This reverts the following commits: 37ca7a795b277c20c02a218bf44052278c03344b 9aa6c72b92b6c89cc6d23b693257df9af7de2d15 705387c5074bcca36d626882462ebbc2bcc3bed4 8ca4b3ef19fe82d7ad6a6e1515317dcc01b41515 80dba72a669b5416e97a42fd2c2a7bc5a6d3f44a
41 lines
1.6 KiB
Plaintext
41 lines
1.6 KiB
Plaintext
// RUN: %clang_cc1 -x hip -triple amdgcn-amd-amdhsa -fcuda-is-device \
|
|
// RUN: -emit-llvm %s -o - | FileCheck -check-prefix=AMDGCN %s
|
|
// RUN: %clang_cc1 -x cuda -triple nvptx64-nvidia-cuda- -fcuda-is-device \
|
|
// RUN: -emit-llvm %s -o - | FileCheck -check-prefix=NVPTX %s
|
|
#include "Inputs/cuda.h"
|
|
|
|
struct A {
|
|
int a[32];
|
|
float *p;
|
|
};
|
|
|
|
// AMDGCN: define{{.*}} amdgpu_kernel void @_Z6kernel1A(%struct.A addrspace(4)* byref(%struct.A) align 8 %{{.+}})
|
|
// NVPTX: define{{.*}} void @_Z6kernel1A(%struct.A* byval(%struct.A) align 8 %x)
|
|
__global__ void kernel(A x) {
|
|
}
|
|
|
|
class Kernel {
|
|
public:
|
|
// AMDGCN: define{{.*}} amdgpu_kernel void @_ZN6Kernel12memberKernelE1A(%struct.A addrspace(4)* byref(%struct.A) align 8 %{{.+}})
|
|
// NVPTX: define{{.*}} void @_ZN6Kernel12memberKernelE1A(%struct.A* byval(%struct.A) align 8 %x)
|
|
static __global__ void memberKernel(A x){}
|
|
template<typename T> static __global__ void templateMemberKernel(T x) {}
|
|
};
|
|
|
|
|
|
template <typename T>
|
|
__global__ void templateKernel(T x) {}
|
|
|
|
void launch(void*);
|
|
|
|
void test() {
|
|
Kernel K;
|
|
// AMDGCN: define{{.*}} amdgpu_kernel void @_Z14templateKernelI1AEvT_(%struct.A addrspace(4)* byref(%struct.A) align 8 %{{.+}}
|
|
// NVPTX: define{{.*}} void @_Z14templateKernelI1AEvT_(%struct.A* byval(%struct.A) align 8 %x)
|
|
launch((void*)templateKernel<A>);
|
|
|
|
// AMDGCN: define{{.*}} amdgpu_kernel void @_ZN6Kernel20templateMemberKernelI1AEEvT_(%struct.A addrspace(4)* byref(%struct.A) align 8 %{{.+}}
|
|
// NVPTX: define{{.*}} void @_ZN6Kernel20templateMemberKernelI1AEEvT_(%struct.A* byval(%struct.A) align 8 %x)
|
|
launch((void*)Kernel::templateMemberKernel<A>);
|
|
}
|