commit 84df12375cdec370fd09a99e3de2e788351ff403
author Michael Zolotukhin <mzolotukhin@apple.com> Tue Sep 08 23:52:33 2015 +0000
committer Michael Zolotukhin <mzolotukhin@apple.com> Tue Sep 08 23:52:33 2015 +0000
tree e1f89510fbda184151560b0c8246103ff7d5f7c9
parent 00691e3169fc90e4202c6a592e9fda20e006c299

Introduce __builtin_nontemporal_store and __builtin_nontemporal_load.

Summary:
Currently clang provides no general way to generate nontemporal loads/stores.
There are some architecture specific builtins for doing so (e.g. in x86), but
there is no way to generate non-temporal store on, e.g. AArch64. This patch adds
generic builtins which are expanded to a simple store with '!nontemporal'
attribute in IR.

Differential Revision: http://reviews.llvm.org/D12313

llvm-svn: 247104

clang/lib/CodeGen/CGExpr.cpp

diff --git a/clang/lib/CodeGen/CGExpr.cpp b/clang/lib/CodeGen/CGExpr.cpp
index 6635e57..b7d1ef1 100644
--- a/clang/lib/CodeGen/CGExpr.cpp
+++ b/clang/lib/CodeGen/CGExpr.cpp
@@ -1160,7 +1160,8 @@
   return EmitLoadOfScalar(lvalue.getAddress(), lvalue.isVolatile(),
                           lvalue.getType(), Loc, lvalue.getAlignmentSource(),
                           lvalue.getTBAAInfo(),
-                          lvalue.getTBAABaseType(), lvalue.getTBAAOffset());
+                          lvalue.getTBAABaseType(), lvalue.getTBAAOffset(),
+                          lvalue.isNontemporal());
 }
 
 static bool hasBooleanRepresentation(QualType Ty) {
@@ -1226,7 +1227,8 @@
                                                AlignmentSource AlignSource,
                                                llvm::MDNode *TBAAInfo,
                                                QualType TBAABaseType,
-                                               uint64_t TBAAOffset) {
+                                               uint64_t TBAAOffset,
+                                               bool isNontemporal) {
   // For better performance, handle vector loads differently.
   if (Ty->isVectorType()) {
     const llvm::Type *EltTy = Addr.getElementType();
@@ -1258,6 +1260,11 @@
   }
 
   llvm::LoadInst *Load = Builder.CreateLoad(Addr, Volatile);
+  if (isNontemporal) {
+    llvm::MDNode *Node = llvm::MDNode::get(
+        Load->getContext(), llvm::ConstantAsMetadata::get(Builder.getInt32(1)));
+    Load->setMetadata(CGM.getModule().getMDKindID("nontemporal"), Node);
+  }
   if (TBAAInfo) {
     llvm::MDNode *TBAAPath = CGM.getTBAAStructTagInfo(TBAABaseType, TBAAInfo,
                                                       TBAAOffset);
@@ -1330,7 +1337,8 @@
                                         AlignmentSource AlignSource,
                                         llvm::MDNode *TBAAInfo,
                                         bool isInit, QualType TBAABaseType,
-                                        uint64_t TBAAOffset) {
+                                        uint64_t TBAAOffset,
+                                        bool isNontemporal) {
 
   // Handle vectors differently to get better performance.
   if (Ty->isVectorType()) {
@@ -1365,6 +1373,12 @@
   }
 
   llvm::StoreInst *Store = Builder.CreateStore(Value, Addr, Volatile);
+  if (isNontemporal) {
+    llvm::MDNode *Node =
+        llvm::MDNode::get(Store->getContext(),
+                          llvm::ConstantAsMetadata::get(Builder.getInt32(1)));
+    Store->setMetadata(CGM.getModule().getMDKindID("nontemporal"), Node);
+  }
   if (TBAAInfo) {
     llvm::MDNode *TBAAPath = CGM.getTBAAStructTagInfo(TBAABaseType, TBAAInfo,
                                                       TBAAOffset);
@@ -1378,7 +1392,7 @@
   EmitStoreOfScalar(value, lvalue.getAddress(), lvalue.isVolatile(),
                     lvalue.getType(), lvalue.getAlignmentSource(),
                     lvalue.getTBAAInfo(), isInit, lvalue.getTBAABaseType(),
-                    lvalue.getTBAAOffset());
+                    lvalue.getTBAAOffset(), lvalue.isNontemporal());
 }
 
 /// EmitLoadOfLValue - Given an expression that represents a value lvalue, this