Filters








60 Hits in 1.8 sec

HARD: Hardware-Assisted Lockset-based Race Detection

Pin Zhou, Radu Teodorescu, Yuanyuan Zhou
2007 2007 IEEE 13th International Symposium on High Performance Computer Architecture  
However, all existing hardware proposals for race detection are based on the happensbefore algorithm which is sensitive to thread interleaving and cannot detect races that are not exposed during the monitored  ...  This paper proposes the first hardware implementation (called HARD) of the lockset algorithm to exploit the race detection capability of this algorithm with minimal overhead.  ...  Conclusions and Future Work This paper has presented HARD, an efficient hardware implementation of lockset-based race detection to detect more data races (compared to other hardware race detectors) with  ... 
doi:10.1109/hpca.2007.346191 dblp:conf/hpca/ZhouTZ07 fatcat:tdhp3tb3hbainn5hrjrd24t2jy

Software Analysis Techniques for Detecting Data Race

Pilsung KANG
2017 IEICE transactions on information and systems  
In this paper, we survey data race detection techniques in each of these two approaches.  ...  Data races are well-known to be hard to debug, mainly because the effect of the conflicting accesses depends on the interleaving of the thread executions.  ...  Data races are hard to debug.  ... 
doi:10.1587/transinf.2017edr0004 fatcat:3pvnugswmfcondv6wxaha6dwee

NUDA: A Non-Uniform Debugging Architecture and Nonintrusive Race Detection for Many-Core Systems

Chi-Neng Wen, Shu-Hsuan Chou, Chien-Chih Chen, Tien-Fu Chen
2012 IEEE transactions on computers  
Our second contribution is to propose a nonintrusive approach to lockset-based race detection supported by the NUDA.  ...  Our approach makes hardware-assisted debugging both feasible and scalable for many-core processing scenarios.  ...  HARD [11] provides a novel hardware-assisted lockset-based race detection approach, and it employs additional fields (such as a Bloom filter vector(BFVector)) in the cache and detects the race condition  ... 
doi:10.1109/tc.2010.254 fatcat:6bcrurc6p5aenojnwikfsqhvcy

Using hardware transactional memory for data race detection

Shantanu Gupta, Florin Sultan, Srihari Cadambi, Franjo Ivancic, Martin Rotteler
2009 2009 IEEE International Symposium on Parallel & Distributed Processing  
In particular, we show how emerging hardware support for transactional memory can be leveraged to aid data race detection.  ...  Dependable multithreaded software will have to rely on the ability to dynamically detect nondeterministic and notoriously hard to reproduce synchronization bugs manifested through data races.  ...  Specialized Hardware Support. HARD [32] implements lockset-based detection using Bloom filters to represent locksets and candidate sets.  ... 
doi:10.1109/ipdps.2009.5161006 dblp:conf/ipps/GuptaSCIR09 fatcat:erm6mlqi4vhlbh3r4qil4x3mjy

AVIO

Shan Lu, Joseph Tucek, Feng Qin, Yuanyuan Zhou
2006 SIGARCH Computer Architecture News  
Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important  ...  The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware.  ...  We propose an innovative, comprehensive, invariant-based approach called AVIO to detect a class of hard bugs: general atomicity violations.  ... 
doi:10.1145/1168919.1168864 fatcat:w3a4p6a7erbifmtuo4tmq7q5vi

AVIO

Shan Lu, Joseph Tucek, Feng Qin, Yuanyuan Zhou
2006 SIGPLAN notices  
Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important  ...  The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware.  ...  We propose an innovative, comprehensive, invariant-based approach called AVIO to detect a class of hard bugs: general atomicity violations.  ... 
doi:10.1145/1168918.1168864 fatcat:7rbve6fntvdpvdjh7cpolxranm

AVIO

Shan Lu, Joseph Tucek, Feng Qin, Yuanyuan Zhou
2006 Proceedings of the 12th international conference on Architectural support for programming languages and operating systems - ASPLOS-XII  
Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important  ...  The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware.  ...  We propose an innovative, comprehensive, invariant-based approach called AVIO to detect a class of hard bugs: general atomicity violations.  ... 
doi:10.1145/1168857.1168864 dblp:conf/asplos/LuTQZ06 fatcat:7kgiofzo65annaxcracbwdp7km

AVIO

Shan Lu, Joseph Tucek, Feng Qin, Yuanyuan Zhou
2006 ACM SIGOPS Operating Systems Review  
Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important  ...  The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware.  ...  We propose an innovative, comprehensive, invariant-based approach called AVIO to detect a class of hard bugs: general atomicity violations.  ... 
doi:10.1145/1168917.1168864 fatcat:czswvptfdrcqnlzjbecrtcccka

Efficient Deterministic Replay Using Complete Race Detection [article]

Qi Guo, Yunji Chen, Tianshi chen, Ling Li
2011 arXiv   pre-print
The key insight of RacX is as follows: although it is NP-hard to accurately identify the existence of data races between a pair of memory operations, we can find out all potential data races in a multi-threaded  ...  Inspired by the advances in data race detection, we propose an efficient software-only deterministic replay scheme for commodity multi-processor systems, which is named RacX.  ...  The concrete detection algorithm can be based on happens-before analysis [25, 8] (which can be further improved with respect to efficiency and accuracy by hardware-based approaches as [42, 33, 29] )  ... 
arXiv:1107.2003v2 fatcat:mlbhuzw2tnaojj3gbrjshljubi

