http://baijia.info/ Tue, 07 Feb 2012 00:26:17 +0000 MyBB http://baijia.info/showthread.php?tid=1089 Thu, 02 Feb 2012 12:56:31 +0800 http://baijia.info/showthread.php?tid=1089
http://mapreduce.stanford.edu/]]>
http://mapreduce.stanford.edu/]]> http://baijia.info/showthread.php?tid=1086 Thu, 02 Feb 2012 01:06:25 +0800 http://baijia.info/showthread.php?tid=1086
http://issues.apache.org/jira/browse/MAPREDUCE-1270

http://apps.hi.baidu.com/share/detail/33790704]]>
http://issues.apache.org/jira/browse/MAPREDUCE-1270

http://apps.hi.baidu.com/share/detail/33790704]]> http://baijia.info/showthread.php?tid=1082 Wed, 18 Jan 2012 14:04:40 +0800 http://baijia.info/showthread.php?tid=1082
I have small knowledge about CDMA network.CDMA work on the same frequency for all user but some deffrent code added for making deffrence between the...

Any one have some browed idea about this..??
Plz tell me.....thanx...]]>
I have small knowledge about CDMA network.CDMA work on the same frequency for all user but some deffrent code added for making deffrence between the...

Any one have some browed idea about this..??
Plz tell me.....thanx...]]> http://baijia.info/showthread.php?tid=1071 Sat, 14 Jan 2012 14:50:12 +0800 http://baijia.info/showthread.php?tid=1071
@phdthesis{kim04codesigned,
author = {Kim, Ho-Seop},
title = {A co-designed virtual machine for instruction-level distributed processing},
year = {2004},
isbn = {0-496-15866-X},
note = {AAI3155115},
publisher = {University of Wisconsin at Madison},
address = {Madison, WI, USA},
}]]>
@phdthesis{kim04codesigned,
author = {Kim, Ho-Seop},
title = {A co-designed virtual machine for instruction-level distributed processing},
year = {2004},
isbn = {0-496-15866-X},
note = {AAI3155115},
publisher = {University of Wisconsin at Madison},
address = {Madison, WI, USA},
}]]> http://baijia.info/showthread.php?tid=1070 Sat, 14 Jan 2012 14:47:53 +0800 http://baijia.info/showthread.php?tid=1070 http://baijia.info/showthread.php?tid=1065 Tue, 10 Jan 2012 17:43:20 +0800 http://baijia.info/showthread.php?tid=1065
PDF from SpringerLink: http://www.springerlink.com/content/rqtq...http://www.springerlink.com/content/rqtq28uakc9l0ler/fu

@incollection {nurnberg04grand,
author = {Nürnberg, Peter and Wiil, Uffe and Hicks, David},
title = {A Grand Unified Theory for Structural Computing},
booktitle = {Metainformatics},
series = {Lecture Notes in Computer Science},
pages = {1-16},
volume = {3002},
year = {2004}
}]]>
PDF from SpringerLink: http://www.springerlink.com/content/rqtq...http://www.springerlink.com/content/rqtq28uakc9l0ler/fu

@incollection {nurnberg04grand,
author = {Nürnberg, Peter and Wiil, Uffe and Hicks, David},
title = {A Grand Unified Theory for Structural Computing},
booktitle = {Metainformatics},
series = {Lecture Notes in Computer Science},
pages = {1-16},
volume = {3002},
year = {2004}
}]]> http://baijia.info/showthread.php?tid=1063 Sun, 08 Jan 2012 20:07:21 +0800 http://baijia.info/showthread.php?tid=1063
IEEE entry: http://dx.doi.org/10.1109/ICECENG.2011.6056763]]>
IEEE entry: http://dx.doi.org/10.1109/ICECENG.2011.6056763]]> http://baijia.info/showthread.php?tid=1057 Wed, 04 Jan 2012 15:16:28 +0800 http://baijia.info/showthread.php?tid=1057
PDF from SIGCOMM: http://conferences.sigcomm.org/sigcomm/2...http://conferences.sigcomm.org/sigcomm/2011/papers/sigcom]]>
PDF from SIGCOMM: http://conferences.sigcomm.org/sigcomm/2...http://conferences.sigcomm.org/sigcomm/2011/papers/sigcom]]> http://baijia.info/showthread.php?tid=1056 Wed, 04 Jan 2012 15:10:05 +0800 http://baijia.info/showthread.php?tid=1056 http://baijia.info/showthread.php?tid=1053 Wed, 28 Dec 2011 21:34:00 +0800 http://baijia.info/showthread.php?tid=1053
http://doi.acm.org/10.1145/209936.209952

