April 2016 - OpenStack-HPC - lists.openstack.org

Re: [openstack-hpc] What's the state of openstack-hpc now?
by Blair Bethwaite 06 Oct '16

06 Oct '16

Hi, Apologies for top-posting but I don't intend to answer all the historical project points you've raised. Regarding old things floating around on github, your mileage may vary, but I doubt at this point you want to be looking at any of that in great detail. You haven't really explained what you mean by or want from HPC in this context, so I'm guessing a little based on your other questions... OpenStack is many things to different people and organisations, but at the software core is a very flexible infrastructure provisioning framework. HPC requires infrastructure (compute, network, storage), and OpenStack can certainly deliver it - make your deployment choices to suit your use-cases. A major choice would be whether you will use full system virtualisation or bare-metal or containers or <insert next trend> - that choice largely depends on your typical workloads and what style of cluster you want. Beyond that, compared to "typical" cloud hardware - faster CPUs, faster memory, faster network (probably with much greater east-west capacity), integration of a suitable parallel file-system. However, OpenStack is not a HPC management / scheduling / queuing / middleware system - there are lots of those already and you should pick one that fits your requirements and then (if it helps) run it atop an OpenStack cloud (it might help, e.g., if you want to run multiple logical clusters on the same physical infrastructure, if you want to mix other more traditional cloud workloads in, if you're just doing everything with OpenStack like the other cool kids). There are lots of nuances here, e.g., where one scheduler might lend itself better to more dynamic infrastructure (adding/removing instances), another might be lighter-weight for use with a Cluster-as-a-Service deployment model, whilst another suits a multi-user managed service style cluster. I'm sure there is good experience and opinion hidden on this list if you want to interrogate those sorts of choices more specifically. Most of the relevant choices you need to make with respect to running HPC workloads on infrastructure that is provisioned through OpenStack will come down to your hypervisor choices. My preference for now is to stick with the OpenStack community's most popular free OS and hypervisor (Ubuntu and KVM+Libvirt) - when I facilitated the hypervisor-tuning ops session at the Vancouver summit (with a bunch of folks interested in HPC on OpenStack) there was no-one in the room running a different hypervisor, though several were using RHEL. With the right tuning KVM can get you to within a hair's breadth of bare-metal performance for a wide range of CPU, memory and inter-process comms benchmarks, plus you can easily make use of PCI passthrough for latency sensitive or "difficult" devices like NICs/HCAs and GPGPUs. And the "right tuning" is not really some arcane knowledge, it's mainly about exposing host CPU capabilities, pinning vCPUs to pCPUs, and tuning or pinning and exposing NUMA topology - most of this is supported directly through OpenStack-native features now. To answer the GPU question more explicitly - yes you can do this. Mainly you need to ensure you're getting compatible hardware (GPU and relevant motherboard components) - most of the typical GPGPU choices (e.g. K80, K40, M60) will work, and you should probably be wary of PCIe switches unless you know exactly what you're doing (recommend trying before buying). At the OpenStack level you just define the PCI devices you want OpenStack Nova to provision and you can then define custom instance-types/flavors that will get a GPU passed through. Similar things go for networking. Lastly, just because you can do this doesn't make it a good idea... OpenStack is complex, HPC systems are complex, layering one complicated thing on another is a good way to create tricky problems that hide in the interface between the two layers. So make sure you're gaining something from having OpenStack in the mix here. HTH, Blair On 15 March 2016 at 23:00, <openstack-hpc-request(a)lists.openstack.org> wrote: > Message: 1 > Date: Tue, 15 Mar 2016 19:05:38 +0800 > From: "me,apporc" <appleorchard2000(a)gmail.com> > To: openstack-hpc(a)lists.openstack.org > Subject: [openstack-hpc] What's the state of openstack-hpc now? > Message-ID: > <CAOBTi0sftGTG-fscM-C5wLu6bTgZMaLaM2eXBJpa0a=vkPDusg(a)mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Hi, all > > I found this etherpad[1] which was created long time ago, inside which > there are some blueprints: support-heterogeneous-archs[2], > heterogeneous-instance-types[3] > and schedule-instances-on-heterogeneous-architectures[4] . > But those blueprints had been obselete since year 2014, and some of its > patches were abandoned. > There however is a forked branch github[5] or launchpad[6], which is > diverged far away from nova/trunk, and not updated since 2014 too. > > Is that we just abandoned those blueprints in openstack or else? > > Besides, there is a CaaS[7] project called Senlin[8], which refered to the > word "HPC" in its wiki. But it seems like not really related. "Cluster" can > mean many things, but hpc is some kind different. > > I can not get the status of GPU support in nova. As the case of network, > SR-IOV[9] seems ok. For storage, i don't know what the word "mi2" means in > etherpad[1]. > > According to what i got above, it seems we can not use hpc in openstack > now. But there are some videos here[10], here[11] and here[12].Since we can > not get GPU in nova instance, are they just building traditional hpcs > without GPU? > > > I need more information, thanks in advance. > > 1. https://etherpad.openstack.org/p/HVHsTqOQGc > 2. https://blueprints.launchpad.net/nova/+spec/support-heterogeneous-archs > 3. https://blueprints.launchpad.net/nova/+spec/heterogeneous-instance-types > 4. > https://blueprints.launchpad.net/nova/+spec/schedule-instances-on-heterogen… > 5. https://github.com/usc-isi/nova > 6. https://code.launchpad.net/~usc-isi/nova/hpc-trunk > 7. https://wiki.openstack.org/wiki/CaaS > 8. https://wiki.openstack.org/wiki/Senlin > 9. https://wiki.openstack.org/wiki/SR-IOV-Passthrough-For-Networking > 10. > https://www.openstack.org/summit/vancouver-2015/summit-videos/presentation/… > 11. > https://www.openstack.org/summit/tokyo-2015/videos/presentation/hpc-on-open… > 12. > https://www.openstack.org/summit/tokyo-2015/videos/presentation/canonical-h… > -- > Regards, > apporc >

