High-performance computers require a highly capable file system. PVFS is an open source parallel file system and joint collaboration led by Argonne National Laboratory, Clemson University, and Ohio Supercomputing Center. PVFS has been delivering features and high-performance on today's top high-end computers, while remaining easy to deploy on clusters of any size. Our previous BOF sessions have been focused on new developments. While we are still actively working on new features, this session will highlight the large and vibrant PVFS user community and a variety of their applications. Several notable users will share with attendees their experiences with PVFS. As always, PVFS developers will be present for an open forum discussion. Users, researchers, or the merely curious are all encouraged to attend.
{"title":"PVFS: a parallel file system","authors":"R. Ross, R. Latham","doi":"10.1145/1188455.1188490","DOIUrl":"https://doi.org/10.1145/1188455.1188490","url":null,"abstract":"High-performance computers require a highly capable file system. PVFS is an open source parallel file system and joint collaboration led by Argonne National Laboratory, Clemson University, and Ohio Supercomputing Center. PVFS has been delivering features and high-performance on today's top high-end computers, while remaining easy to deploy on clusters of any size. Our previous BOF sessions have been focused on new developments. While we are still actively working on new features, this session will highlight the large and vibrant PVFS user community and a variety of their applications. Several notable users will share with attendees their experiences with PVFS. As always, PVFS developers will be present for an open forum discussion. Users, researchers, or the merely curious are all encouraged to attend.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129431422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intel will briefly introduce is new HPC products and upgrades, and future HPC plans and roadmaps and challenges while inviting director of the CERN EGEE Project to demonstrate successful relationship between Intel and this leading scientific organization.
{"title":"Addressing high performance and grid challenges: Intel and CERN","authors":"S. Wheat, Bob Jones","doi":"10.1145/1188455.1188716","DOIUrl":"https://doi.org/10.1145/1188455.1188716","url":null,"abstract":"Intel will briefly introduce is new HPC products and upgrades, and future HPC plans and roadmaps and challenges while inviting director of the CERN EGEE Project to demonstrate successful relationship between Intel and this leading scientific organization.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127460958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper will discuss the current state of multi-gigabit wireless communications for very high bandwidth, short haul connectivity for education, research, and government deployments. It will address spectrum availability and suitability for multi-gigabit services, including the 1 to 10 Gbps GigaBeam has committed to and the 100 Gbps possibility the company is now exploring. The talk will include the technology evolution that has enabled these wireless data rates allowing fiber-like throughput particularly where it serves the difficulties presented by "last mile" fiber connectivity. There will be a focus on current and soon to be implemented applications and a look at models of how the university, military, government and related IT enterprises are using this technology today. Special attention will be paid to NAS, SAN, remote computing, grid computing and other similar applications.
{"title":"WiFiber: new spectrum links for wireless gigabit transmission","authors":"J. Wells","doi":"10.1145/1188455.1188752","DOIUrl":"https://doi.org/10.1145/1188455.1188752","url":null,"abstract":"This paper will discuss the current state of multi-gigabit wireless communications for very high bandwidth, short haul connectivity for education, research, and government deployments. It will address spectrum availability and suitability for multi-gigabit services, including the 1 to 10 Gbps GigaBeam has committed to and the 100 Gbps possibility the company is now exploring. The talk will include the technology evolution that has enabled these wireless data rates allowing fiber-like throughput particularly where it serves the difficulties presented by \"last mile\" fiber connectivity. There will be a focus on current and soon to be implemented applications and a look at models of how the university, military, government and related IT enterprises are using this technology today. Special attention will be paid to NAS, SAN, remote computing, grid computing and other similar applications.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127371350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Experts in advanced system technologies will predict the design of the best HPC Storage Systems in 2020. They will defend why they think the technology they select will be the winning technology 15 years from now. The panelists will pick one set of technology - not a list of possibilities - to define the system. They will define the performance and aspects of the technologies and explain why their system is the most likely to succeed.Besides questions and comments at the sessions, attendees will vote for the proposed systems of 2020 they think are most likely to succeed. The presentations, votes and attendee comments will all be sealed in a time capsule that will be opened in 2020, which will be used in 2020 to compare the predications to reality. The time capsule will also include an appropriate prize for the presenter who made the best prediction. The winner needs to be present to collect their prize.
