Mars as a Service: Cloud Computing for the Red Planet Exploration Era

By Dr. Jose Luis Vazquez-Poletti

February 3, 2011

What do clouds and a distant red planet with a thin atmosphere have in common? Dr. Jose Luis Vazquez-Poletti from Universidad Complutense de Madrid explains how cloud computing is being deployed in innovative space missions that take aim at Mars.  He reports on the outcome of a meeting of the Mars MetNet Mission, which was held at the Finnish Meteorological Institute headquarters in Helsinki and describes in detail some of the cutting-edge research that is making use of cloud-based resources to handle the massive data expected.

The MetNet project aims to go where no other Mars missions have gone before, at least in terms of the way it will gather and then process data. This mission to Mars will be based on the power of a new type of dandelion seed-shaped, semi-hard landing vehicle called the MetNet Lander.

The leaders of the mission hope to deploy several of these oddly-shaped landers (as shown to the left) on Martian soil. While these lofty goals will take shape over a number of years, the first step in the mission to launch a MetNet Mars precursor mission with the first few landers being deployed in the coming year.

The main idea behind these vehicles is that by using a state-of-the-art inflatable entry and descent systems (instead of rigid heat shields and parachutes like those from the earlier semi-hard landing devices) the ratio of the payload mass to the overall mass is optimized. This means that more mass and volume resources are spared for the science payload.

The scientific payload of the Mars MetNet Mission encompasses separate instrument packages for the Martian surface operation phase. At the Martian surface, the lander will take panoramic pictures and will also perform observations of pressure, temperature, humidity, magnetism, as well as atmospheric optical depth.

The network of MetNet landers will provide valuable scientific data, decisive for studying the Martian atmosphere and its phenomena. Countries involved are Finland (Finnish Meteorological Institute), Russia  (Lavochkin Space Association and Russian Space Institute) and Spain (Instituto Nacional de Técnica Aerospacial).

The collaboration developed in Mars MetNet by our group, the Distributed Systems Architecture Research Group led by Prof. Ignacio M. Llorente from the Universidad Complutense de Madrid has much to do with cloud computing… in fact, the collaborative effort is dedicated to using cloud computing for boosting all possible applications pertaining to the Mars mission, as will be explained in greater detail in a moment.

Project Details

We began this collaboration with the Mars MetNet Mission more than a year ago, when they were dealing with the tracing of Phobos, the biggest Martian moon which orbits at about 9,400 Km (5,800 miles) distance from the planet’s center, completing its cycle nearly 3 times a day (a Martian day lasts 24:39 hours).

The prediction of each Phobos’ eclipse is important for the onboard instruments, which obviously depend on the landing coordinates. The challenge arises when the approximated landing area is not known until two hours before the touchdown. For this reason, an application for tracing Phobos was developed by the Meiga-MetNet Team, in order to provide a Phobos cyclogram, which is the trajectory of the Martian moon in Astronomy terms, using coordinates, dates and time intervals as an input. This way, the MetNet lander would achieve its exact location on the Martian surface by comparing the position of Phobos and the cyclogram, that is to be sent to the probe before the landing procedure.

Martian Clouds

We performed an initial parallelization of the application so that the complete set of coordinates pertaining to the approximated landing area can be processed with a desired grain. This process of profiling brought us to the conclusion that the needed hardware could be too expensive for executing this HPC application only twice a year. We had no way of even knowing if there would be other uses for this costly hardware either.

For this reason we turned to Amazon EC2, the de facto standard public cloud, attracted by its high speed deployment and its “pay-as-you-go” basis. Because all the possible setups that Amazon EC2 was offering by means of instance types and number, we crafted and validated an execution model for the application considering time, cost and a metric involving both [1].  This way, the optimal infrastructure could be obtained given a problem size.

Considering one of the possible setups, its baremetal equivalent could be a cluster consisting in 37 nodes of the latest HP Proliant DL170 G6 Server (for example). Taking its web price of $4,909 per node, we would get our machines for $181,633 without considering any other expenses like shipping or insurances. Great, but… what about electricity? Administrator’s salary? Startup time? Even more, are we going to use this infrastructure at full power in a 24×7 fashion? Probably not.

