A One-of-a-Kind Supercomputer to Map the Cosmos

By Michael Feldman

January 9, 2013

A new petascale supercomputer built to study the universe is one of the fastest calculating machines in the world, and certainly the fastest of its kind. The supercomputer is part of ALMA, a new radio telescope that is claimed to be “largest ground-based astronomical project in existence.”

ALMA, which stands for Atacama Large Millimeter/submillimeter Array, is an international project, which includes partners from Europe (European Southern Observatory, Laboratoire d’Astrophysique de Bordeaux), North America (National Radio Astronomy Observatory), and Japan (National Astronomical Observatory of Japan). The Joint ALMA Observatory, based in Santiago Chile, manages the project.

The ALMA radio telescope is a collection of 66 high-precision antennas (parabolic dishes that act as receivers), strewn over the 5,000 meter-high Chajnantor desert plateau in northern Chile. The dry air and elevation makes it a particularly suitable spot for capturing signals from space in the millimeter and sub-millimeter radio spectrum. At those wavelengths, the antennas can detect the so-called “cool Universe,” molecular gas and dust as well as residual radiation from the Big Bang.

The antennas can be set to capture signals in a variety of configurations, such that the distance between them can vary between 150 meters to 16 kilometers. That gives the ALMA telescope something akin to a “zoom” capability, as well as very high sensitivity and resolution. As a result, it should be able to produce images 10 times sharper than that of the Hubble Space Telescope.

The challenge of multiple radio antennas is to make them behave as a single receiver, and for that you need some hefty number crunching — thus the need for a supercomputer. The one built for ALMA is actually a special-purpose device designed to correlate faint signals from multiple sources. Because of its function, the supercomputer is actually known as “the correlator.” The supercomputer jargon was added later by the public relation guys to bring attention to its exceptional calculating prowess.

And exceptional it is. The correlator deliver 17 quadrillion operations per second. That’s 17 petaOPS (not petaFLOPS). If you discount these are not floating point operations, the system operates at a level comparable to Titan, the fastest general-purpose supercomputer in the world, and the current title-holder on the TOP500.

The ALMA system, which was built by the National Radio Astronomy Observatory (NRAO), uses 32,767 custom ASIC processors to blend the signals from the antenna array. The processors, built on 0.25 micron CMOS technology, run at a modest 125 MHz, with each one drawing just 1.8 watts. But because it is purpose-built for these correlation functions, the silicon is able to deliver 512 billion operations per second (gigaOPS). The processors are arranged 64 to a board, which are connected via a 1 megabit/second Controller Area Network.

There are also 17 ancillary computers involved in acquiring and calibrating data from the correlator hardware. The correlator itself is designed to receive 96 gigabits per second from up to 64 antennas and can sustain an output rate of 1 gigabyte per second.

The supercomputer is not all hard-wired though. According to Rich Lacasse, leader of the ALMA Correlator Team at NRAO, and Joe Greenberg, who worked on the hardware, there are several layers of software. For example, the processor supports about 70 flavors of correlation functions each with programmable features. So coding is required to configure these modes as well as monitor for correct operation. There is also high-level software for configuring the processors.

The proprietary architecture of the correlator was used to overcome cost and power usage constraints of the ALMA project. John Webber, former head of the NRAO Central Development Laboratory, says despite the custom design, their system was built for just $11 million, adding that a comparable general-purpose computer would have cost about $1 billion. Actually a GPU-accelerated supercomputer is quite a bit less expensive these days. Titan, for example, was built for $100 million. Nevertheless, that’s still nearly 10 times the cost of the ALMA machine.

Energy efficiency is even more impressive. Thanks to the low-power processors, the correlator consumes just 140 kilowatts of power. (The general-purpose Titan draws 8 megawatts.) But despite the correlator’s modest power usage, it takes twice the normal airflow to cool it due to the rarified atmosphere at 5,000 meters (16,500 feet). Also, hard drives operate problematically in the thin air, so the correlator is diskless.

ALMA began collecting data in 2011 with a partial array of radio antennas, with a cut-down version of the correlator being used to combine the signals from the initial array. Today, though, the entire array is operational and the correlator is ready for begin slicing and dicing signals from a larger number of antennas. That will increase its sensitivity and resulting image quality. The project is slated to be completely operational in March 2013.

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!

Cray+Azure: Can Cloud Propel Supercomputing?

October 23, 2017

Cray and Microsoft today announced they will offer dedicated Cray supercomputers (the XC and CS-Storm lines) inside the Azure platform allowing customers to run their HPC and AI applications alongside their other cloud w Read more…

By Tiffany Trader

2017 Gordon Bell Prize Finalists Named

October 23, 2017

The three finalists for this year’s Gordon Bell Prize in High Performance Computing have been announced. They include two papers on projects run on China’s Sunway TaihuLight system and a third paper on 3D image recon Read more…

By John Russell

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

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…

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

Cray+Azure: Can Cloud Propel Supercomputing?

October 23, 2017

Cray and Microsoft today announced they will offer dedicated Cray supercomputers (the XC and CS-Storm lines) inside the Azure platform allowing customers to run Read more…

By Tiffany Trader

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

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

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

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

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