![]() In: Proceedings of the 2000 ACM/IEEE Conference on Supercomputing, Dallas, Texas, USA (November 2000) In: Proceedings of the 1999 ACM/IEEE Conference on Supercomputing, Portland, Oregon, USA (November 1999)īircsak, J., Craig, P., Crowell, R., Cvetanovic, Z., Harris, J., Nelson, C.A., Offner, C.D.: Extending OpenMP for NUMA machines. Noordergraaf, L., van der Pas, R.: Performance Experiences on Sun’s WildFire Prototype. In: High Performance Computing Systems and Applications (HPCS), Kingston, Canada (June 1999)ĭormanns, M.: Shared-Memory Parallelization of the GROMOS 1996 Molecular Dynamics Code. IEEE Computational Science & Engineering 5(1), 46–55 (1998)ĭormanns, M., Lankes, S., Bemmerl, T., Bolz, G., Pfeiffle, E.: Parallelization of an Airline Flight-Scheduling Module on a SCI-Coupled NUMA Shared Memory Cluster. This process is experimental and the keywords may be updated as the learning algorithm improves.ĭagum, L., Menon, R.: OpenMP: An Industry-Standard API for Shared-Memory Programming. These keywords were added by machine and not by the authors. In this paper, we present an extension to the Linux kernel which implements this strategy and compare it with alternative approaches. Affinity-on-next-touch may be a useful page placement strategy to distribute the data in a suitable manner, but support for it is missing from the current Linux kernel. Unfortunately, memory access patterns are often very complex and difficult to predict. On a NUMA machine, the distribution of data has a significant impact on the performance and scalability of data-intensive programs, because of the difference in access speed between local and remote parts of the memory system. For many years now, NUMA architectures are being used in the design of large shared memory computers and they are gaining importance even for smaller-scale systems.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |