Fix invalid address space generation for clk_event_t

[vmaksimo]

Summary

Addrspace(32) was generated when putting 0 in clk_event_t * event_ret parameter for enqueue_kernel function.

[Anastasia]

LGTM. Thanks! Could you please add prefix [OpenCL] in the final commit title.

[Anastasia]

lib/CodeGen/CGBuiltin.cpp

3614

It doesn't seem like we are testing the cast however?

[AlexeySotkin]

lib/CodeGen/CGBuiltin.cpp

3614

Sorry, could you elaborate on your question/concern ?

lib/CodeGen/CGBuiltin.cpp

if (NumArgs >= 7) {
           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 = Builder.CreatePointerCast(ClkEvent, EventPtrTy);
+      ClkEvent = ClkEvent->getType()->isIntegerTy()
+                   ? Builder.CreateBitOrPointerCast(ClkEvent, EventPtrTy)
+                   : Builder.CreatePointerCast(ClkEvent, EventPtrTy);
       auto Info =
           CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(6));
       llvm::Value *Kernel =
           Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
       llvm::Value *Block =
           Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
 
       std::vector<llvm::Type *> ArgTys = {

test/CodeGenOpenCL/cl20-device-side-enqueue.cl

kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]],
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVLK2:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* [[BL_I8]])
   enqueue_kernel(default_queue, flags, ndrange, 2, &event_wait_list, &clk_event,
                  ^(void) {
                    a[i] = b[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,
+                 ^(void) {
+                   return;
+                 });
+
   // Emits global block literal [[BLG1]] and block kernel [[INVGK1]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // CHECK-LIFETIMES: [[LIFETIME_PTR:%[0-9]+]] = bitcast [1 x i64]* %[[BLOCK_SIZES1]] to i8*
   // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]])
   // CHECK-LIFETIMES-NEXT: getelementptr inbounds [1 x i64], [1 x i64]* %[[BLOCK_SIZES1]], i64 0, i64 0
   // CHECK-LIFETIMES-LABEL: call i32 @__enqueue_kernel_varargs(
   // CHECK-LIFETIMES-NEXT: call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull [[LIFETIME_PTR]])

 // COMMON: define internal spir_kernel void [[INVLK2]](i8 addrspace(4)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK1]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK2]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK3]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK4]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK5]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK6]](i8 addrspace(4)*, i8 addrspace(3)*, i8 addrspace(3)*, i8 addrspace(3)*) #{{[0-9]+}} {
 // COMMON: entry:
-// COMMON:  call void @__device_side_enqueue_block_invoke_8(i8 addrspace(4)* %0, i8 addrspace(3)* %1, i8 addrspace(3)* %2, i8 addrspace(3)* %3)
+// COMMON:  call void @__device_side_enqueue_block_invoke_9(i8 addrspace(4)* %0, i8 addrspace(3)* %1, i8 addrspace(3)* %2, i8 addrspace(3)* %3)
 // COMMON:  ret void
 // COMMON: }
 // COMMON: define internal spir_kernel void [[INVGK7]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_func void [[INVG8]](i8 addrspace(4)*{{.*}})
 // COMMON: define internal spir_func void [[INVG9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)* %{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK8]](i8 addrspace(4)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVLK3]](i8 addrspace(4)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK9]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INV_G_K]](i8 addrspace(4)*{{.*}}, i8 addrspace(3)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK10]](i8 addrspace(4)*{{.*}})
 // COMMON: define internal spir_kernel void [[INVGK11]](i8 addrspace(4)*{{.*}})