Title: Improving DRAM Performance by Parallelizing Refreshes with Accesses
Kevin Chang
Tuesday, Mar. 25th, 4:00pm-5:00pm
Hamerschlag Hall D-210
Abstract
Modern DRAM cells are periodically refreshed to prevent data loss due to
leakage. Commodity DRAM refreshes cells at the rank level. This degrades
performance significantly because it prevents an entire DRAM rank from serving
memory requests while being refreshed. We propose two new complementary
techniques, DARP (Dynamic Access Refresh Parallelization) and SARP (Subarray
Access Refresh Parallelization), to mitigate the DRAM refresh penalty
by enhancing refresh-access parallelization at the bank and subarray levels,
respectively. DARP 1) issues per-bank refreshes to idle banks in an
out-of-order manner instead of issuing refreshes in a strict round-robin
order, 2) proactively schedules per-bank refreshes during intervals when a
batch of writes are draining to DRAM. SARP enables a bank to serve requests
from idle subarrays in parallel with other subarrays that are being refreshed.
Extensive evaluations on a wide variety of workloads and systems show that our
mechanisms improve system performance (and energy efficiency) compared to
state-of-the-art refresh policies.
Bio
Kevin Chang is a third year PhD student in the Electrical and Computer
Engineering Department at Carnegie Mellon University, where he is advised by
Professor Onur Mutlu. His research focuses on improving performance and
energy-efficiency of memory sub-systems. He has also done work in the past on
high-performance on-chip interconnects. He received his B.S./M.S. in Electrical
and Computer Engineering in 2011.