[Clang][AVX512][Builtin] adding missing intrinsics for vpmultishiftqb{128|256|512} instruction set

[AsafBadouh]

LGTM

include/clang/Basic/BuiltinsX86.def

 TARGET_BUILTIN(__builtin_ia32_cvtsi2sd64, "V2dV2dLLiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtsi2ss32, "V4fV4fiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtsi2ss64, "V4fV4fLLiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtss2sd_round_mask, "V2dV2dV4fV2dUcIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2sd32, "V2dV2dUi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2sd64, "V2dV2dULLiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2ss32, "V4fV4fUiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_cvtusi2ss64, "V4fV4fULLiIi","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb512_mask, "V64cV64cV64cV64cULLi","","avx512vbmi")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb128_mask, "V16cV16cV16cV16cUs","","avx512vbmi,avx512vl")
+TARGET_BUILTIN(__builtin_ia32_vpmultishiftqb256_mask, "V32cV32cV32cV32cUi","","avx512vbmi,avx512vl")
 
 // MONITORX/MWAITX
 TARGET_BUILTIN(__builtin_ia32_monitorx, "vv*UiUi", "", "mwaitx")
 TARGET_BUILTIN(__builtin_ia32_mwaitx, "vUiUiUi", "", "mwaitx")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN

lib/Headers/avx512vbmiintrin.h

_mm512_mask_permutexvar_epi8 (__m512i __W, __mmask64 __M, __m512i __A,
              __m512i __B)
 {
   return (__m512i) __builtin_ia32_permvarqi512_mask ((__v64qi) __B,
                  (__v64qi) __A,
                  (__v64qi) __W,
                  (__mmask64) __M);
 }
 
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_mask_multishift_epi64_epi8 (__m512i __W, __mmask64 __M, __m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi) __W,
+                (__mmask64) __M);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_maskz_multishift_epi64_epi8 (__mmask64 __M, __m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi)
+                _mm512_setzero_si512 (),
+                (__mmask64) __M);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_multishift_epi64_epi8 (__m512i __X, __m512i __Y)
+{
+  return (__m512i) __builtin_ia32_vpmultishiftqb512_mask ((__v64qi) __X,
+                (__v64qi) __Y,
+                (__v64qi)
+                _mm512_undefined_epi32 (),
+                (__mmask64) -1);
+}
+
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif

lib/Headers/avx512vbmivlintrin.h

 #ifndef __IMMINTRIN_H
 #error "Never use <avx512vbmivlintrin.h> directly; include <immintrin.h> instead."
 #endif
 
 #ifndef __VBMIVLINTRIN_H
 #define __VBMIVLINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__(( __nodebug__, __target__("avx512vbmi,avx512vl")))
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("avx512vbmi,avx512vl")))
 
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_mask2_permutex2var_epi8 (__m128i __A, __m128i __I, __mmask16 __U,
             __m128i __B)
 {
   return (__m128i) __builtin_ia32_vpermi2varqi128_mask ((__v16qi) __A,
               (__v16qi) __I
_mm256_mask_permutexvar_epi8 (__m256i __W, __mmask32 __M, __m256i __A,
              __m256i __B)
 {
   return (__m256i) __builtin_ia32_permvarqi256_mask ((__v32qi) __B,
                  (__v32qi) __A,
                  (__v32qi) __W,
                  (__mmask32) __M);
 }
 
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_mask_multishift_epi64_epi8 (__m128i __W, __mmask16 __M, __m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi) __W,
+                (__mmask16) __M);
+}
+
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_maskz_multishift_epi64_epi8 (__mmask16 __M, __m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi)
+                _mm_setzero_si128 (),
+                (__mmask16) __M);
+}
+
+static __inline__ __m128i __DEFAULT_FN_ATTRS
+_mm_multishift_epi64_epi8 (__m128i __X, __m128i __Y)
+{
+  return (__m128i) __builtin_ia32_vpmultishiftqb128_mask ((__v16qi) __X,
+                (__v16qi) __Y,
+                (__v16qi)
+                _mm_undefined_si128 (),
+                (__mmask16) -1);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_mask_multishift_epi64_epi8 (__m256i __W, __mmask32 __M, __m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi) __W,
+                (__mmask32) __M);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_maskz_multishift_epi64_epi8 (__mmask32 __M, __m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi)
+                _mm256_setzero_si256 (),
+                (__mmask32) __M);
+}
+
+static __inline__ __m256i __DEFAULT_FN_ATTRS
+_mm256_multishift_epi64_epi8 (__m256i __X, __m256i __Y)
+{
+  return (__m256i) __builtin_ia32_vpmultishiftqb256_mask ((__v32qi) __X,
+                (__v32qi) __Y,
+                (__v32qi)
+                _mm256_undefined_si256 (),
+                (__mmask32) -1);
+}
+
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif

