Cambricon-U: A Systolic Random Increment Memory Architecture for Unary Computing
Open Access
- 28 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 424-437
Abstract
Unary computing, whose arithmetics require only one logic gate, has enabled efficient DNN processing, especially on strictly power-constrained devices. However, unary computing still confronts the power efficiency bottleneck for buffering unary bitstreams. The buffering of unary bitstreams requires accumulating bits into large bitwidth binary numbers. The large bitwidth binary number needs to activate all bits per cycle in case of carry propagation. As a result, the accumulation process accounts for 32%-70% of the power budget. To push the boundary of power efficiency, we propose Cambricon-U, a systolic random increment memory architecture featuring efficient accumulation. By leveraging skew number data format, Cambricon-U only activates no more than three bits (instead of all bits) from each number per accumulating cycle. Experimental results show that Cambricon-U reduces 51% power on unary accumulation, and improves 1.18-1.45 × energy efficiency over uSystolic, the SOTA unary computing scheme baseline, with -1.9% ∼ +0.77% area overhead.Keywords
Funding Information
- The National Key R&D Program of China (2022YFB4501601)
- the NSF of China (62102398, 62222214, 62102399, U22A2028, U19B2019)
- Youth Innovation Promotion Association CAS
- CAS Project for Young Scientists in Basic Research (YSBR-029)
This publication has 48 references indexed in Scilit:
- Dynamic energy-accuracy trade-off using stochastic computing in deep neural networks2016
- A New Stochastic Computing Methodology for Efficient Neural Network ImplementationIEEE Transactions on Neural Networks and Learning Systems, 2015
- Race Logic: A hardware acceleration for dynamic programming algorithms2014
- Exploiting correlation in stochastic circuit design2013
- Survey of Stochastic ComputingACM Transactions on Embedded Computing Systems, 2013
- Two Skew-Binary Numeral Systems and One ApplicationTheory of Computing Systems, 2011
- Stochastic arithmetic implementations of neural networks with in situ learning2002
- Stochastic neural computation. I. Computational elementsIEEE Transactions on Computers, 2001
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- An applicative random-access stackInformation Processing Letters, 1983