[LLVM][AVX512]PSRAWI Change imm8 to int..

[delena]

LGTM

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

let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
   def int_x86_avx512_mask_psra_w_256 : GCCBuiltin<"__builtin_ia32_psraw256_mask">,
               Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
                          llvm_v8i16_ty, llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_w_512 : GCCBuiltin<"__builtin_ia32_psraw512_mask">,
               Intrinsic<[llvm_v32i16_ty], [llvm_v32i16_ty,
                          llvm_v8i16_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_wi_128 : GCCBuiltin<"__builtin_ia32_psrawi128_mask">,
               Intrinsic<[llvm_v8i16_ty], [llvm_v8i16_ty,
-                         llvm_i8_ty, llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_wi_256 : GCCBuiltin<"__builtin_ia32_psrawi256_mask">,
               Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
-                         llvm_i8_ty, llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_wi_512 : GCCBuiltin<"__builtin_ia32_psrawi512_mask">,
               Intrinsic<[llvm_v32i16_ty], [llvm_v32i16_ty,
-                         llvm_i8_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
+                         llvm_i32_ty, llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
 
   def int_x86_avx512_mask_psll_d : GCCBuiltin<"__builtin_ia32_pslld512_mask">,
               Intrinsic<[llvm_v16i32_ty], [llvm_v16i32_ty,
                          llvm_v4i32_ty, llvm_v16i32_ty, llvm_i16_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psll_q : GCCBuiltin<"__builtin_ia32_psllq512_mask">,
               Intrinsic<[llvm_v8i64_ty], [llvm_v8i64_ty,
                          llvm_v2i64_ty, llvm_v8i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psrl_d : GCCBuiltin<"__builtin_ia32_psrld512_mask">,
let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
   def int_x86_avx512_mask_psra_d_128 : GCCBuiltin<"__builtin_ia32_psrad128_mask">,
               Intrinsic<[llvm_v4i32_ty], [llvm_v4i32_ty,
                          llvm_v4i32_ty, llvm_v4i32_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_d_256 : GCCBuiltin<"__builtin_ia32_psrad256_mask">,
              Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty, 
                          llvm_v4i32_ty, llvm_v8i32_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_di_128 : GCCBuiltin<"__builtin_ia32_psradi128_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_psra_di_256 : GCCBuiltin<"__builtin_ia32_psradi256_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_psra_di_512 : GCCBuiltin<"__builtin_ia32_psradi512_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_psra_q_128 : GCCBuiltin<"__builtin_ia32_psraq128_mask">,
               Intrinsic<[llvm_v2i64_ty], [llvm_v2i64_ty, 
                          llvm_v2i64_ty, llvm_v2i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_q_256 : GCCBuiltin<"__builtin_ia32_psraq256_mask">,
              Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty, 
                          llvm_v2i64_ty, llvm_v4i64_ty, llvm_i8_ty], [IntrNoMem]>;
   def int_x86_avx512_mask_psra_qi_128 : GCCBuiltin<"__builtin_ia32_psraqi128_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_psra_qi_256 : GCCBuiltin<"__builtin_ia32_psraqi256_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_psra_qi_512 : GCCBuiltin<"__builtin_ia32_psraqi512_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_psrl_d_128: GCCBuiltin<"__builtin_ia32_psrld128_mask">,
               Intrinsic<[llvm_v4i32_ty], [ llvm_v4i32_ty,
                          llvm_v4i32_ty, llvm_v4i32_ty, llvm_i8_ty ], [IntrNoMem]>;
   def int_x86_avx512_mask_psrl_d_256: GCCBuiltin<"__builtin_ia32_psrld256_mask">,
               Intrinsic<[llvm_v8i32_ty], [ llvm_v8i32_ty, 
                          llvm_v4i32_ty, llvm_v8i32_ty, llvm_i8_ty ], [IntrNoMem]>;
   def int_x86_avx512_mask_psrl_di_128: GCCBuiltin<"__builtin_ia32_psrldi128_mask">,

