nicolas/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Introduce __builtin_nontemporal_store and __builtin_nontemporal_load.

Browse Source 
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
This commit is contained in:
Michael Zolotukhin
2015-09-08 23:52:33 +00:00
parent 00691e3169
commit 84df12375c
9 changed files with 188 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
clang/lib/CodeGen/CGExpr.cpp
View File

@@ -1160,7 +1160,8 @@ llvm::Value *CodeGenFunction::EmitLoadOfScalar(LValue lvalue,
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 @@ llvm::Value *CodeGenFunction::EmitLoadOfScalar(Address Addr, bool Volatile,
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::Value *CodeGenFunction::EmitLoadOfScalar(Address Addr, bool Volatile,
}
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 @@ void CodeGenFunction::EmitStoreOfScalar(llvm::Value *Value, Address Addr,
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 @@ void CodeGenFunction::EmitStoreOfScalar(llvm::Value *Value, Address Addr,
}
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 @@ void CodeGenFunction::EmitStoreOfScalar(llvm::Value *value, LValue lvalue,
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