Filters








10,851 Hits in 3.6 sec

Memory buddies

Timothy Wood, Gabriel Tarasuk-Levin, Prashant Shenoy, Peter Desnoyers, Emmanuel Cecchet, Mark D. Corner
2009 ACM SIGOPS Operating Systems Review  
In this paper we present Memory Buddies, a memory sharingaware placement system for virtual machines.  ...  Page sharing identifies virtual machine memory pages with identical content and consolidates them into a single shared page.  ...  Finally we would like to thank the members of our department who volunteered to run the memory tracer on their machine. This work was supported in part by NSF grants CNS-0720271 and CNS-0720616.  ... 
doi:10.1145/1618525.1618529 fatcat:4xv4er5tpzajdmnl6y4novcwqy

Memory buddies

Timothy Wood, Gabriel Tarasuk-Levin, Prashant Shenoy, Peter Desnoyers, Emmanuel Cecchet, Mark D. Corner
2009 Proceedings of the 2009 ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE '09  
In this paper we present Memory Buddies, a memory sharingaware placement system for virtual machines.  ...  Page sharing identifies virtual machine memory pages with identical content and consolidates them into a single shared page.  ...  Finally we would like to thank the members of our department who volunteered to run the memory tracer on their machine. This work was supported in part by NSF grants CNS-0720271 and CNS-0720616.  ... 
doi:10.1145/1508293.1508299 dblp:conf/vee/WoodTSDCC09 fatcat:l6reemmzm5ckti3sj5g6gurga4

Randomized PRAM simulation using T9000 transputers [chapter]

Zbigniew J. Czech, Wojciech Mikanik
1996 Lecture Notes in Computer Science  
Unfortunately the PRAM model is not physically realizable, since on large machines a parallel shared memory access can only be accomplished at the cost of a signi cant time delay.Anumber of PRAM simulation  ...  In this paper we study the randomized simulation of an EREW (exclusive read, exclusive write) PRAM on a module parallel computer (MPC). The simulation is based on utilizing universal hashing.  ...  Acknowledgments We wish to thank the Department of Computer Science, the UniversityofKentatCanterbury, Great Britain, for providing access to the parallel computing facilities.  ... 
doi:10.1007/3-540-61142-8_621 fatcat:lzieatcsijhbrbukxupzlk2koe

Toward Efficient In-memory Data Analytics on NUMA Systems [article]

Puya Memarzia, Suprio Ray, Virendra C Bhavsar
2020 arXiv   pre-print
In this work, we evaluate a variety of strategies that aim to accelerate memory-intensive data analytics workloads on NUMA systems.  ...  We analyze the impact of different memory allocators, memory placement strategies, thread placement, and kernel-level load balancing and memory management mechanisms.  ...  ACKNOWLEDGEMENTS We would like to thank Kenneth Kent and Aaron Graham from IBM CASA and Serguei Vassiliev and Kaizaad Bilimorya from Compute Canada, for providing access to Machine B and Machine C respectively  ... 
arXiv:1908.01860v3 fatcat:3ri4vadygzce5ao5dslmakn7zm

Using shared virtual memory for parallel join processing

Ambuj Shatdal, Jeffrey F. Naughton
1993 Proceedings of the 1993 ACM SIGMOD international conference on Management of data - SIGMOD '93  
Repropose twovariants ofan algorithm for parallel join processing using shared virtual memory, and perform a detailed simulation to investigate their performance.  ...  In this paper, we show that shared virtual memory, in a shared-nothing multiprocessor, facilitates the design and implementation of parallel join processing algorithms that perform significantly better  ...  Acknowledgment The idea of looking at shared virtual memory for join processing was originally suggested to us by David De-Witt, We also thank the numerous writers of the original Gamma simulator without  ... 
doi:10.1145/170035.170062 dblp:conf/sigmod/ShatdalN93 fatcat:hgx2arj35rabzfmkavbef535zi

A Survey of Parallel A* [article]

Alex Fukunaga, Adi Botea, Yuu Jinnai, Akihiro Kishimoto
2017 arXiv   pre-print
A* benefits significantly from parallelism because in many applications, A* is limited by memory usage, so distributed memory implementations of A* that use all of the aggregate memory on the cluster enable  ...  A* is a best-first search algorithm for finding optimal-cost paths in graphs.  ...  Then, in Section 4, we describe hash-based work distribution, the class of algorithms which is the current, state-of-the-art approach for parallelizing A* both on single, shared-memory multi-core machines  ... 
arXiv:1708.05296v1 fatcat:grbv7txlorbcxf3gstzj6lugny

Using shared virtual memory for parallel join processing

Ambuj Shatdal, Jeffrey F. Naughton
1993 SIGMOD record  
Repropose twovariants ofan algorithm for parallel join processing using shared virtual memory, and perform a detailed simulation to investigate their performance.  ...  In this paper, we show that shared virtual memory, in a shared-nothing multiprocessor, facilitates the design and implementation of parallel join processing algorithms that perform significantly better  ...  Acknowledgment The idea of looking at shared virtual memory for join processing was originally suggested to us by David De-Witt, We also thank the numerous writers of the original Gamma simulator without  ... 
doi:10.1145/170036.170062 fatcat:3mz7exov4jbjnlcq55mkoyct4i

