Filters








197,326 Hits in 7.9 sec

Effect of program localities on memory management strategies

Takashi Masuda
1977 Proceedings of the sixth symposium on Operating systems principles - SOSP '77  
However, the phase transition behavior of programs has been rarely taken into account in the analysis of memory management strategies.  ...  These properties depend on the tendency of program locality references and program phase transitions. The significant effects on system performances arise from the phase transition behavior.  ...  Hosaka and Professor S. 0suga of the University of Tokyo during the course of this research. The author is also indebted to Mr. I. 0hnishi and Dr. K.  ... 
doi:10.1145/800214.806554 dblp:conf/sosp/Masuda77 fatcat:wvmrdpf6vbbg5ms4i2zqgxxjfu

Simple but effective techniques for NUMA memory management

W. Bolosky, R. Fitzgerald, M. Scott
1989 Proceedings of the twelfth ACM symposium on Operating systems principles - SOSP '89  
We have implemented an automatic page placement strategy in the Mach operating system on the IBM ACE multiprocessor workstation.  ...  Multiprocessors with non-uniform memory access times introduce the problem of placing data near the processes that use them, in order to improve performance.  ...  to Felicia Ferlin, Dave Redell and the referees for helping to improve the presentation of this paper.  ... 
doi:10.1145/74850.74854 dblp:conf/sosp/BoloskyFS89 fatcat:ditm7jm6djgvzlsyulpcmq6yry

Simple but effective techniques for NUMA memory management

W. Bolosky, R. Fitzgerald, M. Scott
1989 ACM SIGOPS Operating Systems Review  
We have implemented an automatic page placement strategy in the Mach operating system on the IBM ACE multiprocessor workstation.  ...  Multiprocessors with non-uniform memory access times introduce the problem of placing data near the processes that use them, in order to improve performance.  ...  to Felicia Ferlin, Dave Redell and the referees for helping to improve the presentation of this paper.  ... 
doi:10.1145/74851.74854 fatcat:bhqjesruzvb37hbzvdzamx7ara

Parameters affecting the functionality of memory allocators

Ghassem Barootkoob, Ehsan Musavi Khaneghah, Mohsen Sharifi, Seyedeh Leili Mirtaheri
2011 2011 IEEE 3rd International Conference on Communication Software and Networks  
Parameters affecting the functionality of an operating system's memory management unit depend on a number of factors such as allocation and deallocation strategies, localization, internal and external  ...  Besides identifying the relationships and dependencies between these parameters, we report our experimental measurements of the effect of each parameter on the performance of different memory management  ...  Based on the results of our examinations, Section 3 presents the effective parameters on functionality of memory management units.  ... 
doi:10.1109/iccsn.2011.6014774 fatcat:lawlis3vrbanpptofeqac6dlnm

Optimizing Memory using Knapsack Algorithm

Dominic Asamoah, Evans Baidoo, Stephen Opoku Oppong
2017 International Journal of Modern Education and Computer Science  
In this paper a Dynamic Programming (DP) algorithm is proposed for the 0/1 one dimensional knapsack problem.  ...  The study was about how to select contending data/processes to be stacked to memory to enhance maximization of memory utilization and efficiency.  ...  CONCLUSION In this paper, we propose a partial enumeration technique based on an exact enumeration algorithm like the dynamic programming for effective utilisation and optimization of memory.  ... 
doi:10.5815/ijmecs.2017.05.05 fatcat:srxprf7zuvffpkdrz57vcbitsq

On modeling program behavior

Peter J. Denning
1971 Proceedings of the November 16-18, 1971, fall joint computer conference on - AFIPS '71 (Fall)  
To summarize: it has led to a sharpening of the notions "working information" and "locality of reference" ; it has aided in the development of multiprogrammed memory management strategies which guarantee  ...  IS In other words, the use of locality as a basis for memory management is close to being optimal.  ... 
doi:10.1145/1478873.1478998 dblp:conf/afips/Denning72a fatcat:jpljize3b5an7goqwfrtv2rp6i

Cell GC

Chen-Yong Cher, Michael Gschwind
2008 Proceedings of the fourth ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE '08  
We also explore object-based and block-based caching strategies for explicitly managed memory hierarchies, and explore to effectiveness of several prefetching schemes in the context of garbage collection  ...  software investment to rewrite, retune or recompile programs to take advantage of the new designs.  ...  Acknowledgments The authors would like to thank Mark Nutter, Kevin O'Brien, Sid Manning, Tong Chen, Kathryn O'Brien for their help and many useful discussions during the development of the Cell BDW garbage  ... 
doi:10.1145/1346256.1346276 dblp:conf/vee/CherG08 fatcat:v37jdo5btjbx3jdyg5ffdxaygu

ParalleX: A Study of A New Parallel Computation Model

Guang R. Gao, Thomas Sterling, Rick Stevens, Mark Hereld, Weirong Zhu
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
productivity (e.g. explicit locality management and scheduling, performance tuning, fragmented memory, and synchronous global barriers) to dramatically enhance the broad effectiveness of parallel processing  ...  In this paper, we present the progress of our research on a parallel programming and execution model -mainly, ParalleX.  ...  Dept. of Energy under Contract DE-AC02-06CH11357, IBM, ETI, and other government sponsors. We would also like to acknowl-  ... 
doi:10.1109/ipdps.2007.370484 dblp:conf/ipps/GaoSSHZ07 fatcat:5qflf6y5zffy7i32p7ktmkxeny

