StarPU Handbook
|
Macros | |
#define | STARPU_USE_CUDA |
#define | STARPU_HAVE_LIBNVIDIA_ML |
#define | STARPU_MAXCUDADEVS |
#define | STARPU_CUBLAS_REPORT_ERROR(status) |
#define | STARPU_CUDA_REPORT_ERROR(status) |
Functions | |
void | starpu_cublas_report_error (const char *func, const char *file, int line, int status) |
void | starpu_cuda_report_error (const char *func, const char *file, int line, cudaError_t status) |
cudaStream_t | starpu_cuda_get_local_stream (void) |
const struct cudaDeviceProp * | starpu_cuda_get_device_properties (unsigned workerid) |
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) |
int | starpu_cuda_copy2d_async_sync (void *src_ptr, unsigned src_node, void *dst_ptr, unsigned dst_node, size_t blocksize, size_t numblocks, size_t ld_src, size_t ld_dst, cudaStream_t stream, enum cudaMemcpyKind kind) |
int | starpu_cuda_copy3d_async_sync (void *src_ptr, unsigned src_node, void *dst_ptr, unsigned dst_node, size_t blocksize, size_t numblocks_1, size_t ld1_src, size_t ld1_dst, size_t numblocks_2, size_t ld2_src, size_t ld2_dst, cudaStream_t stream, enum cudaMemcpyKind kind) |
void | starpu_cuda_set_device (unsigned devid) |
void | starpu_cusparse_init (void) |
void | starpu_cusparse_shutdown (void) |
cusparseHandle_t | starpu_cusparse_get_local_handle (void) |
void | starpu_cublas_init (void) |
void | starpu_cublas_set_stream (void) |
void | starpu_cublas_shutdown (void) |
cublasHandle_t | starpu_cublas_get_local_handle (void) |
#define STARPU_USE_CUDA |
Defined when StarPU has been installed with CUDA support. It should be used in your code to detect the availability of CUDA.
#define STARPU_HAVE_LIBNVIDIA_ML |
Defined when StarPU has been installed with NVidia-ML support. It should be used in your code to detect the availability of NVML-related functions.
#define STARPU_MAXCUDADEVS |
Define the maximum number of CUDA devices that are supported by StarPU.
#define STARPU_CUBLAS_REPORT_ERROR | ( | status | ) |
Call starpu_cublas_report_error(), passing the current function, file and line position.
#define STARPU_CUDA_REPORT_ERROR | ( | status | ) |
Call starpu_cuda_report_error(), passing the current function, file and line position.
void starpu_cusparse_init | ( | void | ) |
Initialize CUSPARSE on every CUDA device controlled by StarPU. This call blocks until CUSPARSE has been properly initialized on every device.
void starpu_cublas_init | ( | void | ) |
Initialize 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.
cublasHandle_t starpu_cublas_get_local_handle | ( | void | ) |
Return the CUBLAS handle to be used to queue CUBLAS kernels. It is properly initialized and configured for multistream by starpu_cublas_init().
void starpu_cublas_report_error | ( | const char * | func, |
const char * | file, | ||
int | line, | ||
int | status | ||
) |
Report a CUBLAS error.
void starpu_cuda_report_error | ( | const char * | func, |
const char * | file, | ||
int | line, | ||
cudaError_t | status | ||
) |
Report a CUDA error.
cudaStream_t starpu_cuda_get_local_stream | ( | void | ) |
Return 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 cudaDeviceSynchronize()
is allowed, but will reduce the likelihood of having all transfers overlapped.
const struct cudaDeviceProp* starpu_cuda_get_device_properties | ( | unsigned | workerid | ) |
Return a pointer to device properties for worker workerid
(assumed to be a CUDA worker).
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.
int starpu_cuda_copy2d_async_sync | ( | void * | src_ptr, |
unsigned | src_node, | ||
void * | dst_ptr, | ||
unsigned | dst_node, | ||
size_t | blocksize, | ||
size_t | numblocks, | ||
size_t | ld_src, | ||
size_t | ld_dst, | ||
cudaStream_t | stream, | ||
enum cudaMemcpyKind | kind | ||
) |
Copy numblocks
blocks of blocksize
bytes from the pointer src_ptr
on src_node
to the pointer dst_ptr
on dst_node
.
The blocks start at addresses which are ld_src (resp. ld_dst) bytes apart in the source (resp. destination) interface.
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.
int starpu_cuda_copy3d_async_sync | ( | void * | src_ptr, |
unsigned | src_node, | ||
void * | dst_ptr, | ||
unsigned | dst_node, | ||
size_t | blocksize, | ||
size_t | numblocks_1, | ||
size_t | ld1_src, | ||
size_t | ld1_dst, | ||
size_t | numblocks_2, | ||
size_t | ld2_src, | ||
size_t | ld2_dst, | ||
cudaStream_t | stream, | ||
enum cudaMemcpyKind | kind | ||
) |
Copy numblocks_1
* numblocks_2
blocks of blocksize
bytes from the pointer src_ptr
on src_node
to the pointer dst_ptr
on dst_node
.
The blocks are grouped by numblocks_1
blocks whose start addresses are ld1_src (resp. ld1_dst) bytes apart in the source (resp. destination) interface.
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.
void starpu_cuda_set_device | ( | unsigned | devid | ) |
Call cudaSetDevice(
or devid
)cudaGLSetGLDevice(
, according to whether devid
)devid
is among the field starpu_conf::cuda_opengl_interoperability.
void starpu_cublas_set_stream | ( | void | ) |
Set the proper CUBLAS stream for CUBLAS v1. This must be called from the CUDA codelet before calling CUBLAS v1 kernels, so that they are queued on the proper CUDA stream. When using one thread per CUDA worker, this function does not do anything since the CUBLAS stream does not change, and is set once by starpu_cublas_init().
void starpu_cublas_shutdown | ( | void | ) |
Synchronously deinitialize the CUBLAS library on every CUDA device.
void starpu_cusparse_shutdown | ( | void | ) |
Synchronously deinitialize the CUSPARSE library on every CUDA device.
cusparseHandle_t starpu_cusparse_get_local_handle | ( | void | ) |
Return the CUSPARSE handle to be used to queue CUSPARSE kernels. It is properly initialized and configured for multistream by starpu_cusparse_init().