![]() |
MAGMA 2.9.0
Matrix Algebra for GPU and Multicore Architectures
|
Functions | |
magma_int_t | magma_getdevice_arch () |
Returns CUDA architecture capability for the current device. | |
void | magma_getdevices (magma_device_t *devices, magma_int_t size, magma_int_t *num_dev) |
Fills in devices array with the available devices. | |
void | magma_getdevice (magma_device_t *device) |
Get the current device. | |
void | magma_setdevice (magma_device_t device) |
Set the current device. | |
magma_int_t | magma_getdevice_multiprocessor_count () |
Returns the multiprocessor count for the current device. | |
magma_int_t | magma_getdevice_num_threads_block () |
Returns the maximum number of threads per block for the current device. | |
magma_int_t | magma_getdevice_num_threads_multiprocessor () |
Returns the maximum number of threads per multiprocessor for the current device. | |
size_t | magma_getdevice_shmem_block () |
Returns the maximum shared memory per block (in bytes) for the current device. | |
size_t | magma_getdevice_shmem_block_optin () |
Returns the maximum shared memory per block (in bytes) with a special opt-in for the current device. | |
size_t | magma_getdevice_shmem_multiprocessor () |
Returns the maximum shared memory multiprocessor (in bytes) for the current device. | |
void | magma_device_sync () |
magma_int_t magma_getdevice_arch | ( | ) |
Returns CUDA architecture capability for the current device.
This requires magma_init() to be called first to cache the information. Version is an integer xyz, where x is major, y is minor, and z is micro, the same as CUDA_ARCH. Thus for architecture 1.3.0 it returns 130.
void magma_getdevices | ( | magma_device_t * | devices, |
magma_int_t | size, | ||
magma_int_t * | num_dev ) |
Fills in devices array with the available devices.
(This makes much more sense in OpenCL than in CUDA.)
[out] | devices | Array of dimension (size). On output, devices[0, ..., num_dev-1] contain device IDs. Entries >= num_dev are not touched. |
[in] | size | Dimension of the array devices. |
[out] | num_dev | Number of devices, limited to size. |
void magma_getdevice | ( | magma_device_t * | device | ) |
Get the current device.
[out] | device | On output, device ID of the current device. Each thread has its own current device. |
void magma_setdevice | ( | magma_device_t | device | ) |
Set the current device.
[in] | device | Device ID to set as the current device. Each thread has its own current device. |
magma_int_t magma_getdevice_multiprocessor_count | ( | ) |
Returns the multiprocessor count for the current device.
This requires magma_init() to be called first to cache the information.
magma_int_t magma_getdevice_num_threads_block | ( | ) |
Returns the maximum number of threads per block for the current device.
This requires magma_init() to be called first to cache the information.
magma_int_t magma_getdevice_num_threads_multiprocessor | ( | ) |
Returns the maximum number of threads per multiprocessor for the current device.
This requires magma_init() to be called first to cache the information.
size_t magma_getdevice_shmem_block | ( | ) |
Returns the maximum shared memory per block (in bytes) for the current device.
This requires magma_init() to be called first to cache the information.
size_t magma_getdevice_shmem_block_optin | ( | ) |
Returns the maximum shared memory per block (in bytes) with a special opt-in for the current device.
This requires magma_init() to be called first to cache the information.
size_t magma_getdevice_shmem_multiprocessor | ( | ) |
Returns the maximum shared memory multiprocessor (in bytes) for the current device.
This requires magma_init() to be called first to cache the information.
void magma_device_sync | ( | ) |