[X86] Add missing _m_prefetch intrinsic

[RKSimon]

Summary

The 3DNOW/PRFCHW cpu targets define both the PREFETCHW (set cache line modified) and PREFETCH (set cache line exclusive) instructions but only the _m_prefetchw (PREFETCHW) intrinsic is included in the header. This patch adds the missing _m_prefetch intrinsic.

I'm basing this off AMD documentation - the intel docs on the support for PREFETCHW isn't clear whether Silvermont/Broadwell properly support PREFETCH but given that the intrinsic implementation is a default __builtin_prefetch call, it is safe whatever.

Fix for PR23648

[echristo]

LGTM.

-eric

cfe/trunk/lib/Headers/prfchwintrin.h

 #error "Never use <prfchwintrin.h> directly; include <x86intrin.h> or <mm3dnow.h> instead."
 #endif
 
 #ifndef __PRFCHWINTRIN_H
 #define __PRFCHWINTRIN_H
 
 #if defined(__PRFCHW__) || defined(__3dNOW__)
 static __inline__ void __attribute__((__always_inline__, __nodebug__))
+_m_prefetch(void *__P)
+{
+  __builtin_prefetch (__P, 0, 3 /* _MM_HINT_T0 */);
+}
+
+static __inline__ void __attribute__((__always_inline__, __nodebug__))
 _m_prefetchw(void *__P)
 {
   __builtin_prefetch (__P, 1, 3 /* _MM_HINT_T0 */);
 }
 #endif
 
 #endif /* __PRFCHWINTRIN_H */

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

 // RUN: %clang_cc1 -triple x86_64-unknown-unknown -target-feature +prfchw -emit-llvm -o - %s | FileCheck %s
 
 // Don't include mm_malloc.h, it's system specific.
 #define __MM_MALLOC_H
 
 #include <x86intrin.h>
 
-void prefetch_w(void *p) {
+void test_m_prefetch(void *p) {
+  return _m_prefetch(p);
+  // CHECK-LABEL: define void @test_m_prefetch
+  // CHECK: call void @llvm.prefetch({{.*}}, i32 0, i32 3, i32 1)
+}
+
+void test_m_prefetch_w(void *p) {
   return _m_prefetchw(p);
-// CHECK: @prefetch_w
+// CHECK-LABEL: define void : @test_m_prefetch_w
 // CHECK: call void @llvm.prefetch({{.*}}, i32 1, i32 3, i32 1)
 }