cuda-shared-basis-tensor-templates.h - OpenGrok cross reference for /libCEED/include/ceed/jit-source/cuda/cuda-shared-basis-tensor-templates.h

Lines Matching refs:r_U
52 inline __device__ void Interp1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const Ce…  in Interp1d()  argument
54     ContractX1d<NUM_COMP, P_1D, Q_1D>(data, &r_U[comp], c_B, &r_V[comp]);  in Interp1d()
62 inline __device__ void InterpTranspose1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U,…  in InterpTranspose1d()  argument
65     ContractTransposeX1d<NUM_COMP, P_1D, Q_1D>(data, &r_U[comp], c_B, &r_V[comp]);  in InterpTranspose1d()
73 …erpCollocatedNodes1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpCollocatedNodes1d()  argument
76     r_V[comp] = r_U[comp];  in InterpCollocatedNodes1d()
84 …oseCollocatedNodes1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTransposeCollocatedNodes1d()  argument
87     r_V[comp] = r_U[comp];  in InterpTransposeCollocatedNodes1d()
95 inline __device__ void Grad1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const Ceed…  in Grad1d()  argument
98     ContractX1d<NUM_COMP, P_1D, Q_1D>(data, &r_U[comp], c_G, &r_V[comp]);  in Grad1d()
106 inline __device__ void GradTranspose1d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, c…  in GradTranspose1d()  argument
109     ContractTransposeX1d<NUM_COMP, P_1D, Q_1D>(data, &r_U[comp], c_G, &r_V[comp]);  in GradTranspose1d()
208 inline __device__ void InterpTensor2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, co…  in InterpTensor2d()  argument
212     ContractX2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_B, r_t);  in InterpTensor2d()
221 …erpTransposeTensor2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTransposeTensor2d()  argument
225     ContractTransposeY2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_B, r_t);  in InterpTransposeTensor2d()
234 …sorCollocatedNodes2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTensorCollocatedNodes2d()  argument
237     r_V[comp] = r_U[comp];  in InterpTensorCollocatedNodes2d()
245 …sorCollocatedNodes2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTransposeTensorCollocatedNodes2d()  argument
248     r_V[comp] = r_U[comp];  in InterpTransposeTensorCollocatedNodes2d()
256 inline __device__ void GradTensor2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, cons…  in GradTensor2d()  argument
260     ContractX2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_G, r_t);  in GradTensor2d()
262     ContractX2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_B, r_t);  in GradTensor2d()
271 …radTransposeTensor2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTransposeTensor2d()  argument
275     ContractTransposeY2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp + 0 * NUM_COMP], c_B, r_t);  in GradTransposeTensor2d()
277     ContractTransposeY2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp + 1 * NUM_COMP], c_G, r_t);  in GradTransposeTensor2d()
286 …sorCollocatedNodes2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTensorCollocatedNodes2d()  argument
289     ContractX2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_G, &r_V[comp + 0 * NUM_COMP]);  in GradTensorCollocatedNodes2d()
290     ContractY2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp], c_G, &r_V[comp + 1 * NUM_COMP]);  in GradTensorCollocatedNodes2d()
298 …sorCollocatedNodes2d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTransposeTensorCollocatedNodes2d()  argument
301 …ContractTransposeY2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp + 1 * NUM_COMP], c_G, &r_V[comp]);  in GradTransposeTensorCollocatedNodes2d()
302 …ContractTransposeAddX2d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp + 0 * NUM_COMP], c_G, &r_V[com…  in GradTransposeTensorCollocatedNodes2d()
488 inline __device__ void InterpTensor3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, co…  in InterpTensor3d()  argument
493     ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_B, r_t1);  in InterpTensor3d()
503 …erpTransposeTensor3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTransposeTensor3d()  argument
508     ContractTransposeZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D], c_B, r_t1);  in InterpTransposeTensor3d()
518 …sorCollocatedNodes3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTensorCollocatedNodes3d()  argument
522       r_V[i + comp * Q_1D] = r_U[i + comp * P_1D];  in InterpTensorCollocatedNodes3d()
531 …sorCollocatedNodes3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in InterpTransposeTensorCollocatedNodes3d()  argument
535       r_V[i + comp * P_1D] = r_U[i + comp * Q_1D];  in InterpTransposeTensorCollocatedNodes3d()
544 inline __device__ void GradTensor3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, cons…  in GradTensor3d()  argument
549     ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_G, r_t1);  in GradTensor3d()
552     ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_B, r_t1);  in GradTensor3d()
555     ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_B, r_t1);  in GradTensor3d()
565 …radTransposeTensor3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTransposeTensor3d()  argument
570 …ContractTransposeZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 0 * NUM_COMP * Q_1D], c_…  in GradTransposeTensor3d()
573 …ContractTransposeZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 1 * NUM_COMP * Q_1D], c_…  in GradTransposeTensor3d()
576 …ContractTransposeZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 2 * NUM_COMP * Q_1D], c_…  in GradTransposeTensor3d()
586 …adTensorCollocated3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTensorCollocated3d()  argument
591     ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_B, r_t1);  in GradTensorCollocated3d()
604 …seTensorCollocated3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTransposeTensorCollocated3d()  argument
609 …ContractTransposeZ3d<NUM_COMP, Q_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 2 * NUM_COMP * Q_1D], c_…  in GradTransposeTensorCollocated3d()
610 …ContractTransposeAddY3d<NUM_COMP, Q_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 1 * NUM_COMP * Q_1D],…  in GradTransposeTensorCollocated3d()
611 …ContractTransposeAddX3d<NUM_COMP, Q_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 0 * NUM_COMP * Q_1D],…  in GradTransposeTensorCollocated3d()
622 …sorCollocatedNodes3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTensorCollocatedNodes3d()  argument
625 …ContractX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_G, &r_V[comp * Q_1D + 0 * NUM_C…  in GradTensorCollocatedNodes3d()
626 …ContractY3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_G, &r_V[comp * Q_1D + 1 * NUM_C…  in GradTensorCollocatedNodes3d()
627 …ContractZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * P_1D], c_G, &r_V[comp * Q_1D + 2 * NUM_C…  in GradTensorCollocatedNodes3d()
635 …sorCollocatedNodes3d(SharedData_Cuda &data, const CeedScalar *__restrict__ r_U, const CeedScalar *…  in GradTransposeTensorCollocatedNodes3d()  argument
638 …ContractTransposeZ3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 2 * NUM_COMP * Q_1D], c_…  in GradTransposeTensorCollocatedNodes3d()
639 …ContractTransposeAddY3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 1 * NUM_COMP * Q_1D],…  in GradTransposeTensorCollocatedNodes3d()
640 …ContractTransposeAddX3d<NUM_COMP, P_1D, Q_1D, T_1D>(data, &r_U[comp * Q_1D + 0 * NUM_COMP * Q_1D],…  in GradTransposeTensorCollocatedNodes3d()