Merging the interface
Open Access
- 7 June 2015
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Abstract
The invention of resistive-switching random access memory (RRAM) devices and RRAM crossbar-based computing system (RCS) demonstrate a promising solution for better performance and power efficiency. The interfaces between analog and digital units, especially AD/DAs, take up most of the area and power consumption of RCS and are always the bottleneck of mixed-signal computing systems. In this work, we propose a novel architecture, MEI, to minimize the overhead of AD/DA by MErging the Interface into the RRAM crossbar. An optional ensemble method, the Serial Array Adaptive Boosting (SAAB), is also introduced to take advantage of the area and power saved by MEI and boost the accuracy and robustness of RCS. On top of these two methods, a design space exploration is proposed to achieve trade-offs among accuracy, area, and power consumption. Experimental results on 6 diverse benchmarks demonstrate that, compared with the traditional architecture with AD/DAs, MEI is able to save 54.63%~86.14% area and reduce 61.82%~86.80% power consumption under quality guarantees; and SAAB can further improve the accuracy by 5.76% on average and ensure the system performance under noisy conditions.Keywords
Funding Information
- National Natural Science Foundation of China (61373026)
- Tsinghua University Initiative Scientific Research Program
- 973 Project (2013CB329000)
- Huawei Technologies
- Brain Inspired Computing Research, Tsinghua university (20141080934)
- the Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions
This publication has 13 references indexed in Scilit:
- Reduction and IR-drop compensations techniques for reliable neuromorphic computing systems2014
- General-purpose code acceleration with limited-precision analog computationACM SIGARCH Computer Architecture News, 2014
- ICE: Inline calibration for memristor crossbar-based computing engine2014
- Design and optimization methodology for 3D RRAM arrays2013
- A Low Energy Oxide‐Based Electronic Synaptic Device for Neuromorphic Visual Systems with Tolerance to Device VariationAdvanced Materials, 2013
- Neural Acceleration for General-Purpose Approximate Programs2012
- Hardware realization of BSB recall function using memristor crossbar arrays2012
- Memristor crossbar based hardware realization of BSB recall function2012
- The brain of a new machineIEEE Spectrum, 2010
- Reflections on the memory wall2004