As compute technology evolves at an increasingly accelerated pace, so, too, does the world’s reliance on compute hardware that is diverse enough to handle expansive data-centric workloads.
According to Bill Savage, vice president and general manager of Compute Performance and Developer Products at Intel, it’s the precise focus of oneAPI, an Intel-led initiative that simplifies the programming of diverse architectures—CPUs, GPUs, FPGAs, AI accelerators—to meet customer workload needs.
Tech.Decoded recently sat down with Bill to discuss the new initiative in-depth, including
- What it is and what it’s comprised of (including the new common source language called Data Parallel C++)
- Why a unified programming model will help developers
- How to try out the beta software—tools, libraries, frameworks, languages—both in the cloud and on your system
- And a lot more
If you’ve got 10 minutes to spare, this video would be a great way to spend it (particularly since it’s under 7 minutes long).
Watch.
Get Started Now
- Learn more about Intel® oneAPI Beta Products—Visit the Beta website to learn about this initiative, including downloading free software toolkits like the essential Intel® oneAPI Base Toolkit.
- Try your code in the Intel® DevCloud—Sign up to develop, test, and run your solution in this free development sandbox with access to the latest Intel® hardware and oneAPI software. No downloads. No configuration steps. No installations.