[clang] [Win/X86] Make _m_prefetch[w] builtins to avoid winnt.h conflicts (PR #115099)

[Reid Kleckner via cfe-commits]

https://github.com/rnk updated https://github.com/llvm/llvm-project/pull/115099

>From e1331b2c00db0cdff09345b36fd484f2269ee1cc Mon Sep 17 00:00:00 2001
From: Reid Kleckner <rnk at google.com>
Date: Tue, 5 Nov 2024 16:05:53 -0800
Subject: [PATCH 1/2] [Win/X86] Make _m_prefetch[w] builtins to avoid winnt.h
 conflicts

---
 clang/include/clang/Basic/BuiltinsX86.def |  6 +++++-
 clang/lib/CodeGen/CGBuiltin.cpp           | 10 ++++++++++
 clang/lib/Headers/prfchwintrin.h          | 23 ++++++++++-------------
 3 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/clang/include/clang/Basic/BuiltinsX86.def b/clang/include/clang/Basic/BuiltinsX86.def
index 4486eb73a11fa6..485374ae0337ee 100644
--- a/clang/include/clang/Basic/BuiltinsX86.def
+++ b/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")
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index a57c95d5b96672..582d0d5351d5ef 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/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]);
diff --git a/clang/lib/Headers/prfchwintrin.h b/clang/lib/Headers/prfchwintrin.h
index eaea5f3cf8febf..8ec55d7073716f 100644
--- a/clang/lib/Headers/prfchwintrin.h
+++ b/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 */

>From 7bdcba77722518a155f543baf29a2d8dc39222eb Mon Sep 17 00:00:00 2001
From: Reid Kleckner <rnk at google.com>
Date: Wed, 6 Nov 2024 00:45:51 +0000
Subject: [PATCH 2/2] format

---
 clang/lib/CodeGen/CGBuiltin.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 5db354d8fab4e3..59ab43a03f43e3 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -14778,7 +14778,8 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
   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 *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());