fix generic addr space ocl test

Author: ronlieb

clang/lib/CodeGen/CGExpr.cpp

@@ -103,11 +103,15 @@ RawAddress CodeGenFunction::CreateTempAlloca(llvm::Type *Ty, CharUnits Align,
   if (AllocaAddr)
     *AllocaAddr = Alloca;
   llvm::Value *V = Alloca.getPointer();
+  assert((!getLangOpts().OpenCL ||
+          CGM.getTarget().getTargetAddressSpace(getASTAllocaAddressSpace()) ==
+              CGM.getTarget().getTargetAddressSpace(LangAS::opencl_private)) &&
+         "For OpenCL allocas must allocate in the private address space!");
   // Alloca always returns a pointer in alloca address space, which may
   // be different from the type defined by the language. For example,
   // in C++ the auto variables are in the default address space. Therefore
   // cast alloca to the default address space when necessary.
-  if (getASTAllocaAddressSpace() != LangAS::Default) {
+  if (!getLangOpts().OpenCL && getASTAllocaAddressSpace() != LangAS::Default) {
     auto DestAddrSpace = getContext().getTargetAddressSpace(LangAS::Default);
     llvm::IRBuilderBase::InsertPointGuard IPG(Builder);
     // When ArraySize is nullptr, alloca is inserted at AllocaInsertPt,

clang/test/CodeGenOpenCL/addr-space-struct-arg.cl

@@ -15,9 +15,8 @@
 // CL20-SAME: ptr noundef [[X:%.*]]) #[[ATTR0:[0-9]+]] {
 // CL20-NEXT:  [[ENTRY:.*:]]
 // CL20-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
-// CL20-NEXT:    [[X_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[X_ADDR]] to ptr
-// CL20-NEXT:    store ptr [[X]], ptr [[X_ADDR_ASCAST]], align 8
-// CL20-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[X_ADDR_ASCAST]], align 8
+// CL20-NEXT:    store ptr [[X]], ptr addrspace(5) [[X_ADDR]], align 8
+// CL20-NEXT:    [[TMP0:%.*]] = load ptr, ptr addrspace(5) [[X_ADDR]], align 8
 // CL20-NEXT:    store i32 1, ptr [[TMP0]], align 4
 // CL20-NEXT:    ret void
 //
@@ -55,22 +54,19 @@ void func1(int *x) {
 // CL20-NEXT:    [[LP1:%.*]] = alloca ptr, align 8, addrspace(5)
 // CL20-NEXT:    [[LP2:%.*]] = alloca ptr, align 8, addrspace(5)
 // CL20-NEXT:    [[LVC:%.*]] = alloca i32, align 4, addrspace(5)
+// CL20-NEXT:    store i32 1, ptr addrspace(5) [[LV1]], align 4
+// CL20-NEXT:    store i32 2, ptr addrspace(5) [[LV2]], align 4
+// CL20-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x i32], ptr addrspace(5) [[LA]], i64 0, i64 0
+// CL20-NEXT:    store i32 3, ptr addrspace(5) [[ARRAYIDX]], align 4
 // CL20-NEXT:    [[LV1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LV1]] to ptr
-// CL20-NEXT:    [[LV2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LV2]] to ptr
-// CL20-NEXT:    [[LA_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LA]] to ptr
-// CL20-NEXT:    [[LP1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LP1]] to ptr
-// CL20-NEXT:    [[LP2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LP2]] to ptr
-// CL20-NEXT:    [[LVC_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LVC]] to ptr
-// CL20-NEXT:    store i32 1, ptr [[LV1_ASCAST]], align 4
-// CL20-NEXT:    store i32 2, ptr [[LV2_ASCAST]], align 4
-// CL20-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x i32], ptr [[LA_ASCAST]], i64 0, i64 0
-// CL20-NEXT:    store i32 3, ptr [[ARRAYIDX]], align 4
-// CL20-NEXT:    store ptr [[LV1_ASCAST]], ptr [[LP1_ASCAST]], align 8
-// CL20-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [100 x i32], ptr [[LA_ASCAST]], i64 0, i64 0
-// CL20-NEXT:    store ptr [[ARRAYDECAY]], ptr [[LP2_ASCAST]], align 8
-// CL20-NEXT:    call void @func1(ptr noundef [[LV1_ASCAST]]) #[[ATTR2:[0-9]+]]
-// CL20-NEXT:    store i32 4, ptr [[LVC_ASCAST]], align 4
-// CL20-NEXT:    store i32 4, ptr [[LV1_ASCAST]], align 4
+// CL20-NEXT:    store ptr [[LV1_ASCAST]], ptr addrspace(5) [[LP1]], align 8
+// CL20-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [100 x i32], ptr addrspace(5) [[LA]], i64 0, i64 0
+// CL20-NEXT:    [[ARRAYDECAY_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[ARRAYDECAY]] to ptr
+// CL20-NEXT:    store ptr [[ARRAYDECAY_ASCAST]], ptr addrspace(5) [[LP2]], align 8
+// CL20-NEXT:    [[LV1_ASCAST1:%.*]] = addrspacecast ptr addrspace(5) [[LV1]] to ptr
+// CL20-NEXT:    call void @func1(ptr noundef [[LV1_ASCAST1]]) #[[ATTR2:[0-9]+]]
+// CL20-NEXT:    store i32 4, ptr addrspace(5) [[LVC]], align 4
+// CL20-NEXT:    store i32 4, ptr addrspace(5) [[LV1]], align 4
 // CL20-NEXT:    ret void
 //
 void func2(void) {
@@ -102,8 +98,7 @@ void func2(void) {
 // CL20-SAME: ) #[[ATTR0]] {
 // CL20-NEXT:  [[ENTRY:.*:]]
 // CL20-NEXT:    [[A:%.*]] = alloca [16 x [1 x float]], align 4, addrspace(5)
-// CL20-NEXT:    [[A_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[A]] to ptr
-// CL20-NEXT:    call void @llvm.memset.p0.i64(ptr align 4 [[A_ASCAST]], i8 0, i64 64, i1 false)
+// CL20-NEXT:    call void @llvm.memset.p5.i64(ptr addrspace(5) align 4 [[A]], i8 0, i64 64, i1 false)
 // CL20-NEXT:    ret void
 //
 void func3(void) {