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

   X86_INTRINSIC_DATA(avx512_mask_psllv32hi,     INTR_TYPE_2OP_MASK, ISD::SHL, 0),
   X86_INTRINSIC_DATA(avx512_mask_psllv4_di,     INTR_TYPE_2OP_MASK, ISD::SHL, 0),
   X86_INTRINSIC_DATA(avx512_mask_psllv4_si,     INTR_TYPE_2OP_MASK, ISD::SHL, 0),
   X86_INTRINSIC_DATA(avx512_mask_psllv8_hi,     INTR_TYPE_2OP_MASK, ISD::SHL, 0),
   X86_INTRINSIC_DATA(avx512_mask_psllv8_si,     INTR_TYPE_2OP_MASK, ISD::SHL, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_d,        INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_d_128,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_d_256,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_di_128,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_di_256,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_di_512,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_di_128,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_di_256,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_di_512,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_q,        INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_q_128,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_q_256,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_qi_128,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_qi_256,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_qi_512,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_qi_128,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_qi_256,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_qi_512,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_w_128,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_w_256,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psra_w_512,    INTR_TYPE_2OP_MASK, X86ISD::VSRA, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_wi_128,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_wi_256,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
-  X86_INTRINSIC_DATA(avx512_mask_psra_wi_512,   INTR_TYPE_2OP_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_wi_128,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_wi_256,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
+  X86_INTRINSIC_DATA(avx512_mask_psra_wi_512,   INTR_TYPE_2OP_IMM8_MASK, X86ISD::VSRAI, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrai_d,       VSHIFT_MASK, X86ISD::VSRAI, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrai_q,       VSHIFT_MASK, X86ISD::VSRAI, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav_d,       INTR_TYPE_2OP_MASK, ISD::SRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav_q,       INTR_TYPE_2OP_MASK, ISD::SRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav_q_128,   INTR_TYPE_2OP_MASK, ISD::SRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav_q_256,   INTR_TYPE_2OP_MASK, ISD::SRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav16_hi,    INTR_TYPE_2OP_MASK, ISD::SRA, 0),
   X86_INTRINSIC_DATA(avx512_mask_psrav32_hi,     INTR_TYPE_2OP_MASK, ISD::SRA, 0),

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

; CHECK-NEXT:    retq
   %res = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> %x2, i16 %x3)
   %res1 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> %x2, i16 -1)
   %res2 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> zeroinitializer, i16 %x3)
   %res3 = add <16 x i32> %res, %res1
   %res4 = add <16 x i32> %res3, %res2
   ret <16 x i32> %res4
 }
 
-declare <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32>, i8, <16 x i32>, i16)
+declare <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32>, i32, <16 x i32>, i16)
 
-define <16 x i32>@test_int_x86_avx512_mask_psra_di_512(<16 x i32> %x0, i8 %x1, <16 x i32> %x2, i16 %x3) {
+define <16 x i32>@test_int_x86_avx512_mask_psra_di_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_512:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vpsrad $3, %zmm0, %zmm1 {%k1}
 ; CHECK-NEXT:    vpsrad $3, %zmm0, %zmm2 {%k1} {z}
 ; CHECK-NEXT:    vpsrad $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.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 %x3)
-  %res1 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> zeroinitializer, i16 %x3)
-  %res2 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i8 3, <16 x i32> %x2, i16 -1)
+  %res = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 %x3)
+  %res1 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i32 3, <16 x i32> zeroinitializer, i16 %x3)
+  %res2 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.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.psra.qi.512(<8 x i64>, i8, <8 x i64>, i8)
+declare <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64>, i32, <8 x i64>, i8)
 
-define <8 x i64>@test_int_x86_avx512_mask_psra_qi_512(<8 x i64> %x0, i8 %x1, <8 x i64> %x2, i8 %x3) {
+define <8 x i64>@test_int_x86_avx512_mask_psra_qi_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_512:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vpsraq $3, %zmm0, %zmm1 {%k1}
 ; CHECK-NEXT:    vpsraq $3, %zmm0, %zmm2 {%k1} {z}
 ; CHECK-NEXT:    vpsraq $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.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 %x3)
-  %res1 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> zeroinitializer, i8 %x3)
-  %res2 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i8 3, <8 x i64> %x2, i8 -1)
+  %res = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 %x3)
+  %res1 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i32 3, <8 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.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.psll.di.512(<16 x i32>, i32, <16 x i32>, i16)
 
 define <16 x i32>@test_int_x86_avx512_mask_psll_di_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {

llvm/trunk/test/CodeGen/X86/avx512bw-intrinsics.ll

; 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)
   %res3 = add <32 x i16> %res, %res1
   %res4 = add <32 x i16> %res3, %res2
   ret <32 x i16> %res4
 }
 
-declare <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16>, i8, <32 x i16>, i32)
+declare <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16>, i32, <32 x i16>, i32)
 
