cuda.h
1.91 KB
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
42
43
/* Minimal declarations for CUDA support. Testing purposes only. */
#include <stddef.h>
#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) {}
};
#ifdef __HIP__
typedef struct hipStream *hipStream_t;
typedef enum hipError {} hipError_t;
int hipConfigureCall(dim3 gridSize, dim3 blockSize, size_t sharedSize = 0,
hipStream_t stream = 0);
extern "C" hipError_t __hipPushCallConfiguration(dim3 gridSize, dim3 blockSize,
size_t sharedSize = 0,
hipStream_t stream = 0);
extern "C" hipError_t hipLaunchKernel(const void *func, dim3 gridDim,
dim3 blockDim, void **args,
size_t sharedMem,
hipStream_t stream);
#else
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);
#endif
extern "C" __device__ int printf(const char*, ...);