadu.q.512(i8* %ptr2, <8 x i64> %res, i8 %mask)
   %res2 = call <8 x i64> @llvm.x86.avx512.mask.loadu.q.512(i8* %ptr, <8 x i64> zeroinitializer, i8 %mask)
   %res4 = add <8 x i64> %res2, %res1
   ret <8 x i64> %res4
 }
 
-declare <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32>, i8, <16 x i32>, i16)
+declare <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32>, i32, <16 x i32>, i16)
 
-define <16 x i32>@test_int_x86_avx512_mask_prol_d_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) {
+define <16 x i32>@test_int_x86_avx512_mask_prol_d_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_d_512:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprold $3, %zmm0, %zmm1 {%k1}
 ; CHECK-NEXT:    vprold $3, %zmm0, %zmm2 {%k1} {z}
 ; CHECK-NEXT:    vprold $3, %zmm0, %zmm0
 ; CHECK-NEXT:    vpaddd %zmm2, %zmm1, %zmm1
 ; CHECK-NEXT:    vpaddd %zmm0, %zmm1, %zmm0
 ; CHECK-NEXT:    retq
-  %res = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 %x3)
-  %res1 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i8 3, <16 x i32> zeroinitializer, i16 %x3)
-  %res2 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 -1)
+  %res = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 %x3)
+  %res1 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> zeroinitializer, i16 %x3)
+  %res2 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 -1)
   %res3 = add <16 x i32> %res, %res1
   %res4 = add <16 x i32> %res3, %res2
   ret <16 x i32> %res4
 }
 
-declare <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64>, i8, <8 x i64>, i8)
+declare <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64>, i32, <8 x i64>, i8)
 
-define <8 x i64>@test_int_x86_avx512_mask_prol_q_512(<8 x i64> %x0, i8 %x1, <8 x i64> %x2, i8 %x3) {
+define <8 x i64>@test_int_x86_avx512_mask_prol_q_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_q_512:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprolq $3, %zmm0, %zmm1 {%k1}
 ; CHECK-NEXT:    vprolq $3, %zmm0, %zmm2 {%k1} {z}
 ; CHECK-NEXT:    vprolq $3, %zmm0, %zmm0
 ; CHECK-NEXT:    vpaddq %zmm2, %zmm1, %zmm1
 ; CHECK-NEXT:    vpaddq %zmm0, %zmm1, %zmm0
 ; CHECK-NEXT:    retq
-  %res = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 %x3)
-  %res1 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i8 3, <8 x i64> zeroinitializer, i8 %x3)
-  %res2 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 -1)
+  %res = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 %x3)
+  %res1 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 -1)
   %res3 = add <8 x i64> %res, %res1
   %res4 = add <8 x i64> %res3, %res2
   ret <8 x i64> %res4
 }
 
 declare <16 x i32> @llvm.x86.avx512.mask.load.d.512(i8*, <16 x i32>, i16)
 
 define <16 x i32> @test_mask_load_aligned_d(<16 x i32> %data, i8* %ptr, i16 %mask) {

llvm/trunk/test/CodeGen/X86/avx512vl-intrinsics.ll

 ; CHECK-NEXT:    retq
   %res = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 -1)
   %res1 = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr2, <4 x i64> %res, i8 %mask)
   %res2 = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 %mask)
   %res4 = add <4 x i64> %res2, %res1
   ret <4 x i64> %res4
 }
 
-declare <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32>, i8, <4 x i32>, i8)
+declare <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32>, i32, <4 x i32>, i8)
 
-define <4 x i32>@test_int_x86_avx512_mask_prol_d_128(<4 x i32> %x0, i8 %x1, <4 x i32> %x2, i8 %x3) {
+define <4 x i32>@test_int_x86_avx512_mask_prol_d_128(<4 x i32> %x0, i32 %x1, <4 x i32> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_d_128:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprold $3, %xmm0, %xmm1 {%k1}
 ; CHECK-NEXT:    vprold $3, %xmm0, %xmm2 {%k1} {z}
 ; CHECK-NEXT:    vprold $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.prol.d.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 %x3)
-  %res1 = call <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32> %x0, i8 3, <4 x i32> zeroinitializer, i8 %x3)
-  %res2 = call <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32> %x0, i8 3, <4 x i32> %x2, i8 -1)
+  %res = call <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32> %x0, i32 3, <4 x i32> %x2, i8 %x3)
+  %res1 = call <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32> %x0, i32 3, <4 x i32> zeroinitializer, i8 %x3)
+  %res2 = call <4 x i32> @llvm.x86.avx512.mask.prol.d.128(<4 x i32> %x0, i32 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.prol.d.256(<8 x i32>, i8, <8 x i32>, i8)
+declare <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32>, i32, <8 x i32>, i8)
 
