[CLNAG][AVX512][BUILTIN] adding storeup{d|s}{128|256} in to Clang

[delena]

LGTM

[m_zuckerman]

Builtin was committed to http://reviews.llvm.org/D18925

include/clang/Basic/BuiltinsX86.def

 TARGET_BUILTIN(__builtin_ia32_vpermi2varqi128_mask, "V16cV16cV16cV16cUs","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vpermi2varqi256_mask, "V32cV32cV32cV32cUi","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vpermt2varqi128_mask, "V16cV16cV16cV16cUs","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vpermt2varqi128_maskz, "V16cV16cV16cV16cUs","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vpermt2varqi256_mask, "V32cV32cV32cV32cUi","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vpermt2varqi256_maskz, "V32cV32cV32cV32cUi","","avx512vbmi,avx512vl")
 TARGET_BUILTIN(__builtin_ia32_vcomisd, "iV2dV2dIiIi","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_vcomiss, "iV4fV4fIiIi","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_storeapd128_mask, "vV2d*V2dUc","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_storeapd256_mask, "vV4d*V4dUc","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_storeaps128_mask, "vV4f*V4fUc","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_storeaps256_mask, "vV8f*V8fUc","","avx512f")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN

lib/Headers/avx512vlintrin.h

 static __inline__ __m256i __DEFAULT_FN_ATTRS
 _mm256_maskz_set1_epi64 (__mmask8 __M, long long __A)
 {
   return (__m256i) __builtin_ia32_pbroadcastq256_gpr_mask (__A,
                  (__v4di)
                  _mm256_setzero_si256 (),
                  __M);
 }
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_mask_store_pd (void *__P, __mmask8 __U, __m128d __A)
+{
+  __builtin_ia32_storeapd128_mask ((__v2df *) __P,
+           (__v2df) __A,
+           (__mmask8) __U);
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm256_mask_store_pd (void *__P, __mmask8 __U, __m256d __A)
+{
+  __builtin_ia32_storeapd256_mask ((__v4df *) __P,
+           (__v4df) __A,
+           (__mmask8) __U);
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm_mask_store_ps (void *__P, __mmask8 __U, __m128 __A)
+{
+  __builtin_ia32_storeaps128_mask ((__v4sf *) __P,
+           (__v4sf) __A,
+           (__mmask8) __U);
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm256_mask_store_ps (void *__P, __mmask8 __U, __m256 __A)
+{
+  __builtin_ia32_storeaps256_mask ((__v8sf *) __P,
+           (__v8sf) __A,
+           (__mmask8) __U);
+}
+
+
 #undef __DEFAULT_FN_ATTRS
 #undef __DEFAULT_FN_ATTRS_BOTH
 
 #endif /* __AVX512VLINTRIN_H */

test/CodeGen/avx512vl-builtins.c

 }
 
 __m256i test_mm256_maskz_set1_epi64(__mmask8 __M, long long __A) {
   // CHECK-LABEL: @test_mm256_maskz_set1_epi64
   // CHECK: @llvm.x86.avx512.mask.pbroadcast.q.gpr.256
   return _mm256_maskz_set1_epi64(__M, __A); 
 }
 
+void test_mm_mask_store_pd(void *__P, __mmask8 __U, __m128d __A) {
+  // CHECK-LABEL: @test_mm_mask_store_pd
+  // CHECK: @llvm.x86.avx512.mask.store.pd.128
+  return _mm_mask_store_pd(__P, __U, __A); 
+}
+
+void test_mm256_mask_store_pd(void *__P, __mmask8 __U, __m256d __A) {
+  // CHECK-LABEL: @test_mm256_mask_store_pd
+  // CHECK: @llvm.x86.avx512.mask.store.pd.256
+  return _mm256_mask_store_pd(__P, __U, __A); 
+}
+
+void test_mm_mask_store_ps(void *__P, __mmask8 __U, __m128 __A) {
+  // CHECK-LABEL: @test_mm_mask_store_ps
+  // CHECK: @llvm.x86.avx512.mask.store.ps.128
+  return _mm_mask_store_ps(__P, __U, __A); 
+}
+
+void test_mm256_mask_store_ps(void *__P, __mmask8 __U, __m256 __A) {
+  // CHECK-LABEL: @test_mm256_mask_store_ps
+  // CHECK: @llvm.x86.avx512.mask.store.ps.256
+  return _mm256_mask_store_ps(__P, __U, __A); 
+}
+