e0c06a9ac1
CMake: Fix for older versions of cmake ( #536 )
2024-04-02 06:24:30 +00:00
e320c204b1
[CLIENTS]fix cuda_runtime not found and assert len(MARKERS) >= len(y_keys[index]) ( #535 )
...
fix cuda_runtime not found and assert len(MARKERS) >= len(y_keys[index])
2024-03-13 19:25:00 +00:00
b35737b066
Supply formatting string to fprintf ( #530 )
...
This restores compatibility with -Werror=format-security.
2024-02-11 13:18:20 +01:00
faa2109707
Bump to version 1.6.2 ( #527 )
2024-02-09 21:38:37 +01:00
6e2ab6ee96
Add tuning results for 5 devices ( #526 )
2024-02-08 20:33:33 +01:00
32ad2a67ae
Add openblas PATH_SUFFIX to FindCBLAS ( #525 )
...
This is needed on e.g. Fedora to find openblas.
2024-02-07 19:11:10 +00:00
162783a414
Python module mutli-platform setup ( #519 )
...
* Change to pyproject.toml file
* Switch to cmake for building the extension
* Update readme
* Update CHANGELOG
* Add hint fot CLBlast discovery
* Update README about detecting the library
* Switch to scikit-build-core for using CMake
2024-01-21 10:58:38 +01:00
9535155ad8
Add tuning results for 4 devices ( #518 )
2023-11-12 20:47:00 +01:00
564629cafd
Fix floating point conversion in Python wrapper ( #515 )
...
* Generator.py: use LF ending when run from windows
* Convert scalar input to float16 in cython
* Index buffer as uints in cython wrapper
* Update CHANGELOG and bump ver. 1.4.0
2023-11-10 20:33:21 +01:00
bcd294a93a
Compress tar files in release.yml action ( #508 )
2023-10-02 07:38:13 +00:00
42264dab42
CMake: Install pkgconfig file with mingw toolchain ( #506 )
2023-09-25 12:18:24 +02:00
60e7574113
CMake: Fix DLL install directory in mingw ( #505 )
...
This installs DLL in 'bin' directory instead of 'lib' by default.
In mingw environment, all DLLs and EXEs are installed in 'bin'
and static & import libraries are installed in 'lib' directory.
This does not affect other environment because the 'RUNTIME'
and 'LIBRARY' targets are automatically set by cmake. See
https://cmake.org/cmake/help/latest/command/install.html
Signed-off-by: Biswapriyo Nath <nathbappai@gmail.com>
2023-09-25 08:57:12 +00:00
29e13d5a33
Add tuning results for 5 devices ( #503 )
2023-09-14 21:14:26 +02:00
afb3d8a604
Fix preprocessor and extend test coverage ( #498 )
...
* Improve coverage of pre-processor test
* Make the preprocessor handle the not-defined() construct
* Update the changelog
2023-08-07 20:32:30 +02:00
e3ce21bb93
Bump to v1.6.1 ( #496 )
2023-07-09 11:24:24 +02:00
6762e8480c
Fix a multithreading bug related to storing objects in the cache ( #495 )
2023-07-08 20:08:00 +02:00
83bd474eda
Add tuning results for 7 devices ( #494 )
2023-07-04 21:09:12 +02:00
af667c45fe
Add 6 tuning results ( #493 )
...
* Add tuning results for 6 devices
* Add GPU generation names for NVIDIA and AMD GPUs in the documentation
2023-06-24 12:10:08 +02:00
28a61c53a6
Fix pointer error in `pyclblast` on ARM ( #490 )
...
* Fix pointer error in `pyclblast` on ARM
Use `ptrdiff_t` instead of `size_t` for pointers.
Fix error in `setup.py`
* Fix ARM pointer error in `pyclblast` generator
Update CHANGELOG file
2023-06-16 09:45:16 +00:00
2b98c6a28c
Add tuning results for more devices ( #488 )
...
Add tuning results for 13 devices
2023-06-06 21:31:35 +02:00
ec733402a8
Add tuning results for Radeon RX 6700 XT ( #484 )
2023-06-01 21:51:33 +02:00
05a26111f7
Add tuning results for 14 devices ( #483 )
2023-05-31 21:06:52 +02:00
8d1cbde036
Fix folder name of Windows release ( #482 )
2023-05-26 21:21:23 +02:00
1b66a1149e
Use NMake for Windows builds ( #481 )
2023-05-26 20:11:44 +02:00
26ceab814f
Update README.md with a useful link ( #476 )
...
* Update README.md with a useful link
* Update README.md
Co-authored-by: Cedric Nugteren <web@cedricnugteren.nl>
---------
Co-authored-by: Cedric Nugteren <web@cedricnugteren.nl>
2023-05-23 09:09:21 +02:00
107beaac17
Fix issues in Windows release script ( #477 )
2023-05-22 21:05:36 +02:00
b0b302889c
Update to version 1.6.0 ( #475 )
2023-05-21 20:51:05 +02:00
036684204e
Github Actions Windows builds with tests ( #472 )
...
