| /libCEED/include/ceed/jit-source/hip/ |
| H A D | hip-shared-basis-nontensor.h | 30 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
57 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
84 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
114 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM]; in __launch_bounds__() local
141 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
168 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
|
| H A D | hip-shared-basis-tensor.h | 30 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
99 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
168 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
241 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
285 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
326 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
370 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
411 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
455 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in __launch_bounds__() local
|
| H A D | hip-shared-basis-tensor-templates.h | 52 …p &data, const CeedScalar *__restrict__ r_U, const CeedScalar *c_B, CeedScalar *__restrict__ r_V) { in Interp1d()
63 CeedScalar *__restrict__ r_V) { in InterpTranspose1d()
74 CeedScalar *__restrict__ r_V) { in InterpCollocatedNodes1d()
85 CeedScalar *__restrict__ r_V) { in InterpTransposeCollocatedNodes1d()
96 CeedScalar *__restrict__ r_V) { in Grad1d()
107 CeedScalar *__restrict__ r_V) { in GradTranspose1d()
208 …p &data, const CeedScalar *__restrict__ r_U, const CeedScalar *c_B, CeedScalar *__restrict__ r_V) { in InterpTensor2d()
221 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor2d()
234 CeedScalar *__restrict__ r_V) { in InterpTensorCollocatedNodes2d()
245 CeedScalar *__restrict__ r_V) { in InterpTransposeTensorCollocatedNodes2d()
[all …]
|
| H A D | hip-shared-basis-nontensor-templates.h | 48 CeedScalar *__restrict__ r_V) { in InterpNonTensor()
59 CeedScalar *__restrict__ r_V) { in InterpTransposeNonTensor()
70 …p &data, const CeedScalar *__restrict__ r_U, const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradNonTensor()
83 CeedScalar *__restrict__ r_V) { in GradTransposeNonTensor()
|
| H A D | hip-shared-basis-tensor-at-points.h | 38 CeedScalar r_V[BASIS_NUM_COMP]; in __launch_bounds__() local
94 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
164 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
226 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM]; in __launch_bounds__() local
282 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
353 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in __launch_bounds__() local
|
| H A D | hip-shared-basis-tensor-flattened-templates.h | 132 CeedScalar *__restrict__ r_V) { in InterpTensor2dFlattened()
151 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor2dFlattened()
169 CeedScalar *__restrict__ r_V) { in InterpTensorCollocatedNodes2dFlattened()
186 … CeedScalar *__restrict__ r_V) { in InterpTransposeTensorCollocatedNodes2dFlattened()
202 CeedScalar *__restrict__ r_V) { in GradTensor2dFlattened()
223 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTransposeTensor2dFlattened()
243 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTensorCollocatedNodes2dFlattened()
261 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTransposeTensorCollocatedNodes2dFlattened()
469 CeedScalar *__restrict__ r_V) { in InterpTensor3dFlattened()
489 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor3dFlattened()
[all …]
|
| H A D | hip-ref-basis-nontensor-templates.h | 21 CeedScalar r_V[Q_COMP]; in Contract() local
48 CeedScalar r_V; in ContractTranspose() local
|
| H A D | hip-shared-basis-tensor-at-points-templates.h | 45 CeedScalar *__restrict__ r_V) { in InterpAtPoints1d()
92 CeedScalar *__restrict__ r_V) { in GradAtPoints1d()
143 CeedScalar *__restrict__ r_V) { in InterpAtPoints2d()
212 CeedScalar *__restrict__ r_V) { in GradAtPoints2d()
293 CeedScalar *__restrict__ r_V) { in InterpAtPoints3d()
374 CeedScalar *__restrict__ r_V) { in GradAtPoints3d()
|
| H A D | hip-gen-templates.h | 477 CeedScalar *__restrict__ r_V) { in GradColloSlice3d()
507 CeedScalar *__restrict__ r_V) { in GradColloSliceTranspose3d()
|
| /libCEED/include/ceed/jit-source/cuda/ |
| H A D | cuda-shared-basis-tensor-templates.h | 52 …a &data, const CeedScalar *__restrict__ r_U, const CeedScalar *c_B, CeedScalar *__restrict__ r_V) { in Interp1d()
63 CeedScalar *__restrict__ r_V) { in InterpTranspose1d()
74 CeedScalar *__restrict__ r_V) { in InterpCollocatedNodes1d()
85 CeedScalar *__restrict__ r_V) { in InterpTransposeCollocatedNodes1d()
96 CeedScalar *__restrict__ r_V) { in Grad1d()
107 CeedScalar *__restrict__ r_V) { in GradTranspose1d()
209 CeedScalar *__restrict__ r_V) { in InterpTensor2d()
222 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor2d()
235 CeedScalar *__restrict__ r_V) { in InterpTensorCollocatedNodes2d()
246 CeedScalar *__restrict__ r_V) { in InterpTransposeTensorCollocatedNodes2d()
[all …]
|
| H A D | cuda-shared-basis-nontensor.h | 29 CeedScalar r_V[BASIS_NUM_COMP]; in Interp() local
56 CeedScalar r_V[BASIS_NUM_COMP]; in InterpTranspose() local
83 CeedScalar r_V[BASIS_NUM_COMP]; in InterpTransposeAdd() local
