diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -170,8 +170,9 @@ // 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); diff --git a/clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl b/clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl new file mode 100644 --- /dev/null +++ b/clang/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl @@ -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); +}