ArrayFire recently gave two webinar presentations to OpenCL developers as part of a joint webinar series with AMD. Due to popular demand for the first webinar, we ended up presenting a second! In case you missed it, here’s a recording of the webinar complete with the presentation and an informative Q&A session: http://bit.ly/SkzIJs
This webinar focused on enhancing productivity by using existing OpenCL libraries while achieving a high level of performance and maximizing system utilization. We demonstrated how our ArrayFire software library offers simple GPU programming with the benefit of awesome performance. In the webinar we showed how to use several image processing and computer vision building blocks in less than 3 lines of code. The immediate takeaway message of these examples is that ArrayFire offers a large number of highly optimized building blocks. And because ArrayFire fully supports OpenCL, that high level of performance is portable to any OpenCL supported device. This means you only have to write the code once and then you can run it everywhere OpenCL is supported.
The Q&A session of the webinar had lots of fantastic questions! Many of them focused on performance and capabilities of ArrayFire and OpenCL. The least technical question asked how difficult it would be for a life-science PhD to enter the GPU arena (if it at all feasible). As a person who worked in social network analysis for several years, I responded saying that it is very feasible for a life-science student or any other student to do GPU computing – high level or low level. The high level programming includes the use of existing GPU libraries, including ArrayFire. Typically this requires domain expertise. The low level programming would be the creation of GPU libraries. The latter requires more than just domain expertise, it requires computational expertise. As the number of applications benefiting from the usage of GPUs increases, it is crucial that domain experts and computational experts meet up: 1) Find the right set of building blocks needed by the community, and 2) implement those building blocks as best as possible with an understanding of the real-world requirement of the applications.
At ArrayFire, we are constantly on the lookout for people who: 1) know what challenging problems are out there, and 2) have the skills to solve those problems. This allows us to greatly extend the capabilities of our software library.
We hope you enjoyed the webinar. Contact us at sales@arrayfire.com with any questions, we’re here to help!