We are pleased to announce a new release of the ArrayFire library, v3.9.0. This release makes it easier than ever to target new devices without sacrificing performance. This post describes four of these new features, including: oneAPI Backend This release is the first time since v3.0 that introduces a new backend. The new backend is built with the oneAPI specification on top of the SYCL language. oneAPI is an open specification providing a full framework for high-performance computing applications without vendor lock-in. While this has been possible with OpenCL, the oneAPI specification includes libraries like BLAS and FFT significantly reducing the burden on the developers to maintain math functions and increasing the performance of these common operations. Here is a …
ArrayFire v3.8.3 Release
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. Notable improvements include: Additionally, several bugs have been patched. Visit our GitHub project for more information on the ArrayFire Roadmap. 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 expert engineers to help you take your project to the next level.
Exciting Updates at ArrayFire
Today, we are pleased to announce that our open-source team has joined Intel to focus on building an open future for accelerated computing with oneAPI. At Intel, we will build towards a vision that flourishes at scale, serves domain professionals worldwide, and participates in the exciting oneAPI ecosystem of open-source technical computing. Read more about this on the Intel blog: ArrayFire Team joins Intel for oneAPI. The ArrayFire open-source project will continue to follow The ArrayFire Mission. It will be governed by its maintainers sponsored by a variety of companies, including Google, Twitter, VoltronData, and now Intel. ArrayFire’s support for CUDA, OpenCL, and x86 will continue unchanged. We are also excited to announce that our consulting and training services team …
ArrayFire v3.8.2 Release
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 …
Call for ArrayFire User Stories
There’s a sweet ArrayFire T-Shirt for anyone that submits a write-up of your success with the ArrayFire library. We’ve been working on a new website for our community, and we’d love to hear what you’re doing with the library. Also, your stories are important to the ArrayFire open source project in that we share them with project funders to motivate their continued investment in our community and library development. Please take some time to help us by sharing your success. We recognize that most people are not constantly focused on performance improvement. Most of you have ArrayFire in your toolbelt to accelerate code when your application demands excellent performance. If you have found it helpful in a project, please consider …
ArrayFire Updates to Kickoff 2022
We are excited to report a great kickoff to 2022 with this quick list of notable ArrayFire developments underway. ArrayFire v3.8.1 Release We recently announced ArrayFire v3.8.1, available on Github (source) and on our download page (binaries). Flashlight Project for Machine Learning The open source Flashlight project from Facebook is growing rapidly. In a single repository, Flashlight provides apps for research across multiple domains: Automatic speech recognition Image classification Object detection Language modeling Flashlight builds atop ArrayFire as the tensor library for GPU and CPU training. Parallel Universe Magazine ArrayFire was recently featured in Intel’s Parallel Universe Magazine. Check out the article entitled, “ArrayFire Interoperability with oneAPI, Libraries, and OpenCL Code.” This article explains how, with minor code changes, whole OpenCL libraries …
Bringing Together the GPU Computing Ecosystem for Python
To date, we have not done a lot for the Python ecosystem. A few months ago, we decided it was time to change that. Like NVIDIA said in this post, the current slate of GPU tools available to Python developers is scattered. With some attention to community building, perhaps we can build something better — together. NVIDIA spoke some about its plans to help cleanup the ecosystem. We’re onboard with that mentality and have two ways we propose to contribute: We’re working on a survey paper that assesses the state of the ecosystem. What technical computing things can you do with each package? What benchmarks result from the packages on real Python user code? What plans does each group have …
ArrayFire v3.8 Release
We are excited to share the v3.8 release of ArrayFire! ArrayFire is used in commercial, academic, and government projects around the world, solving some of the toughest computing problems in the most innovative projects. It is well-tested and amazingly fast! In this post, we share some of the major features added to ArrayFire in its 3.8 feature release. The binaries and source code can be downloaded from these locations: Official installers GitHub repository Official APT repository Starting with this release, we will provide Ubuntu packages form our APT repository. To install our packages add our apt repository with the below commands. At this moment we are only supporting bionic(18.04) and focal(20.04). apt-key adv –fetch-key https://repo.arrayfire.com/GPG-PUB-KEY-ARRAYFIRE-2020.PUB echo “deb [arch=amd64] https://repo.arrayfire.com/ubuntu $(lsb_release …
ArrayFire v3.7.x Release
With the release of the 3.7.2 patch release, we wanted to discuss some of the major features added to ArrayFire. The binaries have been available for a few weeks but we wanted to discuss the changes here. It can be downloaded from these locations: Official installers GitHub repository This version of ArrayFire is better than ever! We have added many new features that expand the capabilities of ArrayFire while improving its performance and flexibility. Some of the new features include: 16-bit floating point support Neural network compatible convolution and gradient functions Reduce-by-key Confidence Connected Components Array padding functions Support for sparse-sparse arithmetic operations Pseudo-inverse, meanvar(), rqsrt() and much more! We have also spent a significant amount of effort exposing the …
ArrayFire v3.6 Release
Today we are pleased to announce the release of ArrayFire v3.6. It can be downloaded from these locations: Official installers GitHub repository This latest version of ArrayFire is better than ever! We added several new features that improve the performance and usability of the ArrayFire library. The main features are: Support for batched matrix multiply Added the topk function Added the anisotropic diffusion filter We have also spent a significant amount of effort improving the internals of the library. The build system is significantly improved and organized. Batched Matrix Multiplication The new batch matmul allows you to perform several matrix multiplication operations in one call of matmul. You might want to call this function if you are performing multiple smaller matrix multiplication operations. Here …