ceed-cuda-shared-basis.c - OpenGrok cross reference for /libCEED/backends/cuda-shared/ceed-cuda-shared-basis.c

Lines Matching refs:shared_mem
64         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
68                                                       elems_per_block, shared_mem, interp_args));  in CeedBasisApplyTensorCore_Cuda_shared()
70 …ared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, 1, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyTensorCore_Cuda_shared()
77         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
81 …                                             thread_1d, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyTensorCore_Cuda_shared()
83 …elDimShared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyTensorCore_Cuda_shared()
89         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
93 …                                             thread_1d, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyTensorCore_Cuda_shared()
95 …elDimShared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyTensorCore_Cuda_shared()
118         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  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()
131         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
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()
142         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
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()
328         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
332 …                                          thread_1d, 1, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
334 …elDimShared_Cuda(ceed, data->InterpAtPoints, NULL, grid, thread_1d, 1, elems_per_block, shared_mem,  in CeedBasisApplyAtPointsCore_Cuda_shared()
342         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
346 …                                  thread_1d, thread_1d, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
348 …red_Cuda(ceed, data->InterpAtPoints, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyAtPointsCore_Cuda_shared()
354         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
358 …                                  thread_1d, thread_1d, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
360 …red_Cuda(ceed, data->InterpAtPoints, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyAtPointsCore_Cuda_shared()
378         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  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()
391         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
395 …                                    thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
397 …hared_Cuda(ceed, data->GradAtPoints, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyAtPointsCore_Cuda_shared()
403         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
407 …                                    thread_1d, thread_1d, elems_per_block, shared_mem, grad_args));  in CeedBasisApplyAtPointsCore_Cuda_shared()
409 …hared_Cuda(ceed, data->GradAtPoints, NULL, grid, thread_1d, thread_1d, elems_per_block, shared_mem,  in CeedBasisApplyAtPointsCore_Cuda_shared()
487         CeedInt shared_mem      = elems_per_block * thread * sizeof(CeedScalar);  in CeedBasisApplyNonTensorCore_Cuda_shared()  local
491                                                       elems_per_block, shared_mem, interp_args));  in CeedBasisApplyNonTensorCore_Cuda_shared()
493 …mShared_Cuda(ceed, data->Interp, NULL, grid, thread, 1, elems_per_block, shared_mem, interp_args));  in CeedBasisApplyNonTensorCore_Cuda_shared()
511         CeedInt shared_mem      = elems_per_block * thread * sizeof(CeedScalar);  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()