StarPU Handbook
CUDA Extensions




cudaStream_t starpu_cuda_get_local_stream (void)
const struct cudaDeviceProp * starpu_cuda_get_device_properties (unsigned workerid)
void starpu_cuda_report_error (const char *func, const char *file, int line, cudaError_t status)
int starpu_cuda_copy_async_sync (void *src_ptr, unsigned src_node, void *dst_ptr, unsigned dst_node, size_t ssize, cudaStream_t stream, enum cudaMemcpyKind kind)
void starpu_cuda_set_device (unsigned devid)
void starpu_cublas_init (void)
void starpu_cublas_shutdown (void)
void starpu_cublas_report_error (const char *func, const char *file, int line, int status)

Detailed Description

Macro Definition Documentation



This macro is defined when StarPU has been installed with CUDA support. It should be used in your code to detect the availability of CUDA as shown in Full source code for the ’Scaling a Vector’ example.



This macro defines the maximum number of CUDA devices that are supported by StarPU.


#define STARPU_CUDA_REPORT_ERROR (   status)

Calls starpu_cuda_report_error(), passing the current function, file and line position.


#define STARPU_CUBLAS_REPORT_ERROR (   status)

Calls starpu_cublas_report_error(), passing the current function, file and line position.

Function Documentation

◆ starpu_cuda_get_local_stream()

cudaStream_t starpu_cuda_get_local_stream ( void  )

This function gets the current worker’s CUDA stream. StarPU provides a stream for every CUDA device controlled by StarPU. This function is only provided for convenience so that programmers can easily use asynchronous operations within codelets without having to create a stream by hand. Note that the application is not forced to use the stream provided by starpu_cuda_get_local_stream() and may also create its own streams. Synchronizing with cudaThreadSynchronize() is allowed, but will reduce the likelihood of having all transfers overlapped.

◆ starpu_cuda_get_device_properties()

const struct cudaDeviceProp * starpu_cuda_get_device_properties ( unsigned  workerid)

This function returns a pointer to device properties for worker workerid (assumed to be a CUDA worker).

◆ starpu_cuda_report_error()

void starpu_cuda_report_error ( const char *  func,
const char *  file,
int  line,
cudaError_t  status 

Report a CUDA error.

◆ starpu_cuda_copy_async_sync()

int starpu_cuda_copy_async_sync ( void *  src_ptr,
unsigned  src_node,
void *  dst_ptr,
unsigned  dst_node,
size_t  ssize,
cudaStream_t  stream,
enum cudaMemcpyKind  kind 

Copy ssize bytes from the pointer src_ptr on src_node to the pointer dst_ptr on dst_node. The function first tries to copy the data asynchronous (unless stream is NULL). If the asynchronous copy fails or if stream is NULL, it copies the data synchronously. The function returns -EAGAIN if the asynchronous launch was successfull. It returns 0 if the synchronous copy was successful, or fails otherwise.

◆ starpu_cuda_set_device()

void starpu_cuda_set_device ( unsigned  devid)

Calls cudaSetDevice(devid) or cudaGLSetGLDevice(devid), according to whether devid is among the field starpu_conf::cuda_opengl_interoperability.

◆ starpu_cublas_init()

void starpu_cublas_init ( void  )

This function initializes CUBLAS on every CUDA device. The CUBLAS library must be initialized prior to any CUBLAS call. Calling starpu_cublas_init() will initialize CUBLAS on every CUDA device controlled by StarPU. This call blocks until CUBLAS has been properly initialized on every device.

◆ starpu_cublas_shutdown()

void starpu_cublas_shutdown ( void  )

This function synchronously deinitializes the CUBLAS library on every CUDA device.

◆ starpu_cublas_report_error()

void starpu_cublas_report_error ( const char *  func,
const char *  file,
int  line,
int  status 

Report a cublas error.