Abstract
Machine Learning (ML) Recommendation workloads have demanding performance and memory requirements, and to date have largely been run on servers with x86 processors. To accelerate these workloads (and others) Esperanto Technologies has implemented over a thousand low-power RISC-V processors on a single chip along with a distributed on-die memory system. The ET-SoC-1 chip is designed to compute at peak rates between 100 and 200 TOPS and to be able to run ML Recommendation workloads while consuming than 20 watts. Preliminary data presented at the Hot Chips 33 Conference projected over a hundred times better performance per watt for an Esperanto based accelerator card versus a standard server platform for the MLPerf Deep Learning Recommendation Model benchmark.

This publication has 1 reference indexed in Scilit: