Letter from the Editor
You'll notice a new editor for The Parallel Universe. Before I delve into what's in this issue, I would like to extend my heartfelt gratitude to Henry Gabb for his exceptional leadership as editor of The Parallel Universe, starting with issue 27 in 2016. With his recent retirement from Intel, I am honored to take on this role. Henry's dedication to high-performance and parallel computing has not only enriched the magazine but also inspired countless practitioners in the field. I deeply appreciate his invaluable contributions, including his insightful publications and collaborative efforts in advancing parallel programming. Thank you, Henry, for setting such a high standard and for your unwavering support. I will work hard to uphold your impeccable standards for this publication.
Now, I'm excited to introduce seven insightful articles that explore the latest advancements in AI, data science, and high-performance computing.
In our lead article, "Accelerate Quantitative Finance with SYCL* and Intel® oneAPI Math Kernel Library (oneMKL)," Andrey Fedorov and Robert Mueller-Albrecht discuss how the financial markets rely on mathematical models using the Greeks as risk parameters. They also show us how financial engineering combines the mathematical theory of quantitative finance with computational simulations to make price, trade, hedge, and other investment decisions.
As heterogeneous platforms become more prevalent, the Unified Acceleration Foundation (UXL Foundation*) is creating an open standard software ecosystem for programming accelerators, focusing on vendor- and platform-agnostic solutions. The article, "Portable Data Parallel Extensions for Python*: Accelerate Computations by Taking Advantage of GPUs," by Nikita Grigorian and Oleksandr Pavlyk, discusses extending UXL Foundation to Python, enabling users to develop portable data-parallel native extensions and compute across various vendor accelerators within the same session.
Moving on to our next two articles, Bob Chesebrough collaborated with clients focused on time series analysis, prompting him to explore both current and traditional methods of prediction and clustering. His investigation is divided into two articles: "Cluster Time Series Data with PCA and DBSCAN" and "Implement a Transformer-Based Time Series Predictor" (with coauthor Jack Erickson).
Zhenming Wang and team provide a two-part look into the JAX framework and OpenXLA*, demonstrating how Python programs use these technologies for efficiency in "JAX Plus OpenXLA Run Process and Underlying Logic," Part 1 and Part 2.
In a milestone for the developer community, Fujitsu* has successfully ported the Intel® oneAPI Data Analytics Library (oneDAL) to Arm* architecture. Details can be found in the Fujitsu Tech Blog Developer Story: How We Ported oneDAL on Arm for Accelerated AI Workloads for Fujitsu-Monaka. While the article is not featured in this issue, we encourage you to take a look at the performance gains that they achieved across various machine learning algorithms.
I hope these articles inspire you to explore new techniques and tools in your own work. 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 Intel® AI Tools.
If you have topics you'd like to see in future issues of The Parallel Universe, reach out to me on LinkedIn.
Susan E. Kahler
April 2025
Susan E. Kahler is a developer advocate for AI and machine learning products and solutions at Intel Corporation, where she drives innovative solutions in the technology industry. As Intel’s representative on the PyTorch* Foundation Marketing Committee and a member of The Linux Foundation* AI & Data Foundation Outreach Committee, she influences community engagement and collaboration. Holding a PhD in Human Factors and Ergonomics, Susan has used mathematical algorithms to analyze human learning models. Her diverse background includes roles in user-centered design, product management, customer insights, and operational risk, establishing her as a credible expert in enhancing user experiences and advancing technology.