@inproceedings{tseng1995compiler,
title={Compiler optimizations for eliminating barrier synchronization},
author={Tseng, C.W.},
booktitle={ACM SIGPLAN Notices},
volume={30},
number={8},
pages={144--155},
year={1995},
organization={ACM}
}]]>
http://doi.acm.org/10.1145/209936.209952

@inproceedings{tseng1995compiler,
title={Compiler optimizations for eliminating barrier synchronization},
author={Tseng, C.W.},
booktitle={ACM SIGPLAN Notices},
volume={30},
number={8},
pages={144--155},
year={1995},
organization={ACM}
}]]> http://baijia.info/showthread.php?tid=1052 Wed, 28 Dec 2011 21:30:55 +0800 http://baijia.info/showthread.php?tid=1052
From ACM: http://doi.acm.org/10.1145/325096.325150


@inproceedings{Chen1990impact,
author = {Chen, Ding-Kai and Su, Hong-Men and Yew, Pen-Chung},
title = {The impact of synchronization and granularity on parallel systems},
booktitle = {Proceedings of the 17th annual international symposium on Computer Architecture},
series = {ISCA '90},
year = {1990},
pages = {239--248},
numpages = {10},
}]]>
From ACM: http://doi.acm.org/10.1145/325096.325150


@inproceedings{Chen1990impact,
author = {Chen, Ding-Kai and Su, Hong-Men and Yew, Pen-Chung},
title = {The impact of synchronization and granularity on parallel systems},
booktitle = {Proceedings of the 17th annual international symposium on Computer Architecture},
series = {ISCA '90},
year = {1990},
pages = {239--248},
numpages = {10},
}]]> http://baijia.info/showthread.php?tid=1049 Tue, 27 Dec 2011 10:38:45 +0800 http://baijia.info/showthread.php?tid=1049
PDF from ACM: http://dl.acm.org/ft_gateway.cfm?id=2237...http://dl.acm.org/ft_gateway.cfm?id=223785&type=pdf&CFID=59538495&CFTOKE

PDF from MSR: http://research.microsoft.com/pubs/69541/tr-95-51.pdf

@inproceedings{Berenson95critiqu,
author = {Berenson, Hal and Bernstein, Phil and Gray, Jim and Melton, Jim and O'Neil, Elizabeth and O'Neil, Patrick},
title = {A critique of ANSI SQL isolation levels},
booktitle = {Proceedings of the 1995 ACM SIGMOD international conference on Management of data},
series = {SIGMOD '95},
year = {1995},
pages = {1--10},
numpages = {10},
}]]>
PDF from ACM: http://dl.acm.org/ft_gateway.cfm?id=2237...http://dl.acm.org/ft_gateway.cfm?id=223785&type=pdf&CFID=59538495&CFTOKE

PDF from MSR: http://research.microsoft.com/pubs/69541/tr-95-51.pdf

@inproceedings{Berenson95critiqu,
author = {Berenson, Hal and Bernstein, Phil and Gray, Jim and Melton, Jim and O'Neil, Elizabeth and O'Neil, Patrick},
title = {A critique of ANSI SQL isolation levels},
booktitle = {Proceedings of the 1995 ACM SIGMOD international conference on Management of data},
series = {SIGMOD '95},
year = {1995},
pages = {1--10},
numpages = {10},
}]]> http://baijia.info/showthread.php?tid=1048 Tue, 27 Dec 2011 10:30:44 +0800 http://baijia.info/showthread.php?tid=1048
The PDF of this Paper is included in the workshop's all paper package: http://www.cs.purdue.edu/homes/jv/events...http://www.cs.purdue.edu/homes/jv/events/TRANSACT/trans

@article{riegel2006snapshot,
title={Snapshot isolation for software transactional memory},
author={Riegel, T. and Fetzer, C. and Felber, P.},
journal={TRANSACT06},
volume={298},
year={2006}
}]]>
The PDF of this Paper is included in the workshop's all paper package: http://www.cs.purdue.edu/homes/jv/events...http://www.cs.purdue.edu/homes/jv/events/TRANSACT/trans

