No Travel? No Problem.

Remote Participation
The Role of Embedded AI/ML Cores in Hardware-Based Accelerators
Event Type
Exhibitor Forum
Tags
Architectures
Registration Categories
TP
XO / EX
TimeTuesday, 16 November 202110:30am - 11am CST
Location263
Description“When all you have is a hammer, all the world’s a nail.” For decades in computing, all we had was the CPU, so every computational problem was viewed from this perspective. Eventually, math co-processors came along to offload instruction cycle-intensive math operations. This then led to offload solutions via graphical processing units (GPUs), field-programmable gate arrays (FPGAs), and, more recently, application-specific integrated circuits (ASICs). Specialized Artificial Intelligence (AI)/Machine Learning (MLP) Processing cores have also been developed in recent years, which run on GPUs, FPGAs and/or ASICs. These computational platforms specialize in specific HPC problem domains where their computational resources offer the best ratio of results to power consumption. For FPGAs, HPC problems like genomic analysis or video data can be up to 100x faster than GPUs. Various types of machine learning map exceptionally well into MLP cores, dramatically improve training time. This talk will examine each of these computational platforms, but it will focus on the most recent two platforms, ASICs and FPGAs with enhanced MLP cores, diving into why these platforms, for specific problem domains, are so much better than earlier competing platforms.
Back To Top Button