(great links to resources)
I often mention “cool stuff” in my talks – this page is a link to more information for various “cool stuff” so you can connect with the material directly.
I am a huge believe in open choices – not just open software, but true openness that comes from open governance. Real choice. When our programming code is not portable, innovation is slowed and our choices are limited artificially.
I hope the links below help connect you to useful programming information, and help you see ways to use and support making the future open for us all.
AI PC Development
CPU: Fast Response + GPU: High Throughput + NPU: Power Efficiency
The CPU handles smaller and diverse workloads with low latency. The GPU handles large and symmetric workloads that require parallel throughput. NPU handles sustained heavily-used AI workloads with much less power and greater efficiency.
- Overview: AI PC. Transformational technology.
- Resources to Learn Programming/Usage: AI PC Development
- AI Courses and Certifications
- Connect with Intel as an ISV/IHV: AI PC Acceleration Program
- Reading: The Parallel Universe Magazine
- Introductory videos: video 75 on NPUs in series on oneAPI (Intel tools) Basics
Unified Acceleration Foundation
The Linux Foundation’s UXL (Unified Acceleration Foundation) is an important player in the world of helping create an open future for us all.
More information can be found at https://github.com/uxlfoundation/foundation.
This is an important foundational effort that holds the power to help our C++ level code be open and portable, and equally importantly to help many things higher on the stack be open and portable.
Learn more by visiting their official site: www.uxlfoundation.org
The Unified Acceleration (UXL) Foundation exists to define a standards-based, cross-architecture open specification for accelerated computing and to foster the open-source implementations of the specification.
The community is invited to join the meetings, review the oneAPI Specification, and read the information in this repo. Contributions can be made by joining the Special Interest Groups (SIGs) or posting comments or questions as GitHub issues. General questions can go to this repo, and issues specific to parts of the specification can go to the Specification repo.
The public calendar of UXL Foundation meetings is available using Google Calendar.
You can join, or just watch what is happening. Of course, I encouraging joining! It is very important to support efforts to create open access for all software and hardware so we all enjoy the benefits of having portability and the freedom to choose what vendors we use at all times!
SYCL – open C++ access to accelerators of all vendors and architectures
C++ programmers should learn SYCL because it is Khronos standard for proving open standard which has great support for using accelerators regardless of vendor or architecture!
Here are key ways (read them all!) to get better informed quickly:
- Know that support for NVIDIA and AMD is strong:
- Blog “SYCL™ Performance for Nvidia® and AMD GPUs Matches Native System Language“
- Download them now (add-ons to the Intel tools): oneAPI plugins for Nvidia and AMD GPUs
- Great support from Intel:
- Download them now: intel.com/content/www/us/en/developer/tools/oneapi/toolkits.html
- Read my blog introducing the latest major version: 2024-tools-standards-perf-dependable-innovation.html
- Learn SYCL with these great resources:
- Webinar: Learn SYCL in an Hour (Maybe Less)
- Download the 2nd edition SYCL book: https://link.springer.com/book/10.1007/978-1-4842-9691-2
- Visit sycl.tech – a site that has emerged as an unequaled resource for SYCL programmers.
Intel Developer Cloud with Free Training Courses
Cloud access to Intel technologies. Training courses on the hardware are free. Dedicated access to new hardware is very affordable. Sign-up, learn more, and take training courses for free!
- Sign up for immediate access to the latest Intel technology without downloads or hardware setup.
- Training courses are available for free. Visit https://console.cloud.intel.com/training after you sign-up (free at https://cloud.intel.com).
Recommended reading: “A New Golden Age for Computer Architecture“
Simply a must read!
by John L. Hennessy, David A. Patterson
Communications of the ACM, February 2019, Vol. 62 No. 2, Pages 48-60
10.1145/3282307 (direct access: PDF)