HOME / PUBLICATIONS /

A 3mm2 Programmable Bayesian Inference Accelerator for Unsupervised Machine Perception using Parallel Gibbs Sampling in 16nm

Citation:

Glenn Ko, Yuji Chai, Marco Donato, Paul Whatmough, Thierry Tambe, Rob Rutenbar, David Brooks, and Gu-Yeon Wei. 6/16/2020. “A 3mm2 Programmable Bayesian Inference Accelerator for Unsupervised Machine Perception using Parallel Gibbs Sampling in 16nm.” In IEEE Symposium on VLSI Circuits (VLSI). Publisher's Version
A 3mm2 Programmable Bayesian Inference Accelerator for Unsupervised Machine Perception using Parallel Gibbs Sampling in 16nm2.28 MB

Abstract:

This paper describes a 16nm programmable accelerator for unsupervised probabilistic machine perception tasks that performs Bayesian inference on probabilistic models mapped onto a 2D Markov Random Field, using MCMC. Exploiting two degrees of parallelism, it performs Gibbs sampling inference at up to 1380× faster with 1965× less energy than an Arm Cortex-A53 on the same SoC, and 1.5× faster with 6.3× less energy than an embedded FPGA in the same technology. At 0.8V, it runs at 450MHz, producing 44.6 MSamples/s at 0.88 nJ/sample.
See also: “Agile” Chip Building (CRAFT, ChipKit, Chip Gallery)
Last updated on 04/29/2022