130         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
134 …d_Hip(ceed, apply_add ? data->InterpTransposeAdd : data->InterpTranspose, NULL, grid, thread_1d, 1,  in CeedBasisApplyTensorCore_Hip_shared()
137 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Interp, NULL, grid, thread_1d, 1, elems_per…  in CeedBasisApplyTensorCore_Hip_shared()
142 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
146 …ared_Hip(ceed, apply_add ? data->InterpTransposeAdd : data->InterpTranspose, NULL, grid, thread_1d,  in CeedBasisApplyTensorCore_Hip_shared()
149 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, e…  in CeedBasisApplyTensorCore_Hip_shared()
153 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
157 …ared_Hip(ceed, apply_add ? data->InterpTransposeAdd : data->InterpTranspose, NULL, grid, thread_1d,  in CeedBasisApplyTensorCore_Hip_shared()
160 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, e…  in CeedBasisApplyTensorCore_Hip_shared()
182         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
186 …hared_Hip(ceed, apply_add ? data->GradTransposeAdd : data->GradTranspose, NULL, grid, thread_1d, 1,  in CeedBasisApplyTensorCore_Hip_shared()
189 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Grad, NULL, grid, thread_1d, 1, elems_per_b…  in CeedBasisApplyTensorCore_Hip_shared()
194 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
198 …Hip(ceed, apply_add ? data->GradTransposeAdd : data->GradTranspose, NULL, grid, thread_1d, thread_…  in CeedBasisApplyTensorCore_Hip_shared()
201 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Grad, NULL, grid, thread_1d, thread_1d, ele…  in CeedBasisApplyTensorCore_Hip_shared()
205 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyTensorCore_Hip_shared()  local
209 …Hip(ceed, apply_add ? data->GradTransposeAdd : data->GradTranspose, NULL, grid, thread_1d, thread_…  in CeedBasisApplyTensorCore_Hip_shared()
212 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Grad, NULL, grid, thread_1d, thread_1d, ele…  in CeedBasisApplyTensorCore_Hip_shared()
393         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
397 …Hip(ceed, apply_add ? data->InterpTransposeAddAtPoints : data->InterpTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
400 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->InterpAtPoints, NULL, grid, thread_1d, 1, e…  in CeedBasisApplyAtPointsCore_Hip_shared()
405 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
409 …Hip(ceed, apply_add ? data->InterpTransposeAddAtPoints : data->InterpTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
412 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->InterpAtPoints, NULL, grid, thread_1d, thre…  in CeedBasisApplyAtPointsCore_Hip_shared()
417 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
421 …Hip(ceed, apply_add ? data->InterpTransposeAddAtPoints : data->InterpTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
424 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->InterpAtPoints, NULL, grid, thread_1d, thre…  in CeedBasisApplyAtPointsCore_Hip_shared()
441         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
445 …red_Hip(ceed, apply_add ? data->GradTransposeAddAtPoints : data->GradTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
448 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->GradAtPoints, NULL, grid, thread_1d, 1, ele…  in CeedBasisApplyAtPointsCore_Hip_shared()
453 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
457 …red_Hip(ceed, apply_add ? data->GradTransposeAddAtPoints : data->GradTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
460 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->GradAtPoints, NULL, grid, thread_1d, thread…  in CeedBasisApplyAtPointsCore_Hip_shared()
465 …     CeedInt       grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyAtPointsCore_Hip_shared()  local
469 …red_Hip(ceed, apply_add ? data->GradTransposeAddAtPoints : data->GradTransposeAtPoints, NULL, grid,  in CeedBasisApplyAtPointsCore_Hip_shared()
472 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->GradAtPoints, NULL, grid, thread_1d, thread…  in CeedBasisApplyAtPointsCore_Hip_shared()
549         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyNonTensorCore_Hip_shared()  local
553 …ared_Hip(ceed, apply_add ? data->InterpTransposeAdd : data->InterpTranspose, NULL, grid, thread, 1,  in CeedBasisApplyNonTensorCore_Hip_shared()
556 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Interp, NULL, grid, thread, 1, elems_per_bl…  in CeedBasisApplyNonTensorCore_Hip_shared()
572         CeedInt grid            = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedBasisApplyNonTensorCore_Hip_shared()  local
576 …imShared_Hip(ceed, apply_add ? data->GradTransposeAdd : data->GradTranspose, NULL, grid, thread, 1,  in CeedBasisApplyNonTensorCore_Hip_shared()
579 …CeedCallBackend(CeedRunKernelDimShared_Hip(ceed, data->Grad, NULL, grid, thread, 1, elems_per_bloc…  in CeedBasisApplyNonTensorCore_Hip_shared()