Reapply "[Win/X86] Make _m_prefetch[w] builtins to avoid winnt.h conflicts (llvm#115099)" (llvm#138360)

This reverts commit 83ff9d4.

Don't change the builtin signature of _mm_prefetch this time.

Author: rnk

clang/include/clang/Basic/BuiltinHeaders.def

@@ -23,6 +23,7 @@ HEADER(INTRIN_H, "intrin.h")
 HEADER(MALLOC_H, "malloc.h")
 HEADER(MATH_H, "math.h")
 HEADER(MEMORY, "memory")
+HEADER(MMINTRIN_H, "mmintrin.h")
 HEADER(OBJC_MESSAGE_H, "objc/message.h")
 HEADER(OBJC_OBJC_AUTO_H, "objc/objc-auto.h")
 HEADER(OBJC_OBJC_EXCEPTION_H, "objc/objc-exception.h")

clang/include/clang/Basic/BuiltinsX86.td

@@ -138,6 +138,14 @@ let Attributes = [Const, NoThrow, RequiredVectorWidth<256>], Features = "avx" in
   }
 }
 
+let Features = "mmx", Header = "mmintrin.h", Attributes = [NoThrow, Const] in {
+  def _m_prefetch : X86LibBuiltin<"void(void *)">;
+}
+
+// PRFCHW
+let Features = "prfchw", Header = "intrin.h", Attributes = [NoThrow, Const] in {
+  def _m_prefetchw : X86LibBuiltin<"void(void volatile const *)">;
+}
 
 // Mechanically ported builtins from the original `.def` file.
 //
@@ -146,8 +154,8 @@ let Attributes = [Const, NoThrow, RequiredVectorWidth<256>], Features = "avx" in
 // current formulation is based on what was easiest to recognize from the
 // pre-TableGen version.
 
-let Features = "mmx", Attributes = [NoThrow, Const] in {
-  def _mm_prefetch : X86NoPrefixBuiltin<"void(char const *, int)">;
+let Features = "sse", Header = "xmmintrin.h", Attributes = [NoThrow, Const] in {
+  def _mm_prefetch : X86LibBuiltin<"void(char const *, int)">;
 }
 
 let Features = "sse", Attributes = [NoThrow] in {

clang/lib/CodeGen/TargetBuiltins/X86.cpp

@@ -804,6 +804,17 @@ 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 */

clang/lib/Headers/xmmintrin.h

@@ -2198,8 +2198,9 @@ _mm_storer_ps(float *__p, __m128 __a)
 #define _MM_HINT_NTA 0
 
 #ifndef _MSC_VER
-/* FIXME: We have to #define this because "sel" must be a constant integer, and
-   Sema doesn't do any form of constant propagation yet. */
+// If _MSC_VER is defined, we use the builtin variant of _mm_prefetch.
+// Otherwise, we provide this macro, which includes a cast, allowing the user
+// to pass a pointer of any time. The _mm_prefetch accepts char to match MSVC.
 
 /// Loads one cache line of data from the specified address to a location
 ///    closer to the processor.