An 88-fJ/40-MHz [0.4 V]–0.61-pJ/1-GHz [0.9 V] Dual-Mode Logic 8 $\times$ 8 bit Multiplier Accumulator With a Self-Adjustment Mechanism in 28-nm FD-SOI

The unique ability of dual-mode logic (DML) to self-adapt to computational needs by providing high speed and/or low energy consumption is demonstrated for the first time by silicon measurements in 28-nm fully depleted silicon on insulator. At the gate level, the DML design offers the possibility to operate either in the static mode to save energy or in the dynamic mode to increase speed, albeit with higher delay or energy consumption, respectively. In this paper, these two operational modes of the DML gates are optimally managed by a self-adjustment mechanism to increase speed or reduce the energy of gates/blocks in the design at run time. As a test case, a two-stage pipelined multiply–accumulate (MAC) circuit was selected to assess the advantages of DML in terms of speed, energy, and area as compared to a conventional CMOS design. We show that the self-adjusted DML MAC achieves both a performance boost of up to 92% and 16% less energy consumption than the equivalent standard CMOS implementation. The energy saved can be even greater (up to 35%) when the low-power (fully static) mode is enabled. In addition, the DML MAC occupies 25% less area.

[1]  Tung Thanh Hoang,et al.  A High-Speed, Energy-Efficient Two-Cycle Multiply-Accumulate (MAC) Architecture and Its Application to a Double-Throughput MAC Unit , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Nitin Chawla,et al.  14.1 A 2.9TOPS/W deep convolutional neural network SoC in FD-SOI 28nm for intelligent embedded systems , 2017, 2017 IEEE International Solid-State Circuits Conference (ISSCC).

[3]  David Bol,et al.  Impact of back gate biasing schemes on energy and robustness of ULV logic in 28nm UTBB FDSOI technology , 2013, International Symposium on Low Power Electronics and Design (ISLPED).

[4]  Milos D. Ercegovac,et al.  An Energy-Efficient Multiplier With Fully Overlapped Partial Products Reduction and Final Addition , 2016, IEEE Transactions on Circuits and Systems I: Regular Papers.

[5]  Trond Ytterdal,et al.  28 nm UTBB-FDSOI energy efficient and variation tolerant custom digital-cell library with application to a subthreshold MAC block , 2016, 2016 MIXDES - 23rd International Conference Mixed Design of Integrated Circuits and Systems.

[6]  Alexander Fish,et al.  Low voltage dual mode logic: Model analysis and parameter extraction , 2013, Microelectron. J..

[7]  Massimo Alioto,et al.  Dynamically Adaptable Pipeline for Energy-Efficient Microarchitectures Under Wide Voltage Scaling , 2018, IEEE Journal of Solid-State Circuits.

[8]  Alexander Fish,et al.  Evaluation of Dual Mode Logic in 28nm FD-SOI technology , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[9]  Behrooz Parhami,et al.  Computer arithmetic - algorithms and hardware designs , 1999 .

[10]  Alexander Fish,et al.  High speed Dual Mode Logic Carry Look Ahead Adder , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[11]  Volkan Kursun,et al.  Carbon Nanotubes Blowing New Life Into NP Dynamic CMOS Circuits , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[12]  Alexander Fish,et al.  Logical Effort for CMOS-Based Dual Mode Logic Gates , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[13]  Alexander Fish,et al.  Design Flow and Characterization Methodology for Dual Mode Logic , 2015, IEEE Access.

[14]  Sying-Jyan Wang,et al.  Low power parallel multiplier with column bypassing , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[15]  Jun-Cheol Park,et al.  Sleepy Stack Leakage Reduction , 2006, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[16]  Shmuel Wimer,et al.  A Low Energy and High Performance ${\rm DM}^{2}$ Adder , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[17]  Sying-Jyan Wang,et al.  Low-power parallel multiplier with column bypassing , 2005 .

[18]  Dawei Huang,et al.  A 3.6 GHz 16-Core SPARC SoC Processor in 28 nm , 2014, IEEE Journal of Solid-State Circuits.

[19]  Alexander Fish,et al.  Low voltage logic circuits exploiting gate level dynamic body biasing in 28 nm UTBB FD-SOI , 2016 .

[20]  Alexander Fish,et al.  Dual Mode Logic—Design for Energy Efficiency and High Performance , 2013, IEEE Access.

[21]  Luca Benini,et al.  A Self-Aware Architecture for PVT Compensation and Power Nap in Near Threshold Processors , 2017, IEEE Design & Test.

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

[23]  Poras T. Balsara,et al.  High performance low power array multiplier using temporal tiling , 1999, IEEE Trans. Very Large Scale Integr. Syst..