Techniques for efficient inline tracing on a shared-memory multiprocessor
Susan J. Eggers, David R. Keppel, Eric J. Koldinger et al. · ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · 1990
While much current research concerns multiprocessor design, few traces of parallel programs are available for analyzing the effect of design trade-offs. Existing trace collection methods have serious drawbacks: trap-driven methods often slow down program execution by more than 1000 times, significantly perturbing program behavior; microcode modification is faster, but the technique is neither general nor portable.
Cited by 124 works. doi:10.1145/98457.98501 Open-access PDF
Authors
References
- Cache Memories
- Aspects of Cache Memory and Instruction Buffer Performance
- ATUM: a new technique for capturing address traces using microcode
- Analysis and performance of computer instruction sets
- PRESTO: A system for object‐oriented parallel programming
- Long Address Traces from RISC Machines: Generation and Analysis
- A case study of VAX-11 instruction set usage for compiler execution
- Logic verification algorithms and their parallel implementation
- The Symmetry Multiprocessor System.
- The effect of sharing on the cache and bus performance of parallel programs