Filters








1,645 Hits in 8.6 sec

Challenges in Building a Flat-Bandwidth Memory Hierarchy for a Large-Scale Computer with Proximity Communication

R. Drost, C. Forrest, B. Guenin, R. Ho, A.V. Krishnamoorthy, D. Cohen, J.E. Cunningham, B. Tourancheau, A. Zingher, A. Chow, G. Lauterbach, I. Sutherland
13th Symposium on High Performance Interconnects (HOTI'05)  
to relieve the memory bottleneck in a large-scale computer that we call "Hero."  ...  Memory systems for conventional large-scale computers provide only limited bytes/s of data bandwidth when compared to their flop/s of instruction execution rate.  ...  In addition we recognize the effective support and guidance from DARPA as part of its HPCS Phase II program.  ... 
doi:10.1109/conect.2005.12 dblp:conf/hoti/DrostFGHKCCTZCLS05 fatcat:jaytoz2qnzalzgz4qnl4eytohe

Scalable Multi-purpose Network Representation for Large Scale Distributed System Simulation

Laurent Bobelin, Arnaud Legrand, David A. Gonz´lez M´rquez, Pierre Navarro, Martin Quinson, Frédéric Suter, Christophe Thiéry
2012 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)  
However, the simulation of large-scale computing systems raises several scalability issues, in terms of speed and memory.  ...  Conducting experiments in large-scale distributed systems is usually time-consuming and labor-intensive.  ...  (P2P) systems, raises new challenges in Computer Science.  ... 
doi:10.1109/ccgrid.2012.31 dblp:conf/ccgrid/BobelinLMNQST12 fatcat:3yqwvfgzkzejrbgxkh4purwkcu

Marrying Many-core Accelerators and InfiniBand for a New Commodity Processor [article]

Konstantin S. Solnushkin, Yuichi Tsujita
2013 arXiv   pre-print
The coming exa-scale era changes the landscape: exa-scale computers will contain components in quantities large enough to justify their custom development and production.  ...  We propose a new heterogeneous processor, equipped with a network controller and designed specifically for HPC.  ...  Here we have the following assumptions about this system: • Complicated hierarchy in memory architecture • Shortage of available memory per core Therefore a multi-layered MPI communicator management is  ... 
arXiv:1307.0100v1 fatcat:yxvtz66fcvahvb3wtytdm6nlhe

Monitoring Large-Scale Cloud Systems with Layered Gossip Protocols [article]

Jonathan Stuart Ward, Adam Barker
2013 arXiv   pre-print
In this paper we propose the development of a cloud monitoring suite to provide scalable and robust lookup, data collection and analysis services for large-scale cloud systems.  ...  The need for robust monitoring tools has become more evident with the advent of cloud computing.  ...  With the immense benefits of this paradigm comes a number of challenges, amongst these is the challenge of monitoring. Monitoring large-scale distributed systems is challenging.  ... 
arXiv:1305.7403v1 fatcat:k5izdtv3rfhvbl2tousan3yriq

Self managing monitoring for highly elastic large scale cloud deployments

Jonathan Stuart Ward, Adam Barker
2014 Proceedings of the sixth international workshop on Data intensive distributed computing - DIDC '14  
Infrastructure as a Service computing exhibits a number of properties, which are not found in conventional server deployments.  ...  This tool breaks with many of the conventions of previous monitoring systems and leverages a multi-tier P2P architecture in order to achieve in situ monitoring without the need for dedicated monitoring  ...  In large scale cloud deployments individual VMs operate under a range of computation and communication constraints.  ... 
doi:10.1145/2608020.2608022 dblp:conf/hpdc/WardB14 fatcat:76cemc5sczgrdf6aeoiau5cc7i

Hardware Locality-Aware Partitioning and Dynamic Load-Balancing of Unstructured Meshes for Large-Scale Scientific Applications

Pavanakumar Mohanamuraly, Gabriel Staffelbach
2020 Proceedings of the Platform for Advanced Scientific Computing Conference  
The tool was successfully integrated into our in-house code and we present results from a large-eddy simulation of a combustion problem.  ...  It provides a range of partitioning methods by interfacing with existing shared and distributed memory parallel partitioning libraries.  ...  This work was granted access to the HPC resources of IDRIS under an allocation by GENCI for the Grand Challenges Jean Zay (2019).  ... 
doi:10.1145/3394277.3401851 dblp:conf/pasc/MohanamuralyS20 fatcat:thhnjsb7ufbgbmvmf6abiyzlri

Beyond Processor-centric Operating Systems

Paolo Faraboschi, Kimberly Keeton, Tim Marsland, Dejan S. Milojicic
2015 USENIX Workshop on Hot Topics in Operating Systems  
At rack scale, we can expect a large pool of non-volatile memory (NVM) that will be accessed by heterogeneous and decentralized compute resources [3, 17].  ...  In this paper, we describe the characteristics and consequences of memory-centric architectures and propose a memory-centric OS design that moves traditional OS functionality outside of the compute node  ...  We thank the anonymous reviewers and our colleagues John Sontag, Brad Morrey, Indrajit Roy, Terence Kelly, Joe Tucek, Keith Packard and Guilherme Magalhaes for their helpful comments.  ... 
dblp:conf/hotos/FaraboschiKMM15 fatcat:wc4ehrbiffazzmdke2m6bmmma4

