Filters








30 Hits in 2.3 sec

POSTER

Pedro Ramalhete, Andreia Correia
2017 Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '17  
Our algorithm uses one mutual exclusion lock and two reader-writer locks with trylock() capabilities, which means it does not need a language with a memory model or atomics API, and as such, it can be  ...  RCU is, among other things, a well known mechanism for memory reclamation that is meant to be used in languages without an automatic Garbage Collector, unfortunately, it requires operating system support  ...  Threads that call rcu read lock() and rcu read unlock() (readers) will attempt to acquire the reader lock on the first of the readerwriter locks (rwlock1) with a trylock(), and if it fails, do a trylock  ... 
doi:10.1145/3018743.3019021 fatcat:dpr64aq34rguba2svcquhxerny

Architectural Support for Fair Reader-Writer Locking

Enrique Vallejo, Ramon Beivide, Adrian Cristal, Tim Harris, Fernando Vallejo, Osman Unsal, Mateo Valero
2010 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture  
Additionally, few proposals cover reader-writer locks and their associated fairness issues.  ...  In this paper we introduce the Lock Control Unit (LCU) which is an acceleration mechanism collocated with each core to explicitly handle fast reader-writer locking.  ...  Other interesting requirements for current workloads are reader-writer (RW) locks and trylock support. Reader-writer locks allow for a single lock owner in write mode or multiple concurrent readers.  ... 
doi:10.1109/micro.2010.12 dblp:conf/micro/VallejoBCHVUV10 fatcat:hftntmhjrfdtdbywsgvgr5ixfa

A Wait-Free Universal Construct for Large Objects [article]

Andreia Correia, Pedro Ramalhete, Pascal Felber
2019 arXiv   pre-print
, safe memory reclamation and high reader scalability.  ...  This need has pushed for generic solutions and specific concurrent data structures.  ...  Reader-Writer Lock with Strong Trylock Access to each Combined instance and, consequently, to each copy of the object is managed by a reader-writer lock, Combined.rwlock.  ... 
arXiv:1911.01676v1 fatcat:y6cfg4do3vhijmwiddteolhy2e

Proving Non-opacity [chapter]

Mohsen Lesani, Jens Palsberg
2013 Lecture Notes in Computer Science  
We then prove that for direct-update TM algorithms, opacity is incompatible with a liveness criterion called local progress, even for fault-free systems.  ...  Guerraoui and Kapalka defined opacity as a safety criterion for transactional memory algorithms in 2008.  ...  Lock and try-locks TryLock.  ... 
doi:10.1007/978-3-642-41527-2_8 fatcat:tdkjeio54jb2lizlhv2233ns3e

SATCheck: SAT-directed stateless model checking for SC and TSO

Brian Demsky, Patrick Lam
2015 SIGPLAN notices  
In this paper we present a new and more scalable technique for model checking concurrent code, based on concrete execution.  ...  Model-checking is a powerful technique for exhaustively testing code. However, scaling model checking presents a significant challenge.  ...  We would also like to thank the anonymous reviewers for their helpful comments.  ... 
doi:10.1145/2858965.2814297 fatcat:zjbnpx7xqfebnogpl4ywp6n2zq

SATCheck: SAT-directed stateless model checking for SC and TSO

Brian Demsky, Patrick Lam
2015 Proceedings of the 2015 ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications - OOPSLA 2015  
In this paper we present a new and more scalable technique for model checking concurrent code, based on concrete execution.  ...  Model-checking is a powerful technique for exhaustively testing code. However, scaling model checking presents a significant challenge.  ...  We would also like to thank the anonymous reviewers for their helpful comments.  ... 
doi:10.1145/2814270.2814297 dblp:conf/oopsla/DemskyL15 fatcat:xigjs2nuhjayxb7wetyc4jpefa

Optimistic concurrency with OPTIK

Rachid Guerraoui, Vasileios Trigonakis
2016 SIGPLAN notices  
Existing state-of-the-art lock-based data structures acquire the lock and then check for conflicts.  ...  These locks enable the use of version numbers for implementing very efficient optimistic concurrent data structures.  ...  We wish to thank our shepherd, Haibo Chen, and the anonymous reviewers for their fruitful comments.  ... 
doi:10.1145/3016078.2851146 fatcat:6cpogpvdqzhjzgal4bet4yts5i

Optimistic concurrency with OPTIK

Rachid Guerraoui, Vasileios Trigonakis
2016 Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '16  
Existing state-of-the-art lock-based data structures acquire the lock and then check for conflicts.  ...  These locks enable the use of version numbers for implementing very efficient optimistic concurrent data structures.  ...  We wish to thank our shepherd, Haibo Chen, and the anonymous reviewers for their fruitful comments.  ... 
doi:10.1145/2851141.2851146 dblp:conf/ppopp/GuerraouiT16 fatcat:bdxf2f77hrhsriycuxe4h73fku