Real-time rendering systems in 2010

William R. Mark, Donald Fussell
2005 ACM SIGGRAPH 2005 Courses on - SIGGRAPH '05  
rendering, and by executing on general-purpose single-chip parallel hardware (CMP's).  ...  We also discuss some of the research questions that must be addressed before such a system can become practical.  ...  We thank Microsoft, Intel, NVIDIA, and the University of Texas for supporting this research.  ... 
doi:10.1145/1198555.1198758 dblp:conf/siggraph/MarkF05 fatcat:rbkmmtkfz5arjktz3hubpntbcm

Source-to-Source Optimization of CUDA C for GPU Accelerated Cardiac Cell Modeling [chapter]

Fred V. Lionetti, Andrew D. McCulloch, Scott B. Baden
2010 Lecture Notes in Computer Science  
We describe a set of domain-specific source transformations on CUDA C that improved performance by ×6.7 on a system of ODEs arising in cardiac electrophysiology running on the nVidia GTX-295, without requiring  ...  Large and complex systems of ordinary differential equations (ODEs) arise in diverse areas of science and engineering, and pose special challenges on a streaming processor owing to the large amount of  ...  Xing Cai (Simula Research Laboratory) for the discussions on ODE Solvers and Dr. Jazmin Aguado-Sierra (UCSD Bioengineering) for supplying the sample Electrophysiology model.  ... 
doi:10.1007/978-3-642-15277-1_5 fatcat:p5lrsujy2jbu7ceo5uuoo6i5ea

Strategies for dynamic memory allocation in hybrid architectures

Peter Bertels, Wim Heirman, Dirk Stroobandt
2009 Proceedings of the 6th ACM conference on Computing frontiers - CF '09  
The proposed self-learning memory allocation strategy finds the optimal location for each Java object's data by means of runtime profiling.  ...  The communication cost is effectively reduced by up to 86% for the benchmarks in the DaCapo suite (51% on average).  ...  We propose several techniques for communication-aware memory management in Section 3. For each Java object, the optimal memory location is determined based on the usage pattern of this object.  ... 
doi:10.1145/1531743.1531778 dblp:conf/cf/BertelsHS09 fatcat:5y4a7oe7anfsdc3uuj6cbv43jm

Page 75 of Hewlett-Packard Journal Vol. 38, Issue 11 [page]

1987 Hewlett-Packard Journal  
The posting routines judiciously manage main memory occu- pancy, file consistency, and disc utilization. Main memory occupancy of file pages is primarily the responsibility of the memory manager.  ...  The prefetch strategy routine views the pattern of both global and local references against a disc file, and makes a heuristic determination of how much data should be prefetched from disc.  ... 

Parallel Processing of Economic Programs, a New Strategy in Groups of Firms

Loredana MOCEAN, Monica-Iuliana CIACA, Alexandru VANCEA
2014 Informatică economică  
In the present paper, authors describe some possibilities of parallel processing at the level of economic programs in groups of firms. The architecture, model and future development are shown below.  ...  In recent years parallel and distributed systems have become increasingly attractive for applications with high computational demands such as simulation of complex systems from groups of companies.  ...  Such a paradigm is focused on the assignment instruction and provides programs whose effect can be described as a sequence of transformations of the memory cells values on which the program acts.  ... 
doi:10.12948/issn14531305/18.2.2014.11 fatcat:2lyk37rptzeplln23tihrb5swe

Challenges in Deeply Heterogeneous High Performance Systems

Giovanni Agosta, William Fornaciari, David Atienza, Ramon Canal, Alessandro Cilardo, Jose Flich, Carles Hernandez Luz, Michal Kulczewski, Giuseppe Massari, Rafael Tornero Gavila, Marina Zapater Sancho
2019 2019 22nd Euromicro Conference on Digital System Design (DSD)  
architectures, HPC memory/interconnection infrastructures, thermal modelling, reliability, programming models, and timing analysis.  ...  For each of these areas, the paper describes the relevant state of the art as well as the specific actions that the project will take to effectively address the identified technological challenges.  ...  Programming models HPC applications are usually programmed by using hybrid programming models, combining a distributed memory model, often MPI, to manage the application parallelism at global level, and  ... 
doi:10.1109/dsd.2019.00068 dblp:conf/dsd/AgostaFACCFHKMG19 fatcat:3zmdras2iraq3nmyw7gn2qaesu

Efficient runtime thread management for the nano-threads programming model [chapter]

Dimitrios S. Nikolopoulos, Eleftherios D. Polychronopoulos, Theodore S. Papatheodorou
1998 Lecture Notes in Computer Science  
The nano-threads programming model was proposed to effectively integrate multiprogramming on shared-memory multiprocessors, with the exploitation of fine-grain parallelism from standard applications.  ...  Through the use of synthetic benchmarks, we find that our mechanism for memory management in the runtime system reduces overheads by 52% on average, compared to other known mechanisms.  ...  Acknowledgements We would like to thank Constantine Polychronopoulos for his support of this work, Xavier Martorell for his help in conducting the experiments, the European Center for Parallelism in Barcelona  ... 
doi:10.1007/3-540-64359-1_688 fatcat:54eahhbswfb2pe37piqtibzpoi
« Previous Showing results 1 — 15 out of 197,326 results