AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[HIPIFY][SPARSE] Preconditioners Reference: Tridiagonal and Pentadiagonal solves

Browse Source 
+ Tridiagonal Solve, Batched Tridiagonal and Pentadiagonal Solve
+ cuSPARSE_07 test
+ update CUSPARSE_API_supported_by_HIP.md
This commit is contained in:
Evgeny Mankov
2018-11-29 18:46:51 +03:00
parent 7317dce7bd
commit e8054fe485
3 changed files with 708 additions and 271 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hipamd/docs/markdown/CUSPARSE_API_supported_by_HIP.md
+67
View File
@@ -393,3 +393,70 @@
|`cusparseCbsrilu02` | |
|`cusparseZbsrilu02` | |
|`cusparseXbsrilu02_zeroPivot` | |
## ***7.3. Tridiagonal Solve***
| **CUDA** | **HIP** |
|-----------------------------------------------------------|-------------------------------------------------|
|`cusparseSgtsv` | |
|`cusparseDgtsv` | |
|`cusparseCgtsv` | |
|`cusparseZgtsv` | |
|`cusparseSgtsv_nopivot` | |
|`cusparseDgtsv_nopivot` | |
|`cusparseCgtsv_nopivot` | |
|`cusparseZgtsv_nopivot` | |
|`cusparseSgtsv2_bufferSizeExt` | |
|`cusparseDgtsv2_bufferSizeExt` | |
|`cusparseCgtsv2_bufferSizeExt` | |
|`cusparseZgtsv2_bufferSizeExt` | |
|`cusparseSgtsv2` | |
|`cusparseDgtsv2` | |
|`cusparseCgtsv2` | |
|`cusparseZgtsv2` | |
|`cusparseSgtsv2_nopivot_bufferSizeExt` | |
|`cusparseDgtsv2_nopivot_bufferSizeExt` | |
|`cusparseCgtsv2_nopivot_bufferSizeExt` | |
|`cusparseZgtsv2_nopivot_bufferSizeExt` | |
|`cusparseSgtsv2_nopivot` | |
|`cusparseDgtsv2_nopivot` | |
|`cusparseCgtsv2_nopivot` | |
|`cusparseZgtsv2_nopivot` | |
## ***7.4. Batched Tridiagonal Solve***
| **CUDA** | **HIP** |
|-----------------------------------------------------------|-------------------------------------------------|
|`cusparseSgtsvStridedBatch` | |
|`cusparseDgtsvStridedBatch` | |
|`cusparseCgtsvStridedBatch` | |
|`cusparseZgtsvStridedBatch` | |
|`cusparseSgtsv2StridedBatch_bufferSizeExt` | |
|`cusparseDgtsv2StridedBatch_bufferSizeExt` | |
|`cusparseCgtsv2StridedBatch_bufferSizeExt` | |
|`cusparseZgtsv2StridedBatch_bufferSizeExt` | |
|`cusparseSgtsv2StridedBatch` | |
|`cusparseDgtsv2StridedBatch` | |
|`cusparseCgtsv2StridedBatch` | |
|`cusparseZgtsv2StridedBatch` | |
|`cusparseSgtsvInterleavedBatch_bufferSizeExt` | |
|`cusparseDgtsvInterleavedBatch_bufferSizeExt` | |
|`cusparseCgtsvInterleavedBatch_bufferSizeExt` | |
|`cusparseZgtsvInterleavedBatch_bufferSizeExt` | |
|`cusparseSgtsvInterleavedBatch` | |
|`cusparseDgtsvInterleavedBatch` | |
|`cusparseCgtsvInterleavedBatch` | |
|`cusparseZgtsvInterleavedBatch` | |
## ***7.5. Batched Pentadiagonal Solve***
| **CUDA** | **HIP** |
|-----------------------------------------------------------|-------------------------------------------------|
|`cusparseSgpsvInterleavedBatch_bufferSizeExt` | |
|`cusparseDgpsvInterleavedBatch_bufferSizeExt` | |
|`cusparseCgpsvInterleavedBatch_bufferSizeExt` | |
|`cusparseZgpsvInterleavedBatch_bufferSizeExt` | |
|`cusparseSgpsvInterleavedBatch` | |
|`cusparseDgpsvInterleavedBatch` | |
|`cusparseCgpsvInterleavedBatch` | |
|`cusparseZgpsvInterleavedBatch` | |