On the other hand and according to our model, Amazon EC2 provides the needed infrastructure for $7.50.

During the meeting, I performed a comprehensive presentation explaining what Cloud Computing is and its elements to the rest of the Mars MetNet Scientific Team. The best way to make a base scientist understand Cloud Computing is to provide a good assortment of working examples and success stories. Of course, I recommended “HPC in the Cloud” as one of the main sources of news about our favorite technology.

Among these examples was the NASA case. They begun with the Nebula initiative in 2009, providing an alternative to the costly construction of additional data centers whenever NASA scientist or engineers require additional processing. This is accomplished in a fancy way and, in my point of view, following a real life “on demand” definition, as truck containers are delivered to the demanding research centers. These shipping containers can hold up to 15,000 CPU cores or 15 petabytes of storage while proving 50% more energy efficient than traditional data centers.

However, NASA decided last December 2010 to make another step on its Cloud path: they started to use the Amazon public cloud for its ATHLETE (All-Terrain Hex-Limbed Extra-Terrestrial Explorer), to be commissioned to future Mars exploring Missions. Machine instances from Amazon EC2 are used for processing satellite high-definition images in order to take navigation decisions.

But one year before NASA, the Mars MetNet Mission was already using Amazon EC2 as I explained at the beginning of this article. The results obtained for the locations of the different Martian probes were presented during the meeting and the detection of eclipses was confirmed by the experimental (and historic) data retrieved. This confirmed that the Phobos tracing model will help the Mars MetNet Mission and that Cloud Computing will be an indispensable tool, due to the huge amount of computational power needed in a very short term of time.

After my presentation, a new application was proposed. This time it has to do with the process of the meteorological data from landers pertaining to previous Mars Missions. This work has much to do with what could be addressed as “Archaeological Computing”, because much of the raw data is about 30  years old! Despite its age, the meteorological information obtained from the landers will be very useful for the Mars MetNet Mission.

The amount of data is huge and parallelization may solve some of the problems, considering several processes which respond to certain parameters. These parameters are provided by a Meteorological Model, developed within the Finnish Meteorological Institute. However, computing resource availability is another thing to take into account regarding the numerous application executions needed, so this is where a public cloud infrastructure helps reaching the goal.

But the advantages are more, because the final framework is intended to be used with the data obtained by the Mars MetNet probe, and it will be increased while more probes from the meteorological network become part of the Martian landscape.

To conclude, space missions are bringing many HPC challenges and adopting cloud computing is a decisive move for meeting them. Additionally, all research done on cloud computing for fulfilling the space mission’s demands will revert in other areas, as other achievements outside computing already did–like lyophilized food or Velcro straps.

If you are curious about the landing procedure of these dandelion-seed-shaped landers, I really encourage you to visit the Mars MetNet Mission website and watch the animation.

About the Author

Dr. Jose Luis Vazquez-Poletti is Assistant Professor in Computer Architecture at Universidad Complutense de Madrid (Spain), and a Cloud Computing Researcher. He is (and has been) directly involved in EU funded projects, such as EGEE (Grid Computing) and 4CaaSt (PaaS Cloud), as well as many Spanish national initiatives. His interests lie mainly in how the Cloud benefits real life applications, specially those pertaining to the High Performance Computing domain.

Dr. Vazquez-Poletti is also the author of a popular article that appeared in HPC in the Cloud describing a range of upcoming cloud computing research projects pending in Europe.

Linkedin: http://es.linkedin.com/in/jlvazquezpoletti/

Website: http://dsa-research.org/jlvazquez/

[1] J. L. Vázquez-Poletti, G. Barderas, I. M. Llorente and P. Romero: A Model for Efficient Onboard Actualization of an Instrumental Cyclogram for the Mars MetNet Mission on a Public Cloud Infrastructure. PARA2010: State of the Art in Scientific and Parallel Computing, Reykjavík (Iceland), June 2010. Proceedings to appear in Lecture Notes in Computer Science (LNCS).
 

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

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

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

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

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

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

Leading Solution Providers

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

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