Implementing cooperative prefetching and caching in a globally-managed memory system Export

@article{citeulike:1272624, abstract = {This paper presents cooperative prefetching and caching --- the use of network-wide global resources (memories, CPUs, and disks) to support prefetching and caching in the presence of hints of future demands. Cooperative prefetching and caching effectively unites disk-latency reduction techniques from three lines of research: prefetching algorithms, cluster-wide memory management, and parallel I/O. When used together, these techniques greatly increase the power of prefetching relative to a conventional (non-global-memory) system. We have designed and implemented PGMS, a cooperative prefetching and caching system, under the Digital Unix operating system running on a 1.28 Gb/sec Myrinet-connected cluster of DEC Alpha workstations. Our measurements and analysis show that by using available global resources, cooperative prefetching can obtain significant speedups for I/O-bound programs. For example, for a graphics rendering application, our system achieves a speedup of 4.9 over a non-prefetching version of the same program, and a 3.1-fold improvement over that program using local-disk prefetching alone.}, address = {New York, NY, USA}, author = {Voelker, Geoffrey M. and Anderson, Eric J. and Kimbrel, Tracy and Feeley, Michael J. and Chase, Jeffrey S. and Karlin, Anna R. and Levy, Henry M.}, booktitle = {SIGMETRICS '98/PERFORMANCE '98: Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems}, citeulike-article-id = {1272624}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=277869}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/277851.277869}, doi = {10.1145/277851.277869}, issn = {0163-5999}, journal = {SIGMETRICS Perform. Eval. Rev.}, keywords = {predictive-caching}, number = {1}, pages = {33--43}, posted-at = {2007-05-02 20:24:52}, priority = {3}, publisher = {ACM}, title = {Implementing cooperative prefetching and caching in a globally-managed memory system}, url = {http://dx.doi.org/10.1145/277851.277869}, volume = {26}, year = {1998} }

TY - JOUR ID - citeulike:1272624 L3 - citeulike-article-id:1272624 N2 - This paper presents cooperative prefetching and caching --- the use of network-wide global resources (memories, CPUs, and disks) to support prefetching and caching in the presence of hints of future demands. Cooperative prefetching and caching effectively unites disk-latency reduction techniques from three lines of research: prefetching algorithms, cluster-wide memory management, and parallel I/O. When used together, these techniques greatly increase the power of prefetching relative to a conventional (non-global-memory) system. We have designed and implemented PGMS, a cooperative prefetching and caching system, under the Digital Unix operating system running on a 1.28 Gb/sec Myrinet-connected cluster of DEC Alpha workstations. Our measurements and analysis show that by using available global resources, cooperative prefetching can obtain significant speedups for I/O-bound programs. For example, for a graphics rendering application, our system achieves a speedup of 4.9 over a non-prefetching version of the same program, and a 3.1-fold improvement over that program using local-disk prefetching alone. IS - 1 JF - SIGMETRICS Perform. Eval. Rev. SN - 0163-5999 AD - New York, NY, USA EP - 43 TI - Implementing cooperative prefetching and caching in a globally-managed memory system PB - ACM VL - 26 T2 - SIGMETRICS '98/PERFORMANCE '98: Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems SP - 33 KW - predictive-caching AU - Voelker, Geoffrey AU - Anderson, Eric AU - Kimbrel, Tracy AU - Feeley, Michael AU - Chase, Jeffrey AU - Karlin, Anna AU - Levy, Henry PY - 1998/// UR - http://dx.doi.org/10.1145/277851.277869 ER -