Michigan State University
Large scientific parallel applications demand large amounts of memory space. Current parallel computing platforms schedule jobs without fully knowing their memory requirements. This paper leads to uneven memory allocation in which some nodes are overloaded. This, in turn, leads to disk paging, which is extremely expensive in the context of scientific parallel computing. To solve this problem, the authors propose a new peer-to-peer solution called parallel network RAM. This approach avoids the use of disk and better utilizes available RAM resources.