Frequent Value Cache for Low-Power Asynchronous Dual-Rail Bus

We study a power reduction method for the asynchronous dual-rail bus. A preliminary analysis of data communication patterns between a processor and a memory module reveals that many communications deliver a set of data items repeatedly. To exploit such communication characteristics, a frequent value cache(FVC) method is proposed that delivers not always data itself but sometimes an index of data item of FVC. Because of the lower switching activity, FVC reduces the power consumption of the asynchronous dual-rail bus. Simulation results illustrate that FVC reduces the power consumption of the normal asynchronous dual-rail bus by 25% and 30% at maximum for integer and floating-point benchmarks, respectively.

[1]  Tomás Lang,et al.  Working-zone encoding for reducing the energy in microprocessor address buses , 1998, IEEE Trans. Very Large Scale Integr. Syst..

[2]  A. Bahuman,et al.  A low-energy adaptive bus coding scheme , 2001, Proceedings IEEE Computer Society Workshop on VLSI 2001. Emerging Technologies for VLSI Systems.

[3]  Luca Benini,et al.  Reducing switching activity on datapath buses with control-signal gating , 1999 .

[4]  Tomás Lang,et al.  Extension of the working-zone-encoding method to reduce the energy on the microprocessor data bus , 1998, Proceedings International Conference on Computer Design. VLSI in Computers and Processors (Cat. No.98CB36273).

[5]  Anantha P. Chandrakasan,et al.  Low power bus coding techniques considering inter-wire capacitances , 2000, Proceedings of the IEEE 2000 Custom Integrated Circuits Conference (Cat. No.00CH37044).

[6]  Jörg Henkel,et al.  An adaptive dictionary encoding scheme for SOC data buses , 2002, Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition.

[7]  Scott Hauck,et al.  Asynchronous design methodologies: an overview , 1995, Proc. IEEE.

[8]  Mircea R. Stan,et al.  Bus-invert coding for low-power I/O , 1995, IEEE Trans. Very Large Scale Integr. Syst..

[9]  Naresh R. Shanbhag,et al.  Coding for low-power address and data busses: a source-coding framework and applications , 1998, Proceedings Eleventh International Conference on VLSI Design.

[10]  Massoud Pedram,et al.  High-level power modeling, estimation, and optimization , 1998, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[11]  William John Bainbridge,et al.  Delay insensitive system-on-chip interconnect using 1-of-4 data encoding , 2001, Proceedings Seventh International Symposium on Asynchronous Circuits and Systems. ASYNC 2001.

[12]  Kiyoung Choi,et al.  Partial bus-invert coding for power optimization of system level bus , 1998, ISLPED '98.

[13]  Tom Verhoeff,et al.  Delay-insensitive codes — an overview , 1988, Distributed Computing.

[14]  V. Kamakoti,et al.  Dynamic coding technique for low-power data bus , 2003, IEEE Computer Society Annual Symposium on VLSI, 2003. Proceedings..

[15]  Todd M. Austin,et al.  The SimpleScalar tool set, version 2.0 , 1997, CARN.

[16]  Ran Ginosar,et al.  A low power video processor , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[17]  Rung-Bin Lin,et al.  Low power CMOS off-chip drivers with slew-rate difference , 1999, Proceedings of the ASP-DAC '99 Asia and South Pacific Design Automation Conference 1999 (Cat. No.99EX198).

[18]  Kiyoung Choi,et al.  Narrow bus encoding for low power systems , 2000, Proceedings 2000. Design Automation Conference. (IEEE Cat. No.00CH37106).

[19]  Mircea R. Stan,et al.  Low-power encodings for global communication in CMOS VLSI , 1997, IEEE Trans. Very Large Scale Integr. Syst..