-define <32 x i16>@test_int_x86_avx512_mask_psra_wi_512(<32 x i16> %x0, i8 %x1, <32 x i16> %x2, i32 %x3) {
+define <32 x i16>@test_int_x86_avx512_mask_psra_wi_512(<32 x i16> %x0, i32 %x1, <32 x i16> %x2, i32 %x3) {
 ; AVX512BW-LABEL: test_int_x86_avx512_mask_psra_wi_512:
 ; AVX512BW:       ## BB#0:
 ; AVX512BW-NEXT:    kmovd %esi, %k1
 ; AVX512BW-NEXT:    vpsraw $3, %zmm0, %zmm1 {%k1}
 ; AVX512BW-NEXT:    vpsraw $3, %zmm0, %zmm2 {%k1} {z}
 ; AVX512BW-NEXT:    vpsraw $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_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)
+  %res = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i32 3, <32 x i16> %x2, i32 %x3)
+  %res1 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i32 3, <32 x i16> zeroinitializer, i32 %x3)
+  %res2 = call <32 x i16> @llvm.x86.avx512.mask.psra.wi.512(<32 x i16> %x0, i32 3, <32 x i16> %x2, i32 -1)
   %res3 = add <32 x i16> %res, %res1
   %res4 = add <32 x i16> %res3, %res2
   ret <32 x i16> %res4
 }
 
 declare <32 x i16> @llvm.x86.avx512.mask.pshufh.w.512(<32 x i16>, i32, <32 x i16>, i32)
 
 define <32 x i16>@test_int_x86_avx512_mask_pshufh_w_512(<32 x i16> %x0, i32 %x1, <32 x i16> %x2, i32 %x3) {

llvm/trunk/test/CodeGen/X86/avx512bwvl-intrinsics.ll

; CHECK-NEXT:    retq
   %res = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
   %res1 = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> zeroinitializer, i8 %x3)
   %res2 = call <8 x i16> @llvm.x86.avx512.mask.psra.w.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 -1)
   %res3 = add <8 x i16> %res, %res1
   %res4 = add <8 x i16> %res3, %res2
   ret <8 x i16> %res4
 }
 
-declare <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16>, i8, <8 x i16>, i8)
+declare <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16>, i32, <8 x i16>, i8)
 
-define <8 x i16>@test_int_x86_avx512_mask_psra_wi_128(<8 x i16> %x0, i8 %x1, <8 x i16> %x2, i8 %x3) {
+define <8 x i16>@test_int_x86_avx512_mask_psra_wi_128(<8 x i16> %x0, i32 %x1, <8 x i16> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_wi_128:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vpsraw $3, %xmm0, %xmm1 {%k1}
 ; CHECK-NEXT:    vpsraw $3, %xmm0, %xmm2 {%k1} {z}
 ; CHECK-NEXT:    vpsraw $3, %xmm0, %xmm0
 ; CHECK-NEXT:    vpaddw %xmm2, %xmm1, %xmm1
 ; CHECK-NEXT:    vpaddw %xmm0, %xmm1, %xmm0
 ; CHECK-NEXT:    retq
-  %res = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> %x2, i8 %x3)
-  %res1 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> zeroinitializer, i8 %x3)
-  %res2 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i8 3, <8 x i16> %x2, i8 -1)
+  %res = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i32 3, <8 x i16> %x2, i8 %x3)
+  %res1 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i32 3, <8 x i16> zeroinitializer, i8 %x3)
+  %res2 = call <8 x i16> @llvm.x86.avx512.mask.psra.wi.128(<8 x i16> %x0, i32 3, <8 x i16> %x2, i8 -1)
   %res3 = add <8 x i16> %res, %res1
   %res4 = add <8 x i16> %res3, %res2
   ret <8 x i16> %res4
 }
 
 declare <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16>, <8 x i16>, <16 x i16>, i16)
 
 define <16 x i16>@test_int_x86_avx512_mask_psra_w_256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; CHECK-NEXT:    retq
   %res = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 %x3)
   %res1 = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> zeroinitializer, i16 %x3)
   %res2 = call <16 x i16> @llvm.x86.avx512.mask.psra.w.256(<16 x i16> %x0, <8 x i16> %x1, <16 x i16> %x2, i16 -1)
   %res3 = add <16 x i16> %res, %res1
   %res4 = add <16 x i16> %res3, %res2
   ret <16 x i16> %res4
 }
 
