index
:
debian-clblast
debian/sid
upstream/latest
Debian package for CLBlast.
gspr@nonempty.org
summary
refs
log
tree
commit
diff
log msg
author
committer
range
Age
Commit message (
Collapse
)
Author
2016-03-28
Added preliminary support for the xNRM2 routines
Cedric Nugteren
2016-03-25
Added prototypes for ScNRM2/DzNRM2 routines
Cedric Nugteren
2016-03-25
Added prototypes for SNRM2/DNRM2 routines
Cedric Nugteren
2016-03-23
Fixed the C-api export to be able to properly build a DLL on Windows
Cedric Nugteren
2016-03-23
Fixed compilation of the two SGEMM samples
Cedric Nugteren
2016-03-19
Added __declspec(dllexport) to create a DLL on Windows
Cedric Nugteren
2016-03-14
Made the library thread-safe by guarding the kernel cache with a mutex
Cedric Nugteren
2016-03-13
Prepared the changelog for the next release
Cedric Nugteren
2016-03-13
Updated to version 0.6.0
Cedric Nugteren
2016-03-13
Updated Travis to reflect the changes in the Khronos website
Cedric Nugteren
2016-03-13
Updated the README file
Cedric Nugteren
2016-03-13
Updated Travis script to take into account the missing OpenCL packages
Cedric Nugteren
2016-03-13
Updated Travis script to fix the fglrx=2:8.960-0ubuntu1 issue
Cedric Nugteren
2016-03-12
Added tuning results for the newest xGER family kernels
Cedric Nugteren
2016-03-12
Added performance graphs for Intel Iris and Radeon M370X
Cedric Nugteren
2016-03-12
Added tuning results for the ARM Mali-T628 GPU
Cedric Nugteren
2016-03-06
Fixed a bug in the GER-family of routines due to incorrect division of the ↵
Cedric Nugteren
workgroup size
2016-03-06
Made testing against clBLAS in the client binaries truely optional (was ↵
Cedric Nugteren
partly implemented before)
2016-03-06
Adjusted the correctness-test error margins
Cedric Nugteren
2016-03-06
Merge branch 'rank2_update_routines' into development
Cedric Nugteren
2016-03-06
Added preliminary support for xHPR2 and xSPR2 routines
Cedric Nugteren
2016-03-02
Added preliminary support for xHER2 and xSYR2 routines
Cedric Nugteren
2016-02-28
Added tuning results for Intel Iris Pro and AMD R9 M370X
Cedric Nugteren
2016-02-28
Updated the changelog with newly supported level-2 routines
Cedric Nugteren
2016-02-28
Merge branch 'ger_routines' into development
Cedric Nugteren
2016-02-28
Fixed a couple of correctness bugs in the Xher kernels
Cedric Nugteren
2016-02-28
Added support for xHER, xHPR, xSYR, and xSPR routines
Cedric Nugteren
2016-02-28
Fixed a compilation issue under AppleClang
Cedric Nugteren
2016-02-20
Set a proper default precision for the CLBlast clients
Cedric Nugteren
2016-02-20
Added support for xGERU and xGERC routines
Cedric Nugteren
2016-02-20
Added XGER routine, kernel, and tuner
Cedric Nugteren
2016-02-10
Updated the changelog
Cedric Nugteren
2016-02-08
Fixed warnings under MSVC
CNugteren
2016-02-08
Separated the GEMM kernel in two parts to reduce string length for MSVC
Cedric Nugteren
2016-02-08
Split-up the XGEMV kernel in two parts
Cedric Nugteren
2016-02-07
Added tuning parameters for various devices using the new database script
Cedric Nugteren
2016-02-07
Various fixes to the database script
Cedric Nugteren
2016-02-07
Added dictionary with short and long OpenCL vendor names to fix issues with ↵
Cedric Nugteren
Intel having multiple names
2016-02-07
Made the tuning database an optional external download
Cedric Nugteren
2016-02-06
Made the database script compatible with Python 3
CNugteren
2016-02-06
Reduced the maximum workgroup-size for GEMV kernels further
CNugteren
2016-02-06
Changed the order of tuners in the alltuners target
Cedric Nugteren
2016-02-06
Reduced unrolling factor in xgemv kernel to reduce compilation times
CNugteren
2016-02-06
Fixed a linker error in the performance client under GCC
CNugteren
2016-01-30
Fixes for compilation under Visual Studio
CNugteren
2016-01-30
Prepared for MSVC support
Cedric Nugteren
2016-01-30
Fixed a bug in the graph scripts (thanks to Victor Pakhomov)
Cedric Nugteren
2016-01-30
Updated to version 4.0 of the CLCudaAPI header
Cedric Nugteren
2016-01-30
Merge branch 'tuning_database' into development
Cedric Nugteren
is merge is necessary,
2016-01-30
Added first auto-generated database headers from the Python database; only ↵
Cedric Nugteren
K40 and Iris supported now
[next]