From ccac957f1735354fc1ad06a6e329c1cdabbad969 Mon Sep 17 00:00:00 2001 From: Cedric Nugteren Date: Sat, 25 Feb 2017 13:02:15 +0100 Subject: [PATCH] Added documentation for the TRSV and TRSM routines --- CHANGELOG | 4 ++++ README.md | 4 +++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/CHANGELOG b/CHANGELOG index 20f17807..e8470206 100644 --- a/CHANGELOG +++ b/CHANGELOG @@ -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 diff --git a/README.md b/README.md index 35e79db8..13b67300 100644 --- a/README.md +++ b/README.md @@ -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)