Enabling Fog Computing using Self-Organizing Compute Nodes

Vasileios Karagiannis, Nuno Preguica, Joao Leitao, Stefan Schulte
2019 Zenodo  
Publication in Conference proceedings/Workshop  ...  For communication within the fog network, intelligent messaging based on bandwidth minimization is implemented along with the querying mechanism, as discussed in Section III-F.  ...  In such hierarchical models, typically, computation requests originate from the bottom and travel upwards the hierarchy until they reach a compute node with enough resources to execute them [5] .  ... 
doi:10.5281/zenodo.5850217 fatcat:ypz6flpqmraxrkdaqry3pc5bxm

The Mondrian Data Engine

Mario Drumond, Alexandros Daglis, Nooshin Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, Dionisios Pnevmatikatos
2017 SIGARCH Computer Architecture News  
The increasing demand for extracting value out of ever-growing data poses an ongoing challenge to system designers, a task only made trickier by the end of Dennard scaling.  ...  In the context of NMP, such random accesses result in wasteful DRAM row buffer activations that account for a significant fraction of the total memory access energy.  ...  ACKNOWLEDGEMENTS The authors thank the anonymous reviewers and Arash Pourhabibi for their precious comments and feedback.  ... 
doi:10.1145/3140659.3080233 fatcat:zjfvuprhmnahhmqfnj6ems7fli

The Mondrian Data Engine

Mario Drumond, Alexandros Daglis, Nooshin Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, Dionisios Pnevmatikatos
2017 Proceedings of the 44th Annual International Symposium on Computer Architecture  
The increasing demand for extracting value out of ever-growing data poses an ongoing challenge to system designers, a task only made trickier by the end of Dennard scaling.  ...  In the context of NMP, such random accesses result in wasteful DRAM row buffer activations that account for a significant fraction of the total memory access energy.  ...  ACKNOWLEDGEMENTS The authors thank the anonymous reviewers and Arash Pourhabibi for their precious comments and feedback.  ... 
doi:10.1145/3079856.3080233 fatcat:lctwfx5ilbdazdhjvjtbvgo3fq

Software challenges in extreme scale systems

Vivek Sarkar, William Harrod, Allan E Snavely
2009 Journal of Physics, Conference Series  
Carlson is a member of the research staff at the IDA Center for Computing Sciences where, since 1990, his focus has been on applications and system tools for large-scale parallel and distributed computers  ...  More recent work is investigating how PIM-like ideas may port into quantum cellular array (QCA) and other nanotechnology logic, where in-stead of "Processing-In-Memory" we have opportunities for "Processing-In-Wire  ...  the memory hierarchy and minimizes overall runtime with effective trade-off of increased computation for reduced memory consumption.  ... 
doi:10.1088/1742-6596/180/1/012045 fatcat:iukutry2dvbitfdh6ng7kgz564

Memory leads the way to better computing

H.-S. Philip Wong, Sayeef Salahuddin
2015 Nature Nanotechnology  
in advancing computing by a thousandfold by 2015.  ...  computing.  ...  For the single job speedup case, bandwidths probably scale linearly with the 1,000X in rate, but total memory capacity will stay roughly flat at what it will be in 2010.  ... 
doi:10.1038/nnano.2015.29 pmid:25740127 fatcat:d6iiuuwcozbxlgn4kxxzdzwd4m

Eurolab-4-HPC Long-Term Vision on High-Performance Computing [article]

Theo Ungerer, Paul Carpenter
2018 arXiv   pre-print
Radical changes in computing are foreseen for the next decade.  ...  The objective of the Eurolab-4-HPC vision is to provide a long-term roadmap from 2023 to 2030 for High-Performance Computing (HPC).  ...  Simultaneously, a high communication bandwidth between layers connected with TSVs can be expected leading to particularly high processor-to-memory bandwidth.  ... 
arXiv:1807.04521v1 fatcat:5neetrgubjhnvcajcktpkohrzq

Scale-out NUMA

Stanko Novakovic, Alexandros Daglis, Edouard Bugnion, Babak Falsafi, Boris Grot
2014 Proceedings of the 19th international conference on Architectural support for programming languages and operating systems - ASPLOS '14  
We introduce Scale-Out NUMA (soNUMA) -an architecture, programming model, and communication protocol for low-latency, distributed in-memory processing. soNUMA layers an RDMA-inspired programming model  ...  The large number of servers needed to accommodate this massive memory footprint requires frequent server-to-server communication in applications such as key-value stores and graph-based applications that  ...  Acknowledgments The authors thank Dushyanth Narayanan and Aleksandar Dragojevic from Microsoft Research for many inspiring conversations on rack-scale computing requirements and applications early in the  ... 
doi:10.1145/2541940.2541965 dblp:conf/asplos/NovakovicDBFG14 fatcat:buiufe62bvfohpvti5gsq3cyoa

Trends in Data Locality Abstractions for HPC Systems

Didem Unat, Anshu Dubey, Torsten Hoefler, John Shalf, Mark Abraham, Mauro Bianco, Bradford L. Chamberlain, Romain Cledat, H. Carter Edwards, Hal Finkel, Karl Fuerlinger, Frank Hannig (+9 others)
2017 IEEE Transactions on Parallel and Distributed Systems  
However, with the increasing complexity of the memory hierarchy and higher parallelism in emerging HPC systems, locality management has acquired a new urgency.  ...  This paper examines these trends and identifies commonalities that can combine various locality concepts to develop a comprehensive approach to expressing and managing data locality on future large-scale  ...  Bandwidth tapering has been a challenge since the dawn of cache hierarchies, and the remedies (loop blocking, strip-mining, tiling, domain decomposition, and communication optimizations/topology mapping  ... 
doi:10.1109/tpds.2017.2703149 fatcat:vjalwrujhrex7cibod3qerf3z4
« Previous Showing results 1 — 15 out of 1,645 results