San Diego Supercomputer Center “Seeds” HPC Clouds

By Amit Chourasia, Jan Zverina, SDSC

June 18, 2014

All sectors of the high-performance computing community – academia, industry, and government – have long been in need of an infrastructure that allows researchers to easily share their findings with other scientists or organizations in an efficient and secure manner.

Sharing these results are of vital importance because they form the basis for validation and potential next steps in any research project, from cosmology to genome sequencing. Computational visualizations and simulations, for example, have become an indispensable resource across numerous science domains. But while quick and effective assessments of such data are necessary for efficient use of the computational resources involved, such an exercise can be challenging when a research team is large and/or geographically dispersed, or some members don’t have direct access to an HPC system.

Moreover, current methods for sharing and assessing results, can be labor-intensive and unsupported by useful tools and procedures. Typically, a research team must create their own scripts and ad hoc procedures just to move results from system to system or user to user. These efforts usually rely on email, ftp, or secure copy (scp) despite the ubiquity of more flexible web-based technologies, and do not fully take advantage of the interactive capabilities of today’s mobile devices.

In late 2012 the San Diego Supercomputer Center (SDSC) at the University of California, San Diego, was awarded a three-year, $810,000 grant from the National Science Foundation to develop a resource that lets researchers seamlessly share and stream scientific visualizations on a variety of platforms, including mobile devices. Called SeedMe for ‘Swiftly Encode, Explore, Disseminate My Experiments’, SDSC’s web-based architecture is designed to enable rapid sharing of content directly from applications running on HPC- or cloud-based resources.

This spring, a team of SDSC researchers developed a working implementation, which in addition to visualizations videos supports other content such as plots, files, and tickers – all of which are essential to scientific research. Easy-to-use programmatic and command line tools with documentation are available for end users to interact with SeedMe.org. A quick start guide, geared for HPC researchers, is also available.

“SeedMe now provides an essential yet missing component in current high-performance computing,” said Amit Chourasia, a senior visualization scientist at SDSC and principal investigator for the project. “We’re now inviting researchers from industry and academia and across numerous domains to take advantage of SeedMe’s easy-to-use functionality for sharing their results with peers or the public at large.”

“The current HPC infrastructure relies heavily on controlled access,” said Michael Norman, SDSC’s director and co-principal investigator for the project. “SeedMe provides secure input and public output complementing HPC resources without compromising their security model. We believe this project will have a transformative impact throughout numerous domains, as research has become increasingly collaborative, requiring better tools and resources that aid the sharing of information.”

seedme1

SeedMe User Interaction Sequence. Source, Amit Chourasia/SDSC

SeedMe is unique from other web-based interfaces in that it is completely focused on efficiently sharing scientific content. While SeedMe could be described in general terms as a DropBox for science, the computational research community requires several additional capabilities and integration tools.

“One such requirement is easy instrumentation of simulation codes, as well as support for instrumenting analysis routines from a variety of software tools,” said Chourasia. “That instrumentation may provide periodic tracking and monitoring by posting progress messages, job status, early data snippets, scripts, parameter files, and other reusable components. But no single web service or tool suite addresses the breadth of scientific computing challenges as effectively and easily as the SeedMe infrastructure.”

According to Chourasia, some of the most common complaints among researchers when needing to share results with colleagues include the fact that many simply cannot afford to spend time and valuable funding dollars to create their own system for sharing their results. “Many find that it is cumbersome or costly. They also don’t want to waste time searching email attachments, or constantly have to check files to monitor progress, or spend long hours encoding videos from a set of images to work on all devices.”

Toward that end, the objective of SeedMe is to foster rapid assessment, iteration, communication, and dissemination of research by making that research ubiquitously accessible on any device, including mobile ones, and on a near real-time basis. Results can be shared within private groups only or posted for public consumption, depending on user preferences.

“SeedMe aims to fill the automation and accessibility gap in computational research,” said Chourasia, noting that a core focus of the project is to promote accessibility of preliminary, ad hoc, and ephemeral content – all vital to efficient and successful research.

Visualization Speed-ups

Visualizations and simulations are an ever growing part of today’s scientific research. These state-of-the-art simulations are now creating visualization images at runtime using in-situ processing. Images or sequence of images can now be shared with others using SeedMe with simple asynchronous integration providing an easy monitoring and assessment mechanism for collaborators.

