A paper to be presented at an IEEE symposium later this month details a new memory management technique that could allow apps to run up to 20 percent faster on multi-core processors. The paper offers a partial solution to a problem that’s been plaguing the application development community: how to write software that can process data in parallel in multi-core systems, using all of the available cores at once.
Report co-author Yan Solihin explains, “We noticed that there’s a large group of software that’s difficult to parallelize,” he said. “A lot of these applications are also memory allocation intensive, meaning that that call malloc or free frequently. So our idea is to move this memory allocation to a separate thread. We call that the memory management thread, or MMT.”