ABSTRACT
This paper reports the results of a study of VAX-11/780 processor performance using a novel hardware monitoring technique. A micro-PC histogram monitor was built for these measurements. It keeps a count of the number of microcode cycles executed at each microcode location. Measurement experiments were performed on live timesharing workloads as well as on synthetic workloads of several types. The histogram counts allow the calculation of the frequency of various architectural events, such as the frequency of different types of opcodes and operand specifiers, as well as the frequency of some implementation-specific events, such as translation buffer misses. The measurement technique also yields the amount of processing time spent in various activities, such as ordinary microcode computation, memory management, and processor stalls of different kinds. This, paper reports in detail the amount of time the “average” VAX instruction spends in these activities.
- 1.Alpert, D. Carberry, D., Yamamura, M.,Chow, Y., and Mak, P32-bit Processor Chip Integrates Major System Functions. Electronics 56, 14 (July 14, 1983), pp. 113-119.Google Scholar
- 2.Clark, D.W. Cache Performance in the VAX-11/780. ACM TOCS 1, 1 (Feb. 1983), pp. 24-37. Google ScholarDigital Library
- 3.Clark, D.W. and Emer, J.S. Performance of the VAX-11/780 Translation Buffer: Simulation and Measurement. Submitted for publication, Nov. 1983.Google Scholar
- 4.Clark, D.W. and Levy, H.M., Measurement and Analysis of Instruction Use in the VAX-11/780. Proc. 9th Annual Symp. on Comp. Arch., Austin, April 1982, pp. 9-17. Google ScholarDigital Library
- 5.Digital Equipment Corp. VAX/VMS Internals and Data Structures. Document No. AA-K785A-TE, Digital Equipment Corp., Maynard, MA.Google Scholar
- 6.Digital Equipment Corp. VAX-11 Architecture Reference Manual. Document No. EK-VAXAR-RM-001, Digital Euipment Corp., Maynard, MA, May 1982.Google Scholar
- 7.Greenbaum, H.J. A Simulator of Multiple Interactive Users to Drive a Time-Shared Computer System. M.S. Thesis, MIT Project MAC report MAR-TR-54, Oct. 1968. Google ScholarDigital Library
- 8.Huck, J.C. Comparative Analysis of Computer Architectures. Ph.D. thesis, TR No. 83-243, Computer Systems Lab., Stanford, May 1983. Google ScholarDigital Library
- 9.Levy, H.M., and Eckhouse, R.H. Computer Programming and Architecture: The VAX-11. Digital Press, Bedford, MA, 1980. Google ScholarDigital Library
- 10.Lunde, A. Empirical Evaluation of Some Features of Instruction Set Processor Architectures. CACM 20, 3 (March 1977), 143-153. Google ScholarDigital Library
- 11.McDaniel, G. An Analysis of a Mesa Instruction Set Using Dynamic Instruction Frequencies. Symposium on Architectural Support for Programming Languages and Operating Systems, Palo Alto, CA, March 1982, pp. 167-176. Google ScholarDigital Library
- 12.Peuto, B.L., and Shustek, L.J. An Instruction Timing Model of CPU Performance. Proc. 4th Annual Symp. on Computer Architecture, 1977, pp. 165-178. Google ScholarDigital Library
- 13.Strecker, W.D., VAX-11/780—A Virtual Address Extension for the PDP-11 Family Computers. Proc. NCC, AFIPS Press, Montvale, N.J., 1978.Google Scholar
- 14.Watkins, S.W., and Abrams, M.D. Survey of Remote Terminal Emulators. NBS Special Publication 500-4, April 1977.Google Scholar
- 15.Wiecek, C.A. A Case Study of VAX-11 Instruction Set Usage for Compiler Execution. Symposium on Architectural Support for Programming Languages and Operating Systems, Palo Alto, CA, March 1982, pp. 177-184. Google ScholarDigital Library
- 16.Winder,. R.O. A Data Base for Computer Performance Evaluation. IEEE Computer 6, 3. (March 1973), pp. 25-29.Google Scholar
Index Terms
- A Characterization of Processor Performance in the vax-11/780
Recommendations
A Characterization of Processor Performance in the vax-11/780
This paper reports the results of a study of VAX-11/780 processor performance using a novel hardware monitoring technique. A micro-PC histogram monitor was built for these measurements. It keeps a count of the number of microcode cycles executed at each ...
Pipelining and performance in the VAX 8800 processor
The VAX 8800 family (models 8800, 8700, 8550), currently the fastest computers in the VAX product line, achieve their speed through a combination of fast cycle time and deep pipelining. Rather than pipeline highly variable VAX instructions as such, the ...
Performance Characterization of the Pentium® Pro Processor
HPCA '97: Proceedings of the 3rd IEEE Symposium on High-Performance Computer ArchitectureIn this paper, we characterize the performance of several business and technical benchmarks on a Pentium â Pro processor based system. Various architectural data are collected using a performance monitoring counter tool. Results show that the Pentium ...
Comments