A Cross-Layer Gate-Level-to-Application Co-Simulation for Design Space Exploration of Approximate Circuits in HEVC Video Encoders

A cross-layer design space exploration (DSE) method based on a proposed co-simulation technique is presented herein. The proposed method is demonstrated evaluating the impacts on both coding efficiency and power dissipation of applying distinct approximate logic operators in a s $\mu {\mathrm{ m}}$ of absolute differences (SAD) kernel that accelerates an H.265/HEVC (high-efficiency video coding) encoder. The proposed method simulates the gate-level circuit dynamically inside the application, with realistic results of the impact of the adder-tree approximate logic implementation on both quality and encoder bit-rate results. A comprehensive DSE is shown herein, with 13 types of 6 classes of approximate adders in the SAD accelerator hardware blocks. Over 3,000 logic variants of approximations at gate-level were developed. Actual video sequences as inputs to the x265 software encoder are co-simulated, to dynamically capture the video motion-estimation (ME) behavior in the presence of logic approximations. While the prior art that only estimates the impact of the approximate logic on power, area, and quality on static designs with statistical assumptions, which are agnostic to the actual algorithm data-dependent behavior in the application, our method explores accurately the trade-off between power dissipation and coding efficiency dynamically over the entire HEVC encoding. Our approach shows that the lower-part-or and error-tolerant adder I approximate adders, as well as truncation-to-zero deliver better compression-power trade-offs, with substantial differences from the static analysis.

[1]  Caro Lucas,et al.  Bio-Inspired Imprecise Computational Blocks for Efficient VLSI Implementation of Soft-Computing Applications , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Nuno Roma,et al.  Power-Efficient Approximate SAD Architecture with LOA Imprecise Adders , 2019, 2019 IEEE 10th Latin American Symposium on Circuits & Systems (LASCAS).

[3]  Kostas Siozios,et al.  VADER: Voltage-Driven Netlist Pruning for Cross-Layer Approximate Arithmetic Circuits , 2019, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[4]  Jörg Henkel,et al.  SlackHammer: Logic Synthesis for Graceful Errors Under Frequency Scaling , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  Yi Wu,et al.  An Efficient Method for Calculating the Error Statistics of Block-Based Approximate Adders , 2019, IEEE Transactions on Computers.

[6]  Sherief Reda,et al.  BLASYS: Approximate Logic Synthesis Using Boolean Matrix Factorization , 2018, 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC).

[7]  Varsha S Kumar LOW POWER DIGITAL IMAGE PROCESSING USING APPROXIMATE ADDERS , 2014 .

[8]  Qiang Xu,et al.  Approximate Computing: A Survey , 2016, IEEE Design & Test.

[9]  John Lach,et al.  A methodology for energy-quality tradeoff using imprecise hardware , 2012, DAC Design Automation Conference 2012.

[10]  Muhammad Shafique,et al.  Embracing approximate computing for energy-efficient motion estimation in high efficiency video coding , 2017, Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017.

[11]  Luciano Volcan Agostini,et al.  Energy-Efficient Hadamard-Based SATD Hardware Architectures Through Calculation Reuse , 2019, IEEE Transactions on Circuits and Systems I: Regular Papers.

[12]  Satoshi Goto,et al.  VLSI Implementation of HEVC Motion Compensation With Distance Biased Direct Cache Mapping for 8K UHDTV Applications , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Muhammad Shafique,et al.  Approximate Multi-Accelerator Tiled Architecture for Energy-Efficient Motion Estimation , 2019, Approximate Circuits.

[14]  Jie Han,et al.  A Novel Heuristic Search Method for Two-Level Approximate Logic Synthesis , 2020, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[15]  Paolo Ienne,et al.  Variable Latency Speculative Addition: A New Paradigm for Arithmetic Circuit Design , 2008, 2008 Design, Automation and Test in Europe.

[16]  Zhi-Hui Kong,et al.  Design of Low-Power High-Speed Truncation-Error-Tolerant Adder and Its Application in Digital Signal Processing , 2010, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[17]  Muhammad Usman Karim Khan,et al.  An adaptive workload management scheme for HEVC encoding , 2013, 2013 IEEE International Conference on Image Processing.

