60   CeedScalar *sW = sT + BASIS_P * BASIS_Q;  in __launch_bounds__()
61   sU[0]          = sW + ty * BASIS_NUM_COMP * (BASIS_P + BASIS_Q);  in __launch_bounds__()
65     sV[comp] = sV[comp - 1] + (1 * BASIS_Q);  in __launch_bounds__()
70     read_T_notrans_gm2sm<BASIS_P, BASIS_Q>(tx, dT, sT);  in __launch_bounds__()
77   magma_interp_1d_device<CeedScalar, BASIS_DIM, BASIS_NUM_COMP, BASIS_P, BASIS_Q>(sT, sU, sV, tx);  in __launch_bounds__()
81   write_1d<CeedScalar, BASIS_Q, BASIS_NUM_COMP>(sV, dV, cstrdV, tx);  in __launch_bounds__()
105   CeedScalar *sW = sT + BASIS_Q * BASIS_P;  in __launch_bounds__()
106   sU[0]          = sW + ty * BASIS_NUM_COMP * (BASIS_Q + BASIS_P);  in __launch_bounds__()
107   sV[0]          = sU[0] + (BASIS_NUM_COMP * 1 * BASIS_Q);  in __launch_bounds__()
109     sU[comp] = sU[comp - 1] + (1 * BASIS_Q);  in __launch_bounds__()
115     read_T_trans_gm2sm<BASIS_Q, BASIS_P>(tx, dT, sT);  in __launch_bounds__()
119   read_1d<CeedScalar, BASIS_Q, BASIS_NUM_COMP>(dU, cstrdU, sU, tx);  in __launch_bounds__()
122   magma_interp_1d_device<CeedScalar, BASIS_DIM, BASIS_NUM_COMP, BASIS_Q, BASIS_P>(sT, sU, sV, tx);  in __launch_bounds__()
150   CeedScalar *sW = sT + BASIS_Q * BASIS_P;  in __launch_bounds__()
151   sU[0]          = sW + ty * BASIS_NUM_COMP * (BASIS_Q + BASIS_P);  in __launch_bounds__()
152   sV[0]          = sU[0] + (BASIS_NUM_COMP * 1 * BASIS_Q);  in __launch_bounds__()
154     sU[comp] = sU[comp - 1] + (1 * BASIS_Q);  in __launch_bounds__()
160     read_T_trans_gm2sm<BASIS_Q, BASIS_P>(tx, dT, sT);  in __launch_bounds__()
164   read_1d<CeedScalar, BASIS_Q, BASIS_NUM_COMP>(dU, cstrdU, sU, tx);  in __launch_bounds__()
167   magma_interp_1d_device<CeedScalar, BASIS_DIM, BASIS_NUM_COMP, BASIS_Q, BASIS_P>(sT, sU, sV, tx);  in __launch_bounds__()