{"title":"HPC storage systems of 2020","authors":"Garth A. Gibson, M. Kryder, R. Freitas","doi":"10.1145/1188455.1188765","DOIUrl":"https://doi.org/10.1145/1188455.1188765","url":null,"abstract":"Experts in advanced system technologies will predict the design of the best HPC Storage Systems in 2020. They will defend why they think the technology they select will be the winning technology 15 years from now. The panelists will pick one set of technology - not a list of possibilities - to define the system. They will define the performance and aspects of the technologies and explain why their system is the most likely to succeed.Besides questions and comments at the sessions, attendees will vote for the proposed systems of 2020 they think are most likely to succeed. The presentations, votes and attendee comments will all be sealed in a time capsule that will be opened in 2020, which will be used in 2020 to compare the predications to reality. The time capsule will also include an appropriate prize for the presenter who made the best prediction. The winner needs to be present to collect their prize.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128888719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. C. Price, V. Bazterra, Wayne B. Bradford, J. Facelli
Currently users of high performance computers are overwhelmed with non-scalable tasks such as job submission and monitoring. Many users are limited by the number of jobs they can submit to one High Performance Computing (HPC) resource at a time, which results in very long queue times. Digital Sherpa is a grid application for executing jobs on many separate HPC resources at a time, which can reduce total queue time. It automates non-scalable tasks such as job submission and monitoring, and includes recovery features such as resubmission of failed jobs. Digital Sherpa has been implemented for MGAC, a parallel distributed application for the prediction of atomic clusters and crystal structures using Genetic Algorithms. Success has been found using Digital Sherpa in a prototype of an HPC oriented combustion simulation application as well as on the TeraGrid. The high level goal is to allow Digital Sherpa to interoperate with any HPC application.
{"title":"Digital Sherpa","authors":"R. C. Price, V. Bazterra, Wayne B. Bradford, J. Facelli","doi":"10.1145/1188455.1188617","DOIUrl":"https://doi.org/10.1145/1188455.1188617","url":null,"abstract":"Currently users of high performance computers are overwhelmed with non-scalable tasks such as job submission and monitoring. Many users are limited by the number of jobs they can submit to one High Performance Computing (HPC) resource at a time, which results in very long queue times. Digital Sherpa is a grid application for executing jobs on many separate HPC resources at a time, which can reduce total queue time. It automates non-scalable tasks such as job submission and monitoring, and includes recovery features such as resubmission of failed jobs. Digital Sherpa has been implemented for MGAC, a parallel distributed application for the prediction of atomic clusters and crystal structures using Genetic Algorithms. Success has been found using Digital Sherpa in a prototype of an HPC oriented combustion simulation application as well as on the TeraGrid. The high level goal is to allow Digital Sherpa to interoperate with any HPC application.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130727503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pharmaceutical research. Weather prediction. Oil exploration. The data analysis demanded for these jobs can be awesome. As more applications are running on Linux clusters, there are a number of applications where job completion is critical. Today's jobs are getting longer and it's not unusual to come across jobs with run times that last for multiple days. As the number of nodes in a cluster expands, the likelihood that a job will be able to complete without a hardware related failure becomes statistically relevant. For an application like this, the "cost" of having the job fail and having to restart the job is enormous. You need efficient ways to help drive jobs to completion or be able to recover from failures.This session will review the importance of high availability functionality in high performance computing MPIs when running communication-intensive applications. Different approaches for cooperative and distributed check-point-restart will also be explored.
{"title":"Exploring the importance of high availability MPIs","authors":"Hakon O. Bugge","doi":"10.1145/1188455.1188496","DOIUrl":"https://doi.org/10.1145/1188455.1188496","url":null,"abstract":"Pharmaceutical research. Weather prediction. Oil exploration. The data analysis demanded for these jobs can be awesome. As more applications are running on Linux clusters, there are a number of applications where job completion is critical. Today's jobs are getting longer and it's not unusual to come across jobs with run times that last for multiple days. As the number of nodes in a cluster expands, the likelihood that a job will be able to complete without a hardware related failure becomes statistically relevant. For an application like this, the \"cost\" of having the job fail and having to restart the job is enormous. You need efficient ways to help drive jobs to completion or be able to recover from failures.This session will review the importance of high availability functionality in high performance computing MPIs when running communication-intensive applications. Different approaches for cooperative and distributed check-point-restart will also be explored.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132260326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Einstein's equations of general relativity govern such exotic phenomena as black holes, neutron stars, and gravitational waves. Known for nearly a century, they are among the most complex in physics, and require very large scale computational power - which we are just on the verge of achieving - and advanced algorithms, to solve in the general case. I will motivate and describe the structure of these equations, and the worldwide effort to develop advanced and collaborative computational tools utilizing supercomputers, data archives, optical networks, grids, and advanced software to solve them in their full generality. I will focus on applications of these tools to extract new physics of relativistic astrophysical systems. In particular, I will summarize recent progress in the study of black hole collisions, considered to be promising sources of observable gravitational waves that may soon be seen for the first time by the worldwide network of gravitational wave detectors (LIGO, VIRGO, GEO, and others).
