haraldwolff/CLBlast
1
0
Fork 0
mirror of https://github.com/CNugteren/CLBlast.git synced 2024-07-04 21:36:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Added documentation for the TRSV and TRSM routines

Browse source
This commit is contained in:
Cedric Nugteren 2017-02-25 13:02:15 +01:00
parent 492ee3d0a5
commit ccac957f17
2 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
CHANGELOG
View file

@ -7,6 +7,10 @@ Development version (next release)
- Tests now also exit with an error code when OpenCL errors or compilation errors occur
- Various minor fixes and enhancements
- Added tuned parameters for various devices (see README)
- Added level-2 routines:
* STRSV/DTRSV/CTRSV/ZTRSV (experimental, un-optimized)
- Added level-3 routines:
* STRSM/DTRSM/CTRSM/ZTRSM (experimental, un-optimized)
Version 0.10.0
- Updated to version 8.0 of the CLCudaAPI C++11 OpenCL header

4
README.md
View file

@ -254,6 +254,7 @@ CLBlast supports almost all the Netlib BLAS routines plus a couple of extra non-
| xSPR | ✔ | ✔ | - | - | ✔ |
| xSYR2 | ✔ | ✔ | - | - | ✔ |
| xSPR2 | ✔ | ✔ | - | - | ✔ |
| xTRSV | ✔ | ✔ | ✔ | ✔ | ✔ | (experimental, un-optimized)
| Level-3 | S | D | C | Z | H |
| ---------|---|---|---|---|---|
@ -265,6 +266,7 @@ CLBlast supports almost all the Netlib BLAS routines plus a couple of extra non-
| xSYR2K | ✔ | ✔ | ✔ | ✔ | ✔ |
| xHER2K | - | - | ✔ | ✔ | - |
| xTRMM | ✔ | ✔ | ✔ | ✔ | ✔ |
| xTRSM | ✔ | ✔ | ✔ | ✔ | ✔ | (experimental, un-optimized)
In addition, some extra non-BLAS routines are also supported by CLBlast, classified as level-X. They are experimental and should be used with care:
@ -275,7 +277,7 @@ In addition, some extra non-BLAS routines are also supported by CLBlast, classif
| IxMIN | ✔ | ✔ | ✔ | ✔ | ✔ |
| xOMATCOPY | ✔ | ✔ | ✔ | ✔ | ✔ |
Some less commonly used BLAS routines are not yet supported yet by CLBlast. They are xROTG, xROTMG, xROT, xROTM, xTRSV, xTBSV, xTPSV, and xTRSM.
Some less commonly used BLAS routines are not yet supported yet by CLBlast. They are xROTG, xROTMG, xROT, xROTM, xTBSV, and xTPSV.
Half precision (fp16)