Searched refs:jj (Results 1 – 5 of 5) sorted by relevance
| /libCEED/backends/avx/ |
| H A D | ceed-avx-tensor.c | 57 for (CeedInt jj = 0; jj < JJ; jj++) { in CeedTensorContract_Avx_Blocked() local 58 … for (CeedInt cc = 0; cc < CC / 4; cc++) vv[jj][cc] = loadu(&v[(a * J + j + jj) * C + c + cc * 4]); in CeedTensorContract_Avx_Blocked() 61 for (CeedInt jj = 0; jj < JJ; jj++) { // unroll in CeedTensorContract_Avx_Blocked() local 62 rtype tqv = set1(t[(j + jj) * t_stride_0 + b * t_stride_1]); in CeedTensorContract_Avx_Blocked() 64 fmadd(vv[jj][cc], tqv, loadu(&u[(a * B + b) * C + c + cc * 4])); in CeedTensorContract_Avx_Blocked() 68 for (CeedInt jj = 0; jj < JJ; jj++) { in CeedTensorContract_Avx_Blocked() local 69 … for (CeedInt cc = 0; cc < CC / 4; cc++) storeu(&v[(a * J + j + jj) * C + c + cc * 4], vv[jj][cc]); in CeedTensorContract_Avx_Blocked() 80 for (CeedInt jj = 0; jj < J - j; jj++) { in CeedTensorContract_Avx_Blocked() local 81 … for (CeedInt cc = 0; cc < CC / 4; cc++) vv[jj][cc] = loadu(&v[(a * J + j + jj) * C + c + cc * 4]); in CeedTensorContract_Avx_Blocked() 84 for (CeedInt jj = 0; jj < J - j; jj++) { // doesn't unroll in CeedTensorContract_Avx_Blocked() local [all …]
|
| /libCEED/include/ceed/jit-source/cuda/ |
| H A D | cuda-shared-basis-tensor-at-points-templates.h | 195 const CeedInt jj = (j + data.t_id_x) % Q_1D; in InterpTransposeAtPoints2d() local 197 …_x < Q_1D && data.t_id_y < Q_1D) atomicAdd_block(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in InterpTransposeAtPoints2d() 271 const CeedInt jj = (j + data.t_id_x) % Q_1D; in GradTransposeAtPoints2d() local 273 …_x < Q_1D && data.t_id_y < Q_1D) atomicAdd_block(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in GradTransposeAtPoints2d() 356 const CeedInt jj = (j + data.t_id_x) % Q_1D; in InterpTransposeAtPoints3d() local 358 …_x < Q_1D && data.t_id_y < Q_1D) atomicAdd_block(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in InterpTransposeAtPoints3d() 456 const CeedInt jj = (j + data.t_id_x) % Q_1D; in GradTransposeAtPoints3d() local 458 …_x < Q_1D && data.t_id_y < Q_1D) atomicAdd_block(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in GradTransposeAtPoints3d()
|
| /libCEED/include/ceed/jit-source/hip/ |
| H A D | hip-shared-basis-tensor-at-points-templates.h | 196 const CeedInt jj = (j + data.t_id_x) % Q_1D; in InterpTransposeAtPoints2d() local 198 …a.t_id_x < Q_1D && data.t_id_y < Q_1D) atomicAdd(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in InterpTransposeAtPoints2d() 272 const CeedInt jj = (j + data.t_id_x) % Q_1D; in GradTransposeAtPoints2d() local 274 …a.t_id_x < Q_1D && data.t_id_y < Q_1D) atomicAdd(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in GradTransposeAtPoints2d() 357 const CeedInt jj = (j + data.t_id_x) % Q_1D; in InterpTransposeAtPoints3d() local 359 …a.t_id_x < Q_1D && data.t_id_y < Q_1D) atomicAdd(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in InterpTransposeAtPoints3d() 456 const CeedInt jj = (j + data.t_id_x) % Q_1D; in GradTransposeAtPoints3d() local 458 …a.t_id_x < Q_1D && data.t_id_y < Q_1D) atomicAdd(&data.slice[jj + ii * Q_1D], chebyshev_x[jj] * bu… in GradTransposeAtPoints3d()
|
| /libCEED/tests/ |
| H A D | t410-qfunction-f.f90 | 11 real*8 jj(q) variable 27 jj(i+1)=1 36 call ceedvectorsetarray(j,ceed_mem_host,ceed_use_pointer,jj,joffset,err)
|
| /libCEED/examples/petsc/ |
| H A D | bpsraw.c | 89 for (CeedInt jj = 0; jj < P; jj++) { in CreateRestriction() local 92 …idx_p[(ii * P + jj) * P + kk] = num_comp * (((i * (P - 1) + ii) * m_nodes[1] + (j * (P - 1) + jj))… in CreateRestriction() 94 …idx_p[ii + P * (jj + P * kk)] = num_comp * (((i * (P - 1) + ii) * m_nodes[1] + (j * (P - 1) + jj))… in CreateRestriction() 503 …for (PetscInt j = 0, jr, jj; jr = j >= m_nodes[1], jj = j - jr * m_nodes[1], j < l_nodes[1]; j++) { in main() local 506 …l_to_g_ind[here] = g_start[ir][jr][kr] + (ii * g_m_nodes[ir][jr][kr][1] + jj) * g_m_nodes[ir][jr][… in main()
|