4 7

FedCSIS 2016 - FINAL CALL FOR PAPERS
by Federated Conference on Computer Science and Information Systems 21 Apr '16

21 Apr '16

FINAL CALL FOR PAPERS 2016 Federated Conference on Computer Science and Information Systems (FedCSIS) Gdansk, Poland, 11 - 14 September, 2016 www.fedcsis.org (FedCSIS on www.ieee.org: http://tinyurl.com/FedCSIS-on-IEEE-2016) FedCSIS a yearly international multi-conference organized by the Polish Information Processing Society (PTI) in technical cooperation with the IEEE Region 8, IEEE Computer Society Technical Committee on Intelligent Informatics, IEEE Poland Section, IEEE Poland (Gdansk) Section Computer Society Chapter, Poland Section Computational Intelligence Society Chapter, ACM Special Interest Group on Applied Computing, Lodz ACM Chapter, Committee of Computer Science of Polish Academy of Sciences, European Alliance for Innovation, Polish Operational and Systems Research Society - POSRS, Eastern Cluster ICT Poland, Mazovia Cluster ICT. Please also forward the announcement to your colleagues and associates who could be interested in it. The FedCSIS Multi-conference consists of Events (conferences, symposia, workshops, dissemination events, special sessions). Each Event may run over any span of time within the conference dates (from half-day to four days). The FedCSIS Events provide a platform for bringing together researchers, practitioners, and academia to present and discuss ideas, challenges and potential solutions on established or emerging topics related to research and practice in computer science and information systems. Since 2012, Proceedings of the FedCSIS conference have been indexed in the Thomson Reuters Web of Science. FedCSIS EVENTS The FedCSIS multi-conference consists of EVENTS (conferences, workshops, consortia, tutorials, etc.), grouped into seven conference areas. * AAIA'16 - 11th International Symposium Advances in Artificial Intelligence and Applications --- AIMaVIG'16 - 2nd International Workshop on Artificial Intelligence in Machine Vision and Graphics --- AIMA'16 - 6th International Workshop on Artificial Intelligence in Medical Applications --- AIRIM'16 - 1st International Workshop on AI aspects of Reasoning, Information, and Memory --- ASIR'16 - 6th International Workshop on Advances in Semantic Information Retrieval --- DSTUI'16 - 6th International Workshop on Dealing with Spatial and Temporal Uncertainty and Imprecision --- LTA'16 - 1st International Workshop on Language Technologies and Applications --- WCO'16 - 9th International Workshop on Computational Optimization * CSS - Computer Science & Systems --- AIPC'16 - 1st International Workshop on Advances in Image Processing and Colorization --- BCPC'16 - 2nd International Workshop on Biological, Chemical and Physical Computations --- CANA'16 - 9th Computer Aspects of Numerical Algorithms --- CPORA'16 - 1st Workshop on Constraint Programming and Operation Research Applications --- IWCPS'16 - 3rd International Workshop on Cyber-Physical Systems --- MMAP'16 - 9th International Symposium on Multimedia Applications and Processing --- WSC'16 - 8th Workshop on Scalable Computing * ECRM - Education, Curricula & Research Methods --- IEES'16 - 1st International E-education Symposium - Education of the Future --- DS-RAIT'16 - 3rd Doctoral Symposium on Recent Advances in Information Technology * iNetSApp'16 - 4th International Conference on Innovative Network Systems and Applications --- EAIS'16 - 3rd Workshop on Emerging Aspects in Information Security --- SoFAST-WS'16 - 5th International Symposium on Frontiers in Network Applications, Network Systems and Web Services --- WSN'16 - 5th International Conference on Wireless Sensor Networks * IT4MBS - Information Technology for Management, Business & Society --- ABICT'16 - 7th International Workshop on Advances in Business ICT --- AITM'16 - 14th Conference on Advanced Information Technologies for Management --- APICSS'16 - 1st Workshop on Autopoiesis Perspective on Information, Communication and Social Systems --- ASEG'16 - 1st Workshop on Advanced Systems for e-Governance and e- Democratization --- ISM'16 - 11th Conference on Information Systems Management --- IT4L'16 - 5th Workshop on Information Technologies for Logistics --- KAM'16 - 22nd Conference on Knowledge Acquisition and Management --- MIQH'16 - 1st Workshop on M-Health Innovations for Quality in Healthcare --- UHH'16 - 2nd International Workshop on Ubiquitous Home Healthcare * JAWS - Joint Agent-oriented Workshops in Synergy --- ABC:MI'16 - 11th Workshop on Agent Based Computing: from Model to Implementation --- MAS&S'16 - 10th International Workshop on Multi-Agent Systems and Simulations --- SEN-MAS'16 - 4th International Workshop on Smart Energy Networks & Multi-Agent Systems * SSD&A - Software Systems Development & Applications --- BTMSPA'16 - 1st Symposium on Balancing Traditional and Modern Software Process Approaches --- MDASD'16 - 4th Workshop on Model Driven Approaches in System Development --- MIDI'16 - 4th Conference on Miltimedia, Interaction, Design and Innovation --- SEW-36 - The 36th IEEE Software Engineering Workshop --- WASE'16 - 1st International Workshop on Affective Software Engineering KEYNOTE SPEAKERS - Frederik Ahlemann, University of Duisburg-Essen, Germany, Keynote title : How enterprise architecture management improves IS capabilities - Results from a multiple case study - Stan Matwin, Dalhousie University, University of Ottawa, Institute of Computer Science, Polish Academy of Science, Keynote title : Big Water Meets Big Data: Analytics of the AIS Ship Tracking Data - Michael Segal, Ben-Gurion University of the Negev, Keynote title : Location always matters: how to improve performance of dynamic networks? - Clemens Szyperski, Microsoft, Redmond, WA, US, Keynote title: Service focus and focused service composition PAPER SUBMISSION AND PUBLICATION Papers should be submitted by May 9, 2016 (strict deadline). Preprints will be published on a USB memory stick provided to the FedCSIS participants. Only papers presented during the conference will be submitted to the IEEE for inclusion in the Xplore Digital Library. Furthermore, proceedings, published in a volume with ISBN, ISSN and DOI numbers will posted at the conference WWW site. Moreover, most Events' organizers arrange quality journals, edited volumes, etc. and may invite selected extended and revised papers for post-conference publications (information can be found at the websites of individual events). IMPORTANT DATES - Paper submission: May 9, 2016 (strict deadline) - Position paper submission: May 30, 2016 - Acceptance decision: June 13, 2016 - Final version of paper submission: July 4, 2016 - Final deadline for discounted fee: July 31, 2016 - Conference dates: September 11-14, 2016 CHAIRS OF FedCSIS CONFERENCE SERIES Maria Ganzha, Leszek A. Maciaszek, Marcin Paprzycki CONTACT FedCSIS AT: secretariat(a)fedcsis.org FedCSIS on Facebook: http://tinyurl.com/FedCSISFacebook FedCSIS on LinkedIN: http://tinyurl.com/FedCSISLinkedIN

