56       CeedInt thread_1d = CeedIntMax(Q_1d, P_1d);  in CeedBasisApplyTensorCore_Cuda_shared()
62 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyTensorCore_Cuda_shared()
75 …      CeedInt elems_per_block = CeedIntMax(thread_1d < 7 ? opt_elems[thread_1d] / num_comp : 1, 1);  in CeedBasisApplyTensorCore_Cuda_shared()
106       CeedInt     thread_1d = CeedIntMax(Q_1d, P_1d);  in CeedBasisApplyTensorCore_Cuda_shared()
116 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyTensorCore_Cuda_shared()
129 …      CeedInt elems_per_block = CeedIntMax(thread_1d < 7 ? opt_elems[thread_1d] / num_comp : 1, 1);  in CeedBasisApplyTensorCore_Cuda_shared()
235   for (CeedInt i = 1; i < num_elem; i++) max_num_points = CeedIntMax(max_num_points, num_points[i]);  in CeedBasisApplyAtPointsCore_Cuda_shared()
293 …CeedIntMax(Q_1d, P_1d), "BASIS_DIM", dim, "BASIS_NUM_COMP", num_comp, "BASIS_NUM_NODES", CeedIntPo…  in CeedBasisApplyAtPointsCore_Cuda_shared()
320       CeedInt thread_1d = CeedIntMax(Q_1d, P_1d);  in CeedBasisApplyAtPointsCore_Cuda_shared()
326 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyAtPointsCore_Cuda_shared()
340 …      CeedInt elems_per_block = CeedIntMax(thread_1d < 7 ? opt_elems[thread_1d] / num_comp : 1, 1);  in CeedBasisApplyAtPointsCore_Cuda_shared()
370       CeedInt thread_1d = CeedIntMax(Q_1d, P_1d);  in CeedBasisApplyAtPointsCore_Cuda_shared()
376 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyAtPointsCore_Cuda_shared()
389 …      CeedInt elems_per_block = CeedIntMax(thread_1d < 7 ? opt_elems[thread_1d] / num_comp : 1, 1);  in CeedBasisApplyAtPointsCore_Cuda_shared()
479       CeedInt thread = CeedIntMax(Q, P);  in CeedBasisApplyNonTensorCore_Cuda_shared()
485 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyNonTensorCore_Cuda_shared()
503       CeedInt thread = CeedIntMax(Q, P);  in CeedBasisApplyNonTensorCore_Cuda_shared()
509 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyNonTensorCore_Cuda_shared()
527       CeedInt thread = CeedIntMax(Q, P);  in CeedBasisApplyNonTensorCore_Cuda_shared()
533 …CeedInt elems_per_block = CeedIntMin(ceed_Cuda->device_prop.maxThreadsDim[2], CeedIntMax(512 / thr…  in CeedBasisApplyNonTensorCore_Cuda_shared()
635 …CeedIntMax(Q_1d, P_1d), "BASIS_DIM", dim, "BASIS_NUM_COMP", num_comp, "BASIS_NUM_NODES", CeedIntPo…  in CeedBasisCreateTensorH1_Cuda_shared()
676 …if (((size_t)num_nodes * (size_t)num_qpts * (size_t)dim + (size_t)CeedIntMax(num_nodes, num_qpts))…  in CeedBasisCreateH1_Cuda_shared()
711 …                   CeedIntMax(num_qpts, num_nodes), "BASIS_DIM", dim, "BASIS_NUM_COMP", num_comp));  in CeedBasisCreateH1_Cuda_shared()