@article{riegel2006snapshot,
title={Snapshot isolation for software transactional memory},
author={Riegel, T. and Fetzer, C. and Felber, P.},
journal={TRANSACT06},
volume={298},
year={2006}
}]]> http://baijia.info/showthread.php?tid=1047 Thu, 22 Dec 2011 13:53:49 +0800 http://baijia.info/showthread.php?tid=1047
PDF available at nih.gov: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2813482/]]>
PDF available at nih.gov: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2813482/]]> http://baijia.info/showthread.php?tid=1045 Tue, 20 Dec 2011 22:04:14 +0800 http://baijia.info/showthread.php?tid=1045 High-Performance Parallel and Distributed Computing
(HPDC'12)

Delft University of Technology, Delft, the Netherlands

June 18-22, 2012

http://www.hpdc.org/2012


The ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC)
is the premier annual conference on the design, the implementation, the evaluation, and
the use of parallel and distributed systems for high-end computing. HPDC'12 will take place
in Delft, the Netherlands, a historical, picturesque city that is less than one hour away
from Amsterdam-Schiphol airport. The conference will be held on June 20-22 (Wednesday to
Friday), with affiliated workshops taking place on June 18-19 (Monday and Tuesday).


**** SUBMISSION DEADLINES ****
Abstracts: 16 January 2012
Papers: 23 January 2012 (No extensions!)]]> High-Performance Parallel and Distributed Computing
(HPDC'12)

Delft University of Technology, Delft, the Netherlands

June 18-22, 2012

http://www.hpdc.org/2012


The ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC)
is the premier annual conference on the design, the implementation, the evaluation, and
the use of parallel and distributed systems for high-end computing. HPDC'12 will take place
in Delft, the Netherlands, a historical, picturesque city that is less than one hour away
from Amsterdam-Schiphol airport. The conference will be held on June 20-22 (Wednesday to
Friday), with affiliated workshops taking place on June 18-19 (Monday and Tuesday).


**** SUBMISSION DEADLINES ****
Abstracts: 16 January 2012
Papers: 23 January 2012 (No extensions!)]]> http://baijia.info/showthread.php?tid=1042 Fri, 09 Dec 2011 17:02:18 +0800 http://baijia.info/showthread.php?tid=1042
Abstract:
This paper presents mechanisms and optimizations to reduce the overhead of network interface virtualization when using the driver domain I/O virtualization model. The driver domain model provides benefits such as support for legacy device drivers and fault isolation. However, the processing overheads incurred in the driver domain to achieve these benefits limit overall I/O performance. This paper demonstrates the effectiveness of two approaches to reduce driver domain overheads. First, Xen is modified to support multi-queue network interfaces to eliminate the software overheads of packet demultiplexing and copying. Second, a grant reuse mechanism is developed to reduce memory protection overheads. These mechanisms shift the bottleneck from the driver domain to the guest domains, improving scalability and enabling significantly higher data rates. This paper also presents and evaluates a series of optimizations that substantially reduce the I/O virtualization overheads in the guest domain. In combination, these mechanisms and optimizations increase the maximum throughput achieved by guest domains from 2.9Gb/s to full 10 Gigabit Ethernet link rates.

Paper can be accessed at http://dl.acm.org/ft_gateway.cfm?id=1508...http://dl.acm.org/ft_gateway.cfm?id=1508303&ftid=602957&dwn=1&CFID=72468371&CFTOKE]]>
Abstract:
This paper presents mechanisms and optimizations to reduce the overhead of network interface virtualization when using the driver domain I/O virtualization model. The driver domain model provides benefits such as support for legacy device drivers and fault isolation. However, the processing overheads incurred in the driver domain to achieve these benefits limit overall I/O performance. This paper demonstrates the effectiveness of two approaches to reduce driver domain overheads. First, Xen is modified to support multi-queue network interfaces to eliminate the software overheads of packet demultiplexing and copying. Second, a grant reuse mechanism is developed to reduce memory protection overheads. These mechanisms shift the bottleneck from the driver domain to the guest domains, improving scalability and enabling significantly higher data rates. This paper also presents and evaluates a series of optimizations that substantially reduce the I/O virtualization overheads in the guest domain. In combination, these mechanisms and optimizations increase the maximum throughput achieved by guest domains from 2.9Gb/s to full 10 Gigabit Ethernet link rates.

