Improved Low-Power Cost-Effective DCT Implementation Based on Markov Random Field and Stochastic Logic

Discrete Cosine Transform (DCT) is a commonly used building block for image and video compression. In this article, we present a Markov Random Field (MRF)-based design for DCT implementation because MRF logic gates outperform standard non-MRF units by achieving high noise immunity for applications to logic-based computing systems in deep sub-micron condition. Furthermore, it is found that stochastic logic, a low-cost form of number representation, can also efficiently simplify computations. By combining these two techniques, we present an improved DCT hardware circuit. The example eight-point one-dimensional DCT (1D DCT) system is simulated using 65 nm CMOS technology. Simulation results show that the proposed MRF design can achieve 13% higher noise immunity and 47% area saving, compared with the typical stochastic 1D DCT using classical Master-and-Slave architecture. While achieving the same error rate of 0.21, power consumption is reduced by 52%.

[1]  Jongeun Lee,et al.  Sign-Magnitude SC: Getting 10X Accuracy for Free in Stochastic Computing for Deep Neural Networks* , 2018, 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC).

[2]  Jianhao Hu,et al.  Low power digital signal processing scheme via stochastic logic protection , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[3]  Chaitali Chakrabarti,et al.  A parallel stochastic computing system with improved accuracy , 2013, SiPS 2013 Proceedings.

[4]  Qi Wei,et al.  A general scheme for noise-tolerant logic design based on probabilistic and DCVS approaches , 2015, 2015 IEEE 13th International New Circuits and Systems Conference (NEWCAS).

[5]  Jianhao Hu,et al.  Area-sharing cyclic structure MRF cirucits design in ultra-low supply voltage , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[6]  Keshab K. Parhi,et al.  Analysis of stochastic logic circuits in unipolar, bipolar and hybrid formats , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[7]  John P. Hayes,et al.  Survey of Stochastic Computing , 2013, TECS.

[8]  Jianhao Hu,et al.  A novel implementation scheme for high area-efficient DCT based on signed stochastic computation , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[9]  Kiat Seng Yeo,et al.  Design of probabilistic-based Markov Random Field logic gates in 65nm CMOS technology , 2010, 2010 International SoC Design Conference.

[10]  Xuan Zeng,et al.  Low-Power Noise-Immune Nanoscale Circuit Design Using Coding-Based Partial MRF Method , 2018, IEEE Journal of Solid-State Circuits.

[11]  I-Chyn Wey,et al.  Reliable ultra-low-voltage low-power probabilistic-based noise-tolerant latch design , 2013, Microelectron. Reliab..

[12]  An-Yeu Wu,et al.  Design and Implementation of Cost-Effective Probabilistic-Based Noise-Tolerant VLSI Circuits , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[13]  Rodrigo Picos,et al.  Effective accuracy estimation and representation error reduction for stochastic logic operations , 2018, 2018 7th International Conference on Modern Circuits and Systems Technologies (MOCAST).

[14]  Joseph L. Mundy,et al.  Optimizing noise-immune nanoscale circuits using principles of Markov random fields , 2006, GLSVLSI '06.

[15]  Andrew B. Watson,et al.  Image Compression Using the Discrete Cosine Transform , 1994 .

[16]  Waleed Fakhr,et al.  An efficient implementation of the 1D DCT using FPGA technology , 2004, Proceedings. 11th IEEE International Conference and Workshop on the Engineering of Computer-Based Systems, 2004..

[17]  Zhongfeng Wang,et al.  Design space exploration for hardware-efficient stochastic computing: A case study on discrete cosine transformation , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Jianhao Hu,et al.  Area-efficient partial-clique-energy MRF pair design with ultra-low supply voltage , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[19]  Naoya Onizawa,et al.  Design of stochastic asymmetric compensation filters for auditory signal processing , 2017, 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[20]  Byung-Geun Lee,et al.  Stochastic implementation of the activation function for artificial neural networks , 2016, 2016 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[21]  John P. Hayes,et al.  Equivalence among stochastic logic circuits and its application , 2015, 2015 52nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[22]  Jongeun Lee,et al.  DPS: Dynamic Precision Scaling for Stochastic Computing-based Deep Neural Networks* , 2018, 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC).

[23]  Yufeng Li,et al.  Low Power Area-Efficient DCT Implementation Based on Markov Random Field-Stochastic Logic , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[24]  Jianhao Hu,et al.  A novel FIR filter based on stochastic logic , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[25]  Joseph L. Mundy,et al.  Designing MRF based Error Correcting Circuits for Memory Elements , 2006, Proceedings of the Design Automation & Test in Europe Conference.

[26]  Lirida A. B. Naviner,et al.  A general cost-effective design structure for probabilistic-based noise-tolerant logic functions in nanometer CMOS technology , 2013, Eurocon 2013.

[27]  Jianhao Hu,et al.  Extensional design for noise-tolerate MRF standard cells via global mapping , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[28]  Joseph L. Mundy,et al.  Designing logic circuits for probabilistic computation in the presence of noise , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[29]  I-Chyn Wey,et al.  Hardware-efficient common-feedback Markov-random-field probabilistic-based noise-tolerant VLSI circuits , 2014, Integr..

[30]  Yan Li,et al.  Feedback-Based Low-Power Soft-Error-Tolerant Design for Dual-Modular Redundancy , 2018, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[31]  S.Y. Foo,et al.  A simplified FPGA implementation of neural network algorithms integrated with stochastic theory for power electronics applications , 2005, 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005..

[32]  R. I. Bahar,et al.  A Probabilistic Approach to Nano-computing , 2003 .

[33]  Arash Ardakani,et al.  Hardware implementation of FIR/IIR digital filters using integral stochastic computation , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[34]  Jianhao Hu,et al.  Implementation of efficient parallel discrete cosine transform using stochastic logic , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[35]  Wang Jian,et al.  Timing performance for MRF-based circuits with low supply voltage , 2016, 2016 International Conference on Integrated Circuits and Microsystems (ICICM).

[36]  An-Yeu Wu,et al.  A 0.18=μm Probabilistic-Based Noise-Tolerate Circuit Design and Implementation with 28.7dB Noise-Immunity Improvement , 2006, 2006 IEEE Asian Solid-State Circuits Conference.