Predicting and precluding problems with memory latency
- 1 August 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 14 (4) , 59-67
- https://doi.org/10.1109/40.296166
Abstract
By examining the rate at which successive generations of processor and DRAM cycle times have been diverging over time, we can track the latency problem of computer memory systems. Our research survey starts with the fundamentals of single-level caches and moves to the need for multilevel cache hierarchies. We look at some of the current techniques for boosting cache performance, especially compiler-based methods for code restructuring and instruction and data prefetching. These two areas will likely yield improvements for a much larger domain of applications in the future.Keywords
This publication has 9 references indexed in Scilit:
- Supercomputers-software on the brinkIEEE Spectrum, 1992
- Computer technology and architecture: an evolving interactionComputer, 1991
- The evolution of instruction sequencingComputer, 1991
- Trends in megabit DRAM circuit designIEEE Journal of Solid-State Circuits, 1990
- The case for the sustained performance computer architectureACM SIGARCH Computer Architecture News, 1989
- Program optimization for instruction cachesPublished by Association for Computing Machinery (ACM) ,1989
- Achieving high instruction cache performance with an optimizing compilerPublished by Association for Computing Machinery (ACM) ,1989
- Cache MemoriesACM Computing Surveys, 1982
- Sequential Program Prefetching in Memory HierarchiesComputer, 1978