test/CodeGen/avx512vbmi-builtins.c

__m512i test_mm512_maskz_permutexvar_epi8(__mmask64 __M, __m512i __A, __m512i __B) {
   return _mm512_maskz_permutexvar_epi8(__M, __A, __B); 
 }
 
 __m512i test_mm512_mask_permutexvar_epi8(__m512i __W, __mmask64 __M, __m512i __A, __m512i __B) {
   // CHECK-LABEL: @test_mm512_mask_permutexvar_epi8
   // CHECK: @llvm.x86.avx512.mask.permvar.qi.512
   return _mm512_mask_permutexvar_epi8(__W, __M, __A, __B); 
 }
+
+__m512i test_mm512_mask_multishift_epi64_epi8(__m512i __W, __mmask64 __M, __m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m512i test_mm512_maskz_multishift_epi64_epi8(__mmask64 __M, __m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m512i test_mm512_multishift_epi64_epi8(__m512i __X, __m512i __Y) {
+  // CHECK-LABEL: @test_mm512_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.512
+  return _mm512_multishift_epi64_epi8(__X, __Y); 
+}

test/CodeGen/avx512vbmivl-builtin.c

-// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -target-feature avx512vbmi -target-feature avx512vl -target-feature avx2 -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -triple=x86_64-apple-darwin -target-feature +avx512vbmi -target-feature +avx512vl -target-feature +avx512bw -emit-llvm -o - -Werror | FileCheck %s
 
 // Don't include mm_malloc.h, it's system specific.
 #define __MM_MALLOC_H
 
 #include <immintrin.h>
 
 __m128i test_mm_permutexvar_epi8(__m128i __A, __m128i __B) {
   // CHECK-LABEL: @test_mm_permutexvar_epi8

 __m256i test_mm256_mask_permutex2var_epi8(__m256i __A, __mmask32 __U, __m256i __I, __m256i __B) {
   // CHECK-LABEL: @test_mm256_mask_permutex2var_epi8
   // CHECK: @llvm.x86.avx512.mask.vpermt2var.qi.256
   return _mm256_mask_permutex2var_epi8(__A, __U, __I, __B); 
 }
 
 __m256i test_mm256_maskz_permutex2var_epi8(__mmask32 __U, __m256i __A, __m256i __I, __m256i __B) {
   // CHECK-LABEL: @test_mm256_maskz_permutex2var_epi8
-  // CHECK: @llvm.x86.avx512.mask.vpermt2var.qi.256
+  // CHECK: @llvm.x86.avx512.maskz.vpermt2var.qi.256
   return _mm256_maskz_permutex2var_epi8(__U, __A, __I, __B); 
-}
+}
+
+__m128i test_mm_mask_multishift_epi64_epi8(__m128i __W, __mmask16 __M, __m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m128i test_mm_maskz_multishift_epi64_epi8(__mmask16 __M, __m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m128i test_mm_multishift_epi64_epi8(__m128i __X, __m128i __Y) {
+  // CHECK-LABEL: @test_mm_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.128
+  return _mm_multishift_epi64_epi8(__X, __Y); 
+}
+
+__m256i test_mm256_mask_multishift_epi64_epi8(__m256i __W, __mmask32 __M, __m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_mask_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_mask_multishift_epi64_epi8(__W, __M, __X, __Y); 
+}
+
+__m256i test_mm256_maskz_multishift_epi64_epi8(__mmask32 __M, __m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_maskz_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_maskz_multishift_epi64_epi8(__M, __X, __Y); 
+}
+
+__m256i test_mm256_multishift_epi64_epi8(__m256i __X, __m256i __Y) {
+  // CHECK-LABEL: @test_mm256_multishift_epi64_epi8
+  // CHECK: @llvm.x86.avx512.mask.pmultishift.qb.256
+  return _mm256_multishift_epi64_epi8(__X, __Y); 
+}
+