75 static int BlockGridCalculate(CeedInt num_elem, int blocks_per_sm, int max_threads_per_block, int m…  in BlockGridCalculate()  argument
77   const int threads_per_sm   = blocks_per_sm * max_threads_per_block;  in BlockGridCalculate()
82   for (int i = 2; i <= CeedIntMin(max_threads_per_block / threads_per_elem, num_elem); i++) {  in BlockGridCalculate()
205   int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorApplyAddCore_Cuda_gen()  local
208 …CeedCallCuda(ceed, cuOccupancyMaxPotentialBlockSize(&min_grid_size, &max_threads_per_block, data->…  in CeedOperatorApplyAddCore_Cuda_gen()
212 …culate(num_elem, min_grid_size / cuda_data->device_prop.multiProcessorCount, max_threads_per_block,  in CeedOperatorApplyAddCore_Cuda_gen()
460     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()  local
463 …CeedCallCuda(ceed, cuOccupancyMaxPotentialBlockSize(&min_grid_size, &max_threads_per_block, data->…  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()
467 …culate(num_elem, min_grid_size / cuda_data->device_prop.multiProcessorCount, max_threads_per_block,  in CeedOperatorLinearAssembleQFunctionCore_Cuda_gen()
636     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda_gen()  local
638 …CeedCallCuda(ceed, cuOccupancyMaxPotentialBlockSize(&min_grid_size, &max_threads_per_block, data->…  in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda_gen()
801     int   max_threads_per_block, min_grid_size, grid;  in CeedOperatorAssembleSingleAtPoints_Cuda_gen()  local
803 …CeedCallCuda(ceed, cuOccupancyMaxPotentialBlockSize(&min_grid_size, &max_threads_per_block, data->…  in CeedOperatorAssembleSingleAtPoints_Cuda_gen()