[Win/X86] Make _m_prefetch[w] builtins to avoid winnt.h conflicts

Author: rnk

clang/include/clang/Basic/BuiltinsX86.def

@@ -42,10 +42,14 @@ TARGET_BUILTIN(__builtin_ia32_writeeflags_u32, "vUi", "n", "")
 // All MMX instructions will be generated via builtins. Any MMX vector
 // types (<1 x i64>, <2 x i32>, etc.) that aren't used by these builtins will be
 // expanded by the back-end.
+//
 // FIXME: _mm_prefetch must be a built-in because it takes a compile-time constant
 // argument and our prior approach of using a #define to the current built-in
 // doesn't work in the presence of re-declaration of _mm_prefetch for windows.
-TARGET_BUILTIN(_mm_prefetch, "vcC*i", "nc", "mmx")
+TARGET_HEADER_BUILTIN(_mm_prefetch, "vcC*i", "nc", IMMINTRIN_H, ALL_LANGUAGES, "mmx")
+TARGET_HEADER_BUILTIN(_m_prefetch, "vv*", "nc", INTRIN_H, ALL_LANGUAGES, "")
+TARGET_HEADER_BUILTIN(_m_prefetchw, "vvDC*", "nc", INTRIN_H, ALL_LANGUAGES, "")
+
 TARGET_BUILTIN(__builtin_ia32_emms, "v", "n", "mmx")
 TARGET_BUILTIN(__builtin_ia32_vec_ext_v4hi, "sV4sIi", "ncV:64:", "sse")
 TARGET_BUILTIN(__builtin_ia32_vec_set_v4hi, "V4sV4ssIi", "ncV:64:", "sse")

clang/lib/CodeGen/CGBuiltin.cpp

@@ -14700,6 +14700,16 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
     Function *F = CGM.getIntrinsic(Intrinsic::prefetch, Address->getType());
     return Builder.CreateCall(F, {Address, RW, Locality, Data});
   }
+  case X86::BI_m_prefetch:
+  case X86::BI_m_prefetchw: {
+    Value *Address = Ops[0];
+    // The 'w' suffix implies write.
+    Value *RW = ConstantInt::get(Int32Ty, BuiltinID == X86::BI_m_prefetchw ? 1 : 0);
+    Value *Locality = ConstantInt::get(Int32Ty, 0x3);
+    Value *Data = ConstantInt::get(Int32Ty, 1);
+    Function *F = CGM.getIntrinsic(Intrinsic::prefetch, Address->getType());
+    return Builder.CreateCall(F, {Address, RW, Locality, Data});
+  }
   case X86::BI_mm_clflush: {
     return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_clflush),
                               Ops[0]);

clang/lib/Headers/prfchwintrin.h

@@ -14,6 +14,10 @@
 #ifndef __PRFCHWINTRIN_H
 #define __PRFCHWINTRIN_H
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 /// Loads a memory sequence containing the specified memory address into
 ///    all data cache levels.
 ///
@@ -26,11 +30,7 @@
 ///
 /// \param __P
 ///    A pointer specifying the memory address to be prefetched.
-static __inline__ void __attribute__((__always_inline__, __nodebug__))
-_m_prefetch(void *__P)
-{
-  __builtin_prefetch (__P, 0, 3 /* _MM_HINT_T0 */);
-}
+void _m_prefetch(void *__P);
 
 /// Loads a memory sequence containing the specified memory address into
 ///    the L1 data cache and sets the cache-coherency state to modified.
@@ -48,13 +48,10 @@ _m_prefetch(void *__P)
 ///
 /// \param __P
 ///    A pointer specifying the memory address to be prefetched.
-static __inline__ void __attribute__((__always_inline__, __nodebug__))
-_m_prefetchw(volatile const void *__P)
-{
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wcast-qual"
-  __builtin_prefetch ((const void*)__P, 1, 3 /* _MM_HINT_T0 */);
-#pragma clang diagnostic pop
-}
+void _m_prefetchw(volatile const void *__P);
+
+#if defined(__cplusplus)
+} // extern "C"
+#endif
 
 #endif /* __PRFCHWINTRIN_H */