Paper can be accessed at http://dl.acm.org/ft_gateway.cfm?id=1508...http://dl.acm.org/ft_gateway.cfm?id=1508303&ftid=602957&dwn=1&CFID=72468371&CFTOKE]]> http://baijia.info/showthread.php?tid=1041 Fri, 09 Dec 2011 16:55:38 +0800 http://baijia.info/showthread.php?tid=1041
Abstract:
The soft real-time nature of large scale web applications in today’s datacenters, combined with their distributed workflow, leads to deadlines being associated with the datacenter application traffic. A network flow is useful, and contributes to application throughput and operator revenue if, and only if, it completes within its deadline. Today’s transport protocols (TCP included), given their Internet origins, are agnostic to such flow deadlines. Instead, they strive to share network resources fairly. We show that this can hurt application performance.

Motivated by these observations, and other (previously known) deficiencies of TCP in the datacenter environment, this paper presents the design and implementation of D3, a deadline-aware control protocol that is customized for the datacenter environment. D3 uses explicit rate control to apportion bandwidth according to flow deadlines. Evaluation from a 19-node two-tier datacenter testbed shows that D3, even without any deadline information, easily outperforms TCP in terms of short flow latency and burst tolerance. Further, by utilizing deadline information, D3 effectively doubles the peak load that the datacenter network can support.

Paper can be accessed at http://research.microsoft.com/pubs/14946...http://research.microsoft.com/pubs/149468/sigcom]]>
Abstract:
The soft real-time nature of large scale web applications in today’s datacenters, combined with their distributed workflow, leads to deadlines being associated with the datacenter application traffic. A network flow is useful, and contributes to application throughput and operator revenue if, and only if, it completes within its deadline. Today’s transport protocols (TCP included), given their Internet origins, are agnostic to such flow deadlines. Instead, they strive to share network resources fairly. We show that this can hurt application performance.

Motivated by these observations, and other (previously known) deficiencies of TCP in the datacenter environment, this paper presents the design and implementation of D3, a deadline-aware control protocol that is customized for the datacenter environment. D3 uses explicit rate control to apportion bandwidth according to flow deadlines. Evaluation from a 19-node two-tier datacenter testbed shows that D3, even without any deadline information, easily outperforms TCP in terms of short flow latency and burst tolerance. Further, by utilizing deadline information, D3 effectively doubles the peak load that the datacenter network can support.

Paper can be accessed at http://research.microsoft.com/pubs/14946...http://research.microsoft.com/pubs/149468/sigcom]]> http://baijia.info/showthread.php?tid=1040 Fri, 09 Dec 2011 16:48:12 +0800 http://baijia.info/showthread.php?tid=1040
Abstract:
Virtualization is a key technology that powers cloud computing platforms such as Amazon EC2. Virtual machine (VM) consolidation, where multiple VMs share a physical host, has seen rapid adoption in practice with increasingly large number of VMs per machine and per CPU core. Our investigations, however, suggest that the increasing degree of VM consolidation has serious negative effects on the VMs' TCP transport performance. As multiple VMs share a given CPU, the scheduling latencies, which can be in the order of tens of milliseconds, substantially increase the typically sub-millisecond round-trip times (RTTs) for TCP connections in a datacenter, causing significant degradation in throughput. In this paper, we propose a light-weight solution called vFlood that (a) allows a TCP sender VM to opportunistically flood the driver domain in the same host, and (b) offloads the VM's TCP congestion control function to the driver domain in order to mask the effects of VM consolidation. Our evaluation of a vFlood prototype on Xen suggests that vFlood substantially improves TCP transmit throughput with minimal per-packet CPU overhead. Further, our application-level evaluation using Apache Olio, a web 2.0 cloud application, indicates a 33% improvement in the number of operations per second.

