[Clang][avx512][Builtin] Adding intrinsics for cvtw2mask{128|256|512} instruction set

[AsafBadouh]

LGTM

cfe/trunk/include/clang/Basic/BuiltinsX86.def

 TARGET_BUILTIN(__builtin_ia32_compressstoredf512_mask, "vV8d*V8dUc","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_compressstoredi512_mask, "vV8LLi*V8LLiUc","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_compressstoresf512_mask, "vV16f*V16fUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_compressstoresi512_mask, "vV16i*V16iUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_vcvtph2ps_mask, "V4fV8sV4fUc","","avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vcvtph2ps256_mask, "V8fV8sV8fUc","","avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vcvtps2ph_mask, "V8sV4fIiV8sUc","","avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vcvtps2ph256_mask, "V8sV8fIiV8sUc","","avx512vl")
+TARGET_BUILTIN(__builtin_ia32_cvtw2mask512, "UiV32s","","avx512bw")
+TARGET_BUILTIN(__builtin_ia32_cvtw2mask128, "UcV8s","","avx512bw,avx512vl")
+TARGET_BUILTIN(__builtin_ia32_cvtw2mask256, "UsV16s","","avx512bw,avx512vl")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN

cfe/trunk/lib/Headers/avx512bwintrin.h

 }
 
 static __inline__ __mmask64 __DEFAULT_FN_ATTRS
 _mm512_movepi8_mask (__m512i __A)
 {
   return (__mmask64) __builtin_ia32_cvtb2mask512 ((__v64qi) __A);
 }
 
+static __inline__ __mmask32 __DEFAULT_FN_ATTRS
+_mm512_movepi16_mask (__m512i __A)
+{
+  return (__mmask32) __builtin_ia32_cvtw2mask512 ((__v32hi) __A);
+}
+
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_movm_epi8 (__mmask64 __A)
 {
   return (__m512i) __builtin_ia32_cvtmask2b512 (__A);
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_movm_epi16 (__mmask32 __A)

cfe/trunk/lib/Headers/avx512vlbwintrin.h

 }
 
 static __inline__ __mmask32 __DEFAULT_FN_ATTRS
 _mm256_movepi8_mask (__m256i __A)
 {
   return (__mmask32) __builtin_ia32_cvtb2mask256 ((__v32qi) __A);
 }
 
+static __inline__ __mmask8 __DEFAULT_FN_ATTRS
+_mm_movepi16_mask (__m128i __A)
+{
+  return (__mmask8) __builtin_ia32_cvtw2mask128 ((__v8hi) __A);
+}
+
+static __inline__ __mmask16 __DEFAULT_FN_ATTRS
+_mm256_movepi16_mask (__m256i __A)
+{
+  return (__mmask16) __builtin_ia32_cvtw2mask256 ((__v16hi) __A);
+}
+
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_movm_epi8 (__mmask16 __A)
 {
   return (__m128i) __builtin_ia32_cvtmask2b128 (__A);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS
 _mm256_movm_epi8 (__mmask32 __A)

cfe/trunk/test/CodeGen/avx512bw-builtins.c

__m512i test_mm512_mm_maskz_dbsad_epu8(__mmask32 __U, __m512i __A, __m512i __B) {
   return _mm512_maskz_dbsad_epu8(__U, __A, __B, 170); 
 }
 
 __m512i test_mm512_sad_epu8(__m512i __A, __m512i __B) {
   // CHECK-LABEL: @test_mm512_sad_epu8
   // CHECK: @llvm.x86.avx512.psad.bw.512
   return _mm512_sad_epu8(__A, __B); 
 }
+
+__mmask32 test_mm512_movepi16_mask(__m512i __A) {
+  // CHECK-LABEL: @test_mm512_movepi16_mask
+  // CHECK: @llvm.x86.avx512.cvtw2mask.512
+  return _mm512_movepi16_mask(__A); 
+}
+

cfe/trunk/test/CodeGen/avx512vlbw-builtins.c

__m256i test_mm256_mask_dbsad_epu8(__m256i __W, __mmask16 __U, __m256i __A, __m256i __B) {
   return _mm256_mask_dbsad_epu8(__W, __U, __A, __B, 170); 
 }
 
 __m256i test_mm256_maskz_dbsad_epu8(__mmask16 __U, __m256i __A, __m256i __B) {
   // CHECK-LABEL: @test_mm256_maskz_dbsad_epu8
   // CHECK: @llvm.x86.avx512.mask.dbpsadbw.256
   return _mm256_maskz_dbsad_epu8(__U, __A, __B, 170); 
 }
+__mmask8 test_mm_movepi16_mask(__m128i __A) {
+  // CHECK-LABEL: @test_mm_movepi16_mask
+  // CHECK: @llvm.x86.avx512.cvtw2mask.128
+  return _mm_movepi16_mask(__A); 
+}
+
+__mmask16 test_mm256_movepi16_mask(__m256i __A) {
+  // CHECK-LABEL: @test_mm256_movepi16_mask
+  // CHECK: @llvm.x86.avx512.cvtw2mask.256
+  return _mm256_movepi16_mask(__A); 
+}
+