[18]  Fabrizio Lombardi,et al.  An Analytical Framework for Evaluating the Error Characteristics of Approximate Adders , 2015, IEEE Transactions on Computers.

[19]  Byeungwoo Jeon,et al.  Fast Quantization Method With Simplified Rate–Distortion Optimized Quantization for an HEVC Encoder , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[20]  Muhammad Shafique,et al.  DeMAS: An efficient design methodology for building approximate adders for FPGA-based systems , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[21]  Sergio Bampi,et al.  Design Methodology to Explore Hybrid Approximate Adders for Energy-Efficient Image and Video Processing Accelerators , 2019, IEEE Transactions on Circuits and Systems I: Regular Papers.

[22]  Sergio Bampi,et al.  Power-Efficient Sum of Absolute Differences Hardware Architecture Using Adder Compressors for Integer Motion Estimation Design , 2017, IEEE Transactions on Circuits and Systems I: Regular Papers.

[23]  Georgios Zervakis,et al.  On Accelerating Data Analytics: An Introduction to the Approximate Computing Technique , 2018, IoT for Smart Grids.

[24]  Vijayalakshmi Srinivasan,et al.  Approximate computing: Challenges and opportunities , 2016, 2016 IEEE International Conference on Rebooting Computing (ICRC).

[25]  Sukumar Nandi,et al.  Analysis and Design of Adders for Approximate Computing , 2018, ACM Trans. Embed. Comput. Syst..

[26]  Gian Carlo Cardarilli,et al.  Imprecise arithmetic for low power image processing , 2012, 2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[27]  Muhammad Shafique,et al.  An Optimized Partial-Distortion-Elimination Based Sum-of-Absolute-Differences Architecture for High-Efficiency-Video-Coding , 2018, ApplePies.

[28]  Jie Han,et al.  Approximate computing: An emerging paradigm for energy-efficient design , 2013, 2013 18th IEEE European Test Symposium (ETS).

[29]  Sergio Bampi,et al.  Design of area and energy-efficient digital CMOS FIR filters with approximate adder circuits , 2016 .

[30]  Massoud Pedram,et al.  A Theoretical Framework for Quality Estimation and Optimization of DSP Applications Using Low-Power Approximate Adders , 2019, IEEE Transactions on Circuits and Systems I: Regular Papers.

[31]  Toshinori Sato,et al.  Approximate Adder Generation for Image Processing Using Convolutional Neural Network , 2018, 2018 International SoC Design Conference (ISOCC).

[32]  Nuno Roma,et al.  Energy-efficient motion estimation with approximate arithmetic , 2017, 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP).

[33]  Muhammad Shafique,et al.  Invited: Cross-layer approximate computing: From logic to architectures , 2016, 2016 53nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[34]  F. Bossen,et al.  Common test conditions and software reference configurations , 2010 .

[35]  Alberto Bosio,et al.  A Comprehensive Analysis of Approximate Computing Techniques: From Component- to Application-Level , 2018, DATE 2019.

[36]  Muhammad Shafique,et al.  A low latency generic accuracy configurable adder , 2015, 2015 52nd ACM/EDAC/IEEE Design Automation Conference (DAC).

[37]  Felipe Restrepo-Calle,et al.  A review of approximate computing techniques towards fault mitigation in HW/SW systems , 2018, 2018 IEEE 19th Latin-American Test Symposium (LATS).

[38]  Kaushik Roy,et al.  IMPACT: IMPrecise adders for low-power approximate computing , 2011, IEEE/ACM International Symposium on Low Power Electronics and Design.

[39]  Sparsh Mittal,et al.  A Survey of Techniques for Approximate Computing , 2016, ACM Comput. Surv..

[40]  Muhammad Shafique,et al.  Approximate-Computing Architectures for Motion Estimation in HEVC , 2018, 2018 New Generation of CAS (NGCAS).

[41]  L. Sekanina,et al.  Approximate Circuits in Low-Power Image and Video Processing: The Approximate Median Filter , 2017 .

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