Content about cloud computing

Link of the Week - Kudos for cloud programming

No, coding while in a plane does not count.
Cloud and moon image courtesy of Leonardini. Code added by iSGTW.

According to Technology Review, cloud programming is one of the top ten emerging technologies of 2010.
Do we mean cloud computing? Nope! Joseph Hellerstein, a researcher at the University of California-Berkeley, is working on a creating a cloud programming language called Bloom, which his team hopes to release in late 2010. They are also preparing a number of domain-specific demonstrations.
Erica Naone of Technology Review writes:
His big idea is to modify database programming languages so that they can be used to quickly build any sort of application in the cloud--social networks, communication tools, games, and more. Such languages have been refined over the years to hide the complexities of shuffling information in and out of large databases. If one could be made cloud-friendly, programmers could just think about t

Back to Basics – Data management

by TRACEY WILSON
Tracey Wilson is a program manager for Avetec’s HPC Research Division, DICE, the Data Intensive Computing Environment. DICE is a non-profit program that serves HPC and IT data centers in commerce, government and academia by providing independent third-party evaluations of data management practices on its geographically distributed test bed.

From smartphones to weather forecasts, data drives our world.
In the simplest terms, data is information, which can be found in many forms. Back when computer scientists used punch cards to store data, keeping them in order was a way of controlling or managing data.
We used to talk about how incredibly large a gigabyte of data was. Now terabytes and petabytes are the norm in scientific circles, and we will soon be talking about exabytes just as casually. And as the amount of data we generate grows, so does our need for data management.
Data management — the effective control

Opinion: Africa Grid?

Official ribbon-cutting for “Blue Gene for Africa” last year. This supercomputer is the fastest scientific computer on the African continent, capable of 11.5 teraflops (11.5 trillion floating point operations per second). Image courtesy Center for High-Performance Computing

At the EGEE User Forum in Uppsala, the author, Bruce Becker of the Meraka Institute and coordinator of the South African National Grid, called for making an AfricaGrid a reality. Here he outlines the reasons why now is the opportune time for work on this to be starting in earnest.
For some years now, many have been hinting at an “AfricaGrid.”
In the Mediterranean basin, we have seen many African countries participating directly in EUMedGrid (and more recently EUMedSupport).
In the southern region of Africa, we have seen much activity over the last couple of years that allows to envisage at least a “Sub-Saharan Grid.”
This prospect is very appealing to the r

Statistics of the week - To lease or buy CPU-hours: that is the question

The cost per CPU-hour is based on a four-year project. More details on how these numbers were calculated is available via both the IEEE and USENIX papers.

Ever wonder if you should just outsource all your cyberinfrastructure needs to your friendly neighborhood cloud provider?
That’s exactly what Edward Walker is researching. So far, it looks like in most cases, the answer is “no.”
“The key take away in the article "The Real Cost of a CPU Hour" is that cluster utilization is a very important factor in determining if leasing from a cloud vendor, or purchasing your own cluster, is cheaper,” said Walker, who is the HPC software group leader at the Texas Advanced Computing Center.
“However, the USENIX ;login: article serves as a cautionary note: the performance that can be achieved in doing science on a cluster, optimized for doing high-performance computing, can be quit

Feature: Virtualization - Key for LHC physics volunteer computing

BOINC is versatile enough that even mobile phones can do volunteer computing. Image courtesy BOINC

In 2006, the team that built LHC@home was given a challenge by Wolfgang von Rueden, then IT Division Leader at CERN: look at the use of the volunteer computing project BOINC (Berkeley Open Infrastructure for Network Computing)  for simulating events of interest in the Large Hadron Collider. It presented a demanding problem.
The software environments used by the experiments such as ATLAS, ALICE, CMS and LHCb are very large.
Furthermore, all LHC physics software development is done under Scientific Linux, whereas most volunteer PCs run under Windows. Porting the large and rapidly changing software is not practical, so another approach was needed.
The solution?
Marrying volunteer computing with the CernVM virtual image management system under development. It would enable the practical use of thousands of volunteer P

Feature - Cloudbus: A tool for utility-oriented cloud computing

A few of the considerations for users of cloud computing. (Click to enlarge.) Image courtesy Rajkumar Buyya

In order for cloud computing to fully meet its expectations, it needs to overcome its present, somewhat chaotic, challenges. (See figure 3 of full-length paper.) A cloud marketplace — composed of different types of clouds such as computing, storage, and content delivery clouds — will need to be easy  to access and easy to use for both end-users and enterprises.
(We define ‘cloud computing’ here as both the applications delivered as services over the internet, and the hardware and system software in the data centers that provide these services. Both software applications and hardware infrastructures are moved from the private environment to third parties data centers and made accessible through the internet.)
To help do so, our CLOUDS Laboratory at the University of Melbourne, o

Image of the week - Seeing with lasers

Top: LiDAR point cloud data for the Old Faithful area of Yellowstone National Park. Data source is EarthScope LiDAR hosted by the OpenTopography Facility. Image shows approximately 8.3 million individual LiDAR returns. The historic Old Faithful Inn is the structure at left. The Old Faithful Geyser is in the middle of the image.
Bottom: LiDAR digital elevation model (DEM)-derived image of Fish Springs cinder cone and the Owens Valley fault in eastern California produced from OpenTopography-hosted EarthScope LiDAR data.
Credit: Christopher Crosby, SDSC. Source: San Diego Supercomputer Center, UC San Diego.

