We are pleased to announce another patch release of the ArrayFire library. This release like all patch releases concentrates on bug fixes and minor performance improvements.
You can access the new version here: installers and source code.
CUDA Version Updates
We have also improved the compatibility of the ArrayFire library to the latest CUDA toolkits and improved the build process and added additional build configurations so that you can customize the library for your specific application.
Better Linux Experience
We have updated the Debian and Ubuntu installers to reduce the binary size and reduced the setup process for the users. You can now download the ArrayFire library using the following commands on a Debian/Ubuntu system.
apt-key adv --fetch-key https://repo.arrayfire.com/GPG-PUB-KEY-ARRAYFIRE-2020.PUB
echo "deb [arch=amd64] https://repo.arrayfire.com/debian all main" | tee /etc/apt/sources.list.d/arrayfire.list
apt install arrayfireImproved JIT Performance
With our collaboration with Facebook’s Flashlight project, we incorporated a new optimization to the ArrayFire library that could improve the performance of your application under certain circumstances. The optimization allows ArrayFire to remove redundant casting operations from a JIT tree. This potentially reduces the number of kernels ArrayFire has to launch for certain operations.
It has never been easier to use the ArrayFire library. With your support, we continue to push the limits of all the accelerators coming to the market. Is there a project where you think we can help?
Please reach out to our team of expert engineers to help you take your project to the next level.
Comments 2
Hi,
I wanted to ask you what the activity of arrayfire looks like. How often do you plan to release new versions? Are major releases coming up?
This is important to know for my job to determine whether we want to keep using arrayfire or move to an alternative.
Best wishes
Cihad
Hi Cihad,
We are actively working on ArrayFire and expect a new release early next year. This major release will provide an additional oneAPI backend to ArrayFire, complementing the existing CUDA, OpenCL, and CPU backends.
You can follow along with our activity on Github, and you can check out the minutes from the community maintainer’s meetings which contain notes about future releases in these links:
* https://github.com/arrayfire/arrayfire
* https://github.com/arrayfire/arrayfire/wiki/Meetings-of-the-Maintainers
You can continue to rely on ArrayFire, and with the news we shared recently about joining Intel, we are developing the library more rapidly than ever before. https://arrayfire.com/blog/exciting-updates-at-arrayfire/
Thank you!
John