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

Updated the documentation in light of the support for a reference CPU BLAS library

Browse source
This commit is contained in:
cnugteren 2016-04-03 16:07:25 -07:00
parent cf841d1840
commit c4ab9bda63
2 changed files with 11 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
CHANGELOG
View file

@ -2,6 +2,7 @@
Development version (next release)
- Added exports to be able to create a DLL on Windows (thanks to Marco Hutter)
- Made the library thread-safe
- Performance and correctness tests can now (on top of clBLAS) be performed against CPU BLAS libraries
- Fixed the use of events within the library
- Added level-1 routines:
* SNRM2/DNRM2/ScNRM2/DzNRM2

13
README.md
View file

@ -52,6 +52,14 @@ The pre-requisites for compilation of CLBlast are:
- Intel OpenCL
- Beignet
Furthermore, to build the (optional) correctness and performance tests, another BLAS library is needed to serve as a reference. This can be either:
* The OpenCL BLAS library [clBLAS](http://github.com/clMathLibraries/clBLAS (maintained by AMD)
* A regular CPU Netlib BLAS library, e.g.:
- OpenBLAS
- BLIS
- Accelerate
An example of an out-of-source build (starting from the root of the CLBlast folder):
mkdir build
@ -135,9 +143,9 @@ To make sure CLBlast is working correctly on your device (recommended), compile
cmake -DTESTS=ON ..
Afterwards, executables in the form of `clblast_test_xxxxx` are available, in which `xxxxx` is the name of a routine (e.g. `xgemm`). Note that CLBlast is tested against [clBLAS](http://github.com/clMathLibraries/clBLAS) for correctness. The library clBLAS is therefore required to be installed on your system for the CLBlast tests.
Afterwards, executables in the form of `clblast_test_xxxxx` are available, in which `xxxxx` is the name of a routine (e.g. `xgemm`). Note that CLBlast is best tested against [clBLAS](http://github.com/clMathLibraries/clBLAS) for correctness. If the library clBLAS is not installed on your system, it will use a regular CPU BLAS library to test against.
With the `-DTESTS=ON` flag, additional performance tests are compiled. These come in the form of client executables named `clblast_client_xxxxx`, in which `xxxxx` is the name of a routine (e.g. `xgemm`). These clients take a bunch of configuration options and directly run both CLBlast and clBLAS in a head-to-head performance test.
With the `-DTESTS=ON` flag, additional performance tests are compiled. These come in the form of client executables named `clblast_client_xxxxx`, in which `xxxxx` is the name of a routine (e.g. `xgemm`). These clients take a bunch of configuration options and directly run CLBlast in a head-to-head performance test against clBLAS and/or a CPU BLAS library.
Performance remarks
@ -249,4 +257,3 @@ To-do list before release of version 1.0
- Support all routines supported by clBLAS
- Allow the user control over events and synchronization
- Add half-precision routines (e.g. HGEMM)
- Enable correctness and performance testing against a CPU-based BLAS library