File: kernel-args.cu

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-16
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 1,496,368 kB
  • sloc: cpp: 5,593,980; ansic: 986,873; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,547; xml: 953; cs: 573; fortran: 567
file content (40 lines) | stat: -rw-r--r-- 1,664 bytes parent folder | download | duplicates (3)
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
// 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* noundef 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* noundef 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* noundef 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* noundef byval(%struct.A) align 8 %x)
  launch((void*)Kernel::templateMemberKernel<A>);
}