112       void *grad_args[] = {(void *)&num_elem, &data->d_interp_1d, &d_grad_1d, &d_u, &d_v};  in CeedBasisApplyTensorCore_Cuda_shared()  local
122                                                       elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
124 …imShared_Cuda(ceed, data->Grad, NULL, grid, thread_1d, 1, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
135 …                                               thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
137 …_Cuda(ceed, data->Grad, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
146 …                                               thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
148 …_Cuda(ceed, data->Grad, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyTensorCore_Cuda_shared()
372 …void *grad_args[] = {(void *)&num_elem, &data->d_chebyshev_interp_1d, &data->d_points_per_elem, &d…  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
382 …                                            thread_1d, 1, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
384 …_Cuda(ceed, data->GradAtPoints, NULL, grid, thread_1d, 1, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
395 …                                    thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
398                                                       grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
407 …                                    thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
410                                                       grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
505       void *grad_args[] = {(void *)&num_elem, &data->d_grad_1d, &d_u, &d_v};  in CeedBasisApplyNonTensorCore_Cuda_shared()  local
515                                                       elems_per_block, shared_mem, grad_args));  in CeedBasisApplyNonTensorCore_Cuda_shared()
517 …elDimShared_Cuda(ceed, data->Grad, NULL, grid, thread, 1, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyNonTensorCore_Cuda_shared()