Filters








579 Hits in 2.5 sec

Fast mutual exclusion for uniprocessors

Brian N. Bershad, David D. Redell, John R. Ellis
1992 Proceedings of the fifth international conference on Architectural support for programming languages and operating systems - ASPLOS-V  
reflect runs using restartable atomic sequences for the applications and for the Unix server.  ...  The designated sequence for acquiring a mutex is shown in Figure 5 .  ... 
doi:10.1145/143365.143523 dblp:conf/asplos/BershadRE92 fatcat:xgnpzcikhjdvfoloou4noemtsa

Fast mutual exclusion for uniprocessors

Brian N. Bershad, David D. Redell, John R. Ellis
1992 SIGPLAN notices  
reflect runs using restartable atomic sequences for the applications and for the Unix server.  ...  The designated sequence for acquiring a mutex is shown in Figure 5 .  ... 
doi:10.1145/143371.143523 fatcat:t4cdjtwp7fdltaoma7o2gwqe6y

Multiprocessor Synchronization and Hierarchical Scheduling

Farhang Nemati, Moris Behnam, Thomas Nolte
2009 2009 International Conference on Parallel Processing Workshops  
The presented protocol groups dependent tasks that directly or indirectly share mutually exclusive resources into independent components.  ...  Within a component dependent tasks use classical uniprocessor synchronization protocols, such as the Stack-based Resource allocation Protocol.  ...  The following sections explain our corresponding task model and approach for mutual exclusion.  ... 
doi:10.1109/icppw.2009.44 dblp:conf/icppw/NematiBN09 fatcat:5clzfh6hofcs7pefpoysxzameq

The Non-blocking Programming Paradigm in Large Scale Scientific Computations [chapter]

Philippas Tsigas, Yi Zhang
2004 Lecture Notes in Computer Science  
Non-blocking implementations allow multiple tasks to access a shared object at the same time, but without enforcing mutual exclusion to accomplish this.  ...  Non-blocking implementation of shared data objects is a new alternative approach to the problem of designing scalable shared data objects for multiprocessor systems.  ...  Non-blocking synchronisation is an alternative to mutual exclusion for implementing shared data objects.  ... 
doi:10.1007/978-3-540-24669-5_144 fatcat:q5yazlwvongxldthamm6ssastq

VIA Communication Performance on a Gigabit Ethernet Cluster [chapter]

Mark Baker, Paul A. Farrell, Hong Ong, Stephen L Scott
2001 Lecture Notes in Computer Science  
In particular, we focus on the performance of the VIA send/receive synchronization mechanism on both uniprocessor and dual processor systems.  ...  The performance statistics were collected using a local version of NetPIPE adapted for VIA.  ...  For an SMP, the overhead of using spinlock primitives to perform mutual exclusion across CPUs is higher than in the uniprocessor case.  ... 
doi:10.1007/3-540-44681-8_20 fatcat:vfmdv2i6pnfu5hcdol3eudejfe

Architectural support for uniprocessor and multiprocessor active memory systems

Daehyun Kim, M. Chaudhuri, M. Heinrich, E. Speight
2004 IEEE transactions on computers  
We introduce an architectural approach to improve memory system performance in both uniprocessor and multiprocessor systems.  ...  We leverage and extend the cache coherence protocol so that our techniques work transparently to efficiently support uniprocessor, SMP and DSM active memory systems.  ...  Instead, processors access both spaces (i.e., v and v 0 ) at the same time, so the mutual exclusion results in false sharing. In a variation on our AM protocol, we relax the mutual exclusion.  ... 
doi:10.1109/tc.2004.1261836 fatcat:2ewquko6ivexff5zifctdxlvie

Chip-multiprocessor hardware locks for safety-critical Java

Tórur Biskopstø Strøm, Wolfgang Puffitsch, Martin Schoeberl
2013 Proceedings of the 11th International Workshop on Java Technologies for Real-time and Embedded Systems - JTRES '13  
The solution is implemented for the chip-multiprocessor version of the Java Optimized Processor in the context of safety-critical Java. The implementation is compared to a software solution.  ...  Acknowledgments This work is part of the project "Certifiable Java for Embedded Systems" (CJ4ES) and has received partial funding from the Danish Research Council for Technology and Production Sciences  ...  We also thank the anonymous reviewers for their detailed reviews where they also pointed out some motivations in the SCJ specification we where not aware of.  ... 
doi:10.1145/2512989.2512995 dblp:conf/jtres/StromPS13 fatcat:c5h3n3zvx5e7hhay2q4vgl3jwu

The power of SIMDs vs. MIMDs in real-time scheduling

Mingxian Jin, J.W. Baker, W.C. Meilander
2002 Proceedings 16th International Parallel and Distributed Processing Symposium  
In this paper, we compare SIMDs and MIMDs in real-time scheduling, e.g., scheduling for air traffic control.  ...  SIMDs and MIMDs are the most important categories of computer systems for parallel computing in Flynn's classification scheme.  ...  This fact eliminates the need for mutual exclusive access to shared resources.  ... 
doi:10.1109/ipdps.2002.1016671 dblp:conf/ipps/JinBM02 fatcat:zbx222oicveuza4r3gftnfcinq

