File: kernel-amdgcn.cu

package info (click to toggle)
llvm-toolchain-9 1%3A9.0.1-16.1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 882,388 kB
  • sloc: cpp: 4,167,636; ansic: 714,256; asm: 457,610; python: 155,927; objc: 65,094; sh: 42,856; lisp: 26,908; perl: 7,786; pascal: 7,722; makefile: 6,881; ml: 5,581; awk: 3,648; cs: 2,027; xml: 888; javascript: 381; ruby: 156
file content (41 lines) | stat: -rw-r--r-- 982 bytes parent folder | download | duplicates (6)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm %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_
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;
}