* Set CMake CMP0074 policy
* Attempt to use pre-compiled OpenBLAS on Windows CI
* Fix an issue and add some debugging
* Improve FindCBLAS for OpenBLAS on Windows
2023-05-21 17:07:31 +02:00
63eb127bad
Intel HD Graphics 770 and AMD RX 6600 XT tuning results ( #474 )
...
* Add tuning results for AMD Radeon RX 6600 XT
* Add tuning results for Intel HD Graphics 770
* Update list of tuned devices
2023-05-21 14:25:15 +02:00
0832ed6a16
Documentation: tuning.md: Add a useful link ( #473 )
2023-05-21 08:07:43 +00:00
ce5e446fbe
Actualize the README and remove the old ROADMAP ( #471 )
2023-05-18 18:10:12 +02:00
db3bd0a32e
Add Windows builds to Github Actions and fix Windows compilation issue ( #470 )
...
* Add Windows builds to Github Actions CI
* Fix failing Windows builds
2023-05-18 16:58:31 +02:00
e73f0b5131
Add Github Actions release script ( #469 )
...
* Add first version of release script
* Several fixes for the Windows release job
* Install OpenCL for Windows release
* Fix issue with environment variable
* Set OpenCL root
* Fix zipping in Windows build
2023-05-17 17:10:51 +02:00
7a3ef92ff2
Add 3 sets of tuning results: RX 5700 XT, 2080 Ti, and 3090 ( #468 )
...
* Add tuning results for AMD Radeon RX 5700 XT
* Add tuning results for NVIDIA GeForce RTX 2080 Ti
* Add tuning results for NVIDIA GeForce RTX 3090
2023-05-17 10:31:47 +02:00
221121b840
Add Github Actions CI ( #464 )
...
This replaces the old Travis CI builds with Github Actions that test on both Ubuntu and MacOS, with both Clang and GCC. The builds on macOS also run the tests and some other programs, on Ubuntu OpenCL is not working at the moment. Because these tests use new/different compilers, I fixed a few warnings and errors along the way.
2023-05-14 11:25:15 +02:00
8d2f3540e9
Merge pull request #465 from CNugteren/fix_override_parameters_test
...
Fix compilation issue in override parameters test
2023-05-11 08:49:26 +02:00
6e6efb72be
Fix compilation issue in override parameters test
2023-05-10 21:31:33 +02:00
3baf823575
Fixes an issue under Android when the driver was already unloaded ( #462 )
2023-05-10 17:10:17 +02:00
d94d086d6f
TBMV/TPMV/TRSV: Use the minimum x buffer size for copying to a temp buffer ( #461 )
2023-05-10 12:48:25 +02:00
4f24d92730
TRMV: Use the minimum x buffer size for copying to a temp buffer ( #458 )
2023-05-07 20:03:16 +02:00
3d0c227fa5
AMAX/AMIN integer testing and bug fixes ( #457 )
...
* Fixed a bug in XAMAX/XMIN routines that caused the increment and offset to be included in the result
* Perform proper integer-output testing in XAMAX tests
* A few changes towards getting it ready for a PR
* Also fix compilation for clBLAS and cuBLAS references
* Fix a bug that would only use the real part of complex numbers in the amax/amin routines
* A few small fixes related to the AMAX tests
2023-05-07 20:02:52 +02:00
1573f7d304
Merge pull request #455 from CNugteren/fix_gemm_documentation_bug
...
Fix documentation bug w.r.t. ld values and matrix layout
2023-03-25 21:25:41 +01:00
9eca896b05
Fix documentation bug w.r.t. ld values and matrix layout
2023-03-25 20:24:40 +01:00
ab5092dd26
Merge pull request #452 from CNugteren/add_tuning_results_adreno
...
Add tuning results for 4 devies
2023-01-22 15:52:49 +01:00
c9856758b3
Add tuning results for Intel FPGA emulation device
2023-01-21 21:13:49 +01:00
f4a14daf8d
Add tuning results for Radeon Pro 450
2023-01-21 21:11:38 +01:00
3ca1f5176e
Add tuning results for Adreno 740
2023-01-21 21:09:09 +01:00
d11b0c8b01
Add tuning results for Adreno 730
2023-01-21 20:33:49 +01:00
e72f87ae5e
Merge pull request #451 from CodeLinaro/master
...
CLBlast modifications to address Qualcomm Adreno performance
2023-01-21 20:28:32 +01:00
73f49e9b3d
Updated according to feedback from CNugteren
2023-01-17 08:35:29 -08:00
Brian Moore
engineer1109
gspr
Cedric Nugteren
Karol Herbst
vathomass
Lawrence Angrave
Biswapriyo Nath
Yubraj Bhoi
Mikko Vedru
Angus, Alexander