43 Hits in 5.0 sec

Reproducible Containers

Omar S. Navarro Leija, Kelly Shiptoski, Ryan G. Scott, Baojun Wang, Nicholas Renner, Ryan R. Newton, Joseph Devietti
2020 Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems  
DetTrace's performance is dictated by the frequency of system calls: IO-intensive software builds have an average overhead of 3.49×, while a compute-bound bioinformatics workflow is under 2%.  ...  All computation that occurs inside a DetTrace container is a pure function of the initial filesystem state of the container.  ...  Acknowledgments This work is supported by the National Science Foundation under grant #1703541.  ... 
doi:10.1145/3373376.3378519 dblp:conf/asplos/LeijaSSWRND20 fatcat:234ucu6hrzbajahchp5y2tud7a

Processing Panorama Video in Real-time

Håkon Kvale Stensland, Vamsidhar Reddy Gaddam, Marius Tennøe, Espen Helgedagsrud, Mikkel Næss, Henrik Kjus Alstad, Carsten Griwodz, Pål Halvorsen, Dag Johansen
2014 International Journal of Semantic Computing (IJSC)  
When programing multimedia workloads, it is very important to know how the algorithms perform on the target architecture.  ...  Two simple workloads show that we can express multimedia workloads in the system. We also demonstrate the scalability of the designed solution.  ...  Multimedia Workloads A multimedia workload is often characterized as being time sensitive and iterative.  ... 
doi:10.1142/s1793351x14400054 fatcat:hafewx3ekrcfpat2osb67fjugi

Strategic directions in real-time and embedded systems

John A. Stankovic
1996 ACM Computing Surveys  
-What empirical studies should be undertaken to help support the creation of real-time models? -What are good resource and workload characterization models for real-time systems?  ...  of the individual applications for validating the workload model.  ... 
doi:10.1145/242223.242291 fatcat:evt5gbvcjnfc3g3hauytxuuv6i

A Scalable and Distributed Dynamic Formal Verifier for MPI Programs

Anh Vo, Sriram Aananthakrishnan, Ganesh Gopalakrishnan, Bronis R. de Supinski, Martin Schulz, Greg Bronevetsky
2010 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis  
Programs tested by these methods can have untested paths (bugs) that may become manifest unexpectedly.  ...  Standard testing methods of MPI programs do not guarantee coverage of all non-deterministic interactions (e.g., wildcard-receives).  ...  In effect, its scheduler poorly exploits the parallelism offered by the cluster on which the MPI program is being dynamically verified.  ... 
doi:10.1109/sc.2010.7 dblp:conf/sc/VoAGSSB10 fatcat:2b75w2dqorbnbngelkfzz2263i

Accelerating Multiprocessor Simulation with a Memory Timestamp Record

K.C. Barr, H. Pan, M. Zhang, K. Asanovic
2005 IEEE International Symposium on Performance Analysis of Systems and Software, 2005. ISPASS 2005.  
We evaluate MTR using a full-system simulation of a directory-based cachecoherent multiprocessor running a range of multithreaded workloads.  ...  Both MTR and a multiprocessor version of functional fast-forwarding (FFW) make similar performance estimates, usually within 15% of our detailed model.  ...  But applications generally contain multiple phases of execution with varying properties and much better characterization is possible by using multiple sample points spread throughout a run [5, 11, 21,  ... 
doi:10.1109/ispass.2005.1430560 dblp:conf/ispass/BarrPZA05 fatcat:bnsfxw65kjhorof2fdxvmw7wiu

Understanding performance variability in standard and pipelined parallel Krylov solvers

Hannah Morgan, Patrick Sanan, Matthew Knepley, Richard Tran Mills
2020 The international journal of high performance computing applications  
Based on these results, we improve upon a previously introduced nondeterministic performance model by allowing iterations to fluctuate over time.  ...  In this work, we collect data from runs of Krylov subspace methods and pipelined Krylov algorithms in an effort to understand and model the impact of machine noise and other sources of variability on performance  ...  Also in the future, nondeterministic performance models can be derived for other parallel algorithms where unpredictable system interference could impact performance.  ... 
doi:10.1177/1094342020966835 fatcat:au2cbsyzbjh47pumlmmptymht4

Addressing failures in exascale computing

Marc Snir, Robert W Wisniewski, Jacob A Abraham, Sarita V Adve, Saurabh Bagchi, Pavan Balaji, Jim Belak, Pradip Bose, Franck Cappello, Bill Carlson, Andrew A Chien, Paul Coteus (+16 others)
2014 The international journal of high performance computing applications  
Maintaining the current rate of hardware SDC seems possible, at the expense of <20% of additional silicon and energy; and vendor research can further lower the overhead.  ...  The additional power consumption is low, but the acquisition cost of platforms will rise because of the need for additional memory.  ...  Acknowledgments Lead: Marc Snir This work was supported by the U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research, under Contract DE-AC02-06CH11357.  ... 
doi:10.1177/1094342014522573 fatcat:menonpmgdfflzamz2fsivevxqm