The data used to create these images was gathered using LiDAR (Light Detection and Ranging), a technology that utilizes lasers to record precise and extremely high resolution topographical information.
The San Diego Supercomputer Center′s OpenTopography portal provides free access to LiDAR data sets, including the EarthScope data

Announcement - Journal of Grid Computing: Special Issue on Clouds and Grids

The Journal of Grid Computing is now accepting paper submissions for a special issue on clouds and grids.
The issue will be dedicated to recent advances in cloud computing that could simplify and optimize the use and operation of existing distributed computing infrastructures in science and engineering. Authors are invited to submit original unpublished work describing current research and novel ideas in the area of cloud computing and its application to grid and cluster computing. Additional information about this special issue can be found at the journal website.
Topics of interest include, but are not limited to:

Experiences, performance and reliability running scientific applications in clouds
Grid, Cluster and data-intensive computing in clouds
Limitations of cloud services and technologies for capability and capacity computing
Impact of virtualization on the performance of memory, CPU and I/O intensive,

Case study: The GeoChronos web portal

Surface reflectance and ocean temperature, an example of Earth observation science. Image courtesy of Jacques Descloitres, MODIS Land Rapid Response Team, NASA/GSFC.

When GeoChronos launches, it will serve up a buffet of scientific and social networking ingredients that together empower Earth observation scientists to collaborate and make new discoveries.
The GeoChronos recipe didn't come out right the first time, however. The path the GeoChronos team has followed provides valuable insight into the process of creating a scientific web portal.
“The idea is that scientists can come to a portal where they process and share their data without having to worry about the overall technical details of how that’s being done,” said Cameron Kiddle, a research fellow for the Grid Research Centre at the University of Calgary in Alberta, Canada.
Social networking features and collaborative tools are a must for the project, and so the first GeoC

I see crime scenes

IC-CRIME’s laser scanner technology will allow investigators to accurately record room and object dimensions, as well as the placement of every piece of evidence in a crime scene.Image courtesy NCSU

Fighting crime with science isn’t as simple as popular TV shows like CSI would have you believe. But those shows get one thing right: science and technology have a tremendous potential for changing the way crime is investigated.
Today, investigators record crime scenes using sketches and photographs. Bullet trajectories are determined using lasers or even lengths of string. “They take a microsnapshot,” said Mitzi Montoya, a North Carolina State University researcher who specializes in knowledge and virtual team management. “You don’t really know what’s relevant in a crime scene, and you can’t go back and create it, because once it’s cleaned it’s gone forever.”
That could change if the IC-CRIME (Interdiscip

Feature - Big science facilities meet the cloud

Dylan Maxwell explains the Science Studio system to a bystander at Summit 2009 in Banff, Alberta. Photo by Miriam Boon.

Lab notebooks are so passé. In the brave new world of cloud computing, the entire experimental process will take place in your web browser.
And if a team of Canadian researchers at the University of Western Ontario and the Canadian Light Source in Saskatchewan has anything to say about it, researchers around the world will be using a web platform called Science Studio.
“One of the aims of Science Studio is to be able to access big science facilities such as the Canadian Light Source,” said Marina Fuller, a chemistry researcher with the project. “It’s a complete experiment management system.”
The test case for Science Studio is the VESPERS beamline at the Canadian Light Source synchrotron. When Science Studio is complete in 2011, researchers will be able to use the platform to apply

Feature - iPlant: A new paradigm for a scientific field

Image courtesy of Asif Akbar.

iPlant is going to solve the grand challenges of plant biology. It’s a big bite to chew, but the creators of iPlant think big.
“One of the really neat things about this project is that it was funded to exist by, for, and of the community,” said Dan Stanzione, co-director of the iPlant project. “The idea was to be collaborative from square one, and not to take the ‘if you build it’ approach.”
That’s why the developers behind iPlant didn’t propose specific tools or structures. Instead, they created a process whereby the plant biology community could come together and decide what the field’s grand challenges are.
Stanzione estimates that over 100 faculty members from forty different institutions worldwide participated in the grand challenge process. “Most everything was done remotely,” said Stanzione. The tools used included telecon