112 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM]; in Grad() local
139 CeedScalar r_V[BASIS_NUM_COMP]; in GradTranspose() local
166 CeedScalar r_V[BASIS_NUM_COMP]; in GradTransposeAdd() local
|
| H A D | cuda-shared-basis-nontensor-templates.h | 48 CeedScalar *__restrict__ r_V) { in InterpNonTensor()
59 CeedScalar *__restrict__ r_V) { in InterpTransposeNonTensor()
70 …a &data, const CeedScalar *__restrict__ r_U, const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradNonTensor()
83 CeedScalar *__restrict__ r_V) { in GradTransposeNonTensor()
|
| H A D | cuda-shared-basis-tensor.h | 29 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in Interp() local
98 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in InterpTranspose() local
167 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in InterpTransposeAdd() local
239 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in Grad() local
282 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in GradCollocated() local
322 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in GradTranspose() local
365 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in GradCollocatedTranspose() local
405 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in GradTransposeAdd() local
448 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in GradCollocatedTransposeAdd() local
|
| H A D | cuda-shared-basis-tensor-flattened-templates.h | 132 CeedScalar *__restrict__ r_V) { in InterpTensor2dFlattened()
151 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor2dFlattened()
169 CeedScalar *__restrict__ r_V) { in InterpTensorCollocatedNodes2dFlattened()
186 … CeedScalar *__restrict__ r_V) { in InterpTransposeTensorCollocatedNodes2dFlattened()
202 CeedScalar *__restrict__ r_V) { in GradTensor2dFlattened()
223 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTransposeTensor2dFlattened()
243 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTensorCollocatedNodes2dFlattened()
261 … const CeedScalar *c_G, CeedScalar *__restrict__ r_V) { in GradTransposeTensorCollocatedNodes2dFlattened()
469 CeedScalar *__restrict__ r_V) { in InterpTensor3dFlattened()
489 CeedScalar *__restrict__ r_V) { in InterpTransposeTensor3dFlattened()
[all …]
|
| H A D | cuda-shared-basis-tensor-at-points.h | 37 CeedScalar r_V[BASIS_NUM_COMP]; in InterpAtPoints() local
93 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in InterpTransposeAtPoints() local
163 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in InterpTransposeAddAtPoints() local
224 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM]; in GradAtPoints() local
280 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in GradTransposeAtPoints() local
351 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in GradTransposeAddAtPoints() local
|
| H A D | cuda-ref-basis-nontensor-templates.h | 21 CeedScalar r_V[Q_COMP]; in Contract() local
48 CeedScalar r_V; in ContractTranspose() local
|
| H A D | cuda-shared-basis-tensor-at-points-templates.h | 45 CeedScalar *__restrict__ r_V) { in InterpAtPoints1d()
91 CeedScalar *__restrict__ r_V) { in GradAtPoints1d()
142 CeedScalar *__restrict__ r_V) { in InterpAtPoints2d()
211 CeedScalar *__restrict__ r_V) { in GradAtPoints2d()
292 CeedScalar *__restrict__ r_V) { in InterpAtPoints3d()
373 CeedScalar *__restrict__ r_V) { in GradAtPoints3d()
|
| H A D | cuda-gen-templates.h | 480 CeedScalar *__restrict__ r_V) { in GradColloSlice3d()
510 CeedScalar *__restrict__ r_V) { in GradColloSliceTranspose3d()
|
| /libCEED/include/ceed/jit-source/sycl/ |
| H A D | sycl-shared-basis-tensor.h | 28 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in Interp() local
62 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in InterpTranspose() local
98 CeedScalar r_V[BASIS_NUM_COMP * BASIS_DIM * (BASIS_DIM > 2 ? BASIS_Q_1D : 1)]; in Grad() local
133 CeedScalar r_V[BASIS_NUM_COMP * (BASIS_DIM > 2 ? BASIS_P_1D : 1)]; in GradTranspose() local
|
| H A D | sycl-shared-basis-tensor-templates.h | 58 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in Interp1d()
68 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in InterpTranspose1d()
78 …local const CeedScalar *restrict s_G, private CeedScalar *restrict r_V, local CeedScalar *restrict… in Grad1d()
88 …local const CeedScalar *restrict s_G, private CeedScalar *restrict r_V, local CeedScalar *restrict… in GradTranspose1d()
209 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in InterpTensor2d()
222 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in InterpTransposeTensor2d()
235 …t CeedScalar *restrict s_B, local const CeedScalar *restrict s_G, private CeedScalar *restrict r_V, in GradTensor2d()
251 …t CeedScalar *restrict s_B, local const CeedScalar *restrict s_G, private CeedScalar *restrict r_V, in GradTransposeTensor2d()
475 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in InterpTensor3d()
490 …local const CeedScalar *restrict s_B, private CeedScalar *restrict r_V, local CeedScalar *restrict… in InterpTransposeTensor3d()
[all …]
|
| H A D | sycl-gen-templates.h | 286 …const local CeedScalar *s_G, private CeedScalar *restrict r_V, local CeedScalar *restrict scratch)… in gradCollo3d()
320 …const local CeedScalar *restrict s_G, private CeedScalar *restrict r_V, local CeedScalar *restrict… in gradColloTranspose3d()
|