Filters








41 Hits in 5.0 sec

ANTAREX -- AutoTuning and Adaptivity appRoach for Energy Efficient eXascale HPC Systems

Cristina Silvano, Giovanni Agosta, Andrea Bartolini, Andrea Beccari, Luca Benini, Joao M. P. Cardoso, Carlo Cavazzoni, Radim Cmar, Jan Martinovic, Gianluca Palermo, Martin Palkovic, Erven Rohou (+2 others)
2015 2015 IEEE 18th International Conference on Computational Science and Engineering  
Computing (HPC) systems up to the Exascale level.  ...  The DSL approach will allow the definition of energy-efficiency, performance, and adaptivity strategies as well as their enforcement at runtime through application autotuning and resource and power management  ...  Machine learning techniques are also adopted in the decision-making engine to support the autotuning by predicting the most promising set of parameter settings. Precision Autotuning.  ... 
doi:10.1109/cse.2015.58 dblp:conf/cse/SilvanoABBBCCCM15 fatcat:relhamsj2zgjdns43rfl7fimby

Energy-efficient Algorithms for Ultrascale Systems

2015 Supercomputing Frontiers and Innovations  
The US DOE Exascale Initiative has set a target of 20 MW for the power consumption of an Exascale system.  ...  In the software area, there also exist a multitude of research approaches towards energy saving, often concentrating either on the system software level or the application organization level, reflecting  ...  on the top of (physical or virtual) machines.  ... 
doi:10.14529/jsfi150205 fatcat:hceabokapvgozc4tsgikcjyq3u

The International Exascale Software Project roadmap

Jack Dongarra, Pete Beckman, Terry Moore, Patrick Aerts, Giovanni Aloisio, Jean-Claude Andre, David Barkai, Jean-Yves Berthou, Taisuke Boku, Bertrand Braunschweig, Franck Cappello, Barbara Chapman (+53 others)
2011 The international journal of high performance computing applications  
Make a thorough assessment of needs, issues and strategies: A successful plan in this arena requires a thorough assessment of the technology drivers for future peta/exascale systems and of the short-term  ...  science on extreme-scale systems.  ...  For example, all areas need some I/O, but the ones checked were deemed to need considerable I/O, based on the problems that exist today.  ... 
doi:10.1177/1094342010391989 fatcat:twdszcjfxraijpsdcdacvpp6vm

Advanced Stencil-Code Engineering (Dagstuhl Seminar 15161)

Christian Lengauer, Matthias Bolten, Robert D. Falgout, Olaf Schenk, Marc Herbstritt
2015 Dagstuhl Reports  
Its aim was to lay the basis for a new interdisciplinary research community on high-performance stencil codes.  ...  The seminar was hosted by the DFG project with the same name (ExaStencils for short) in the DFG priority programme "Software for Exascale Computing" (SPPEXA).  ...  To master this challenge, we created a machine-learning approach for the derivation of a performance-influence model.  ... 
doi:10.4230/dagrep.5.4.56 dblp:journals/dagstuhl-reports/LengauerBFS15 fatcat:suk5zayvlnb63ozlamrw2vk2w4

Software challenges in extreme scale systems

Vivek Sarkar, William Harrod, Allan E Snavely
2009 Journal of Physics, Conference Series  
He also leads the UPC language effort, a consortium of industry and academic research institutions aiming to produce a unified approach to parallel C programming based on global address space methods.  ...  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  ...  As with companion computations, off-line autotuning is feasible in today's powerful systems, and on-line autotuning will become feasible in light of the vast resources available in exascale systems.  ... 
doi:10.1088/1742-6596/180/1/012045 fatcat:iukutry2dvbitfdh6ng7kgz564

Towards Autonomic Science Infrastructure

Rajkumar Kettimuthu, Alok Choudhary, Zhengchun Liu, Ian Foster, Peter H. Beckman, Alex Sim, Kesheng Wu, Wei-keng Liao, Qiao Kang, Ankit Agrawal
2018 Proceedings of the 1st International Workshop on Autonomous Infrastructure for Science - AI-Science'18  
Growing interest and recent developments in machine learning have spurred proposals to apply machine learning for goal-based optimization of computing systems in an autonomous fashion.  ...  In order to address this problem, autonomic, goal-driven management actions based on machine learning must be applied end to end across the scienti c computing landscape.  ...  ACKNOWLEDGMENT This material is based upon work supported by the U.S.  ... 
doi:10.1145/3217197.3217205 dblp:conf/hpdc/KettimuthuLFBSW18 fatcat:q465b3cyibarnowssx4jny6jvu

Analytical Cost Metrics : Days of Future Past [article]

Nirmal Prajapati, Sanjay Rajopadhye, Hristo Djidjev
2018 arXiv   pre-print
These problems arise in almost all areas of computing, ranging from big data analytics, artificial intelligence, search, machine learning, virtual/augmented reality, computer vision, image/signal processing  ...  The architectures are constantly evolving making the current performance optimizing strategies less applicable and new strategies to be invented.  ...  In contrast, our approach develops analytical models based on (i) machine and architecture parameters, (ii) program size parameters as found in the polyhedral model, and (iii) tiling parameters.  ... 
arXiv:1802.01957v1 fatcat:r6lajnt75zb4xahkznt5gb4wx4

