diff options
author | Yaxun Liu <Yaxun.Liu@amd.com> | 2017-10-14 12:23:50 +0000 |
---|---|---|
committer | Yaxun Liu <Yaxun.Liu@amd.com> | 2017-10-14 12:23:50 +0000 |
commit | c2a87a05f1a6715d5a62fa9db658cce98a3e95cb (patch) | |
tree | ab413656ac93540373c5fc473b50e50ed0810811 /clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl | |
parent | 09c234f857e7e09e15121b2dfca326fcc6c6f73d (diff) | |
download | bcm5719-llvm-c2a87a05f1a6715d5a62fa9db658cce98a3e95cb.tar.gz bcm5719-llvm-c2a87a05f1a6715d5a62fa9db658cce98a3e95cb.zip |
[OpenCL] Emit enqueued block as kernel
In OpenCL the kernel function and non-kernel function has different calling conventions.
For certain targets they have different argument ABIs. Also kernels have special function
attributes and metadata for runtime to launch them.
The blocks passed to enqueue_kernel is supposed to be executed as kernels. As such,
the block invoke function should be emitted as kernel with proper calling convention and
argument ABI.
This patch emits enqueued block as kernel. If a block is both called directly and passed
to enqueue_kernel, separate functions will be generated.
Differential Revision: https://reviews.llvm.org/D38134
llvm-svn: 315804
Diffstat (limited to 'clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl')
-rw-r--r-- | clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl new file mode 100644 index 00000000000..92f2306f26d --- /dev/null +++ b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl @@ -0,0 +1,36 @@ +// RUN: %clang_cc1 %s -cl-std=CL2.0 -O0 -emit-llvm -o - -triple amdgcn | FileCheck %s --check-prefix=CHECK + +typedef struct {int a;} ndrange_t; + +// CHECK-LABEL: define amdgpu_kernel void @test +kernel void test(global char *a, char b, global long *c, long d) { + queue_t default_queue; + unsigned flags = 0; + ndrange_t ndrange; + + enqueue_kernel(default_queue, flags, ndrange, + ^(void) { + a[0] = b; + }); + + enqueue_kernel(default_queue, flags, ndrange, + ^(void) { + a[0] = b; + c[0] = d; + }); +} + +// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>) +// CHECK-SAME: #[[ATTR:[0-9]+]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}} +// CHECK: entry: +// CHECK: %1 = alloca <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, align 8 +// CHECK: store <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %0, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1, align 8 +// CHECK: %2 = addrspacecast <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1 to i8 addrspace(4)* +// CHECK: call void @__test_block_invoke(i8 addrspace(4)* %2) +// CHECK: ret void +// CHECK:} + +// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>) +// 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" } |