-define <8 x i32>@test_int_x86_avx512_mask_prol_d_256(<8 x i32> %x0, i8 %x1, <8 x i32> %x2, i8 %x3) {
+define <8 x i32>@test_int_x86_avx512_mask_prol_d_256(<8 x i32> %x0, i32 %x1, <8 x i32> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_d_256:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprold $3, %ymm0, %ymm1 {%k1}
 ; CHECK-NEXT:    vprold $3, %ymm0, %ymm2 {%k1} {z}
 ; CHECK-NEXT:    vprold $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.prol.d.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 %x3)
-  %res1 = call <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32> %x0, i8 3, <8 x i32> zeroinitializer, i8 %x3)
-  %res2 = call <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32> %x0, i8 3, <8 x i32> %x2, i8 -1)
+  %res = call <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32> %x0, i32 3, <8 x i32> %x2, i8 %x3)
+  %res1 = call <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32> %x0, i32 3, <8 x i32> zeroinitializer, i8 %x3)
+  %res2 = call <8 x i32> @llvm.x86.avx512.mask.prol.d.256(<8 x i32> %x0, i32 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.prol.q.128(<2 x i64>, i8, <2 x i64>, i8)
+declare <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64>, i32, <2 x i64>, i8)
 
-define <2 x i64>@test_int_x86_avx512_mask_prol_q_128(<2 x i64> %x0, i8 %x1, <2 x i64> %x2, i8 %x3) {
+define <2 x i64>@test_int_x86_avx512_mask_prol_q_128(<2 x i64> %x0, i32 %x1, <2 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_q_128:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprolq $3, %xmm0, %xmm1 {%k1}
 ; CHECK-NEXT:    vprolq $3, %xmm0, %xmm2 {%k1} {z}
 ; CHECK-NEXT:    vprolq $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.prol.q.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 %x3)
-  %res1 = call <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64> %x0, i8 3, <2 x i64> zeroinitializer, i8 %x3)
-  %res2 = call <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64> %x0, i8 3, <2 x i64> %x2, i8 -1)
+  %res = call <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64> %x0, i32 3, <2 x i64> %x2, i8 %x3)
+  %res1 = call <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64> %x0, i32 3, <2 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <2 x i64> @llvm.x86.avx512.mask.prol.q.128(<2 x i64> %x0, i32 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.prol.q.256(<4 x i64>, i8, <4 x i64>, i8)
+declare <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64>, i32, <4 x i64>, i8)
 
-define <4 x i64>@test_int_x86_avx512_mask_prol_q_256(<4 x i64> %x0, i8 %x1, <4 x i64> %x2, i8 %x3) {
+define <4 x i64>@test_int_x86_avx512_mask_prol_q_256(<4 x i64> %x0, i32 %x1, <4 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_prol_q_256:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vprolq $3, %ymm0, %ymm1 {%k1}
 ; CHECK-NEXT:    vprolq $3, %ymm0, %ymm2 {%k1} {z}
 ; CHECK-NEXT:    vprolq $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.prol.q.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 %x3)
-  %res1 = call <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64> %x0, i8 3, <4 x i64> zeroinitializer, i8 %x3)
-  %res2 = call <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64> %x0, i8 3, <4 x i64> %x2, i8 -1)
+  %res = call <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64> %x0, i32 3, <4 x i64> %x2, i8 %x3)
+  %res1 = call <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64> %x0, i32 3, <4 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <4 x i64> @llvm.x86.avx512.mask.prol.q.256(<4 x i64> %x0, i32 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.load.d.128(i8*, <4 x i32>, i8)
 
 define <4 x i32> @test_mask_load_aligned_d_128(<4 x i32> %data, i8* %ptr, i8 %mask) {