[OpenCL] Fix __enqueue_block for block with captures
The following test case causes issue with codegen of __enqueue_block
void (^block)(void) = ^{ callee(id, out); };
enqueue_kernel(queue, 0, ndrange, block);
Clang first does codegen for block expression in the first line and deletes its block info.
Clang then tries to do codegen for the same block expression again for the second line,
and fails because the block info is gone.
The fix is to do normal codegen for both lines. Introduce an API to OpenCL runtime to
record llvm block invoke function and llvm block literal emitted for each AST block
expression, and use the recorded information for generating the wrapper kernel.
The EmitBlockLiteral APIs are cleaned up to minimize changes to the normal codegen
of blocks.
Another minor issue is that some clean up AST expression is generated for block
with captures, which can be stripped by IgnoreImplicit.
Differential Revision: https://reviews.llvm.org/D43240
llvm-svn: 325264
diff --git a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
index 0efcce2..875c35c 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
@@ -2,6 +2,10 @@
typedef struct {int a;} ndrange_t;
+void callee(long id, global long *out) {
+ out[id] = id;
+}
+
// CHECK-LABEL: define amdgpu_kernel void @test
kernel void test(global char *a, char b, global long *c, long d) {
queue_t default_queue;
@@ -24,6 +28,12 @@
c[0] = d;
((local int*)lp)[0] = 1;
}, 100);
+
+ void (^block)(void) = ^{
+ callee(d, c);
+ };
+
+ enqueue_kernel(default_queue, flags, ndrange, block);
}
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i8 }>)
@@ -42,4 +52,7 @@
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, i8 addrspace(3)*)
// CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
+// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_4_kernel(<{ i32, i32, i8*, i64, i64 addrspace(1)* }>)
+// CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
+
// CHECK: attributes #[[ATTR]] = { nounwind "enqueued-block" }