An in-depth look at computer performance growth

ABSTRACT

It is a common belief that computer performance growth is over 50% annually, or that performance doubles every 18-20 months. By analyzing publicly available results from the SPEC integer (CINT) benchmark suites, we conclude that this was true between 1985 and 1996 -- the early years of the RISC paradigm.During the last 7.5 years (1996-2004), however, performance growth has slowed down to 41%, with signs of a continuing decline. Meanwhile, clock frequency has improved with about 29% annually. The improvement in clock frequency was enabled both by an annual device speed scaling of 20% as well as by longer pipelines with a lower gate-depth in each stage. This paper takes a fresh look at -- and tries to remove the confusion about -- performance scaling that exists in the computer architecture community.

REFERENCES

• 1: Vikas Agarwal , M. S. Hrishikesh , Stephen W. Keckler , Doug Burger, Clock rate versus IPC: the end of the road for conventional microarchitectures, Proceedings of the 27th annual international symposium on Computer architecture, p.248-259, June 2000, Vancouver, British Columbia, Canada
• 2: Rajagopalan Desikan , Doug Burger , Stephen W. Keckler, Measuring Experimental Error in Microprocessor Simulation, Proceedings of the 28th annual international symposium on Computer architecture, p.266-277, June 30-July 04, 2001, Göteborg, Sweden [doi>10.1145/379240.565338]
• 3: Paul E. Gronowski, William J. Bowhill, Ronald P. Preston, Michael K. Gowan and Randy L. Allmon, High-Performance Microprocessor Design, Journal of Solid-State Circuits, vol. 33, 676--686, 1998.
• 4: Carver A. Mead, Scaling of MOS technology to submicrometer feature sizes, Journal of VLSI Signal Processing Systems, v.8 n.1, p.9-25, July 1994 [doi>10.1007/BF02407107]
• 5: John L. Hennessy , David A. Patterson, Computer architecture (2nd ed.): a quantitative approach, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1996
• 6: John L. Hennessy , David A. Patterson, Computer Architecture: A Quantitative Approach, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2003
• 7: Lawrence G. Roberts, Beyond Moore's Law: Internet Growth Trends, Computer, v.33 n.1, p.117-119, January 2000 [doi>10.1109/2.963131]
• 8: I. Tuimi, The Lives and Death of Moore's Law, First Monday, Oct 11, 2002.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.0 GENERAL
      Subjects: Instruction set design (e.g., RISC, CISC, VLIW)

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.1 Single Data Stream Architectures
          Subjects: RISC/CISC, VLIW architectures

  K. Computing Milieux
  K.1 THE COMPUTER INDUSTRY
      Subjects: Standards

General Terms:
Design