Exciting Updates at ArrayFire

John Melonakos Announcements, ArrayFire Leave a Comment

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

Umar Arshad Announcements, ArrayFire Leave a Comment

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

John Melonakos Announcements, Case Studies Leave a Comment

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

John Melonakos Announcements Leave a Comment

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

John Melonakos Announcements, ArrayFire, Computing Trends, CUDA, Open Source, Python Leave a Comment

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

John Melonakos Announcements, ArrayFire Leave a Comment

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

Stefan Yurkevitch Announcements, ArrayFire Leave a Comment

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

Umar Arshad Announcements, ArrayFire 3 Comments

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 …

ArrayFire v3.5.1 Release

Miguel Lloreda Announcements, ArrayFire 1 Comment

We are excited to announce ArrayFire v3.5.1! This release focuses on fixing bugs and improving performance. Here are the improvements we think are most important: Performance improvements We’ve improved element-wise operation performance for the CPU backend. The af::regions() function has been modified to leverage texture memory, improving its performance. Our JIT engine has been further optimized to boost performance. Bug fixes We’ve squashed a long standing bug in the CUDA backend responsible for breaking whenever the second, third, or fourth dimensions were large enough to exceed limits imposed by the CUDA runtime. The previous implementation of af::mean() suffered from overflows when the summation of the values lied outside the range of the backing data type. New kernels for each of …

ArrayFire v3.5 Official Release

Umar Arshad Announcements, ArrayFire, CUDA, Open Source, OpenCL 1 Comment

Today we are pleased to announce the release of ArrayFire v3.5, our open source library of parallel computing functions supporting CUDA, OpenCL, and CPU devices. This new version of ArrayFire improves features and performance for applications in machine learning, computer vision, signal processing, statistics, finance, and more. This release focuses on thread-safety, support for simple sparse-dense arithmetic operations, canny edge detector function, and a genetic algorithm example. A complete list of ArrayFire v3.5 updates and new features are found in the product Release Notes. Thread Safety ArrayFire now supports threading programming models. This is not intended to improve the performance since most of the parallelism is happening on the device, but it does allow you to use multiple devices in …