In-Memory Computing Architectures for Sparse Distributed Memory
- 10 June 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 10 (4) , 855-863
Abstract
This paper presents an energy-efficient and high-throughput architecture for Sparse Distributed Memory (SDM)-a computational model of the human brain [1]. The proposed SDM architecture is based on the recently proposed in-memory computing kernel for machine learning applications called Compute Memory (CM) [2], [3]. CM achieves energy and throughput efficiencies by deeply embedding computation into the memory array. SDM-specific techniques such as hierarchical binary decision (HBD) are employed to reduce the delay and energy further. The CM-based SDM (CM-SDM) is a mixed-signal circuit, and hence circuit-aware behavioral, energy, and delay models in a 65 nm CMOS process are developed in order to predict system performance of SDM architectures in the autoand hetero-associative modes. The delay and energy models indicate that CM-SDM, in general, can achieve up to 25 × and 12 × delay and energy reduction, respectively, over conventional SDM. When classifying 16 ×16 binary images with high noise levels (input bad pixel ratios: 15%-25%) into nine classes, all SDM architectures are able to generate output bad pixel ratios (B o ) ≤ 2%. The CM-SDM exhibits negligible loss in accuracy, i.e., its B o degradation is within 0.4% as compared to that of the conventional SDM.Keywords
Funding Information
- Systems On Nanoscale Information fabriCs (SONIC) (2013-MA-2385)
- SRC STARnet Centers
- SRC
- DARPA
This publication has 17 references indexed in Scilit:
- Energy-efficient and high throughput sparse distributed memory architecture2015
- An energy-efficient memory-based high-throughput VLSI architecture for convolutional networks2015
- Neuron Array With Plastic Synapses and Programmable DendritesIEEE Transactions on Biomedical Circuits and Systems, 2013
- Energy-Efficient Neuron, Synapse and STDP Integrated CircuitsIEEE Transactions on Biomedical Circuits and Systems, 2012
- A 300-MHz 25-/spl mu/A/Mb-leakage on-chip SRAM module featuring process-variation immunity and low-leakage-active mode for mobile-phone application processorIEEE Journal of Solid-State Circuits, 2005
- Intelligent RAM (IRAM): chips that remember and compute2002
- Smart Memories: a modular reconfigurable architecture2002
- Configurable sparse distributed memory hardware implementation1991
- VLSI architectures of sparse distributed memory1991
- Can programming be liberated from the von Neumann style?Communications of the ACM, 1978