[OpenCL][CodeGen] Fix replacing memcpy with addrspacecast

Summary:
If a function argument is byval and RV is located in default or alloca address space
an optimization of creating addrspacecast instead of memcpy is performed. That is
not correct for OpenCL, where that can lead to a situation of address space casting
from __private * to __global *. See an example below:

```
typedef struct {
  int x;
} MyStruct;

void foo(MyStruct val) {}

kernel void KernelOneMember(__global MyStruct* x) {
  foo (*x);
}
```

for this code clang generated following IR:
...
%0 = load %struct.MyStruct addrspace(1)*, %struct.MyStruct addrspace(1)**
%x.addr, align 4
%1 = addrspacecast %struct.MyStruct addrspace(1)* %0 to %struct.MyStruct*
...

So the optimization was disallowed for OpenCL if RV is located in an address space
different than that of the argument (0).


Reviewers: yaxunl, Anastasia

Reviewed By: Anastasia

Subscribers: cfe-commits, asavonic

Differential Revision: https://reviews.llvm.org/D54947

llvm-svn: 348752

2 files changed, 29 insertions, 7 deletions

diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index 6d89f3919fd..2fddc4bd99d 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -3958,15 +3958,28 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
         } else if (I->hasLValue()) {
           auto LV = I->getKnownLValue();
           auto AS = LV.getAddressSpace();
+
           if ((!ArgInfo.getIndirectByVal() &&
                (LV.getAlignment() >=
-                getContext().getTypeAlignInChars(I->Ty))) ||
-              (ArgInfo.getIndirectByVal() &&
-               ((AS != LangAS::Default && AS != LangAS::opencl_private &&
-                 AS != CGM.getASTAllocaAddressSpace())))) {
+                getContext().getTypeAlignInChars(I->Ty)))) {
+            NeedCopy = true;
+          }
+          if (!getLangOpts().OpenCL) {
+            if ((ArgInfo.getIndirectByVal() &&
+                (AS != LangAS::Default &&
+                 AS != CGM.getASTAllocaAddressSpace()))) {
+              NeedCopy = true;
+            }
+          }
+          // For OpenCL even if RV is located in default or alloca address space
+          // we don't want to perform address space cast for it.
+          else if ((ArgInfo.getIndirectByVal() &&
+                    Addr.getType()->getAddressSpace() != IRFuncTy->
+                      getParamType(FirstIRArg)->getPointerAddressSpace())) {
             NeedCopy = true;
           }
         }
+
         if (NeedCopy) {
           // Create an aligned temporary, and copy to it.
           Address AI = CreateMemTempWithoutCast(
diff --git a/clang/test/CodeGenOpenCL/addr-space-struct-arg.cl b/clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
index f8d7073f92e..6f923b7fd40 100644
--- a/clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
+++ b/clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
@@ -1,6 +1,9 @@
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -ffake-address-space-map -triple i686-pc-darwin | FileCheck -enable-var-scope -check-prefixes=COM,X86 %s
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN %s
-// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL2.0 -O0 -finclude-default-header -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN,AMDGCN20 %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -ffake-address-space-map -triple i686-pc-darwin | FileCheck -enable-var-scope -check-prefixes=COM,X86 %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL2.0 -O0 -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN,AMDGCN20 %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL1.2 -O0 -triple spir-unknown-unknown-unknown | FileCheck -enable-var-scope -check-prefixes=SPIR %s
+
+typedef int int2 __attribute__((ext_vector_type(2)));
 
 typedef struct {
   int cells[9];
@@ -130,6 +133,12 @@ kernel void KernelOneMember(struct StructOneMember u) {
   FuncOneMember(u);
 }
 
+// SPIR: call void @llvm.memcpy.p0i8.p1i8.i32
+// SPIR-NOT: addrspacecast
+kernel void KernelOneMemberSpir(global struct StructOneMember* u) {
+  FuncOneMember(*u);
+}
+
 // AMDGCN-LABEL: define amdgpu_kernel void @KernelLargeOneMember(
 // AMDGCN:  %[[U:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
 // AMDGCN:  store %struct.LargeStructOneMember %u.coerce, %struct.LargeStructOneMember addrspace(5)* %[[U]], align 8