{"title":"Sidney Fernbach award lecture: solving Einstein's equations through computational science","authors":"E. Seidel","doi":"10.1145/1188455.1188659","DOIUrl":"https://doi.org/10.1145/1188455.1188659","url":null,"abstract":"Einstein's equations of general relativity govern such exotic phenomena as black holes, neutron stars, and gravitational waves. Known for nearly a century, they are among the most complex in physics, and require very large scale computational power - which we are just on the verge of achieving - and advanced algorithms, to solve in the general case. I will motivate and describe the structure of these equations, and the worldwide effort to develop advanced and collaborative computational tools utilizing supercomputers, data archives, optical networks, grids, and advanced software to solve them in their full generality. I will focus on applications of these tools to extract new physics of relativistic astrophysical systems. In particular, I will summarize recent progress in the study of black hole collisions, considered to be promising sources of observable gravitational waves that may soon be seen for the first time by the worldwide network of gravitational wave detectors (LIGO, VIRGO, GEO, and others).","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130906942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David M. Kunzman, G. Zheng, Eric J. Bohm, James C. Phillips, L. Kalé
While the Cell processor, jointly developed by IBM, Sony, and Toshiba, has great computational power, it also presents many challenges including portability and ease of programming. We have been adapting the Charm++ Runtime System to utilize the Cell. We believe that the Charm++ model fits well with the Cell for many reasons: encapsulation of data, effective prefetching, the ability to peak ahead in message queues, virtualization, etc. To these ends, we have developed the Offload API (an independent code) which allows Charm++ applications to easily take advantage of the Cell. Our goal is to allow Charm++ programs to run on Cell-based and non-Cell-based platforms without modification to application code. Example Charm++ programs using the Offload API already exist. We have also begun modifying NAMD, a popular molecular dynamics code, to use the Cell. In this poster, we plan to present current progress and future plans for this work.
{"title":"Charm++ simplifies coding for the cell processor","authors":"David M. Kunzman, G. Zheng, Eric J. Bohm, James C. Phillips, L. Kalé","doi":"10.1145/1188455.1188596","DOIUrl":"https://doi.org/10.1145/1188455.1188596","url":null,"abstract":"While the Cell processor, jointly developed by IBM, Sony, and Toshiba, has great computational power, it also presents many challenges including portability and ease of programming. We have been adapting the Charm++ Runtime System to utilize the Cell. We believe that the Charm++ model fits well with the Cell for many reasons: encapsulation of data, effective prefetching, the ability to peak ahead in message queues, virtualization, etc. To these ends, we have developed the Offload API (an independent code) which allows Charm++ applications to easily take advantage of the Cell. Our goal is to allow Charm++ programs to run on Cell-based and non-Cell-based platforms without modification to application code. Example Charm++ programs using the Offload API already exist. We have also begun modifying NAMD, a popular molecular dynamics code, to use the Cell. In this poster, we plan to present current progress and future plans for this work.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130937702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This years BOF presentation will concentrate on the new features and functionality released during 2006 (PBS Professional Versions 7.1 and 8.0) with a glimpse into our development roadmap. The BOF provides PBS users with an oportunity to ask Altair personnel questions about the new features and also provide direction to Altair relative to our future roadmap.PBS Professional is the preferred workload management solution for HPC data centers with more than 1,400 sites deployed worldwide. PBS Professional is utilized in many vertical industries: Defense, Intelligence, Weather prediction, Automotive, Aerospace, life Sciences, Digital Content Creation, Oil/Gas exploration and Academic research.
{"title":"Altair's PBS professional update","authors":"M. Humphrey","doi":"10.1145/1188455.1188484","DOIUrl":"https://doi.org/10.1145/1188455.1188484","url":null,"abstract":"This years BOF presentation will concentrate on the new features and functionality released during 2006 (PBS Professional Versions 7.1 and 8.0) with a glimpse into our development roadmap. The BOF provides PBS users with an oportunity to ask Altair personnel questions about the new features and also provide direction to Altair relative to our future roadmap.PBS Professional is the preferred workload management solution for HPC data centers with more than 1,400 sites deployed worldwide. PBS Professional is utilized in many vertical industries: Defense, Intelligence, Weather prediction, Automotive, Aerospace, life Sciences, Digital Content Creation, Oil/Gas exploration and Academic research.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Linux clusters are receiving widespread attention in performance-driven environments like life sciences, manufacturing, oil and gas and financial services. With its growing popularity, more organizations are looking to learn how they can out-perform their competitors by implementing their own cluster solution. As such, the focus within the high performance computing market has shifted from whether an organization should implement a cluster management solution to how they should begin the process. If planned for and carried out effectively, clusters can help an organization increase their ROI, improve system performance and minimize business risk. Without proper strategy, an organization's cluster implementation process can result in slower time to resolution and increased costs - the very opposite of what clusters serve to achieve. This session will educate attendees on how to efficiently scale out Linux clusters, identify common implementation pitfalls and discover what steps their organization should take when executing Linux clusters.
{"title":"Best practices in cluster management","authors":"Rick Friedman","doi":"10.1145/1188455.1188485","DOIUrl":"https://doi.org/10.1145/1188455.1188485","url":null,"abstract":"Linux clusters are receiving widespread attention in performance-driven environments like life sciences, manufacturing, oil and gas and financial services. With its growing popularity, more organizations are looking to learn how they can out-perform their competitors by implementing their own cluster solution. As such, the focus within the high performance computing market has shifted from whether an organization should implement a cluster management solution to how they should begin the process. If planned for and carried out effectively, clusters can help an organization increase their ROI, improve system performance and minimize business risk. Without proper strategy, an organization's cluster implementation process can result in slower time to resolution and increased costs - the very opposite of what clusters serve to achieve. This session will educate attendees on how to efficiently scale out Linux clusters, identify common implementation pitfalls and discover what steps their organization should take when executing Linux clusters.","PeriodicalId":115940,"journal":{"name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127914540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：