Log-based architectures for general-purpose monitoring of deployed code

Shimin Chen, Bin Lin, Steven W. Schlosser, Babak Falsafi, Phillip B. Gibbons, Michael Kozuch, Todd C. Mowry, Radu Teodorescu, Anastassia Ailamaki, Limor Fix, Gregory R. Ganger
2006 Proceedings of the 1st workshop on Architectural and system support for improving software dependability - ASID '06  
rewind. tects possible data races in multithreaded programs using the LockSet algorithm.  ...  Moreover, the hardware-based logging captures hardware state directly.  ... 
doi:10.1145/1181309.1181319 dblp:conf/asplos/ChenFGKMTAFGLS06 fatcat:lsbm5ylwlzgphai2rginxhe3vi

Flexible Hardware Acceleration for Instruction-Grain Program Monitoring

Shimin Chen, Evangelos Vlachos, Michael Kozuch, Theodoros Strigkos, Babak Falsafi, Phillip B. Gibbons, Todd C. Mowry, Vijaya Ramachandran, Olatunji Ruwase, Michael Ryan
2008 SIGARCH Computer Architecture News  
By examining a number of diverse tools (for memory checking, security tracking, and data race detection), we identify three significant common sources of overheads and then propose three novel hardware  ...  Unfortunately, their fine-grain nature implies very high monitoring overheads for softwareonly tools, which are typically based on dynamic binary instrumentation.  ...  HARD [41] implements hardware-based LOCKSET by extending every cache line with a hardware bloom filter representing the candidate lockset and augmenting the snoopy-based cache coherence protocol for  ... 
doi:10.1145/1394608.1382153 fatcat:auj2fmes3vcihejabwgdfsxlei

Flexible Hardware Acceleration for Instruction-Grain Program Monitoring

Shimin Chen, Michael Kozuch, Theodoros Strigkos, Babak Falsafi, Phillip B. Gibbons, Todd C. Mowry, Vijaya Ramachandran, Olatunji Ruwase, Michael Ryan, Evangelos Vlachos
2008 2008 International Symposium on Computer Architecture  
By examining a number of diverse tools (for memory checking, security tracking, and data race detection), we identify three significant common sources of overheads and then propose three novel hardware  ...  Unfortunately, their fine-grain nature implies very high monitoring overheads for softwareonly tools, which are typically based on dynamic binary instrumentation.  ...  HARD [41] implements hardware-based LOCKSET by extending every cache line with a hardware bloom filter representing the candidate lockset and augmenting the snoopy-based cache coherence protocol for  ... 
doi:10.1109/isca.2008.20 dblp:conf/isca/ChenKSFGMRRRV08 fatcat:sf6a6h723zdpbkp2ymdlxmb67u

SigRace

Abdullah Muzahid, Dario Suárez, Shanxiang Qi, Josep Torrellas
2009 SIGARCH Computer Architecture News  
Recently, there have been several proposals for hardware-assisted data race detection.  ...  Our experiments show that SigRace is signicantly more effective than a state-ofthe-art conventional hardware-assisted race detector.  ...  Hardware Schemes for Race Detection There are at least four proposals for hardware-assisted data-race detectors, namely Min and Choi's [12] , ReEnact [19] , CORD [18] and HARD [30] .  ... 
doi:10.1145/1555815.1555797 fatcat:zthk6ed4srbmvolxi7u7m27jwy

SigRace

Abdullah Muzahid, Dario Suárez, Shanxiang Qi, Josep Torrellas
2009 Proceedings of the 36th annual international symposium on Computer architecture - ISCA '09  
Recently, there have been several proposals for hardware-assisted data race detection.  ...  Our experiments show that SigRace is signicantly more effective than a state-ofthe-art conventional hardware-assisted race detector.  ...  Hardware Schemes for Race Detection There are at least four proposals for hardware-assisted data-race detectors, namely Min and Choi's [12] , ReEnact [19] , CORD [18] and HARD [30] .  ... 
doi:10.1145/1555754.1555797 dblp:conf/isca/MuzahidSQT09 fatcat:26sb43trvrbxdj4sualhnxs7ni

Guardrail

Olatunji Ruwase, Michael A. Kozuch, Phillip B. Gibbons, Todd C. Mowry
2014 Proceedings of the 19th international conference on Architectural support for programming languages and operating systems - ASPLOS '14  
and mitigate more challenging correctness bugs (e.g., data races, uninitialized memory accesses) that cannot be detected by today's fault isolation techniques.  ...  Also, with hardware logging support, Guardrail can be used for online protection of persistent device state from driver bugs with at most 10% overhead on the end-to-end performance of most standard I/O  ...  If there is no such common lock, Lockset reports a potential data race. DRCheck extends Lockset as follows.  ... 
doi:10.1145/2541940.2541970 dblp:conf/asplos/RuwaseKGM14 fatcat:h7qrjl77srfdtixpvl7fv3ts4m
« Previous Showing results 1 — 15 out of 60 results