Performance Analysis of AI Hardware and Software

The performance characteristics of AI training and inference can be quite distinct from HPC applications despite possessing similar computational methods (large/small matrix multiplications, stencils, gather/scatter, etc...) albeit at reduced precision (single, half, BFLOAT16).  Where possible, vendors are attempting to create specialized architectures subset of computations used in AI training and inference.  Understanding the interplay between science, AI method, framework, and architecture is essential in not only in quantifying the computational potential for current and future architectures running AI models, but also identifying the bottlenecks and the ultimate limits of today's models.

Research Topics

Researchers

• Samuel Williams

• Nick Wright

• Khaled Ibrahim

• Hai Ah Nam

• Leonid Oliker

• Tan Nguyen

• Nan Ding

• Steve Farrell

• Wahid Bhimji

Publications