The Parallel Universe Magazine
Intel’s quarterly magazine for software innovation helps you take your software development into the future with the latest tools, tips, and training to expand your expertise.
Issue 53, July 2023
Feature: Beyond Direct Memory Access—Reducing the Data Center Tax with Intel® Data Streaming Accelerator (Intel® DSA)
This issue takes a look at several topics including generative AI, and provides insights into training and optimizing large language models.
Download Issue 53 to find:
- A featured article on how to take advantage of on-chip acceleration for data transformation
- Articles on the figurative “moat” around AI, building customized, high-performing chatbots, and optimizing open source large-language models
- Details on the process of aligning SYCL* with future C++ language concepts
- An exploration into performance tuning on the Intel® Xeon® CPU Max Series
Contents
Take advantage of on-chip acceleration for data transformation in 4th generation Intel® Xeon® Scalable processors with a high-level overview of Intel® DSA and its fundamental uses. Learn about several guidelines to make the most out of this accelerator.
Take a look into the future of standards-based parallel programming. In a follow-up to Issue 51’s discussion of SYCL and ISO C++, this article describes the process of aligning SYCL with future C++ language concepts.
Minimize the risks of generative AI. Huma Abidi and Haihao Shen directly address the figurative “moat” around AI in response to the leaked Google* memo, “We Have No Moat and Neither Does OpenAI*.”
Train large language models quickly and easily on Intel processors. Learn how to train and fine-tune a custom, high-performing chatbot using open models and readily available hardware.
See how to optimize large language models on Intel Xeon processors with Intel® Advanced Matrix Extensions thanks to Hugging Face* APIs, Intel’s accelerated AI tooling, accessibility of CPU hardware, and Falcon open source licensing.
Get a look at the strengths and limitations of using standard Fortran for heterogeneous computing.
Learn more about the performance tuning techniques to achieve optimal performance on the Intel Xeon CPU Max Series.
Stay In the Know on All Things CODE
Sign up to receive the latest tech articles, tutorials, dev tools, training opportunities, product updates, and more, hand-curated to help you optimize your code, no matter where you are in your developer journey. Take a chance and subscribe. You can change your mind at any time.