13 template <typename T, int Q_COMP, int P, int Q, int NB>
22   dB += id * P * NB;  in magma_basis_nontensor_device_n()
26   CeedScalar *sB = shared_data + ty * P * NB;  in magma_basis_nontensor_device_n()
27   CeedScalar *sA = shared_data + blockDim.y * P * NB;  in magma_basis_nontensor_device_n()
31     read_B_g2s_1D_nosync<CeedScalar, Q, P, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_n()
37     CeedScalar rA[P];  in magma_basis_nontensor_device_n()
38 …read_A_trans_g2r_1D_nosync<CeedScalar, Q, P, MAGMA_BASIS_NTCOL(Q, MAGMA_MAXTHREADS_1D)>(tx, ty, dA…  in magma_basis_nontensor_device_n()
41     mul_rAsBrC_1D_nosync<CeedScalar, Q, P, NB>(rA, sB, rC);  in magma_basis_nontensor_device_n()
45       write_C_r2g_1D_nosync<CeedScalar, Q, P, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_n()
48     dA += Q * P;  in magma_basis_nontensor_device_n()
56 template <typename T, int Q_COMP, int P, int Q, int NB>
66   dC += id * P * NB;  in magma_basis_nontensor_device_t()
78 …read_A_notrans_g2r_1D_nosync<CeedScalar, P, Q, MAGMA_BASIS_NTCOL(P, MAGMA_MAXTHREADS_1D)>(tx, ty, …  in magma_basis_nontensor_device_t()
83       read_B_g2s_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_t()
87     addmul_rAsBrC_1D_nosync<CeedScalar, P, Q, NB>(rA, sB, rC);  in magma_basis_nontensor_device_t()
89     dA += P * Q;  in magma_basis_nontensor_device_t()
97     write_C_r2g_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_t()
102 template <typename T, int Q_COMP, int P, int Q, int NB>
112   dC += id * P * NB;  in magma_basis_nontensor_device_ta()
124 …read_A_notrans_g2r_1D_nosync<CeedScalar, P, Q, MAGMA_BASIS_NTCOL(P, MAGMA_MAXTHREADS_1D)>(tx, ty, …  in magma_basis_nontensor_device_ta()
129       read_B_g2s_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_ta()
133     addmul_rAsBrC_1D_nosync<CeedScalar, P, Q, NB>(rA, sB, rC);  in magma_basis_nontensor_device_ta()
135     dA += P * Q;  in magma_basis_nontensor_device_ta()
143     sum_C_r2g_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_ta()
148 template <typename T, int P, int Q, int NB>
157   dB += id * P * NB;  in magma_basis_nontensor_device_n1()
162   CeedScalar *sB = shared_data + ty * P * NB;  in magma_basis_nontensor_device_n1()
165   CeedScalar rA[P];  in magma_basis_nontensor_device_n1()
166 …read_A_trans_g2r_1D_nosync<CeedScalar, Q, P, MAGMA_BASIS_NTCOL(Q, MAGMA_MAXTHREADS_1D)>(tx, ty, dA…  in magma_basis_nontensor_device_n1()
173   read_B_g2s_1D_nosync<CeedScalar, Q, P, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_n1()
177   mul_rAsBrC_1D_nosync<CeedScalar, Q, P, NB>(rA, sB, rC);  in magma_basis_nontensor_device_n1()
180   write_C_r2g_1D_nosync<CeedScalar, Q, P, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_n1()
184 template <typename T, int P, int Q, int NB>
194   dC += id * P * NB;  in magma_basis_nontensor_device_t1()
202 …read_A_notrans_g2r_1D_nosync<CeedScalar, P, Q, MAGMA_BASIS_NTCOL(P, MAGMA_MAXTHREADS_1D)>(tx, ty, …  in magma_basis_nontensor_device_t1()
209   read_B_g2s_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_t1()
213   mul_rAsBrC_1D_nosync<CeedScalar, P, Q, NB>(rA, sB, rC);  in magma_basis_nontensor_device_t1()
216   write_C_r2g_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_t1()
220 template <typename T, int P, int Q, int NB>
230   dC += id * P * NB;  in magma_basis_nontensor_device_ta1()
238 …read_A_notrans_g2r_1D_nosync<CeedScalar, P, Q, MAGMA_BASIS_NTCOL(P, MAGMA_MAXTHREADS_1D)>(tx, ty, …  in magma_basis_nontensor_device_ta1()
245   read_B_g2s_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, dB, sB);  in magma_basis_nontensor_device_ta1()
249   mul_rAsBrC_1D_nosync<CeedScalar, P, Q, NB>(rA, sB, rC);  in magma_basis_nontensor_device_ta1()
252   sum_C_r2g_1D_nosync<CeedScalar, P, Q, NB>(tx, myn, rC, dC);  in magma_basis_nontensor_device_ta1()