76                               int *grid) {  in BlockGridCalculate()  argument
95   *grid    = CeedDivUpInt(num_elem, elems_per_block);  in BlockGridCalculate()
205   int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorApplyAddCore_Cuda_gen()  local
213 …          cuda_data->device_prop.maxThreadsDim[2], cuda_data->device_prop.warpSize, block, &grid));  in CeedOperatorApplyAddCore_Cuda_gen()
217     grid     = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedOperatorApplyAddCore_Cuda_gen()
222 …CeedCallBackend(CeedTryRunKernelDimShared_Cuda(ceed, data->op, stream, grid, block[0], block[1], b…  in CeedOperatorApplyAddCore_Cuda_gen()
460     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()  local
468 …          cuda_data->device_prop.maxThreadsDim[2], cuda_data->device_prop.warpSize, block, &grid));  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()
472       grid     = num_elem / elems_per_block + (num_elem % elems_per_block > 0);  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()
477 …CeedCallBackend(CeedTryRunKernelDimShared_Cuda(ceed, data->assemble_qfunction, NULL, grid, block[0…  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()
636     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda_gen()  local
642 …          cuda_data->device_prop.maxThreadsDim[2], cuda_data->device_prop.warpSize, block, &grid));  in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda_gen()
645 …CeedCallBackend(CeedTryRunKernelDimShared_Cuda(ceed, data->assemble_diagonal, NULL, grid, block[0]…  in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda_gen()
801     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorAssembleSingleAtPoints_Cuda_gen()  local
807 …          cuda_data->device_prop.maxThreadsDim[2], cuda_data->device_prop.warpSize, block, &grid));  in CeedOperatorAssembleSingleAtPoints_Cuda_gen()
810 …CeedCallBackend(CeedTryRunKernelDimShared_Cuda(ceed, data->assemble_full, NULL, grid, block[0], bl…  in CeedOperatorAssembleSingleAtPoints_Cuda_gen()