Filters








34,508 Hits in 2.7 sec

All-window profiling of concurrent executions

Chen Ding, Trishul Chilimbi
2008 Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming - PPoPP '08  
This paper first demonstrates the need for all-window profiling in a concurrent execution, then presents an approximate algorithm, and finally discusses related work.  ...  Acknowledgments The authors wish to thank Bao Bin at Rochester and the reviewers of PPOPP 2008 for their comments, which helped to improve the presentation.  ...  This motivated us to develop the all-window profiling.  ... 
doi:10.1145/1345206.1345248 dblp:conf/ppopp/DingC08 fatcat:a3qqkwp77rextjxvi5sra4i3fa

MC-Checker: Detecting Memory Consistency Errors in MPI One-Sided Applications

Zhezhe Chen, James Dinan, Zhen Tang, Pavan Balaji, Hua Zhong, Jun Wei, Tao Huang, Feng Qin
2014 SC14: International Conference for High Performance Computing, Networking, Storage and Analysis  
One-sided communication decouples data movement and synchronization by providing support for asynchronous reads and updates of distributed shared data.  ...  Experiments indicate that MC-Checker is effective at detecting and diagnosing memory consistency bugs in MPI one-sided applications, with low overhead, ranging from 24.6% to 71.1%, with an average of 45.2%  ...  Department of Energy, Office of Science, Advanced Scientific Computing Research, under Contract DE-AC02-06CH11357, by an allocation of computing time from the Ohio Supercomputer Center, and by the CAS/  ... 
doi:10.1109/sc.2014.46 dblp:conf/sc/ChenDTBZWHQ14 fatcat:fa2ooryt2zc5dohmkagfrm2wom

An Actor Based Software Framework for Scalable Applications [chapter]

Federico Bergenti, Agostino Poggi, Michele Tomaiuolo
2014 Lecture Notes in Computer Science  
publish-subscribe Execution Profiles • Active • Each actor has its own execution thread • Passive • All actors share an execution thread • Shared • All actors share an execution thread  ...  services Actor Space Supports actors with additional services  Drives the execution of actors  Usually defines the execution profile Actor Space Services • A means to • Access services provided by legacy  ... 
doi:10.1007/978-3-319-11692-1_3 fatcat:tkrmeefpvbg5hnuhvu7vkcagm4

A co-design platform for algorithm/architecture design exploration

Christophe Lucarz, Marco Mattavelli, Julien Dubois
2008 2008 IEEE International Conference on Multimedia and Expo  
The efficient implementation of multimedia algorithms, for the ever increasing complexity of the specifications and the emergence of the new generation of processing platforms characterized by multicore  ...  The process is based on profiling capabilities supported by the new platform specifically conceived to study and optimize data flows and data transfers between SW and HW modules.  ...  In fact, if all actors of a CAL model are independent concurrent entities, the sequence of actions executed is considered atomic within data flow model simulations and requires the evaluation of the execution  ... 
doi:10.1109/icme.2008.4607623 dblp:conf/icmcs/LucarzMD08 fatcat:kavylwgxzbc53hoksb5jn2ka5y

Dynamic Feature Selection for Machine-Learning Based Concurrency Regulation in STM

Diego Rughetti, Pierangelo Di Sanzo, Bruno Ciciani, Francesco Quaglia
2014 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing  
In this paper we explore machine-learning based approaches for dynamically selecting the well suited amount of concurrent threads in applications relying on Software Transactional Memory (STM).  ...  This allows for tuning the concurrency level while also minimizing the overhead for input-features sampling, given that the cardinality of the inputfeature set is always tuned to the minimum value that  ...  provided to NN along the execution of all the active concurrent threads.  ... 
doi:10.1109/pdp.2014.24 dblp:conf/pdp/RughettiSCQ14 fatcat:oe75grgoeje6dog5kp2n6tdh3m

A thread monitoring system for multithreaded Java programs

Sewon Moon, Byeong-Mo Chang
2006 SIGPLAN notices  
It also provides profile information after execution, which summarizes behavior of running threads and synchronized actions during execution.  ...  We consider a multithreaded Java program in Figure 1 , which is a running example of this paper.  ...  A main window for selecting options is shown in Figure 5 , which shows all files in the package of a sample program.  ... 
doi:10.1145/1149982.1149985 fatcat:j26osokbungwviuo67nhj25kfm

Runtime-Guided Mitigation of Manufacturing Variability in Power-Constrained Multi-Socket NUMA Nodes

Dimitrios Chasapis, Martin Schulz, Marc Casas, Eduard Ayguadé, Mateo Valero, Miquel Moretó, Jesus Labarta
2016 Proceedings of the 2016 International Conference on Supercomputing - ICS '16  
In the context of a NUMA node composed of several multi-core sockets, our system is able to optimize the energy and concurrency levels assigned to each socket to maximize performance.  ...  In this work we show how a parallel runtime system can be used to effectively deal with this new kind of performance heterogeneity by compensating the uneven effects of power capping.  ...  of LLNL for their technical support and useful feedback.  ... 
doi:10.1145/2925426.2926279 dblp:conf/ics/ChasapisSCAVML16 fatcat:xfmnf3uon5hila7r3yfgxr5f3u