The parallelism motifs of genomic data analysis

Katherine Yelick, Aydın Buluç, Muaaz Awan, Ariful Azad, Benjamin Brock, Rob Egan, Saliya Ekanayake, Marquita Ellis, Evangelos Georganas, Giulia Guidi, Steven Hofmeyr, Oguz Selvitopi (+2 others)
2020 Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences  
These applications differ from scientific simulations that dominate the workload on high-end parallel systems today and place different requirements on programming support, software libraries and parallel  ...  For example, they involve irregular communication patterns such as asynchronous updates to shared data structures.  ...  These represent problems like genome assembly and protein clustering that until recently were done only on shared memory machines.  ... 
doi:10.1098/rsta.2019.0394 pmid:31955674 fatcat:kzujmq5u2refvhoovtb2ap5vha

Massively Parallel NUMA-Aware Hash Joins [chapter]

Harald Lang, Viktor Leis, Martina-Cezara Albutiu, Thomas Neumann, Alfons Kemper
2015 Lecture Notes in Computer Science  
We then develop a NUMA-aware hash join for massively parallel environments, and show how the specic implementation details aect the performance on a NUMA system.  ...  We study recent proposals of main memory hash join implementations and identify their major performance problems on NUMA architectures.  ...  First we employed eight threads on eight physical cores within a single NUMA node, thereby simulating a uniform-memory-access machine.  ... 
doi:10.1007/978-3-319-13960-9_1 fatcat:g72my4iak5eyfjv7msepxs4do4

Meeting the Memory Challenges of Brain-Scale Network Simulation

Susanne Kunkel, Tobias C. Potjans, Jochen M. Eppler, Hans Ekkehard Plesser, Abigail Morrison, Markus Diesmann
2012 Frontiers in Neuroinformatics  
Applying the model to our freely available Neural Simulation Tool (NEST), we identify the software components dominant at different scales, and develop general strategies for reducing the memory consumption  ...  machines.  ...  Partially funded by JUGENE Grant JINB33, BMBF Grant 01GQ0420 to BCCN Freiburg, EU Grant 15879 (FACETS), EU Grant 269921 (Brain-ScaleS), DIP F1.2, the Helmholtz Alliance on Systems Biology (Germany), the  ... 
doi:10.3389/fninf.2011.00035 pmid:22291636 pmcid:PMC3264885 fatcat:huyh5hbrjzbnlorg37bgcge7bm

Exploiting storage redundancy to speed up randomized shared memory simulations

Friedhelm Meyer auf der Heide, Christian Scheideler, Volker Stemann
1996 Theoretical Computer Science  
The paper presents and analyses a simple process executing the above task on distributed memory machines (DMMs) with n processors.  ...  Assume that a set U of memory locations is distributed among n memory modules, using some number a of hash functions /II,. , h" randomly and independently drawn from a highperformance universal class of  ...  Dictionaries and shared memory simulations Shared memory simulations on a DMM based on hashing begin with a preprocessing phase.  ... 
doi:10.1016/0304-3975(96)00032-1 fatcat:5dujwgv2g5hoflhie4dajd2j4a

Design and evaluation of main memory hash join algorithms for multi-core CPUs

Spyros Blanas, Yinan Li, Jignesh M. Patel
2011 Proceedings of the 2011 international conference on Management of data - SIGMOD '11  
The focus of this paper is on investigating efficient hash join algorithms for modern multi-core processors in main memory environments.  ...  Based on our results, we propose that database implementers consider adding this simple join algorithm to their repertoire of main memory join algorithms, or adapt their methods to mimic the strategy employed  ...  Acknowledgments We thank David DeWitt for his deeply insightful comments on this paper. We also thank the reviewers of this paper and Willis Lang for their feedback on an earlier draft of this paper.  ... 
doi:10.1145/1989323.1989328 dblp:conf/sigmod/BlanasLP11 fatcat:b66qtmxzoze57knf6pgfqjh2bi

Architectural support for translation table management in large address space machines

Jerry Huck, Jim Hays
1993 SIGARCH Computer Architecture News  
Traditional methoak for managing the page translation tables are inappropriate for large address space architectures.  ...  In simulations of over 4 billion instructions, improvements of 5 to IO% were observed. 0884-7495/93 $3.00 @ 1993 IEEE  ...  a machine with 32 Megabytes of memory.  ... 
doi:10.1145/173682.165128 fatcat:uefr5qbmizdyjdy6qabcox45oi

Integrating Caching and Prefetching Mechanisms in a Distributed Transactional Memory

Alokika Dash, Brian Demsky
2011 IEEE Transactions on Parallel and Distributed Systems  
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.  ...  We present a distributed transactional memory system that exploits a new opportunity to automatically hide network latency by speculatively prefetching and caching objects.  ...  We would like to thank the anonymous reviewers and our editor for their helpful feedback. We would also like to thank Brad Chamberlain for feedback on our paper.  ... 
doi:10.1109/tpds.2011.23 fatcat:nitbuelfjvffdk2polrmuxpibq

Simulation tools to study a distributed shared memory for clusters of symmetric multiprocessors

Darshan D. Thaker, Vipin Chaudhary
2006 Future generations computer systems  
The simulator also accepts the same code as the software distributed shared memory.  ...  Distributed shared memory (DSM) systems have become popular as a means of utilizing clusters of computers for solving large applications. We have developed a high-performance DSM, Strings.  ...  Hence, an alternate approach to using these computing clusters is to provide an illusion of logically shared memory over physically distributed memory, known as a distributed shared memory (DSM) or shared  ... 
doi:10.1016/j.future.2003.12.024 fatcat:bbigxtcl2jdk7kijr6wkfi3q2y
« Previous Showing results 1 — 15 out of 10,851 results