| /libCEED/include/ceed/jit-source/cuda/ |
| H A D | cuda-shared-basis-read-write-templates.h | 31 const CeedInt node = data.t_id_x; in ReadElementStrided1d() local
47 const CeedInt node = data.t_id_x; in WriteElementStrided1d() local
60 const CeedInt node = data.t_id_x; in SumElementStrided1d() local
80 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadElementStrided2d() local
96 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteElementStrided2d() local
109 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in SumElementStrided2d() local
130 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in ReadElementStrided3d() local
148 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in WriteElementStrided3d() local
163 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in SumElementStrided3d() local
|
| H A D | cuda-ref-restriction-strided.h | 16 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in StridedNoTranspose() local
31 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in StridedTranspose() local
|
| H A D | cuda-gen-templates.h | 76 const CeedInt node = data.t_id_x; in ReadLVecStandard1d() local
90 const CeedInt node = data.t_id_x; in ReadLVecStrided1d() local
104 const CeedInt node = data.t_id_x; in WriteLVecStandard1d() local
166 const CeedInt node = data.t_id_x; in WriteLVecStrided1d() local
198 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadLVecStandard2d() local
212 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadLVecStrided2d() local
226 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStandard2d() local
242 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStandard2d_Single() local
295 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStrided2d() local
329 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in ReadLVecStandard3d() local
[all …]
|
| H A D | cuda-ref-restriction-offset.h | 16 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OffsetNoTranspose() local
32 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OffsetTranspose() local
|
| H A D | cuda-ref-restriction-oriented.h | 17 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OrientedNoTranspose() local
35 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OrientedTranspose() local
|
| H A D | cuda-ref-restriction-curl-oriented.h | 17 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedNoTranspose() local
42 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedUnsignedNoTranspose() local
68 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedTranspose() local
126 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedUnsignedTranspose() local
|
| H A D | cuda-ref-restriction-at-points.h | 18 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in AtPointsTranspose() local
|
| /libCEED/include/ceed/jit-source/hip/ |
| H A D | hip-shared-basis-read-write-templates.h | 31 const CeedInt node = data.t_id_x; in ReadElementStrided1d() local
47 const CeedInt node = data.t_id_x; in WriteElementStrided1d() local
60 const CeedInt node = data.t_id_x; in SumElementStrided1d() local
80 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadElementStrided2d() local
96 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteElementStrided2d() local
109 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in SumElementStrided2d() local
130 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in ReadElementStrided3d() local
148 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in WriteElementStrided3d() local
163 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in SumElementStrided3d() local
|
| H A D | hip-ref-restriction-strided.h | 16 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in StridedNoTranspose() local
31 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in StridedTranspose() local
|
| H A D | hip-gen-templates.h | 76 const CeedInt node = data.t_id_x; in ReadLVecStandard1d() local
89 const CeedInt node = data.t_id_x; in ReadLVecStrided1d() local
103 const CeedInt node = data.t_id_x; in WriteLVecStandard1d() local
165 const CeedInt node = data.t_id_x; in WriteLVecStrided1d() local
197 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadLVecStandard2d() local
