|
| template<typename ValueT > |
| static __host__ hipError_t | CsrMV (void *d_temp_storage, size_t &temp_storage_bytes, ValueT *d_values, int *d_row_offsets, int *d_column_indices, ValueT *d_vector_x, ValueT *d_vector_y, int num_rows, int num_cols, int num_nonzeros, hipStream_t stream=0, bool debug_synchronous=false) |
| |
|
template<typename ValueT > |
| static __global__ void | CsrMVKernel (SpmvParams< ValueT, int > spmv_params) |
| |
| template<typename ValueT > |
| static __host__ hipError_t | CsrMV (void *d_temp_storage, size_t &temp_storage_bytes, ValueT *d_values, int *d_row_offsets, int *d_column_indices, ValueT *d_vector_x, ValueT *d_vector_y, int num_rows, int num_cols, int num_nonzeros, hipStream_t stream=0, bool debug_synchronous=false) |
| |
|
|
static constexpr uint32_t | CsrMVKernel_MaxThreads = 256 |
| |
◆ CsrMV() [1/2]
template<typename ValueT >
| static __host__ hipError_t hipcub::DeviceSpmv::CsrMV |
( |
void * |
d_temp_storage, |
|
|
size_t & |
temp_storage_bytes, |
|
|
ValueT * |
d_values, |
|
|
int * |
d_row_offsets, |
|
|
int * |
d_column_indices, |
|
|
ValueT * |
d_vector_x, |
|
|
ValueT * |
d_vector_y, |
|
|
int |
num_rows, |
|
|
int |
num_cols, |
|
|
int |
num_nonzeros, |
|
|
hipStream_t |
stream = 0, |
|
|
bool |
debug_synchronous = false |
|
) |
| |
|
inlinestatic |
- Parameters
-
| [in] | d_temp_storage | Device-accessible allocation of temporary storage. When NULL, the required allocation size is written to temp_storage_bytes and no work is done. |
| [in,out] | temp_storage_bytes | Reference to size in bytes of d_temp_storage allocation |
| [in] | d_values | Pointer to the array of num_nonzeros values of the corresponding nonzero elements of matrix A. |
| [in] | d_row_offsets | Pointer to the array of m + 1 offsets demarcating the start of every row in d_column_indices and d_values (with the final entry being equal to num_nonzeros) |
| [in] | d_column_indices | Pointer to the array of num_nonzeros column-indices of the corresponding nonzero elements of matrix A. (Indices are zero-valued.) |
| [in] | d_vector_x | Pointer to the array of num_cols values corresponding to the dense input vector x |
| [out] | d_vector_y | Pointer to the array of num_rows values corresponding to the dense output vector y |
| [in] | num_rows | number of rows of matrix A. |
| [in] | num_cols | number of columns of matrix A. |
| [in] | num_nonzeros | number of nonzero elements of matrix A. |
| [in] | stream | [optional] hip stream to launch kernels within. Default is stream0. |
| [in] | debug_synchronous | [optional] Whether or not to synchronize the stream after every kernel launch to check for errors. May cause significant slowdown. Default is false. |
◆ CsrMV() [2/2]
template<typename ValueT >
| static __host__ hipError_t hipcub::DeviceSpmv::CsrMV |
( |
void * |
d_temp_storage, |
|
|
size_t & |
temp_storage_bytes, |
|
|
ValueT * |
d_values, |
|
|
int * |
d_row_offsets, |
|
|
int * |
d_column_indices, |
|
|
ValueT * |
d_vector_x, |
|
|
ValueT * |
d_vector_y, |
|
|
int |
num_rows, |
|
|
int |
num_cols, |
|
|
int |
num_nonzeros, |
|
|
hipStream_t |
stream = 0, |
|
|
bool |
debug_synchronous = false |
|
) |
| |
|
inlinestatic |
- Parameters
-
| [in] | d_temp_storage | Device-accessible allocation of temporary storage. When NULL, the required allocation size is written to temp_storage_bytes and no work is done. |
| [in,out] | temp_storage_bytes | Reference to size in bytes of d_temp_storage allocation |
| [in] | d_values | Pointer to the array of num_nonzeros values of the corresponding nonzero elements of matrix A. |
| [in] | d_row_offsets | Pointer to the array of m + 1 offsets demarcating the start of every row in d_column_indices and d_values (with the final entry being equal to num_nonzeros) |
| [in] | d_column_indices | Pointer to the array of num_nonzeros column-indices of the corresponding nonzero elements of matrix A. (Indices are zero-valued.) |
| [in] | d_vector_x | Pointer to the array of num_cols values corresponding to the dense input vector x |
| [out] | d_vector_y | Pointer to the array of num_rows values corresponding to the dense output vector y |
| [in] | num_rows | number of rows of matrix A. |
| [in] | num_cols | number of columns of matrix A. |
| [in] | num_nonzeros | number of nonzero elements of matrix A. |
| [in] | stream | [optional] hip stream to launch kernels within. Default is stream0. |
| [in] | debug_synchronous | [optional] Whether or not to synchronize the stream after every kernel launch to check for errors. May cause significant slowdown. Default is false. |
The documentation for this class was generated from the following file:
- /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-hipcub/checkouts/docs-5.5.0/hipcub/include/hipcub/backend/cub/device/device_spmv.hpp