Process Synchronization in the UTS Kernel

Lawrence M. Ruane
1990 Computing Systems  
The traditional choice for UNIX systems, the event-wait mechanism, leads to race conditions on multiprocessors.  ...  Any operating system kernel has some form of process synchronization, allowing a process to wait for a particular condition.  ...  Also, blocking mutual exclusion presents difficulties for interrupt handlers, which cannot sleep.  ... 
dblp:journals/csys/Ruane90 fatcat:2fafztoi3vhthlxzvwbqst4w2u

The Impact of Parallel Processing on Operating Systems

Felician ALECU
2009 Oeconomics of Knowledge  
Distributed systems are managed by distributed operating systems that represent the extension for multiprocessor architectures of multitasking and multiprogramming operating systems.  ...  The operating system has to implement mutual exclusion mechanisms (semaphores, monitors, locks or events using busy-wait or sleep-wait protocols) in order to protect the concurrent accesses to the list  ...  The system also appears as a virtual uniprocessor for users and the same operating system is executed in every processing unit.  ... 
doaj:df31a15bb00d4ec79b07de87e14dbecb fatcat:dhnqreyambb4rldxtoc77txqpe

Real-time scheduling with resource sharing on uniform multiprocessors

Gurulingesh Raravi, Vincent Nélis, Björn Andersson
2012 Proceedings of the 20th International Conference on Real-Time and Network Systems - RTNS '12  
The resources have to be accessed in a mutually exclusive manner.  ...  The resources have to be accessed in a mutually exclusive manner.  ...  For each resource r k ∈ R, since r k is accessed in a mutually exclusive way, all the tasks that access resource r k must execute sequentially.  ... 
doi:10.1145/2392987.2393003 dblp:conf/rtns/RaraviNA12 fatcat:cqqq456y7nfdjl5e4yrzjmyovq

Implementation and Evaluation of the Synchronization Protocol Immediate Priority Ceiling in PREEMPT-RT Linux

Andreu Carminati, Rômulo Silva de Oliveira, Luís Fernando Friedrich
2012 Journal of Software  
The objective of this paper is to propose the implementation of an alternative protocol, the Immediate Priority Ceiling, for use in drivers dedicated to real-time applications, for example.  ...  Mutual Exclusion in the Linux Kernel Since there is no mechanism in the mainline kernel that prevents the appearance of priority inversions, situations like the one shown in Figure 1 can occur very easily  ...  Although rt_mutexes are implemented in PREEMPT-RT for both uniprocessor and multiprocesors, our implementation of IPC considers only the uniprocessor case.  ... 
doi:10.4304/jsw.7.3.516-525 fatcat:uzquqfwjabaitbk3nwtqgwwhuq

The java.util.concurrent synchronizer framework

Doug Lea
2005 Science of Computer Programming  
This framework provides common mechanics for atomically managing synchronization state, blocking and unblocking threads, and queuing.  ...  Acknowledgements Thanks to Dave Dice for countless ideas and advice during the development of this framework, to Mark Moir and Michael Scott for urging consideration of CLH queues, to David Holmes for  ...  , Josh Bloch, Brian Goetz, David Holmes, and Tim Peierls) as well as Bill Pugh, for helping with design and specifications  ... 
doi:10.1016/j.scico.2005.03.007 fatcat:f7bxjt6dybfcnk4kykqpwj7upi

Wisconsin Wind Tunnel II: a fast, portable parallel architecture simulator

S.S. Mukherjee, S.K. Reinhardt, B. Falsafi, M. Litzkow, M.D. Hill, D.A. Wood, S. Huss-Lederman, J.R. Larus
2000 IEEE Concurrency  
Mutual exclusion of destination mailbox is ensured through an atomic fetch-and-add operation. A process uses its own source mailbox to enqueue broadcast messages.  ...  WWT II reduces this overhead by providing a fast path for loads and stores that hit in the target cache [10] .  ... 
doi:10.1109/4434.895100 fatcat:zzwlpzf7k5dkpeh3o5kciqr3e4

Towards Customizable CPS: Composability, Efficiency and Predictability [chapter]

Wang Yi
2017 Lecture Notes in Computer Science  
The tools shall support not only verification, but also code generation tailored for both co-simulation (interfaced) with existing design tools such as Open Modelica (for modeling and simulation of physical  ...  This is due to the lack of techniques to preserve crucial safety conditions for the modified system, which severely restricts the benefits of software.  ...  In the implementation of UPPAAL, for verifying functional correctness e.g. deadlock-freeness or mutual exclusion properties, it demands a large amount of memory for keeping track of the timing constraints  ... 
doi:10.1007/978-3-319-68690-5_1 fatcat:wwfoniwr2zayfcvigxggfaed2a
« Previous Showing results 1 — 15 out of 579 results