An Energy Efficient JPEG Encoder with Neural Network Based Approximation and Near-Threshold Computing

JPEG compression is an important part in low-power multimedia applications. This paper proposes an approach that leverages the error resilience of JPEG for different energy budgets. We select and train neural networks to approximate DCT and quantization code regions in JPEG. Then we design an architecture called reconfigurable neural unit (RNU) to accelerate trained neural networks which replace original codes. In addition, some architecture innovations are proposed to make our JPEG encoder works efficiently in near-threshold voltage region. This JPEG encoder synthesized with a 40nm CMOS technology, is able to operate at 40MHz for a 0.6V supply voltage. Results show up to 5.0 × energy reduction with 2.5 × performance degradation when compared to using a 1.0V nominal supply voltage.

[1]  Vivienne Sze,et al.  14.5 Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks , 2016, ISSCC.

[2]  David Blaauw,et al.  CAS-FEST 2010: Mitigating Variability in Near-Threshold Computing , 2011, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[3]  Yu Pu.  An Ultra-Low-Energy Multi-Standard JPEG Co-Processor in 65 nm CMOS With Sub/Near Threshold Supply Voltage , 2010 .

[4]  Saurabh Dighe,et al.  A 280mV-to-1.2V wide-operating-range IA-32 processor in 32nm CMOS , 2012, 2012 IEEE International Solid-State Circuits Conference.

[5]  Kaushik Roy,et al.  Low-Power Digital Signal Processing Using Approximate Adders , 2013, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[6]  Leibo Liu,et al.  Neural approximating architecture targeting multiple application domains , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[7]  Olivier Temam,et al.  A defect-tolerant accelerator for emerging high-performance applications , 2012, 2012 39th Annual International Symposium on Computer Architecture (ISCA).

[8]  Luis Ceze,et al.  Neural Acceleration for General-Purpose Approximate Programs , 2012, 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture.

[9]  David Blaauw,et al.  Near-Threshold Computing: Reclaiming Moore's Law Through Energy Efficient Integrated Circuits , 2010, Proceedings of the IEEE.

[10]  Sachin S. Sapatnekar,et al.  Optimal design of JPEG hardware under the approximate computing paradigm , 2016, 2016 53nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[11]  Luis Ceze,et al.  Neural Acceleration for General-Purpose Approximate Programs , 2012, 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture.

[12]  Wim Dehaene,et al.  27.3 A 210mV 5MHz variation-resilient near-threshold JPEG encoder in 40nm CMOS , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[13]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .