Filters








58 Hits in 6.6 sec

Sandbox Prefetching: Safe run-time evaluation of aggressive prefetchers

Seth H Pugsley, Zeshan Chishti, Chris Wilkerson, Peng-fei Chuang, Robert L Scott, Aamer Jaleel, Shih-Lien Lu, Kingsum Chow, Rajeev Balasubramonian
2014 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)  
Sandbox Prefetching evaluates simple, aggressive offset prefetchers at run-time by adding the prefetch address to a Bloom filter, rather than actually fetching the data into the cache.  ...  In this work, we propose a new mechanism to determine at run-time the appropriate prefetching mechanism for the currently executing program, called Sandbox Prefetching.  ...  Sandbox Prefetching Sandbox Prefetching (SBP) represents another class of prefetcher, and combines the ideas of global confirmation with immediate action to aggressively, and safely, perform prefetches  ... 
doi:10.1109/hpca.2014.6835971 dblp:conf/hpca/PugsleyCWCSJLCB14 fatcat:2ijnlzqfb5ba3l4pfif6b7feam

Automatically Generating Symbolic Prefetches for Distributed Transactional Memories [chapter]

Alokika Dash, Brian Demsky
2010 Lecture Notes in Computer Science  
We evaluate this prefetching mechanism in the context of a middleware framework for distributed transactional memory.  ...  Our results show that symbolic prefetching combined with caching can eliminate an average of 87% of remote reads.  ...  We varied the threshold between 50% for less aggressive prefetching and 5% for more aggressive prefetching.  ... 
doi:10.1007/978-3-642-16955-7_18 fatcat:n3nsbvgzb5h6xoykvya35jbuvu

Integrating Caching and Prefetching Mechanisms in a Distributed Transactional Memory

Alokika Dash, Brian Demsky
2011 IEEE Transactions on Parallel and Distributed Systems  
Our approach makes aggressive use of both prefetching and caching of remote objects to hide network latency while relying on the transaction commit mechanism to preserve the simple transactional consistency  ...  We have observed a speedup of up to 7.26× for distributed applications on our system using prefetching and caching and a speedup of up to 5.55× for parallel applications on our system.  ...  EVALUATION We ran our benchmarks on a cluster of 8 identical 3.06 GHz Intel Xeon servers running Linux version 2.6.25 and connected with gigabit Ethernet.  ... 
doi:10.1109/tpds.2011.23 fatcat:nitbuelfjvffdk2polrmuxpibq

Combining control-flow integrity and static analysis for efficient and validated data sandboxing

Bin Zeng, Gang Tan, Greg Morrisett
2011 Proceedings of the 18th ACM conference on Computer and communications security - CCS '11  
This paper evaluates whether CFI-enabled static analysis can help build efficient and validated data sandboxing.  ...  Previous systems generally sandbox memory writes for integrity, but avoid protecting confidentiality due to the high overhead of sandboxing memory reads.  ...  Second, some of our static analysis such as range analysis is geared toward the purpose of optimizing checks for guaranteeing safe access within data memory. Code sandboxing.  ... 
doi:10.1145/2046707.2046713 dblp:conf/ccs/ZengTM11 fatcat:ko7e67uyg5eznkclpbx5hobyue

MuonTrap: Preventing Cross-Domain Spectre-Like Attacks by Capturing Speculative State [article]

Sam Ainsworth, Timothy M. Jones
2020 arXiv   pre-print
MuonTrap uses these speculative filter caches, which are cleared on context and protection-domain switches, along with a series of extensions to the cache coherence protocol and prefetcher.  ...  with the rest of the cache hierarchy.  ...  We also evaluate on Parsec [10] , running on the simsmall datasets with 4 threads in full-system mode running Linux.  ... 
arXiv:1911.08384v2 fatcat:wehh4h2wz5ffdlrxlctxqzplbe

Performance Improvement via Always-Abort HTM

Joseph Izraelevitz, Lingxiang Xiang, Michael L. Scott
2017 2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT)  
instruction), and is thus guaranteed to be free of side effects.  ...  With always-abort HTM (AAHTM), no such synchronization is necessary, because there is no risk of accidentally committing a transaction that has seen inconsistent state.  ...  Acknowledgments We would like to thank Jongsoo Park for his insights on the use of barriers in HPC applications.  ... 
doi:10.1109/pact.2017.16 dblp:conf/IEEEpact/IzraelevitzXS17 fatcat:n3f45w4iira4zglhwrh3gzn3ay

A file system for safely interacting with untrusted USB flash drives

Ke Zhong, Zhihao Jiang, Ke Ma, Sebastian Angel
2020 USENIX Workshop on Hot Topics in Storage and File Systems  
The result of this decomposition is that the host can access all the files in the flash drive without speaking USB.  ...  This paper introduces RBFuse, a system for interacting with USB flash drives safely in commodity OSes while bypassing the complex and bug-prone USB stack on the host.  ...  To reduce costs, we adapt optimizations that have been proposed for networked file systems to aggressively cache metadata, batch operations, and prefetch files.  ... 
dblp:conf/hotstorage/ZhongJMA20 fatcat:oroqryuo7nc2nahifuji67krh4

