33   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
34   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
41       Interp1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
45       InterpTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
50       InterpTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
102   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
103   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
110       InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
114 …  InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
119 …  InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
171   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
172   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
179       InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
183 …  InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
188 …  InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_V);  in __launch_bounds__()
244   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
245   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
254       Grad1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
258       GradTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
264 …adTensorCollocated3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
265 …   else GradTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
329   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
330   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
339       GradTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
344 …GradTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V…  in __launch_bounds__()
349 …seTensorCollocated3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
350 …else GradTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G…  in __launch_bounds__()
414   __shared__ CeedScalar s_B[BASIS_P_1D * BASIS_Q_1D];  in __launch_bounds__()  local
415   LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B);  in __launch_bounds__()
424       GradTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
429 …GradTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V…  in __launch_bounds__()
434 …seTensorCollocated3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G, r_V);  in __launch_bounds__()
435 …else GradTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, s_G…  in __launch_bounds__()