Enhancing Memory Use in Simple Coma: Multiplexed Simple Coma

Scalable shared-memory multiprocessors that are designed as Cache-Only Memory Architectures Coma allow automatic replication and migration of data in the main memory. This enhances programmability by hopefully eliminating the need for data distribution strategies and page migration schemes. Recently, a variant of Coma called Simple Coma has been proposed as a lower-cost alternative to hardware-intensive systems like Flat Coma. However, we nd that Simple Coma is quite slower than Flat Coma. The main reason is the high page mapping, unmapping, and transfer overhead caused by memory fragmentation in Simple Coma. This paper proposes a solution to the memory fragmentation problem that we call Multiplexed Simple Coma. The idea is to allow multiple virtual pages to map into the same physical page at the same time, therefore compressing the page working set of the application. Multiplexed Simple Coma requires very little support over Simple Coma and reduces its execution time by about 40. We ...

• Type: Conference
• Year: 1998
• Where: HPCA
• Authors: Sujoy Basu, Josep Torrellas
• Keywords: Distributed And Parallel Computing, Flat Coma, HPCA 1998, Multiplexed Simple Coma, Simple Coma