Loading…
ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation
We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer attacks tend to access DRAM rows with the same row address in...
Saved in:
Published in: | arXiv.org 2023-12 |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | |
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Olgun, Ataberk Yahya Can Tugrul Bostanci, Nisa Ismail Emir Yuksel Luo, Haocong Rhyner, Steve Abdullah Giray Yaglikci Oliveira, Geraldo F Mutlu, Onur |
description | We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer attacks tend to access DRAM rows with the same row address in multiple DRAM banks at around the same time. Based on this observation, ABACuS's key idea is to use a single shared row activation counter to track activations to the rows with the same row address in all DRAM banks. Unlike state-of-the-art RowHammer mitigation mechanisms that implement a separate row activation counter for each DRAM bank, ABACuS implements fewer counters (e.g., only one) to track an equal number of aggressor rows. Our evaluations show that ABACuS securely prevents RowHammer bitflips at low performance/energy overhead and low area cost. We compare ABACuS to four state-of-the-art mitigation mechanisms. At a near-future RowHammer threshold of 1000, ABACuS incurs only 0.58% (0.77%) performance and 1.66% (2.12%) DRAM energy overheads, averaged across 62 single-core (8-core) workloads, requiring only 9.47 KiB of storage per DRAM rank. At the RowHammer threshold of 1000, the best prior low-area-cost mitigation mechanism incurs 1.80% higher average performance overhead than ABACuS, while ABACuS requires 2.50X smaller chip area to implement. At a future RowHammer threshold of 125, ABACuS performs very similarly to (within 0.38% of the performance of) the best prior performance- and energy-efficient RowHammer mitigation mechanism while requiring 22.72X smaller chip area. ABACuS is freely and openly available at https://github.com/CMU-SAFARI/ABACuS. |
format | article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2878378545</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2878378545</sourcerecordid><originalsourceid>FETCH-proquest_journals_28783785453</originalsourceid><addsrcrecordid>eNqNi0ELgjAYQEcQJOV_-KCzYJumdFMpPBRBBh1l6azZ3Gqb-veL6Ad0eof33gQ5mJCVFwcYz5BrTOv7Pl5HOAyJgy5JmmR9sYFECC-l8gFJZflALVcSMtVLy7SBRmkoKiroVTCgsoa9GuE4MH1ntIaTGnPadUzDgVt--74LNG2oMMz9cY6Wu-05y72nVq-eGVu2qtfyo0ocRzGJ4jAIyX_VG3JqQFY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2878378545</pqid></control><display><type>article</type><title>ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation</title><source>Publicly Available Content Database</source><creator>Olgun, Ataberk ; Yahya Can Tugrul ; Bostanci, Nisa ; Ismail Emir Yuksel ; Luo, Haocong ; Rhyner, Steve ; Abdullah Giray Yaglikci ; Oliveira, Geraldo F ; Mutlu, Onur</creator><creatorcontrib>Olgun, Ataberk ; Yahya Can Tugrul ; Bostanci, Nisa ; Ismail Emir Yuksel ; Luo, Haocong ; Rhyner, Steve ; Abdullah Giray Yaglikci ; Oliveira, Geraldo F ; Mutlu, Onur</creatorcontrib><description>We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer attacks tend to access DRAM rows with the same row address in multiple DRAM banks at around the same time. Based on this observation, ABACuS's key idea is to use a single shared row activation counter to track activations to the rows with the same row address in all DRAM banks. Unlike state-of-the-art RowHammer mitigation mechanisms that implement a separate row activation counter for each DRAM bank, ABACuS implements fewer counters (e.g., only one) to track an equal number of aggressor rows. Our evaluations show that ABACuS securely prevents RowHammer bitflips at low performance/energy overhead and low area cost. We compare ABACuS to four state-of-the-art mitigation mechanisms. At a near-future RowHammer threshold of 1000, ABACuS incurs only 0.58% (0.77%) performance and 1.66% (2.12%) DRAM energy overheads, averaged across 62 single-core (8-core) workloads, requiring only 9.47 KiB of storage per DRAM rank. At the RowHammer threshold of 1000, the best prior low-area-cost mitigation mechanism incurs 1.80% higher average performance overhead than ABACuS, while ABACuS requires 2.50X smaller chip area to implement. At a future RowHammer threshold of 125, ABACuS performs very similarly to (within 0.38% of the performance of) the best prior performance- and energy-efficient RowHammer mitigation mechanism while requiring 22.72X smaller chip area. ABACuS is freely and openly available at https://github.com/CMU-SAFARI/ABACuS.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Workload ; Workloads</subject><ispartof>arXiv.org, 2023-12</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2878378545?