D2.4: Stakeholder Management in PRACE 2.0

Jean-Philippe Nominé, Philippe Segers
2017 Zenodo  
evolutions of the HPC ecosystem, that could be summarised as a global race to Exascale (potentially available at the beginning of next decade), with an accelerating pace (at least for USA, China and Japan  ...  Whereas previous deliverables were focused on the early identification of core stakeholders of the project and on the legal aspect of relationship with other entities, this one is more focused on the latest  ...  These can possibly be coupled with machine learning algorithms and neural networks for a more guided decision making process.  ... 
doi:10.5281/zenodo.6801676 fatcat:5z7huwaa5vg57go37wtxbkz6iu

D12.1: Heterogeneous and Auto-tuned Runtime System

Christian Perez, Zhengxiong Hou, Judit Planas, Rosa Badia, Eduard Aygüadé, Jesus Labarta, Michael Schliephake, Chandan Basu, Johan Raber, Massimo Guarrasi, Lasse Natvig, Kostis Nikas (+5 others)
2013 Zenodo  
Furthermore, as it is widely accepted that the key to exploiting future high-end systems will be based on research on new numerical algorithms as well as advancing the parallel processing technology used  ...  Work Package 12 (WP12) "Novel Programming Techniques" performs research and development in four key areas for future multi-petascale and exascale systems.  ...  First, FFTW's planner "learns" the fastest way to compute the transform on the selected machine. The planner produces a data structure called a plan that contains this information.  ... 
doi:10.5281/zenodo.6572371 fatcat:uttgomgovjeb5iopc2ccgyar7y

D5.1: Market and Technology Watch Report Year 1

Jean-Philippe Nominé
2016 Zenodo  
It is thus the continuation of a well-established effort, using assessment of the HPC market based on market surveys, supercomputing conferences, and exchanges with vendors and between experts involved  ...  This deliverable is the first one of PRACE-4IP Work Package 5 Task 1, it corresponds to a periodic annual update on technology and market trends.  ...  ALGORITHMS AND MATHEMATICS • Machine Learning: -ExCAPE: better machine learning algorithms for predicting biological activity of drugs and their deployment on HPC systems. • Solvers: -NLAFET: linear solvers  ... 
doi:10.5281/zenodo.6801690 fatcat:zpnjoenqkvb2te74rvci326vba

Hardware and Software Solutions for Energy-Efficient Computing in Scientific Programming

Daniele D'Agostino, Ivan Merelli, Marco Aldinucci, Daniele Cesini, Cristian Mateos
2021 Scientific Programming  
tools and techniques from the other one.  ...  programming because the local computational capabilities are typically limited and require a careful evaluation of power consumption.  ...  Extrae is a tool relying on PAPI that allows collecting its countermetrics (including power and thermal data) for parallel programs [37] .  ... 
doi:10.1155/2021/5514284 fatcat:xcnglwhhabcylokuyknabd2oyu

SMAT

Jiajia Li, Guangming Tan, Mingyu Chen, Ninghui Sun
2013 SIGPLAN notices  
For this purpose, SMAT leverages a learning model, which is generated in an off-line stage by a machine learning method with a training set of more than 2000 matrices from the UF sparse matrix collection  ...  By far, SpMV libraries are optimized by either application-specific or architecture-specific approaches, making the libraries become too complicated to be used extensively in real applications.  ...  Remember that SMAT is only a proof of concept system, and its adoption of reusable machine learning model makes it feasible to extend for more formats and implementations.  ... 
doi:10.1145/2499370.2462181 fatcat:sv6wufh4wbbanayai7rcb4u5zu

D7.2.1 A Report on the Survey of HPC Tools and Techniques

Michael Lysaght, Bjorn Lindi, Vit Vondrak, John Donners, Marc Tajchman
2013 Zenodo  
This perspective is presented so as to inspire new "forward looking" approaches to enable European applications on the road to exascale computing.  ...  The survey covers four separate topics that we consider relevant to enable applications on current multi-petascale systems.  ...  Currently, the fact that trace files need to be collected to the one host system for analysis is a limiting factor for scalability.  ... 
doi:10.5281/zenodo.6575492 fatcat:grwigpxd7naifbzo6w67w4glrm

SMAT

Jiajia Li, Guangming Tan, Mingyu Chen, Ninghui Sun
2013 Proceedings of the 34th ACM SIGPLAN conference on Programming language design and implementation - PLDI '13  
For this purpose, SMAT leverages a learning model, which is generated in an off-line stage by a machine learning method with a training set of more than 2000 matrices from the UF sparse matrix collection  ...  By far, SpMV libraries are optimized by either application-specific or architecture-specific approaches, making the libraries become too complicated to be used extensively in real applications.  ...  Remember that SMAT is only a proof of concept system, and its adoption of reusable machine learning model makes it feasible to extend for more formats and implementations.  ... 
doi:10.1145/2491956.2462181 dblp:conf/pldi/LiTCS13 fatcat:lmmcpzxr6fcqza7kmcaxm6kizu

D12.5: Summary of Novel Programming Techniques Results

Jose Carlos Sanchez, Christian Perez, Cevdet Aykanat, R. Oguz Selvitopi, Alberto Miranda, Ramon Nou, Toni Cortes, Eric Boyer
2014 Zenodo  
to decrease the overall wall-times; and the rest were focusing on improving of workflow executions through meta-model methods and the other using a component based approach to improve the 3D FFT.  ...  This Work Package performed research and development on the programmability of future multi-petascale and exascale systems.  ...  As a matter of fact, variability of results on a machine in concurrent production can often reach 5%.  ... 
doi:10.5281/zenodo.6572440 fatcat:2l3puhyonfbxxhrhdvqjln26vq
« Previous Showing results 1 — 15 out of 41 results