commit 63ebb00e05c90d24fe6f7e8b3d4cfb45297e8e54
author skc7 <Krishna.Sankisa@amd.com> Wed Dec 01 06:12:57 2021 +0000
committer Copybara-Service <copybara-worker@google.com> Wed Dec 01 21:59:39 2021 -0800
tree cd06a22a2e363c332968fdbf53a9f501af2e7c51
parent 233f3f51dd898d85cb6b9b8d0591ba02736cb784

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

Reviewed By: yaxunl, sameerds

Differential Revision: https://reviews.llvm.org/D114849

GitOrigin-RevId: 16b781e6d16dead414a7036c8b59f1700ea49251

lib/CodeGen/CGBuiltin.cpp

diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 849423c..5d6df59 100644
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/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);

test/CodeGenOpenCL/amdgcn-non-temporal-store.cl

diff --git a/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl b/test/CodeGenOpenCL/amdgcn-non-temporal-store.cl
new file mode 100644
index 0000000..539d857
--- /dev/null
+++ b/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);
+}