210 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in ReadLVecStrided2d() local
224 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStandard2d() local
240 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStandard2d_Single() local
293 const CeedInt node = data.t_id_x + data.t_id_y * P_1D; in WriteLVecStrided2d() local
327 const CeedInt node = data.t_id_x + data.t_id_y * P_1D + z * P_1D * P_1D; in ReadLVecStandard3d() local
[all …]
|
| H A D | hip-ref-restriction-offset.h | 16 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OffsetNoTranspose() local
32 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OffsetTranspose() local
|
| H A D | hip-ref-restriction-oriented.h | 17 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OrientedNoTranspose() local
35 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in OrientedTranspose() local
|
| H A D | hip-ref-restriction-curl-oriented.h | 17 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedNoTranspose() local
42 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedUnsignedNoTranspose() local
68 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedTranspose() local
126 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in CurlOrientedUnsignedTranspose() local
|
| H A D | hip-ref-restriction-at-points.h | 18 …for (CeedInt node = blockIdx.x * blockDim.x + threadIdx.x; node < RSTR_NUM_ELEM * RSTR_ELEM_SIZE; … in AtPointsTranspose() local
|
| /libCEED/include/ceed/jit-source/sycl/ |
| H A D | sycl-gen-templates.h | 39 const CeedInt node = item_id_x; in readDofsOffset1d() local
57 const CeedInt node = item_id_x; in readDofsStrided1d() local
74 const CeedInt node = item_id_x; in writeDofsOffset1d() local
91 const CeedInt node = item_id_x; in writeDofsStrided1d() local
113 const CeedInt node = item_id_x + item_id_y * P_1D; in readDofsOffset2d() local
130 const CeedInt node = item_id_x + item_id_y * P_1D; in readDofsStrided2d() local
146 const CeedInt node = item_id_x + item_id_y * P_1D; in writeDofsOffset2d() local
164 const CeedInt node = item_id_x + item_id_y * P_1D; in writeDofsStrided2d() local
185 const CeedInt node = item_id_x + P_1D * (item_id_y + P_1D * z); in readDofsOffset3d() local
204 const CeedInt node = item_id_x + P_1D * (item_id_y + P_1D * z); in readDofsStrided3d() local
[all …]
|
| H A D | sycl-shared-basis-read-write-templates.h | 35 const CeedInt node = item_id_x; in ReadElementStrided1d() local
53 const CeedInt node = item_id_x; in WriteElementStrided1d() local
76 const CeedInt node = item_id_x + item_id_y * P_1D; in ReadElementStrided2d() local
95 const CeedInt node = item_id_x + item_id_y * P_1D; in WriteElementStrided2d() local
119 const CeedInt node = item_id_x + item_id_y * P_1D + z * P_1D * P_1D; in ReadElementStrided3d() local
140 const CeedInt node = item_id_x + item_id_y * P_1D + z * P_1D * P_1D; in WriteElementStrided3d() local
|
| /libCEED/backends/sycl-ref/ |
| H A D | ceed-sycl-restriction.sycl.cpp | 40 sycl_queue.parallel_for<CeedElemRestrSyclStridedNT>(kernel_range, e, [=](sycl::id<1> node) { in CeedElemRestrictionStridedNoTranspose_Sycl()
67 sycl_queue.parallel_for<CeedElemRestrSyclOffsetNT>(kernel_range, e, [=](sycl::id<1> node) { in CeedElemRestrictionOffsetNoTranspose_Sycl()
96 sycl_queue.parallel_for<CeedElemRestrSyclStridedT>(kernel_range, e, [=](sycl::id<1> node) { in CeedElemRestrictionStridedTranspose_Sycl()
127 const CeedInt node = id % num_nodes; in CeedElemRestrictionOffsetTranspose_Sycl() local
|
| /libCEED/examples/fluids/src/ |
| H A D | setupts.c | 86 for (PetscInt node = 0; node < dof / num_comp; node++) { in Surface_Forces_NS() local
|
| /libCEED/interface/ |
| H A D | ceed-basis.c | 2343 for (CeedInt node = 0; node < basis->P; node++) { in CeedBasisGetInterp() local
2397 for (CeedInt node = 0; node < basis->P; node++) { in CeedBasisGetGrad() local
|
| /libCEED/backends/hip-ref/ |
| H A D | ceed-hip-ref-operator.c | 1929 CeedInt node = (s - 1) % elem_size, comp = (s - 1) / elem_size; in CeedOperatorLinearAssembleAddDiagonalAtPoints_Hip() local
|
| /libCEED/backends/cuda-ref/ |
| H A D | ceed-cuda-ref-operator.c | 1932 CeedInt node = (s - 1) % elem_size, comp = (s - 1) / elem_size; in CeedOperatorLinearAssembleAddDiagonalAtPoints_Cuda() local
|