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Olgun, Ataberk</creatorcontrib><creatorcontrib>Yahya Can Tugrul</creatorcontrib><creatorcontrib>Bostanci, Nisa</creatorcontrib><creatorcontrib>Ismail Emir Yuksel</creatorcontrib><creatorcontrib>Luo, Haocong</creatorcontrib><creatorcontrib>Rhyner, Steve</creatorcontrib><creatorcontrib>Abdullah Giray Yaglikci</creatorcontrib><creatorcontrib>Oliveira, Geraldo F</creatorcontrib><creatorcontrib>Mutlu, Onur</creatorcontrib><title>ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation</title><title>arXiv.org</title><description>We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer attacks tend to access DRAM rows with the same row address in multiple DRAM banks at around the same time. Based on this observation, ABACuS's key idea is to use a single shared row activation counter to track activations to the rows with the same row address in all DRAM banks. Unlike state-of-the-art RowHammer mitigation mechanisms that implement a separate row activation counter for each DRAM bank, ABACuS implements fewer counters (e.g., only one) to track an equal number of aggressor rows. Our evaluations show that ABACuS securely prevents RowHammer bitflips at low performance/energy overhead and low area cost. We compare ABACuS to four state-of-the-art mitigation mechanisms. At a near-future RowHammer threshold of 1000, ABACuS incurs only 0.58% (0.77%) performance and 1.66% (2.12%) DRAM energy overheads, averaged across 62 single-core (8-core) workloads, requiring only 9.47 KiB of storage per DRAM rank. At the RowHammer threshold of 1000, the best prior low-area-cost mitigation mechanism incurs 1.80% higher average performance overhead than ABACuS, while ABACuS requires 2.50X smaller chip area to implement. At a future RowHammer threshold of 125, ABACuS performs very similarly to (within 0.38% of the performance of) the best prior performance- and energy-efficient RowHammer mitigation mechanism while requiring 22.72X smaller chip area. ABACuS is freely and openly available at https://github.com/CMU-SAFARI/ABACuS.</description><subject>Workload</subject><subject>Workloads</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNi0ELgjAYQEcQJOV_-KCzYJumdFMpPBRBBh1l6azZ3Gqb-veL6Ad0eof33gQ5mJCVFwcYz5BrTOv7Pl5HOAyJgy5JmmR9sYFECC-l8gFJZflALVcSMtVLy7SBRmkoKiroVTCgsoa9GuE4MH1ntIaTGnPadUzDgVt--74LNG2oMMz9cY6Wu-05y72nVq-eGVu2qtfyo0ocRzGJ4jAIyX_VG3JqQFY</recordid><startdate>20231223</startdate><enddate>20231223</enddate><creator>Olgun, Ataberk</creator><creator>Yahya Can Tugrul</creator><creator>Bostanci, Nisa</creator><creator>Ismail Emir Yuksel</creator><creator>Luo, Haocong</creator><creator>Rhyner, Steve</creator><creator>Abdullah Giray Yaglikci</creator><creator>Oliveira, Geraldo F</creator><creator>Mutlu, Onur</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231223</creationdate><title>ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation</title><author>Olgun, Ataberk ; Yahya Can Tugrul ; Bostanci, Nisa ; Ismail Emir Yuksel ; Luo, Haocong ; Rhyner, Steve ; Abdullah Giray Yaglikci ; Oliveira, Geraldo F ; Mutlu, Onur</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28783785453</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Workload</topic><topic>Workloads</topic><toplevel>online_resources</toplevel><creatorcontrib>Olgun, Ataberk</creatorcontrib><creatorcontrib>Yahya Can Tugrul</creatorcontrib><creatorcontrib>Bostanci, Nisa</creatorcontrib><creatorcontrib>Ismail Emir Yuksel</creatorcontrib><creatorcontrib>Luo, Haocong</creatorcontrib><creatorcontrib>Rhyner, Steve</creatorcontrib><creatorcontrib>Abdullah Giray Yaglikci</creatorcontrib><creatorcontrib>Oliveira, Geraldo F</creatorcontrib><creatorcontrib>Mutlu, Onur</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Olgun, Ataberk</au><au>Yahya Can Tugrul</au><au>Bostanci, Nisa</au><au>Ismail Emir Yuksel</au><au>Luo, Haocong</au><au>Rhyner, Steve</au><au>Abdullah Giray Yaglikci</au><au>Oliveira, Geraldo F</au><au>Mutlu, Onur</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation</atitle><jtitle>arXiv.org</jtitle><date>2023-12-23</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer attacks tend to access DRAM rows with the same row address in multiple DRAM banks at around the same time. Based on this observation, ABACuS's key idea is to use a single shared row activation counter to track activations to the rows with the same row address in all DRAM banks. Unlike state-of-the-art RowHammer mitigation mechanisms that implement a separate row activation counter for each DRAM bank, ABACuS implements fewer counters (e.g., only one) to track an equal number of aggressor rows. Our evaluations show that ABACuS securely prevents RowHammer bitflips at low performance/energy overhead and low area cost. We compare ABACuS to four state-of-the-art mitigation mechanisms. At a near-future RowHammer threshold of 1000, ABACuS incurs only 0.58% (0.77%) performance and 1.66% (2.12%) DRAM energy overheads, averaged across 62 single-core (8-core) workloads, requiring only 9.47 KiB of storage per DRAM rank. At the RowHammer threshold of 1000, the best prior low-area-cost mitigation mechanism incurs 1.80% higher average performance overhead than ABACuS, while ABACuS requires 2.50X smaller chip area to implement. At a future RowHammer threshold of 125, ABACuS performs very similarly to (within 0.38% of the performance of) the best prior performance- and energy-efficient RowHammer mitigation mechanism while requiring 22.72X smaller chip area. ABACuS is freely and openly available at https://github.com/CMU-SAFARI/ABACuS.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2023-12 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2878378545 |
source | Publicly Available Content Database |
subjects | Workload Workloads |
title | ABACuS: All-Bank Activation Counters for Scalable and Low Overhead RowHammer Mitigation |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T02%3A39%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=ABACuS:%20All-Bank%20Activation%20Counters%20for%20Scalable%20and%20Low%20Overhead%20RowHammer%20Mitigation&rft.jtitle=arXiv.org&rft.au=Olgun,%20Ataberk&rft.date=2023-12-23&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2878378545%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28783785453%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2878378545&rft_id=info:pmid/&rfr_iscdi=true |