Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/9250
Title: | HiRA: Hidden Row Activation for Reducing Refresh Latency of Off-the-Shelf DRAM Chips | Authors: | Giray, Yaglikci, A. Olgun, A. Patel, M. Luo, H. Hassan, H. Orosa, L. Ergin, Oğuz |
Keywords: | DRAM memory access latency memory controller refresh rowhammer Dynamic random access storage Failure (mechanical) Memory architecture Data loss DRAM cells DRAM chips Memory access Memory access latency Memory controller Refresh Rowhammer Systems performance Technology nodes Chemical activation |
Publisher: | IEEE Computer Society | Abstract: | DRAM is the building block of modern main memory systems. DRAM cells must be periodically refreshed to prevent data loss. Refresh operations degrade system performance by interfering with memory accesses. As DRAM chip density increases with technology node scaling, refresh operations also increase be-cause: 1) the number of DRAM rows in a chip increases; and 2) DRAM cells need additional refresh operations to mitigate bit failures caused by RowHammer, a failure mechanism that becomes worse with technology node scaling. Thus, it is critical to enable refresh operations at low performance overhead. To this end, we propose a new operation, Hidden Row Activation (HiRA), and the HiRA Memory Controller (HiRA-MC) to perform HiRA operations. HiRA hides a refresh operation's latency by refreshing a row concurrently with accessing or refreshing another row within the same bank. Unlike prior works, HiRA achieves this parallelism without any modifications to off-the-shelf DRAM chips. To do so, it leverages the new observation that two rows in the same bank can be activated without data loss if the rows are connected to different charge restoration circuitry. We experimentally demonstrate on 56 real off-the-shelf DRAM chips that HiRA can reliably parallelize a DRAM row's refresh operation with refresh or activation of any of the 32% of the rows within the same bank. By doing so, HiRA reduces the overall latency of two refresh operations by 51.4%. HiRA-MC modifies the memory request scheduler to perform HiRA when a refresh operation can be performed concurrently with a memory access or another refresh. Our system-level evaluations show that HiRA-MC increases system performance by 12.6% and 3.73× as it reduces the performance degradation due to periodic refreshes and refreshes for RowHammer protection (preventive refreshes), respectively, for future DRAM chips with increased density and RowHammer vulnerability. © 2022 IEEE. | Description: | aws;et al.;Futurewei Technologies;IBM;Intel;Northwestern Engineering 55th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2022 -- 1 October 2022 through 5 October 2022 -- 183812 |
URI: | https://doi.org/10.1109/MICRO56248.2022.00062 https://hdl.handle.net/20.500.11851/9250 |
ISBN: | 9781665462723 | ISSN: | 1072-4451 |
Appears in Collections: | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection |
Show full item record
CORE Recommender
SCOPUSTM
Citations
2
checked on Nov 2, 2024
WEB OF SCIENCETM
Citations
18
checked on Nov 2, 2024
Page view(s)
226
checked on Nov 4, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.