Silicon feedback to improve frequency of high-performance microprocessors: an overview

ABSTRACT

In modern high-performance microprocessors designed using advanced process technologies, the frequency of the part is often slower than what the static timing analysis tools predict before tape out. We give an overview of techniques used to observe the failing path on the tester, identify the dominant devices impacting the delay of the path, and learn from the failing path to fix other similar paths in the design. In particular, we describe a Support Vector Machine based approach for learning from speedpaths observed in silicon.

REFERENCES

• 1: Leonard Lee , Li-C. Wang , Praveen Parvathala , T. M. Mak, On Silicon-Based Speed Path Identification, Proceedings of the 23rd IEEE VLSI Test Symposium, p.35-41, May 01-05, 2005 [doi>10.1109/VTS.2005.61]
• 2: P. Bastani, B. Lee, L. Wang, M. Abadir, "Analyzing the risk of timing modeling based on path delay test," Proc. ITC, 2007.
• 3: Li-C. Wang , Pouria Bastani , Magdy S. Abadir, Design-silicon timing correlation: a data mining perspective, Proceedings of the 44th annual conference on Design automation, June 04-08, 2007, San Diego, California [doi>10.1145/1278480.1278580]
• 4: Kip Killpack , Chandramouli Kashyap , Eli Chiprout, Silicon speedpath measurement and feedback into EDA flows, Proceedings of the 44th annual conference on Design automation, June 04-08, 2007, San Diego, California [doi>10.1145/1278480.1278581]
• 5: Pouria Bastani , Kip Killpack , Li-C. Wang , Eli Chiprout, Speedpath prediction based on learning from a small set of examples, Proceedings of the 45th annual conference on Design automation, June 08-13, 2008, Anaheim, California [doi>10.1145/1391469.1391524]
• 6: B. Gottlieb, et al, "Silicon Debug: What Do You Do When Your ASIC Does Not Work as Fast as Expected?" Proc. DAC, 2004.
• 7: Aseem Agarwal , Florentin Dartu , David Blaauw, Statistical gate delay model considering multiple input switching, Proceedings of the 41st annual conference on Design automation, June 07-11, 2004, San Diego, CA, USA [doi>10.1145/996566.996746]
• 8: D. Barton, P. Tangyunyong, J. Soden, A. Liang, F. Low, et al, "Infrared Light Emission From Semiconductor Devices," ISTFA Proc. 1996.
• 9: P. Larsson and C. Svensson, "Noise in digital dynamic CMOS circuits," IEEE J. Solid-State Circuits June 1994, pp. 655--663.
• 10: Sanjay Pant , Eli Chiprout, Power grid physics and implications for CAD, Proceedings of the 43rd annual conference on Design automation, July 24-28, 2006, San Francisco, CA, USA [doi>10.1145/1146909.1146964]
• 11: Nello Cristianini , John Shawe-Taylor, An introduction to support Vector Machines: and other kernel-based learning methods, Cambridge University Press, New York, NY, 1999
• 12: Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995

INDEX TERMS

Primary Classification:
  B. Hardware
  B.8 Performance and Reliability
      B.8.2 Performance Analysis and Design Aids

General Terms:
Algorithms, Performance, Reliability

Keywords:
learning, speedpath, timing analysis