Foundations of the C++ concurrency memory model

Hans-J. Boehm, Sarita V. Adve
2008 SIGPLAN notices  
programs with trylock.  ...  There are no benign C++ data races. • We use weaker semantics for trylock than existing languages or libraries, allowing us to promise sequential consistency with an intuitive race definition, even for  ...  Lawrence Crowl is also responsible for most of the detailed design of the atomics interface. The anonymous reviewers provided a number of useful suggestions.  ... 
doi:10.1145/1379022.1375591 fatcat:afs6fjtubzgnpphd7jquowt7xu

Foundations of the C++ concurrency memory model

Hans-J. Boehm, Sarita V. Adve
2008 Proceedings of the 2008 ACM SIGPLAN conference on Programming language design and implementation - PLDI '08  
programs with trylock.  ...  There are no benign C++ data races. • We use weaker semantics for trylock than existing languages or libraries, allowing us to promise sequential consistency with an intuitive race definition, even for  ...  Lawrence Crowl is also responsible for most of the detailed design of the atomics interface. The anonymous reviewers provided a number of useful suggestions.  ... 
doi:10.1145/1375581.1375591 dblp:conf/pldi/BoehmA08 fatcat:b6rqjwpzmjcdvdzaqjoeyl5kfy

Analyzing lock contention in multithreaded applications

Nathan R. Tallent, John M. Mellor-Crummey, Allan Porterfield
2010 SIGPLAN notices  
Finally, we propose a new technique for measurement and analysis of lock contention that uses data associated with locks to blame lock holders for the idleness of spinning threads.  ...  Threaded codes typically use locks to coordinate access to shared data. In many cases, contention for locks reduces parallel efficiency and hurts scalability.  ...  We thank Robert Fowler for focusing our attention on MAD-NESS, Robert Harrison for helping us with his MADNESS code, and William Scherer for reminding us of Bacon's prior work on dual-representation locks  ... 
doi:10.1145/1837853.1693489 fatcat:5uzl2v4c6ngvhg7lcdhmzfllom

Checking Concurrent Data Structures Under the C/C++11 Memory Model

Peizhao Ou, Brian Demsky
2017 SIGPLAN notices  
In this paper, we develop a correctness model for concurrent data structures that make use of atomic operations.  ...  The C/C++11 standard introduced a weak memory model with support for low-level atomic operations such as compare and swap (CAS).  ...  Linux Reader-Writer Lock: A reader-writer lock allows either multiple concurrent readers or one exclusive writer to hold a lock.  ... 
doi:10.1145/3155284.3018749 fatcat:nc3k7p4nszhsrizpesbcidooza

Checking Concurrent Data Structures Under the C/C++11 Memory Model

Peizhao Ou, Brian Demsky
2017 Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '17  
In this paper, we develop a correctness model for concurrent data structures that make use of atomic operations.  ...  The C/C++11 standard introduced a weak memory model with support for low-level atomic operations such as compare and swap (CAS).  ...  Linux Reader-Writer Lock: A reader-writer lock allows either multiple concurrent readers or one exclusive writer to hold a lock.  ... 
doi:10.1145/3018743.3018749 fatcat:aouass7o2ngkdeddfpmxyjwxtm

Analyzing lock contention in multithreaded applications

Nathan R. Tallent, John M. Mellor-Crummey, Allan Porterfield
2010 Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming - PPoPP '10  
Finally, we propose a new technique for measurement and analysis of lock contention that uses data associated with locks to blame lock holders for the idleness of spinning threads.  ...  Threaded codes typically use locks to coordinate access to shared data. In many cases, contention for locks reduces parallel efficiency and hurts scalability.  ...  We thank Robert Fowler for focusing our attention on MAD-NESS, Robert Harrison for helping us with his MADNESS code, and William Scherer for reminding us of Bacon's prior work on dual-representation locks  ... 
doi:10.1145/1693453.1693489 dblp:conf/ppopp/TallentMP10 fatcat:g3tyad2z6ja5hmwyuywhpaye3m

Highly-Concurrent Doubly-Linked Lists [article]

Nitin Garg and Ed Zhu and Fabiano C. Botelho
2011 arXiv   pre-print
An adlist node needs an additional 8 bytes of space for keeping synchronization information.  ...  While special cases of lists, such as queues and stacks, have lock-free versions that scale reasonably well, the general form of a doubly-linked list offers no such solution.  ...  Reader-writer lwlock Adlists use a reader-writer lwlock in each adlist node and it accounts for 4 out of the 8 bytes of synchronization space.  ... 
arXiv:1112.1141v1 fatcat:gzkqdao6fzdktcsqwh2wxmq4la
« Previous Showing results 1 — 15 out of 30 results