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

[Reid Kleckner via cfe-commits]

https://github.com/rnk created https://github.com/llvm/llvm-project/pull/138360

This reverts commit 83ff9d4a34b1e579dd809759d13b70b8837f0cde.

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


>From 7da648bdd03a2fce7ab214f0425efb3a1ec1f4fe Mon Sep 17 00:00:00 2001
From: Reid Kleckner <rnk at google.com>
Date: Fri, 2 May 2025 16:15:33 -0700
Subject: [PATCH] Reapply "[Win/X86] Make _m_prefetch[w] builtins to avoid
 winnt.h conflicts (#115099)"

This reverts commit 83ff9d4a34b1e579dd809759d13b70b8837f0cde.

Don't change the builtin signature of _mm_prefetch this time.
---
 clang/include/clang/Basic/BuiltinsX86.td | 10 ++++++++--
 clang/lib/CodeGen/TargetBuiltins/X86.cpp | 11 +++++++++++
 clang/lib/Headers/prfchwintrin.h         | 23 ++++++++++-------------
 clang/lib/Headers/xmmintrin.h            |  9 +++++----
 4 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/clang/include/clang/Basic/BuiltinsX86.td b/clang/include/clang/Basic/BuiltinsX86.td
index 67cbbfdec7aaf..dbf3cca19546e 100644
--- a/clang/include/clang/Basic/BuiltinsX86.td
+++ b/clang/include/clang/Basic/BuiltinsX86.td
@@ -138,6 +138,12 @@ let Attributes = [Const, NoThrow, RequiredVectorWidth<256>], Features = "avx" in
   }
 }
 
+// PRFCHW
+let Features = "prfchw", Header = "intrin.h", Attributes = [NoThrow, Const] in {
+  def _m_prefetch : X86LibBuiltin<"void(void *)">;
+  def _m_prefetchw : X86LibBuiltin<"void(void volatile const *)">;
+}
+
 
 // Mechanically ported builtins from the original `.def` file.
 //
@@ -146,8 +152,8 @@ 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 {
diff --git a/clang/lib/CodeGen/TargetBuiltins/X86.cpp b/clang/lib/CodeGen/TargetBuiltins/X86.cpp
index 3c2a77ab3fe4e..e23d19d2f6b6b 100644
--- a/clang/lib/CodeGen/TargetBuiltins/X86.cpp
+++ b/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]);
diff --git a/clang/lib/Headers/prfchwintrin.h b/clang/lib/Headers/prfchwintrin.h
index eaea5f3cf8feb..8ec55d7073716 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 */
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 20e66d190113a..1fb070bca827e 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2197,10 +2197,7 @@ _mm_storer_ps(float *__p, __m128 __a)
 #define _MM_HINT_T2  1
 #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 0
 /// Loads one cache line of data from the specified address to a location
 ///    closer to the processor.
 ///
@@ -2225,6 +2222,10 @@ _mm_storer_ps(float *__p, __m128 __a)
 ///    be generated. \n
 ///    _MM_HINT_T2: Move data using the T2 hint. The PREFETCHT2 instruction will
 ///    be generated.
+///
+/// _mm_prefetch is implemented as a "library builtin" directly in Clang,
+/// similar to how it is done in MSVC. Clang will warn if the user doesn't
+/// include xmmintrin.h or immintrin.h.
 #define _mm_prefetch(a, sel) (__builtin_prefetch((const void *)(a), \
                                                  ((sel) >> 2) & 1, (sel) & 0x3))
 #endif