c62214da3d
Instead of calling CUDA runtime to arrange function arguments, the new API constructs arguments in a local array and the kernels are launched with __cudaLaunchKernel(). The old API has been deprecated and is expected to go away in the next CUDA release. Differential Revision: https://reviews.llvm.org/D57488 llvm-svn: 352799
35 lines
1.4 KiB
C
35 lines
1.4 KiB
C
/* 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) {}
|
|
};
|
|
|
|
typedef struct cudaStream *cudaStream_t;
|
|
typedef enum cudaError {} cudaError_t;
|
|
#ifdef __HIP__
|
|
int hipConfigureCall(dim3 gridSize, dim3 blockSize, size_t sharedSize = 0,
|
|
cudaStream_t stream = 0);
|
|
#else
|
|
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*, ...);
|