Power-aware RAM mapping for FPGA embedded memory blocks

ABSTRACT

Embedded memory blocks are important resources in contemporary FPGA devices. When targeting FPGAs, application designers often specify high-level memory functions which exhibit a range of sizes and control structures. These logical memories must be mapped to FPGA embedded memory resources such that physical design objectives are met. In this work a set of power-aware logical-to-physical RAM mapping algorithms are described which convert user-defined memory specifications to on-chip FPGA memory block resources. These algorithms minimize RAM dynamic power by evaluating a range of possible embedded memory block mappings and selecting the most power-efficient choice. Our automated approach has been integrated into a commercial FPGA compiler and tested with 40 large FPGA benchmarks. Through experimentation, we show that, on average, embedded memory dynamic power can be reduced by 21% and overall core dynamic power can be reduced by 7% with a minimal loss (1%) in design performance.

References

1. Altera Corp. Quartus II Handbook, Chapter 7, vol. 1, July 2005.
2. Altera Corp. Stratix II Device Handbook, vol. 2, July 2005.
3. Altera Corp. Stratix Device Handbook, vol. 1, July 2005.
4. S. Bakshi and D. Gajski. A memory selection algorithm for high-performance pipelines, In Proceedings of the European Design Automation Conference, Brighton, England, Sept. 1995, pp. 124--129.
5. L. Benini, A. Macii, and M. Poncino. A recursive algorithm for low-power memory partitioning, In Proceedings of the International Symposium on Low Power Electronics and Design, Rapallo, Italy, July, 2000, pp. 78--83.
6. Y. Cao, H. Tomiyama, T. Okuma and H. Yasuura. Data memory design considering effective bitwidth for low-energy embedded systems, In Proceedings of the IEEE International Symposium of System Synthesis, Kyoto, Japan, Oct. 2002, pp. 201--206.
7. A. Ferrahi, G. Tellez, and M. Sarrafzadeh. Memory segmentation to exploit sleep mode operation, In Proceedings of the ACM/IEEE Design Automation Conference, San Francisco CA, Jun. 1995, pp. 36--41.
8. C. Gebotys. Low energy memory and register allocation using network flow, In Proceedings of the ACM/IEEE Design Automation Conference, Anaheim, CA, Jun. 1997, pp. 435--440.
9. W. Ho and S. Wilton. Logical-to-physical memory mapping for FPGAs with dual-port embedded memories, In Proceedings of the International Workshop of Field Programmable Logic and Applications, Glasgow, UK, Aug. 1999, pp. 111--123.
10. J. Lamoureux and S. Wilton. On the interaction between FPGA CAD algorithms, In Proceedings of the IEEE International Conference on Computer-Aided Design, San Jose, CA, Nov. 2003, pp. 701--708.
11. M. Margala. Low-power SRAM circuit design, In Proceedings of the IEEE International Workshop on Memory Technology, Design, and Testing, San Jose, CA, Aug. 1999, pp. 115--122.
12. M. Mamidipaka and N. Dutt. An Enhanced Power Estimation Model for On-Chip Caches. CECS Technical Report #04-28, University of California, Irvine, 2004.
13. P. Petrov and A. Orailoglu. Virtual page tag reduction for low-power TLBs, In Proceedings of the IEEE International Conference on Computer Design, San Jose, CA, Oct. 2003, pp. 371--374.
14. H. Schmit and D. Thomas. Address generation for memories containing multiple arrays, IEEE Transactions on VLSI Systems, vol. 17, pp. 377--385, May 1998.
15. O. Unsal, R. Ashok, I. Koren, C. Krishna, and C. Moritz. Cool-cache for hot multimedia, In Proceedings of the ACM/IEEE International Symposium on Microarchitecture, Austin, TX, Dec. 2001, pp. 274--283.
16. S. Wuytack, F. Catthoor, L. Nachtergaele and H. De Man. Power exploration for data dominated video applications, In Proceedings of the IEEE International Symposium on Low Power Design, Monterey, CA, Aug. 1996, pp. 359--364.
17. Xilinx Corp. Virtex-4 User's Guide, July 2005.
18. Xilinx Corp. Virtex II Platform FPGAs: Complete Data Sheet, March 2005.

Index Terms

• Hardware

  • Electronic design automation

    • Physical design (EDA)