Searched refs:d_W (Results 1 – 5 of 5) sorted by relevance
| /libCEED/include/ceed/jit-source/sycl/ ! |
| H A D | sycl-shared-basis-tensor.h | 163 …CeedInt num_elem, global const CeedScalar *restrict q_weight_1d, global CeedScalar *restrict d_W) { in Weight() argument 171 …eElementStrided1d(1, BASIS_Q_1D, num_elem, 1, BASIS_NUM_QPTS * num_elem, BASIS_NUM_QPTS, r_W, d_W); in Weight() 175 …eElementStrided2d(1, BASIS_Q_1D, num_elem, 1, BASIS_NUM_QPTS * num_elem, BASIS_NUM_QPTS, r_W, d_W); in Weight() 179 …eElementStrided3d(1, BASIS_Q_1D, num_elem, 1, BASIS_NUM_QPTS * num_elem, BASIS_NUM_QPTS, r_W, d_W); in Weight()
|
| /libCEED/include/ceed/jit-source/cuda/ ! |
| H A D | cuda-shared-basis-nontensor.h | 184 …ht(const CeedInt num_elem, const CeedScalar *__restrict__ q_weight, CeedScalar *__restrict__ d_W) { in Weight() argument 198 WriteElementStrided1d<1, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_W, d_W); in Weight()
|
| H A D | cuda-shared-basis-tensor.h | 479 …const CeedInt num_elem, const CeedScalar *__restrict__ q_weight_1d, CeedScalar *__restrict__ d_W) { in Weight() argument 495 … WriteElementStrided1d<1, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D, r_W, d_W); in Weight() 498 … BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem, BASIS_Q_1D * BASIS_Q_1D, r_W, d_W); in Weight() 502 d_W); in Weight()
|
| /libCEED/include/ceed/jit-source/hip/ ! |
| H A D | hip-shared-basis-nontensor.h | 187 …ht(const CeedInt num_elem, const CeedScalar *__restrict__ q_weight, CeedScalar *__restrict__ d_W) { in __launch_bounds__() 201 WriteElementStrided1d<1, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_W, d_W); in __launch_bounds__()
|
| H A D | hip-shared-basis-tensor.h | 487 …const CeedInt num_elem, const CeedScalar *__restrict__ q_weight_1d, CeedScalar *__restrict__ d_W) { in __launch_bounds__() 502 … WriteElementStrided1d<1, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D, r_W, d_W); in __launch_bounds__() 505 … BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem, BASIS_Q_1D * BASIS_Q_1D, r_W, d_W); in __launch_bounds__() 509 d_W); in __launch_bounds__()
|