Lines Matching refs:r_U
131 inline __device__ void InterpTensor2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U,… in InterpTensor2dFlattened() argument
136 if (P_1D != T_1D) QUnpack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTensor2dFlattened()
138 ContractX2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_B, r_t); in InterpTensor2dFlattened()
142 if (P_1D != T_1D) QPack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTensor2dFlattened()
150 …TransposeTensor2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTransposeTensor2dFlattened() argument
155 if (Q_1D != T_1D) QUnpack2d<NUM_COMP, Q_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTransposeTensor2dFlattened()
157 …ContractTransposeY2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_B, r… in InterpTransposeTensor2dFlattened()
168 …CollocatedNodes2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTensorCollocatedNodes2dFlattened() argument
172 if (P_1D != T_1D) QUnpack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTensorCollocatedNodes2dFlattened()
174 r_V[comp] = r_U[comp]; in InterpTensorCollocatedNodes2dFlattened()
177 if (P_1D != T_1D) QPack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTensorCollocatedNodes2dFlattened()
185 …CollocatedNodes2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTransposeTensorCollocatedNodes2dFlattened() argument
189 if (Q_1D != T_1D) QUnpack2d<NUM_COMP, Q_1D, T_1D>(data, t_id_x, t_id_y, r_U); in InterpTransposeTensorCollocatedNodes2dFlattened()
191 r_V[comp] = r_U[comp]; in InterpTransposeTensorCollocatedNodes2dFlattened()
201 inline __device__ void GradTensor2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, c… in GradTensor2dFlattened() argument
206 if (P_1D != T_1D) QUnpack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTensor2dFlattened()
208 ContractX2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_G, r_t); in GradTensor2dFlattened()
210 ContractX2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_B, r_t); in GradTensor2dFlattened()
214 if (P_1D != T_1D) QPack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTensor2dFlattened()
222 …TransposeTensor2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTransposeTensor2dFlattened() argument
227 if (Q_1D != T_1D) QUnpack2d<NUM_COMP * 2, Q_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTransposeTensor2dFlattened()
229 …ContractTransposeY2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp + 0 * NU… in GradTransposeTensor2dFlattened()
231 …ContractTransposeY2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp + 1 * NU… in GradTransposeTensor2dFlattened()
242 …CollocatedNodes2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTensorCollocatedNodes2dFlattened() argument
246 if (P_1D != T_1D) QUnpack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTensorCollocatedNodes2dFlattened()
248 …ContractX2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_G, &r_V[comp … in GradTensorCollocatedNodes2dFlattened()
249 …ContractY2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp], c_G, &r_V[comp … in GradTensorCollocatedNodes2dFlattened()
252 if (P_1D != T_1D) QPack2d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTensorCollocatedNodes2dFlattened()
260 …CollocatedNodes2dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTransposeTensorCollocatedNodes2dFlattened() argument
264 if (Q_1D != T_1D) QUnpack2d<NUM_COMP * 2, Q_1D, T_1D>(data, t_id_x, t_id_y, r_U); in GradTransposeTensorCollocatedNodes2dFlattened()
266 …ContractTransposeY2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp + 1 * NU… in GradTransposeTensorCollocatedNodes2dFlattened()
267 …ContractTransposeAddX2dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, &r_U[comp + 0 *… in GradTransposeTensorCollocatedNodes2dFlattened()
468 inline __device__ void InterpTensor3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U,… in InterpTensor3dFlattened() argument
473 if (P_1D != T_1D) QUnpack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTensor3dFlattened()
475 …ContractX3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp], c_B, r_… in InterpTensor3dFlattened()
480 if (P_1D != T_1D) QPack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTensor3dFlattened()
488 …TransposeTensor3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTransposeTensor3dFlattened() argument
493 if (Q_1D != T_1D) QUnpack3d<NUM_COMP, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTransposeTensor3dFlattened()
495 …ContractTransposeZ3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp]… in InterpTransposeTensor3dFlattened()
507 …CollocatedNodes3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTensorCollocatedNodes3dFlattened() argument
511 if (P_1D != T_1D) QUnpack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTensorCollocatedNodes3dFlattened()
513 r_V[comp] = r_U[comp]; in InterpTensorCollocatedNodes3dFlattened()
516 if (P_1D != T_1D) QPack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTensorCollocatedNodes3dFlattened()
524 …CollocatedNodes3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in InterpTransposeTensorCollocatedNodes3dFlattened() argument
528 if (Q_1D != T_1D) QUnpack3d<NUM_COMP, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in InterpTransposeTensorCollocatedNodes3dFlattened()
530 r_V[comp] = r_U[comp]; in InterpTransposeTensorCollocatedNodes3dFlattened()
540 inline __device__ void GradTensor3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, c… in GradTensor3dFlattened() argument
545 if (P_1D != T_1D) QUnpack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensor3dFlattened()
547 …ContractX3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp], c_G, r_… in GradTensor3dFlattened()
550 …ContractX3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp], c_B, r_… in GradTensor3dFlattened()
553 …ContractX3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp], c_B, r_… in GradTensor3dFlattened()
558 if (P_1D != T_1D) QPack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensor3dFlattened()
566 …TransposeTensor3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTransposeTensor3dFlattened() argument
571 if (Q_1D != T_1D) QUnpack3d<NUM_COMP * 3, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTransposeTensor3dFlattened()
573 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
576 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
579 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
591 …ensorCollocated3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTensorCollocated3dFlattened() argument
596 if (P_1D != T_1D) QUnpack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensorCollocated3dFlattened()
598 …ContractX3dFlattened<NUM_COMP, P_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp], c_B, r_… in GradTensorCollocated3dFlattened()
606 if (P_1D != T_1D) QPack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensorCollocated3dFlattened()
614 …TransposeTensor3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTransposeTensor3dFlattened() argument
619 if (Q_1D != T_1D) QUnpack3d<NUM_COMP * 3, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTransposeTensor3dFlattened()
621 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
624 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
627 …ContractTransposeZ3dFlattened<NUM_COMP, t_id_x, t_id_y, t_id_z, P_1D, Q_1D, T_1D>(data, &r_U[comp … in GradTransposeTensor3dFlattened()
639 …CollocatedNodes3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTensorCollocatedNodes3dFlattened() argument
643 if (P_1D != T_1D) QUnpack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensorCollocatedNodes3dFlattened()
645 …ContractX3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U[comp], c_G, &r_… in GradTensorCollocatedNodes3dFlattened()
646 …ContractY3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U[comp], c_G, &r_… in GradTensorCollocatedNodes3dFlattened()
647 …ContractZ3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U[comp], c_G, &r_… in GradTensorCollocatedNodes3dFlattened()
650 if (P_1D != T_1D) QPack3d<NUM_COMP, P_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTensorCollocatedNodes3dFlattened()
658 …CollocatedNodes3dFlattened(SharedData_Cuda &data, CeedScalar *__restrict__ r_U, const CeedScalar *… in GradTransposeTensorCollocatedNodes3dFlattened() argument
662 if (Q_1D != T_1D) QUnpack3d<NUM_COMP * 3, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, r_U); in GradTransposeTensorCollocatedNodes3dFlattened()
664 …ContractTransposeZ3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[comp … in GradTransposeTensorCollocatedNodes3dFlattened()
665 …ContractTransposeAddY3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[co… in GradTransposeTensorCollocatedNodes3dFlattened()
666 …ContractTransposeAddX3dFlattened<NUM_COMP, Q_1D, Q_1D, T_1D>(data, t_id_x, t_id_y, t_id_z, &r_U[co… in GradTransposeTensorCollocatedNodes3dFlattened()