Delegation and nesting in best-effort hardware transactional memory

Yujie Liu, Stephan Diestelhorst, Michael Spear
2012 Proceedinbgs of the 24th ACM symposium on Parallelism in algorithms and architectures - SPAA '12  
In exchange, the hardware can support only relatively simple multiword atomic operations, and must fall back to a software run-time for any operation that exceeds the abilities of the hardware.  ...  This paper also explores which forms of nesting are possible, and identifies constraints on nesting that are a consequence of how BEHTM is designed.  ...  transactions to a software run-time.  ... 
doi:10.1145/2312005.2312014 dblp:conf/spaa/LiuDS12 fatcat:lpwa2l4gsvethnm42wun7xtsa4

Software-based Microarchitectural Attacks [article]

Daniel Gruss
2017 arXiv   pre-print
Modern processors are highly optimized systems where every single cycle of computation time matters. Many optimizations depend on the data that is being processed.  ...  Furthermore, we show that these attacks can be mounted in highly restricted environments such as sandboxed JavaScript code in websites.  ...  Our countermeasure requires only a small number of changes to operating system kernels and comes with a performance impact of 0.06-5.09%. Our key contributions are: 1.  ... 
arXiv:1706.05973v1 fatcat:4hwdpe4dancmblsxasg3a75h7a

SPECTRE

Jean-Philippe Martin, Christopher J. Rossbach, Michael Isard
2011 Proceedings of the Second Asia-Pacific Workshop on Systems - APSys '11  
We exploit aggressive speculation to hide the latency of remote memory accesses and synchronization, and execute all code transactionally so that mis-speculations can be discovered and reverted.  ...  Stale reads are detected by SNs at commit time, and a prefetching and best-effort invalidation protocol helps to keep cached objects up to date to avoid excessive aborts.  ...  The ON stores the complete task graph, manages the assignment of tasks to CNs, and informs CNs when it is safe to commit a given transaction.  ... 
doi:10.1145/2103799.2103821 dblp:conf/apsys/MartinRI11 fatcat:u5uknv3mqbaipgmf5k655zscvq

Web Browser Privacy: What Do Browsers Say When They Phone Home?

Douglas J. Leith
2021 IEEE Access  
Overall, we find that both the desktop and mobile versions of Brave do not use any identifiers allowing tracking of IP address over time, and do not share details of web pages visited with backend servers  ...  With regard to shared services, all of the browsers make use of a safe browsing service to mitigate phishing attacks and our measurements indicate that this raises few privacy concerns.  ...  Each test is repeated multiple times to allow evaluation of changes in request identifiers across fresh installs.  ... 
doi:10.1109/access.2021.3065243 fatcat:h2ifp2koyzfojlpr6sc7iapuba

Practical and Theoretical Issues in Prefetching and Caching (CMU-CS-97-181)

Andrew Tomkins
2018
in the free-time model.  ...  I then show a connection between this problem and a new on-line k-server model in which the servers may rearrange themselves without cost during "free-time" between requests, and describe a series of results  ...  evaluation of the TIP2 system.  ... 
doi:10.1184/r1/6619739.v1 fatcat:mtrdcelfs5ezzfhggttgac6fwi

SpecBox: A Label-Based Transparent Speculation Scheme Against Transient Execution Attacks [article]

Bowen Tang, Chenggang Wu, Zhe Wang, Lichen Jia, Pen-Chung Yew, Yueqiang Cheng, Yinqian Zhang, Chenxi Wang, Guoqing Harry Xu
2021 arXiv   pre-print
In addition, SpecBox also enhances the auxiliary components in the cache system against transient execution attacks, such as hardware prefetcher.  ...  Our security analysis shows that SpecBox is secure and the performance evaluation shows that the performance overhead on SPEC CPU 2006 and PARSEC-3.0 benchmarks is small.  ...  This situation rarely occurs in general out-of-order processors, and usually only occurs in more aggressive optimizations, such as run-ahead execution [41] .  ... 
arXiv:2107.08367v1 fatcat:3ax63aj3zndoplhjorwu5ly6ti

Active Disks: Programming Model, Algorithms and Evaluation [chapter]

2009 High Performance Mass Storage and Parallel I/O  
To program Active Disks, we propose a stream-based programming model which allows disklets to be executed e ciently and safely.  ...  The key idea is to o oad bulk of the processing to the diskresident processors and to use the host processor primarily for coordination, scheduling and combination of results from individual disks.  ...  We like to thank Sanjeev Setia, Guy Edjlali and anonymous referees for their comments on di erent v ersions of this paper.  ... 
doi:10.1109/9780470544839.ch34 fatcat:qcq4bnecifdldc3krn5vgdna3m

ZombieLoad

Michael Schwarz, Moritz Lipp, Daniel Moghimi, Jo Van Bulck, Julian Stecklina, Thomas Prescher, Daniel Gruss
2019 Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security - CCS '19  
We demonstrate ZombieLoad's effectiveness in a multitude of practical attack scenarios across CPU privilege rings, OS processes, virtual machines, and SGX enclaves.  ...  While this attack has been mitigated through stronger isolation boundaries between user and kernel space, Meltdown inspired an entirely new class of fault-driven transient-execution attacks.  ...  ACKNOWLEDGMENTS We thank Werner Haas (Cyberus Technology), Claudio Canella (Graz University of Technology), Jon Masters (Red Hat), Alex Ionescu (CrowdStrike), and Martin Schwarzl (Graz University of Technology  ... 
doi:10.1145/3319535.3354252 dblp:conf/ccs/0001LMBS0G19 fatcat:wj7yuw3ei5bebhh2vql26hpb7e
« Previous Showing results 1 — 15 out of 58 results