A Review of Parallelization Tools and Introduction to Easypar

Sudhakar Sah, Vinay G. Vaidya
2012 International Journal of Computer Applications  
Multicore processors have paved the way to increase the performance of any application by the virtue of benefits of parallelization.  ...  A number of tools proposed in the past ease the effort of parallel programming. This paper presents a classification of such parallelization tools.  ...  An advantage of transaction memory is that any program can execute concurrently and TM will take care of concurrent execution.  ... 
doi:10.5120/8944-3108 fatcat:mxaohvalvrecrmxlplzyzq7x2i

Dynamic scheduling of process groups

KUEI YU WANG, DAN C. MARINESCU, OCTAVIAN F. CARBUNAR
1998 Concurrency Practice and Experience  
The temporal locality of communlcation can be used to schedule concurrently multiple process groups.  ...  A job consisting of a process group is assigned a partition of the machine with a number of processors equal to the process group size and releases the partition upon the completion of all processes in  ...  Acknowledgments The authors express their thanks to Vietor Abell for pointing out the importance of memory constraints for process group context switching.  ... 
doi:10.1002/(sici)1096-9128(19980410)10:4<265::aid-cpe314>3.0.co;2-u fatcat:mpfvzhetonb45brlmuarfd4xh4

QoS support for end users of I/O-intensive applications using shared storage systems

Xuechen Zhang, Kei Davis, Song Jiang
2011 Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11  
We propose a scheme supporting end-users' QoS goals, specified in terms of program execution time, in shared storage environments.  ...  We automatically translate the users' performance goals into instantaneous I/O throughput bounds using a machine learning technique, and use dynamically determined service time windows to efficiently meet  ...  This work was also funded in part by the Accelerated Strategic Computing program of the Department of Energy.  ... 
doi:10.1145/2063384.2063408 dblp:conf/sc/ZhangDJ11 fatcat:excl5z6labfn7i7w7ga6pg5umi

Monitoring and analysis of performance impact in virtualized environments

Pedro Freire Popiolek, Odorico Machado Mendizabal
2013 Journal of Applied Computing Research  
Further, some specific behaviors were noticed for different load profiles.  ...  Experiments with generation of synthetic workloads in our monitored infrastructure allowed us to identify the main causes of the observed degradation of performance.  ...  As the number of concurrent VMs in execution increases, the benchmark takes longer to finish.  ... 
doi:10.4013/jacr.2012.22.03 fatcat:6rfxzaskkva27mg5uuzcejgqcq

GNAT/ORK: AN OPEN CROSS-DEVELOPMENT ENVIRONMENT FOR EMBEDDED RAVENSCAR–ADA SOFTWARE

Juan Zamorano, José F. Ruiz
2002 IFAC Proceedings Volumes  
However, many implementations of concurrent tasking have been seen as potentially unsafe for critical systems because of their high degree of indeterminism.  ...  The Ravenscar profile is a subset of Ada 95 tasking with purpose of providing a basis for the implementation of certifiable critical systems.  ...  There are thus no concurrent threads of execution, and the application code is made of a set of purely sequential procedures.  ... 
doi:10.3182/20020721-6-es-1901.00950 fatcat:emtkgrsffbgyfoholqnxmivnsa

From Task to Dialog Model in the UML [chapter]

Jan Van den Bergh, Karin Coninx
2007 Lecture Notes in Computer Science  
The proposed approach uses a UML profile to reduce the visual complexity of the state machine.  ...  This paper proposes a semantic mapping of tasks and all temporal relations of the ConcurTaskTrees to UML state machines which forms the basis for a compact dialog modeling notation using UML state machines  ...  Acknowledgements Part of the research at EDM is funded by EFRD (European Fund for Regional Development), the Flemish Government and the Flemish Interdisciplinary institute for Broadband Technology (IBBT  ... 
doi:10.1007/978-3-540-77222-4_9 fatcat:bqdw2kx245euzfo4l7bwbvgpci

Accelerating Boosting-Based Face Detection on GPUs

David Oro, Carles Fern'ndez, Carlos Segura, Xavier Martorell, Javier Hernando
2012 2012 41st International Conference on Parallel Processing  
Particularly, the usage of concurrent kernel execution in combination with cascades generated with the GentleBoost algorithm solves the problem of GPU underutilization, and achieves a 5X speedup in 1080p  ...  The goal of face detection is to determine the presence of faces in arbitrary images, along with their locations and dimensions.  ...  ACKNOWLEDGEMENTS This work has been partially supported by the European Commission in the context of the HiPEAC3 Network of Excellence (FP7/ICT 287759), the Spanish Ministry of Education (TIN2007-60625  ... 
doi:10.1109/icpp.2012.12 dblp:conf/icpp/OroFSMH12 fatcat:c33ms2qt5vbopel4qmkvkuutnu

Aligning Deos and RTEMS with the FACE safety base operating system profile

Gedare Bloom, Joel Sherrill, Gary Gilliland
2018 ACM SIGBED Review  
This paper presents the FACE operating system profiles and discusses the technical challenges of the paravirtualization and integration effort.  ...  Integrating a paravirtualized RTEMS with Deos combines the strengths of both and provides a path to conformance with the FACE Safety Base operating system profile.  ...  gap (w1 − w0) inclusive of the execution time of the previous window.  ... 
doi:10.1145/3199610.3199612 fatcat:7r76nhiuvfbr3huginlaj6gbsm
« Previous Showing results 1 — 15 out of 34,508 results