ACM Home Page
Please provide us with feedback. Feedback
DRG-cache: a data retention gated-ground cache for low power
Full text PdfPdf (417 KB)
Source Annual ACM IEEE Design Automation Conference archive
Proceedings of the 39th annual Design Automation Conference table of contents
New Orleans, Louisiana, USA
SESSION: Low-power physical design table of contents
Pages: 473 - 478  
Year of Publication: 2002
ISBN ~ ISSN:0738-100X , 1-58113-461-4
Authors
Amit Agarwal  Purdue University, West Lafayette, IN
Hai Li  Purdue University, West Lafayette, IN
Kaushik Roy  Purdue University, West Lafayette, IN
Sponsor
SIGDA: ACM Special Interest Group on Design Automation
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 5,   Downloads (12 Months): 21,   Citation Count: 23
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/513918.514037
What is a DOI?

ABSTRACT

In this paper we propose a novel integrated circuit and architectural level technique to reduce leakage power consumption in high performance cache memories using single Vt (transistor threshold voltage) process. We utilize the concept of Gated-Ground [5] (NMOS transistor inserted between Ground line and SRAM cell) to achieve reduction in leakage energy without significantly affecting performance. Experimental results on gated-Ground caches show that data is retained (DRG-Cache) even if the memory are put in the stand-by mode of operation. Data is restored when the gated-Ground transistor is turned on. Turning off the gated-Ground transistor in turn gives large reduction in leakage power. This technique requires no extra circuitry; row decoder itself can be used to control the gated-Ground transistor. The technique is applicable to data and instruction caches as well as different levels of cache hierarchy such as the L1, L2, or L3 caches. We fabricated a test chip in TSMC 0.25m technology to show the data retention capability and the cell stability of DRG-cache. Our simulation results on 100nm and 70nm processes (Berkeley Predictive Technology Model) show 16.5% and 27% reduction in consumed energy in L1 cache and 50% and 47% reduction in L2 cache with less than 5% impact on execution time and within 4% increase in area overhead.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
J. Montanaro et. al. A 160-MHz, 32-b, 0.5-W CMOS RISC microprocessor. IEEE Journal of Solid-State Circuits, 31(11), 1703--1714, 1996.
 
2
V. De. Private communication.
 
3
4
5
 
6
 
7
I. Fukushi, R. Sasagawa, M. Hamaminato, T. Izawa, and S. Kawashima. A low-power SRAM using improved charge transfer sense. In Proceedings of the 1998 Int. Symp. on VLSI Circuits, pages 142--145, 1998.
8
9
10
 
11
 
12
N. Shibata, M. Watanabe and Y. Sato. A 2-V 300-MHz 1-Nb Current-Sensed Double-Density SRAM for Low-Power 0.3-¿m CMOS/SIMOX ASICs. IEEE Journal of Solid State Circuits, Vol. 36, No. 10, pages 1524--1537, Oct. 2001.
 
13
D. Burger and T. M. Austin. The SimpleScalar tool set, version 2.0. Technical Report 1342, Computer Sciences Department, University of Wisconsin-Madison, June 1997
 
14
T. Wada and S. Rajan. An Analytical Access Time Model for On-Chip cache Memories. IEEE Journal of Solid State Circuits, Vol. 27, No 8, pages 1147--1156,August 1992.
 
15
16

CITED BY  23

Collaborative Colleagues:
Amit Agarwal: colleagues
Hai Li: colleagues
Kaushik Roy: colleagues