A comprehensive analysis of energy savings in dynamic supply voltage scaling systems using data dependent voltage level selection

We extend our analysis of the data-dependent quantized voltage level selection (DDLS) technique for dynamic supply voltage scaling (DSVS) systems. The energy analysis was performed using a very conservative energy model considering all combinations of two, three and four quantized voltage levels, and the minimum-energy-yielding quantized voltage levels were selected. For test data, we used nine 300-frame MPEG-2 video sequences in QCIF (Quarter Common Intermediate Format). Our results indicate that energy savings of up to 12% are achievable by selecting quantized voltage levels based on the workload distribution.

[1]  Anantha P. Chandrakasan,et al.  Low-power CMOS digital design , 1992 .

[2]  Anantha P. Chandrakasan,et al.  Low Power Digital CMOS Design , 1995 .

[3]  Anantha P. Chandrakasan,et al.  Data driven signal processing: an approach for energy efficient computing , 1996, Proceedings of 1996 International Symposium on Low Power Electronics and Design.

[4]  Leonard McMillan,et al.  A forward-mapping realization of the inverse discrete cosine transform , 1992, Data Compression Conference, 1992..

[5]  Hiroto Yasuura,et al.  Voltage scheduling problem for dynamically variable voltage processors , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[6]  Anantha Chandrakasan,et al.  Embedded power supply for low-power DSP , 1997, IEEE Trans. Very Large Scale Integr. Syst..

[7]  Lama H. Chandrasena,et al.  Energy minimization in dynamic supply voltage scaling systems using data dependent voltage level selection , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[8]  L. S. Nielsen,et al.  Low-power operation using self-timed circuits and adaptive scaling of the supply voltage , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[9]  Anantha P. Chandrakasan,et al.  A Data-Driven IDCT Architecture for Low Power Video Applications , 1996, ESSCIRC '96: Proceedings of the 22nd European Solid-State Circuits Conference.