Letter from the Editor
Another Year, Another Award for oneAPI
On behalf of the staff at The Parallel Universe, I’d like to wish all our readers a Happy New Year!
I’ll open this issue by congratulating the Intel® Software Developer Toolkits team for winning the 2023 HPCwire Readers’ Choice Award for Best HPC Programming Tool or Technology. This is one of many such awards that either the oneAPI specification or the Intel® oneAPI toolkits have won since they were launched. Our editor emeritus, James Reinders, gives his perspectives in Taking Stock of How Far We’ve Come: Intel® Developer Tools and oneAPI. You may recall in The Parallel Universe (issue 54) that I mentioned the launch of the Unified Acceleration Foundation. In this issue, Rod Burns (VP Ecosystem, Codeplay Software and UXL Foundation Steering Committee Chair) goes into more detail about what this means to oneAPI in Unified Acceleration (UXL) Foundation.
For this issue’s feature article, I invited Numenta to describe how their NuPIC* platform takes advantage of Intel® AMX to do AI inference: Ushering in a New Era of Accelerated AI on Intel® CPUs. Later in this issue, Using Intel’s New Built-in AI Acceleration Engines goes into more detail about how to use Intel AMX and Intel® XMS to improve AI performance.
This is followed by three articles covering different aspects of AI, including trusted AI and anomaly detection: Trusted TorchServe* Using BigDL Privacy Preserving Machine Learning, A Quantization Framework for Bayesian Deep Learning, and State-of-the-Art Visual Quality Inspection.
We close this issue with an article on the Spack*, the Supercomputer PACKage manager from Lawrence Livermore National Laboratory. Specifically, the article covers the Distribution of Intel® Optimized HPC Binaries Using Spack*. I’ll also point out that Spack won the 2023 HPCwire Editors’ Choice Award for Best HPC Programming Tool or Technology.
Finally, let’s welcome back James Reinders as editor for The Parallel Universe. He has kindly agreed to fill in for the next issue while I’m on sabbatical. This will be his first turn at the magazine’s helm since 2016.
As always, don’t forget to check out Tech.Decoded for more information on Intel® solutions for AI and data science, code modernization, visual computing, data center and cloud computing, systems and IoT development, and heterogeneous parallel programming with oneAPI.
Henry A. Gabb
January 2024
Henry A. Gabb, Senior Principal Engineer at Intel Corporation, is a longtime high-performance and parallel computing practitioner who has published numerous articles on parallel programming. He was editor/coauthor of “Developing Multithreaded Applications: A Platform Consistent Approach” and program manager of the Intel/Microsoft Universal Parallel Computing Research Centers.