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 `{{.*}} `.
43 lines
1.1 KiB
Plaintext
43 lines
1.1 KiB
Plaintext
// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm -x hip %s -o - | FileCheck %s
|
|
#include "Inputs/cuda.h"
|
|
|
|
// CHECK: define{{.*}} amdgpu_kernel void @_ZN1A6kernelEv
|
|
class A {
|
|
public:
|
|
static __global__ void kernel(){}
|
|
};
|
|
|
|
// CHECK: define{{.*}} void @_Z10non_kernelv
|
|
__device__ void non_kernel(){}
|
|
|
|
// CHECK: define{{.*}} amdgpu_kernel void @_Z6kerneli
|
|
__global__ void kernel(int x) {
|
|
non_kernel();
|
|
}
|
|
|
|
// CHECK: define{{.*}} amdgpu_kernel void @_Z11EmptyKernelIvEvv
|
|
template <typename T>
|
|
__global__ void EmptyKernel(void) {}
|
|
|
|
struct Dummy {
|
|
/// Type definition of the EmptyKernel kernel entry point
|
|
typedef void (*EmptyKernelPtr)();
|
|
EmptyKernelPtr Empty() { return EmptyKernel<void>; }
|
|
};
|
|
|
|
// CHECK: define{{.*}} amdgpu_kernel void @_Z15template_kernelI1AEvT_{{.*}} #[[ATTR:[0-9][0-9]*]]
|
|
template<class T>
|
|
__global__ void template_kernel(T x) {}
|
|
|
|
void launch(void *f);
|
|
|
|
int main() {
|
|
Dummy D;
|
|
launch((void*)A::kernel);
|
|
launch((void*)kernel);
|
|
launch((void*)template_kernel<A>);
|
|
launch((void*)D.Empty());
|
|
return 0;
|
|
}
|
|
// CHECK: attributes #[[ATTR]] = {{.*}}"amdgpu-flat-work-group-size"="1,256"
|