Paper can be accessed at http://dl.acm.org/ft_gateway.cfm?id=2038...http://dl.acm.org/ft_gateway.cfm?id=2038940&ftid=1037480&dwn=1&CFID=72468371&CFTOKE]]>
Abstract:
Virtualization is a key technology that powers cloud computing platforms such as Amazon EC2. Virtual machine (VM) consolidation, where multiple VMs share a physical host, has seen rapid adoption in practice with increasingly large number of VMs per machine and per CPU core. Our investigations, however, suggest that the increasing degree of VM consolidation has serious negative effects on the VMs' TCP transport performance. As multiple VMs share a given CPU, the scheduling latencies, which can be in the order of tens of milliseconds, substantially increase the typically sub-millisecond round-trip times (RTTs) for TCP connections in a datacenter, causing significant degradation in throughput. In this paper, we propose a light-weight solution called vFlood that (a) allows a TCP sender VM to opportunistically flood the driver domain in the same host, and (b) offloads the VM's TCP congestion control function to the driver domain in order to mask the effects of VM consolidation. Our evaluation of a vFlood prototype on Xen suggests that vFlood substantially improves TCP transmit throughput with minimal per-packet CPU overhead. Further, our application-level evaluation using Apache Olio, a web 2.0 cloud application, indicates a 33% improvement in the number of operations per second.

Paper can be accessed at http://dl.acm.org/ft_gateway.cfm?id=2038...http://dl.acm.org/ft_gateway.cfm?id=2038940&ftid=1037480&dwn=1&CFID=72468371&CFTOKE]]> http://baijia.info/showthread.php?tid=1039 Fri, 09 Dec 2011 16:33:14 +0800 http://baijia.info/showthread.php?tid=1039 Parallel Processing (ICPP-2012)
http://www.icpp2012.org
Pittsburgh, PA, USA
September 10-13, 2012


Scope
The International Conference on Parallel Processing (ICPP) provides a forum for engineers and scientists in academia, industry and government to present their latest research findings in all aspects of parallel and distributed computing.

ICPP 2012 will be focused on 3 crosscutting themes: (1) Disruptive Technologies (Multicore/Manycore, Accelerators, Clouds), (2) Data-Intensive Competing and (3) Green Computing.The meeting will be organized around the following tracks:

= Architecture
= Networking and Communication
= Algorithm Design and Parallelism
= Performance Modeling and Evaluation
= Programming Models, Languages
= Compilers and Run-Time Systems & Environments
= Applications

Conference Timeline
Paper Submission DeadlineMarch 02, 2012
Author NotificationJune 01, 2012
Final Manuscript DueJuly 06, 2012]]> Parallel Processing (ICPP-2012)
http://www.icpp2012.org
Pittsburgh, PA, USA
September 10-13, 2012


Scope
The International Conference on Parallel Processing (ICPP) provides a forum for engineers and scientists in academia, industry and government to present their latest research findings in all aspects of parallel and distributed computing.

ICPP 2012 will be focused on 3 crosscutting themes: (1) Disruptive Technologies (Multicore/Manycore, Accelerators, Clouds), (2) Data-Intensive Competing and (3) Green Computing.The meeting will be organized around the following tracks:

= Architecture
= Networking and Communication
= Algorithm Design and Parallelism
= Performance Modeling and Evaluation
= Programming Models, Languages
= Compilers and Run-Time Systems & Environments
= Applications

Conference Timeline
Paper Submission DeadlineMarch 02, 2012
Author NotificationJune 01, 2012
Final Manuscript DueJuly 06, 2012]]> http://baijia.info/showthread.php?tid=1038 Fri, 09 Dec 2011 13:09:54 +0800 http://baijia.info/showthread.php?tid=1038
PDF from SOSP 2011 conference siet: http://sigops.org/sosp/sosp11/current/20...http://sigops.org/sosp/sosp11/current/2011-Cascais/printable/1

@inproceedings{adya2011thialfi,
title={Thialfi: a client notification service for internet-scale applications},
author={Adya, A. and Cooper, G. and Myers, D. and Piatek, M.},
booktitle={Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles},
pages={129--142},
year={2011},
organization={ACM}
}]]>
PDF from SOSP 2011 conference siet: http://sigops.org/sosp/sosp11/current/20...http://sigops.org/sosp/sosp11/current/2011-Cascais/printable/1

@inproceedings{adya2011thialfi,
title={Thialfi: a client notification service for internet-scale applications},
author={Adya, A. and Cooper, G. and Myers, D. and Piatek, M.},
booktitle={Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles},
pages={129--142},
year={2011},
organization={ACM}
}]]>