maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU][clang] Fix __builtin_nontemporal_store() failure on AMDGPU 

Reviewed By: yaxunl, sameerds

Differential Revision: https://reviews.llvm.org/D114849
This commit is contained in:
skc7 2021-12-01 06:12:57 +00:00
parent f13b43d570
commit 16b781e6d1
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -170,8 +170,9 @@ static Value *EmitNontemporalStore(CodeGenFunction &CGF, const CallExpr *E) {
// Convert the type of the pointer to a pointer to the stored type.
Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
unsigned SrcAddrSpace = Address->getType()->getPointerAddressSpace();
Value *BC = CGF.Builder.CreateBitCast(
Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
Address, llvm::PointerType::get(Val->getType(), SrcAddrSpace), "cast");
LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
LV.setNontemporal(true);
CGF.EmitStoreOfScalar(Val, LV, false);

8
clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl Normal file
View File

@ -0,0 +1,8 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
// CHECK-LABEL: @test_non_temporal_store_kernel
// CHECK: store i32 0, i32 addrspace(1)* %{{.*}}, align 4, !tbaa !{{.*}}, !nontemporal {{.*}}
kernel void test_non_temporal_store_kernel(global unsigned int* io) {
__builtin_nontemporal_store(0, io);
}