[OpenCL] Re-fix invalid address space generation for clk_event_t arguments of enqueue...

Summary:
https://reviews.llvm.org/D53809 fixed wrong address space(assert in debug build)
generated for event_ret argument. But exactly the same problem exists for
event_wait_list argument. This patch should fix both.

Reviewers: Anastasia, yaxunl

Reviewed By:  Anastasia

Subscribers: kristina, ebevhan, cfe-commits

Differential Revision: https://reviews.llvm.org/D59985

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@358151 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 97789218bbe3a94ccaeec29626639b1cd79434ef..d6ae818d6a0d4a70c69cf3183fb03c7554d515fd 100644 (file)
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/lib/CodeGen/CGBuiltin.cpp
@@ -3738,21 +3738,35 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     // Any calls now have event arguments passed.
     if (NumArgs >= 7) {
       llvm::Type *EventTy = ConvertType(getContext().OCLClkEventTy);
-      llvm::Type *EventPtrTy = EventTy->getPointerTo(
+      llvm::PointerType *EventPtrTy = EventTy->getPointerTo(
           CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic));
 
       llvm::Value *NumEvents =
           Builder.CreateZExtOrTrunc(EmitScalarExpr(E->getArg(3)), Int32Ty);
-      llvm::Value *EventList =
-          E->getArg(4)->getType()->isArrayType()
-              ? EmitArrayToPointerDecay(E->getArg(4)).getPointer()
-              : EmitScalarExpr(E->getArg(4));
-      llvm::Value *ClkEvent = EmitScalarExpr(E->getArg(5));
-      // Convert to generic address space.
-      EventList = Builder.CreatePointerCast(EventList, EventPtrTy);
-      ClkEvent = ClkEvent->getType()->isIntegerTy()
-                   ? Builder.CreateBitOrPointerCast(ClkEvent, EventPtrTy)
-                   : Builder.CreatePointerCast(ClkEvent, EventPtrTy);
+
+      // Since SemaOpenCLBuiltinEnqueueKernel allows fifth and sixth arguments
+      // to be a null pointer constant (including `0` literal), we can take it
+      // into account and emit null pointer directly.
+      llvm::Value *EventWaitList = nullptr;
+      if (E->getArg(4)->isNullPointerConstant(
+              getContext(), Expr::NPC_ValueDependentIsNotNull)) {
+        EventWaitList = llvm::ConstantPointerNull::get(EventPtrTy);
+      } else {
+        EventWaitList = E->getArg(4)->getType()->isArrayType()
+                        ? EmitArrayToPointerDecay(E->getArg(4)).getPointer()
+                        : EmitScalarExpr(E->getArg(4));
+        // Convert to generic address space.
+        EventWaitList = Builder.CreatePointerCast(EventWaitList, EventPtrTy);
+      }
+      llvm::Value *EventRet = nullptr;
+      if (E->getArg(5)->isNullPointerConstant(
+              getContext(), Expr::NPC_ValueDependentIsNotNull)) {
+        EventRet = llvm::ConstantPointerNull::get(EventPtrTy);
+      } else {
+        EventRet =
+            Builder.CreatePointerCast(EmitScalarExpr(E->getArg(5)), EventPtrTy);
+      }
+
       auto Info =
           CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(6));
       llvm::Value *Kernel =
@@ -3764,8 +3778,9 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
           QueueTy,    Int32Ty,    RangeTy,          Int32Ty,
           EventPtrTy, EventPtrTy, GenericVoidPtrTy, GenericVoidPtrTy};
 
-      std::vector<llvm::Value *> Args = {Queue,     Flags,    Range,  NumEvents,
-                                         EventList, ClkEvent, Kernel, Block};
+      std::vector<llvm::Value *> Args = {Queue,     Flags,         Range,
+                                         NumEvents, EventWaitList, EventRet,
+                                         Kernel,    Block};
 
       if (NumArgs == 7) {
         // Has events but no variadics.

diff --git a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
index 11e49e0df358670f4edfd4e4c051cb346b346735..8d77c18e7a550cc301827d6ec58bfbc0a5e8961a 100644 (file)
--- a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
+++ b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
@@ -107,8 +107,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
                  });
 
   // COMMON-LABEL: call i32 @__enqueue_kernel_basic_events
-  // COMMON-SAME: (%opencl.queue_t{{.*}}* {{%[0-9]+}}, i32 {{%[0-9]+}}, %struct.ndrange_t* {{.*}}, i32 1, %opencl.clk_event_t{{.*}}* addrspace(4)* {{%[0-9]+}}, %opencl.clk_event_t{{.*}}* addrspace(4)* null,
-  enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, 0,
+  // COMMON-SAME: (%opencl.queue_t{{.*}}* {{%[0-9]+}}, i32 {{%[0-9]+}}, %struct.ndrange_t* {{.*}}, i32 1, %opencl.clk_event_t{{.*}}* addrspace(4)* null, %opencl.clk_event_t{{.*}}* addrspace(4)* null,
+  enqueue_kernel(default_queue, flags, ndrange, 1, 0, 0,
                  ^(void) {
                    return;
                  });