[Clang][BuiltIn][AVX512]Adding intrinsics for vmovntdqa vmovntpd vmovntps instruction set

[AsafBadouh]

minor fixes, LGTM

test/CodeGen/avx512f-builtins.c

5060 ↗

(On Diff #54984)

you can move the "return", its void function.
same for the other two.

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

 TARGET_BUILTIN(__builtin_ia32_kandhi, "UsUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kandnhi, "UsUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_korhi, "UsUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kortestchi, "iUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kortestzhi, "iUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kunpckhi, "UsUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kxnorhi, "UsUsUs","","avx512f")
 TARGET_BUILTIN(__builtin_ia32_kxorhi, "UsUsUs","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_movntdq512, "vV8LLi*V8LLi","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_movntdqa512, "V8LLiV8LLi*","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_movntpd512, "vd*V8d","","avx512f")
+TARGET_BUILTIN(__builtin_ia32_movntps512, "vf*V16f","","avx512f")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN

cfe/trunk/lib/Headers/avx512fintrin.h

 }
 
 static __inline__ __mmask16 __DEFAULT_FN_ATTRS
 _mm512_kxor (__mmask16 __A, __mmask16 __B)
 {
   return (__mmask16) __builtin_ia32_kxorhi ((__mmask16) __A, (__mmask16) __B);
 }
 
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm512_stream_si512 (__m512i * __P, __m512i __A)
+{
+  __builtin_ia32_movntdq512 ((__v8di *) __P, (__v8di) __A);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS
+_mm512_stream_load_si512 (void *__P)
+{
+  return __builtin_ia32_movntdqa512 ((__v8di *)__P);
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm512_stream_pd (double *__P, __m512d __A)
+{
+  __builtin_ia32_movntpd512 (__P, (__v8df) __A);
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm512_stream_ps (float *__P, __m512 __A)
+{
+  __builtin_ia32_movntps512 (__P, (__v16sf) __A);
+}
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif // __AVX512FINTRIN_H

cfe/trunk/test/CodeGen/avx512f-builtins.c

__mmask16 test_mm512_kxnor(__mmask16 __A, __mmask16 __B) {
   return _mm512_kxnor(__A, __B); 
 }
 
 __mmask16 test_mm512_kxor(__mmask16 __A, __mmask16 __B) {
   // CHECK-LABEL: @test_mm512_kxor
   // CHECK: @llvm.x86.avx512.kxor.w
   return _mm512_kxor(__A, __B); 
 }
+
+void test_mm512_stream_si512(__m512i * __P, __m512i __A) {
+  // CHECK-LABEL: @test_mm512_stream_si512
+  // CHECK: @llvm.x86.avx512.storent.q.512
+  _mm512_stream_si512(__P, __A); 
+}
+
+__m512i test_mm512_stream_load_si512(void *__P) {
+  // CHECK-LABEL: @test_mm512_stream_load_si512
+  // CHECK: @llvm.x86.avx512.movntdqa
+  return _mm512_stream_load_si512(__P); 
+}
+
+void test_mm512_stream_pd(double *__P, __m512d __A) {
+  // CHECK-LABEL: @test_mm512_stream_pd
+  // CHECK: @llvm.x86.avx512.storent.pd.512
+  return _mm512_stream_pd(__P, __A); 
+}
+
+void test_mm512_stream_ps(float *__P, __m512 __A) {
+  // CHECK-LABEL: @test_mm512_stream_ps
+  // CHECK: @llvm.x86.avx512.storent.ps.512
+  _mm512_stream_ps(__P, __A); 
+}
+