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
Beyond Direct Memory Access: Reducing the Data Center Tax with Intel Data Streaming Accelerator

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.

Cultivate Parallel Standards: Diversity, Alignment, and Cross-Pollination

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.

The Moat Is Trust or Maybe Just Responsible AI

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*.”

Create Your Own Custom Chatbot

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.

Fine-Tune the Falcon 7 Billion Parameter Model with Hugging Face* and oneAPI

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.

Using Fortran DO CONCURRENT for Accelerator Offload

Get a look at the strengths and limitations of using standard Fortran for heterogeneous computing.

Performance Optimization on Intel Processors with High-Bandwidth Memory

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.

By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.
By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.