-declare <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16>, i8, <16 x i16>, i16)
+declare <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16>, i32, <16 x i16>, i16)
 
-define <16 x i16>@test_int_x86_avx512_mask_psra_wi_256(<16 x i16> %x0, i8 %x1, <16 x i16> %x2, i16 %x3) {
+define <16 x i16>@test_int_x86_avx512_mask_psra_wi_256(<16 x i16> %x0, i32 %x1, <16 x i16> %x2, i16 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_wi_256:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vpsraw $3, %ymm0, %ymm1 {%k1}
 ; CHECK-NEXT:    vpsraw $3, %ymm0, %ymm2 {%k1} {z}
 ; CHECK-NEXT:    vpsraw $3, %ymm0, %ymm0
 ; CHECK-NEXT:    vpaddw %ymm2, %ymm1, %ymm1
 ; CHECK-NEXT:    vpaddw %ymm0, %ymm1, %ymm0
 ; CHECK-NEXT:    retq
-  %res = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> %x2, i16 %x3)
-  %res1 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> zeroinitializer, i16 %x3)
-  %res2 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i8 3, <16 x i16> %x2, i16 -1)
+  %res = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i32 3, <16 x i16> %x2, i16 %x3)
+  %res1 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i32 3, <16 x i16> zeroinitializer, i16 %x3)
+  %res2 = call <16 x i16> @llvm.x86.avx512.mask.psra.wi.256(<16 x i16> %x0, i32 3, <16 x i16> %x2, i16 -1)
   %res3 = add <16 x i16> %res, %res1
   %res4 = add <16 x i16> %res3, %res2
   ret <16 x i16> %res4
 }
 
 declare <4 x i32> @llvm.x86.avx512.mask.pshuf.d.128(<4 x i32>, i16, <4 x i32>, i8)
 
 define <4 x i32>@test_int_x86_avx512_mask_pshuf_d_128(<4 x i32> %x0, i16 %x1, <4 x i32> %x2, i8 %x3) {

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

; 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)
+declare <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32>, i32, <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) {
+define <4 x i32>@test_int_x86_avx512_mask_psra_di_128(<4 x i32> %x0, i32 %x1, <4 x i32> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_128:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %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)
+  %res = call <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32> %x0, i32 3, <4 x i32> %x2, i8 %x3)
+  %res1 = call <4 x i32> @llvm.x86.avx512.mask.psra.di.128(<4 x i32> %x0, i32 3, <4 x i32> zeroinitializer, i8 %x3)
+  %res2 = call <4 x i32> @llvm.x86.avx512.mask.psra.di.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.psra.di.256(<8 x i32>, i8, <8 x i32>, i8)
+declare <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32>, i32, <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) {
+define <8 x i32>@test_int_x86_avx512_mask_psra_di_256(<8 x i32> %x0, i32 %x1, <8 x i32> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_256:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %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)
+  %res = call <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32> %x0, i32 3, <8 x i32> %x2, i8 %x3)
+  %res1 = call <8 x i32> @llvm.x86.avx512.mask.psra.di.256(<8 x i32> %x0, i32 3, <8 x i32> zeroinitializer, i8 %x3)
+  %res2 = call <8 x i32> @llvm.x86.avx512.mask.psra.di.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.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-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)
+declare <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64>, i32, <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) {
+define <2 x i64>@test_int_x86_avx512_mask_psra_qi_128(<2 x i64> %x0, i32 %x1, <2 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_128:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %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)
+  %res = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64> %x0, i32 3, <2 x i64> %x2, i8 %x3)
+  %res1 = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.128(<2 x i64> %x0, i32 3, <2 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <2 x i64> @llvm.x86.avx512.mask.psra.qi.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.psra.qi.256(<4 x i64>, i8, <4 x i64>, i8)
+declare <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64>, i32, <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) {
+define <4 x i64>@test_int_x86_avx512_mask_psra_qi_256(<4 x i64> %x0, i32 %x1, <4 x i64> %x2, i8 %x3) {
 ; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_256:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    kmovw %esi, %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)
+  %res = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64> %x0, i32 3, <4 x i64> %x2, i8 %x3)
+  %res1 = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.256(<4 x i64> %x0, i32 3, <4 x i64> zeroinitializer, i8 %x3)
+  %res2 = call <4 x i64> @llvm.x86.avx512.mask.psra.qi.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.psll.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)