Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How New Memories Will Accelerate Both Inference and General Purpose Compute

SNIAVideo via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore how emerging memory technologies like Magnetic RAM, Resistive RAM, and Ferroelectric RAM are revolutionizing computing beyond traditional Moore's Law scaling limitations in this 50-minute conference presentation. Discover the transformative potential of these nonvolatile memory technologies in accelerating artificial intelligence inference through innovative compute-in-memory engines while simultaneously reducing costs. Learn how bringing inexpensive persistence closer to processor chips, and even integrating it within the chips themselves, will enhance both performance and cost-effectiveness of standard computing applications. Understand the role of new frameworks like CXL (Compute Express Link) in creating persistence-friendly architectures across all levels of the computing hierarchy. Industry analysts Jim Handy and Tom Coughlin present comprehensive insights into how these memory innovations will deliver significant long-term benefits that extend far beyond their initial development drivers, fundamentally changing the landscape of both specialized AI workloads and general-purpose computing systems.

Syllabus

How New Memories Will Accelerate Both Inference and General Purpose Compute

Taught by

SNIAVideo

Reviews

Start your review of How New Memories Will Accelerate Both Inference and General Purpose Compute

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.