ApproxLUT: A novel approximate lookup table-based accelerator
Authors:
- 1 November 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 438-443
Abstract
Computing with memory, which stores function responses of some input patterns into lookup tables offline and retrieves their values when encountering similar patterns (instead of performing online calculation), is a promising energy-efficient computing technique. No doubt to say, with a given lookup table size, the efficiency of this technique depends on which function responses are stored and how they are organized. In this paper, we propose a novel adaptive approximate lookup table based accelerator, wherein we store function responses in a hierarchical manner with increasing fine-grained granularity and accuracy. In addition, the proposed accelerator provides lightweight compensation on output results at different precision levels according to input patterns and output quality requirements. Moreover, our accelerator conducts adaptive lookup table search by exploiting input locality. Experimental results on various computation kernels show significant energy savings of the proposed accelerator over prior solutions.Keywords
This publication has 8 references indexed in Scilit:
- Processing Acceleration with Resistive Memory-based Computation2016
- Resistive Configurable Associative Memory for Approximate Computing2016
- Approximate Associative Memristive Memory for Energy-Efficient GPUs2015
- Energy-efficient computing using adaptive table lookup based on nonvolatile memories2013
- Approximate computing: An emerging paradigm for energy-efficient design2013
- Modeling TCAM power for next generation network devices2006
- Tree bitmapACM SIGCOMM Computer Communication Review, 2004
- Data point selection for piecewise linear curve approximationComputer Aided Geometric Design, 1994