Pico: A Domain-Specific Language For Data Analytics Pipelines

Claudia Misale, Marco Aldinucci, Guy Tremblay
2017 Zenodo  
In the world of Big Data analytics, there is a series of tools aiming at simplifying programming applications to be executed on clusters.  ...  By putting clear separations between all levels of abstraction (i.e., from the runtime to the user API), it is easier for a programmer or software designer to avoid mixing low level with high level aspects  ...  Acknowledgements Funding This work has been partially supported by the Italian Ministry of Education and Research (MIUR), by the EU-H2020 RIA project "Toreador" (no. 688797), the EU-H2020 RIA project  ... 
doi:10.5281/zenodo.579753 fatcat:aadje57qh5hk3ijmqn4j7vkhpm

Factorial design analysis applied to the performance of parallel evolutionary algorithms

Mônica S Pais, Igor S Peretta, Keiji Yamanaka, Edmilson R Pinto
2014 Journal of the Brazilian Computer Society  
As multicore processors become ubiquitous, the improved performance available to parallel programs is a great motivation to computationally demanding EAs to turn into parallel programs and exploit the  ...  Parallel computing is a powerful way to reduce computation time and to improve the quality of solutions of evolutionary algorithms (EAs).  ...  Mônica S Pais and Igor S Peretta were partially supported by IFGoiano/FAPEG/CAPES and CNPq, respectively. Author details  ... 
doi:10.1186/1678-4804-20-6 fatcat:4btwsjlqizf6ro35b32z2odqhq

Partial aborts for transactions via first-class continuations

Matthew Le, Matthew Fluet
2015 Proceedings of the 20th ACM SIGPLAN International Conference on Functional Programming - ICFP 2015  
We have implemented this idea in the context of the Manticore project, an ML-family language with support for parallelism and concurrency.  ...  of the transaction that has not been compromised.  ...  Acknowledgments This research is supported by the National Science Foundation under Grants CCF-0811389 and CCF-101056  ... 
doi:10.1145/2784731.2784736 dblp:conf/icfp/LeF15 fatcat:cngz2e7mmbcfdn7lee6x34iwy4

Partial aborts for transactions via first-class continuations

Matthew Le, Matthew Fluet
2015 SIGPLAN notices  
We have implemented this idea in the context of the Manticore project, an ML-family language with support for parallelism and concurrency.  ...  of the transaction that has not been compromised.  ...  Acknowledgments This research is supported by the National Science Foundation under Grants CCF-0811389 and CCF-101056  ... 
doi:10.1145/2858949.2784736 fatcat:xewokwcg3je3dm7qncyuksap7q


Sebastian Österlund, Koen Koning, Pierre Olivier, Antonio Barbalace, Herbert Bos, Cristiano Giuffrida
2019 Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS '19  
Traditional MVX designs cannot be applied to kernels because of their assumptions on the run-time environment. kMVX, on the other hand, can be applied even to commodity kernels.  ...  By detecting these divergences we can prevent kernel information leaks. Our kMVX design is inspired by multi-variant execution (MVX).  ...  The funding agencies are not responsible for any use that may be made of the information it contains.  ... 
doi:10.1145/3297858.3304054 dblp:conf/asplos/OsterlundKOBBG19 fatcat:dokkcvtczbe4fgwd3ht77myrka

Modeling load imbalance and fuzzy barriers for scalable shared-memory multiprocessors

A.E. Eichenberger, S.G. Abraham
Proceedings of the Twenty-Eighth Annual Hawaii International Conference on System Sciences  
We propose an analytical model that quantifies the overall execution time of a parallel region in the presence of non-deterministic load imbalance introduced by network contention and by random replacement  ...  We also model the performance improvement of fuzzy barriers, where the synchronization between processors at the end of a parallel region is relaxed.  ...  The communication behavior of a parallel region is characterized by the number of communication events Events generated by each processor within its parallel region.  ... 
doi:10.1109/hicss.1995.375387 dblp:conf/hicss/EichenbergerA95 fatcat:3rjeqmbwdfagtembbxniim5xca

Information theory inspired optimization algorithm for efficient service orchestration in distributed systems

Matheus Sant'Ana Lima, Seyedali Mirjalili
2021 PLoS ONE  
The proposed algorithm can be used by applications to deploy services across large cluster of nodes by making better decision in the route design.  ...  The increase in demand for application processing and data management from enterprise and end-user workloads continues to move from a single-node client-server architecture to a distributed multitier design  ...  This characterizes can be interpreted as a generalization of the methods proposed by Simulated Annealing and Genetic Algorithms.  ... 
doi:10.1371/journal.pone.0242285 pmid:33395689 fatcat:suambxwnhfdrjaujxfjsbhkljy

Testing Database Engines via Pivoted Query Synthesis [article]

Manuel Rigger, Zhendong Su
2020 arXiv   pre-print
Differential testing is an effective technique to test systems that support a common language by comparing the outputs of these systems.  ...  We expect that the wide applicability and simplicity of our approach will enable the improvement of robustness of many DBMS.  ...  Gu. et al presented an approach to quantify an optimizer's accuracy for a given workload by defining a metric over different execution plans for this workload, which were gen-erated by using DBMS-specific  ... 
arXiv:2001.04174v1 fatcat:nlmlmxskbvbgjflogrxsy6rfne
« Previous Showing results 1 — 15 out of 43 results