SeedMe also capitalizes on recent strides in video standardization across web-based communities, providing a significant speed-up in video encoding by using parallel-distributed processing, which is not possible on existing HPC platforms due to lack of state-of-the-art video compression tools on Linux-like operating systems.

seed3

Left: An image from a sequence of volume rendering of steam from volcano eruption simulation. A corresponding video created from the image sequence on left at desired frame rate provided by user. The videos are encoded at various resolutions (including native resolution) and are available for playback and download. Source Amit Chourasia / Darcy Ogden, UC San Diego

Right: An image from computation and visualization of Mandelbrot set. Here the computation and visualization are done in-situ and the images are uploaded to SeedMe asynchronously. Source: Brad Whitlock, Intelligent Light and Amit Chourasia, UC San Diego

“Our goal has been to convert a manual, serial, error-prone process into an automatic, easy-to-use streamlined, parallel and web accessible cyberinfrastructure, and at the same time create videos that are not only encoded at very high quality to mitigate compression artifacts for scientific content, but also make these easily downloadable for researchers” said Chourasia.

Early users are welcoming SeedMe. “It is so convenient to share research results with collaborators, compared with sending results through emails,” said Hao Xu, a post-doctoral researcher who has been running simulations about the evolution of galaxies on the Blue Waters supercomputer at National Center for Supercomputing Applications (NCSA).

“SeedMe provides convenient ways to organize results, which can be easily updated, making sure collaborators or new collaborators all see the most recent results,” said Xu, who has been working with SDSC Director Norman, an astrophysicist by training. “It also avoids the pain of finding figures and plots in emails, and is even proving to be a very useful resource during conference calls.”

Going forward, the SeedMe research team will explore the possibility of making the resource a platform for sharing reusable content. NCSA researcher Matthew Turk is currently investigating how best to share IPython Notebooks from yt software, which is used to analyze and visualize datasets from astrophysical simulations, nuclear engineering, and radio telescope data.

“By building in support to yt for uploading directly to SeedMe, we hope to enable faster, easier, and more seamless sharing of results for anyone using yt,” said Turk. “SeedMe also allows easy control over sharing permissions, while providing an easy-to-use interface for uploading images and data to a central location.”

Tutorials Planned

As an open, web-accessible and searchable research archive, SeedMe also is suitable for education and outreach programs. In addition to organizing tutorials, talks, and webinars to train new users and receive user feedback, the program will provide internships to high school and undergraduate students enabling them to learn about web technologies and the diverse range of research, while at the same time support monitoring of content on the project website.

Tutorials and workshops are already in the works, with presentations planned for XSEDE14 and SC14, as well as a webinar as part of SDSC’s Industry Partners program on July 24. Such sessions will show potential users how they can accomplish the following on personal computers and mobile devices directly from compute jobs.

  • Get fast feedback on compute jobs
  • Share that feedback rapidly with collaborators across the globe
  • Provide access to preliminary results to guide further job submission
  • Support discussion of feedback and results among collaborators.

Author Information

Amit Chourasia, 858 822-3656 or amit@sdsc.edu

Jan Zverina, SDSC Communications, 858 534-5111 or jzverina@sdsc.edu

Warren R. Froelich, SDSC Communications, 858 822-3622 or froelich@sdsc.edu

Complete details of the SeedMe project can be found at http://www.seedme.org/. The NSF award number for the SeedMe project is OCI-1235505. In addition to Chourasia and Norman, the SeedMe project team includes Mona Wong-Barnum, David Nadeau, and Andrew Ferbert, all with SDSC.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together about 30 participants from industry, government and academia t Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Researchers Scale COSMO Climate Code to 4888 GPUs on Piz Daint

October 17, 2017

Effective global climate simulation, sorely needed to anticipate and cope with global warming, has long been computationally challenging. Two of the major obstacles are the needed resolution and prolonged time to compute Read more…

By John Russell

HPE Extreme Performance Solutions

Transforming Genomic Analytics with HPC-Accelerated Insights

Advancements in the field of genomics are revolutionizing our understanding of human biology, rapidly accelerating the discovery and treatment of genetic diseases, and dramatically improving human health. Read more…

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Cluster Competition coverage has come to its natural home: H Read more…

By Dan Olds

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together ab Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Read more…

By Dan Olds

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

Fujitsu Tapped to Build 37-Petaflops ABCI System for AIST

October 10, 2017

Fujitsu announced today it will build the long-planned AI Bridging Cloud Infrastructure (ABCI) which is set to become the fastest supercomputer system in Japan Read more…

By John Russell

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Intel Debuts Programmable Acceleration Card

October 5, 2017

With a view toward supporting complex, data-intensive applications, such as AI inference, video streaming analytics, database acceleration and genomics, Intel i Read more…

By Doug Black

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Leading Solution Providers

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

  • arrow
  • Click Here for More Headlines
  • arrow
Share This