aboutsummaryrefslogtreecommitdiff
path: root/test/SemaCUDA/Inputs/cuda.h
blob: 2600bfa9c470b6ec2a156c3bcc91c143a789a613 (plain)
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
/* Minimal declarations for CUDA support.  Testing purposes only. */

#include <stddef.h>

// Make this file work with nvcc, for testing compatibility.

#ifndef __NVCC__
#define __constant__ __attribute__((constant))
#define __device__ __attribute__((device))
#define __global__ __attribute__((global))
#define __host__ __attribute__((host))
#define __shared__ __attribute__((shared))
#define __launch_bounds__(...) __attribute__((launch_bounds(__VA_ARGS__)))

struct dim3 {
  unsigned x, y, z;
  __host__ __device__ dim3(unsigned x, unsigned y = 1, unsigned z = 1) : x(x), y(y), z(z) {}
};

typedef struct cudaStream *cudaStream_t;
typedef enum cudaError {} cudaError_t;

extern "C" int cudaConfigureCall(dim3 gridSize, dim3 blockSize,
                                 size_t sharedSize = 0,
                                 cudaStream_t stream = 0);
extern "C" int __cudaPushCallConfiguration(dim3 gridSize, dim3 blockSize,
                                           size_t sharedSize = 0,
                                           cudaStream_t stream = 0);
extern "C" cudaError_t cudaLaunchKernel(const void *func, dim3 gridDim,
                                        dim3 blockDim, void **args,
                                        size_t sharedMem, cudaStream_t stream);

// Host- and device-side placement new overloads.
void *operator new(__SIZE_TYPE__, void *p) { return p; }
void *operator new[](__SIZE_TYPE__, void *p) { return p; }
__device__ void *operator new(__SIZE_TYPE__, void *p) { return p; }
__device__ void *operator new[](__SIZE_TYPE__, void *p) { return p; }

#endif // !__NVCC__