fd739804e0
For a default visibility external linkage definition, dso_local is set for ELF
-fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar
to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences.
To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition,
which sets dso_local for default visibility external linkage definitions.
To make this flip smooth and enable future (dso_local as definition default),
this patch replaces (function) `define ` with `define{{.*}} `,
(variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
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>);
|
|
}
|