Energy-Efficient Reconfigurable SRAM: Reducing Read Power Through Data Statistics

This paper introduces a framework for designing data-dependent SRAMs taking advantage of statistical dependencies present in the binary values processed and stored in the intermediary stages of various algorithms. To demonstrate the framework, a reconfigurable conditional precharge (CP) SRAM is designed in a 28-nm fully-depleted silicon-on-insulator CMOS process. To reduce read power consumption, the SRAM reconfigures its prediction scheme for each column as the data statistics evolve. A 10T bit cell, a prediction-based CP circuit, and a compact column circuit implemented in a 16-kbit SRAM test chip demonstrate the power savings of 63%, 50%, and up to 69% for the applications sparse fast Fourier transform, object detection, and motion estimation, respectively, as compared with similar memories with naive prediction. Analysis tools for optimal prediction selection for the presented class of low-power memories are also provided.

[1]  Borivoje Nikolic,et al.  SRAM Assist Techniques for Operation in a Wide Voltage Range in 28-nm CMOS , 2012, IEEE Transactions on Circuits and Systems II: Express Briefs.

[2]  Masahiko Yoshimoto,et al.  A 10T Non-Precharge Two-Port SRAM for 74% Power Reduction in Video Processing , 2007, IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07).

[3]  Anantha Chandrakasan,et al.  A 128 Kbit SRAM With an Embedded Energy Monitoring Circuit and Sense-Amplifier Offset Compensation Using Body Biasing , 2014, IEEE Journal of Solid-State Circuits.

[4]  David Blaauw,et al.  A Reconfigurable Sense Amplifier with Auto-Zero Calibration and Pre-Amplification in 28 nm CMOS , 2018 .

[5]  Philippe Flatresse,et al.  UTBB FD-SOI: A process/design symbiosis for breakthrough energy-efficiency , 2013, 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[6]  Jiun-In Guo,et al.  A Dynamic Quality-Adjustable H.264 Video Encoder for Power-Aware Video Applications , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Kaushik Roy,et al.  A Priority-Based 6T/8T Hybrid SRAM Architecture for Aggressive Voltage Scaling in Video Applications , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Vivienne Sze,et al.  Energy-efficient HOG-based object detection at 1080HD 60 fps with multi-scale support , 2014, 2014 IEEE Workshop on Signal Processing Systems (SiPS).

[9]  Lee-Sup Kim,et al.  A low-power SRAM using hierarchical bit line and local sense amplifiers , 2005, IEEE J. Solid State Circuits.

[10]  Anantha Chandrakasan,et al.  27.4 A 0.75-million-point fourier-transform chip for frequency-sparse signals , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[11]  Anh-Tuan Do,et al.  A 0.3 pJ/access 8T data-aware SRAM utilizing column-based data encoding for ultra-low power applications , 2016, 2016 IEEE Asian Solid-State Circuits Conference (A-SSCC).

[12]  Chuhong Duan.  Energy efficient reconfigurable SRAM using data-dependency , 2015 .

[13]  David Blaauw,et al.  13.7 A reconfigurable sense amplifier with auto-zero calibration and pre-amplification in 28nm CMOS , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[15]  Anantha Chandrakasan,et al.  A 0.36V 128Kb 6T SRAM with energy-efficient dynamic body-biasing and output data prediction in 28nm FDSOI , 2016, ESSCIRC Conference 2016: 42nd European Solid-State Circuits Conference.

[16]  Na Gong,et al.  Ultra-Low Voltage Split-Data-Aware Embedded SRAM for Mobile Video Applications , 2012, IEEE Transactions on Circuits and Systems II: Express Briefs.

[17]  Anantha Chandrakasan,et al.  Application-Specific SRAM Design Using Output Prediction to Reduce Bit-Line Switching Activity and Statistically Gated Sense Amplifiers for Up to 1.9$\times$ Lower Energy/Access , 2013, IEEE Journal of Solid-State Circuits.

[18]  Masahiko Yoshimoto,et al.  Novel Video Memory Reduces 45% of Bitline Power Using Majority Logic and Data-Bit Reordering , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[19]  Trevor Mudge,et al.  Yield-driven near-threshold SRAM design , 2007, ICCAD 2007.