1 0

VECPAR 2016: Call for Participation
by Carlos Ferreira 19 Apr '16

19 Apr '16

------------------------------------------------------------------------------------------ CALL FOR PARTICIPATION 12th International Meeting on High-Performance Computing for Computational Science (VECPAR 2016) University of Porto, Porto, Portugal June 28 - 30, 2016 http://vecpar.fe.up.pt/2016/ Porto has been crowned the BEST EUROPEAN DESTINATION of 2014 for its postcard-perfect views, friendly locals and gastronomy. ------------------------------------------------------------------------------------------- This year the VECPAR conference will have a very exciting program with 19 papers from 10 countries. We have a varied selection of paper subjects ranging from distributed to shared and hybrid parallel algorithms and systems, but with a strong focus on computational science applications. Examples are epidemic modeling and word searching. Parallel libraries is also a popular subject this year. Platforms range from clouds to multi-core, many-core, and GPUs. The conference will include invited talks by 4 prominent speakers, very interesting workshops and a crash course, and a fantastic social dinner including Port wine tasting. A list of accepted papers can be found at: http://vecpar.fe.up.pt/2016/papers.html Please, check the conference web site (http://vecpar.fe.up.pt/2016/) for updates and more detailed information. Registrations will be opening soon! Please, check at: http://vecpar.fe.up.pt/2016. We look forward to seeing you soon! The VECPAR 2016 Organizing Committee. Carlos Ferreira ISEP | Instituto Superior de Engenharia do Porto Rua Dr. António Bernardino de Almeida, 431 4249-015 Porto - PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail(a)isep.ipp.pt | www.isep.ipp.pt

1 0