Biomedical Simulation at PSC Gets Major Performance Boost with Anton 2

By John Russell

February 5, 2016

Simulating even small biological systems has long proven computationally difficult. Practically speaking, data-driven bioinformatics such as DNA sequence analysis has progressed more rapidly. Development of Anton 1, the ASIC-based supercomputer specifically designed for simulating molecular dynamics by D. E. Shaw Research (DESRES) in 2008, was a major advance. In 2010 DESRES provided an Anton machine at no charge to the Pittsburgh Supercomputer Center (PSC), which in turn provided access to a wider biomedical research community.

History is now repeating itself. Anton 2, a significant upgrade, was developed in 2014 and PSC announced this week it planned to retire its Anton 1 and provide access to an Anton 2 machine in the fall 2016. As with the first machine, DESRES is providing the supercomputer at no cost. NIH awarded a $1.8 million grant to PSC in support. The new system, though somewhat smaller than its predecessor (128 nodes versus 512) is four times faster and can simulate molecular systems roughly five times larger.

“That opens up all kinds of interesting biological problems,” said Phil Blood, principal investigator of the new grant and senior computational scientist at PSC. Besides accurate prediction of protein folding – long a holy grail of computational biology – simulation of signal transduction, key binding activities, and important molecule conformational changes should all be more do-able.

Simulations run on Anton 1 were typically limited to biomolecular systems of 150,000 to 200,000 atoms in a defined volume. Anton 2 is expected to be able to simulate systems with on the order of 700,000 atoms substantially expanding the size and complexity of potential projects. Just as important, Anton 2’s higher speed will allow investigators to increase the biological timelines, moving closer to the goal of the practical millisecond simulation, long enough for meaningful biological activities to occur.

Molecular dynamics simulations can provide insights into the behavior of proteins, cell membranes, nucleic acids, and other molecules at the atomic scale. But even the most advanced general-purpose supercomputers struggle to simulate beyond the microsecond level—a thousand times shorter than the millisecond level—without taking months of computational time. Anton 1 has changed this, giving researchers practical access to simulations at longer timescales but within limits.

Anton 1 Supercomputer
Anton 1 Supercomputer

“On Anton 1 it took months of dedicated time to achieve a millisecond scale,” said Blood. Given that Anton 1 is a shared resource, achieving millisecond simulation has been basically unfeasible. “We were seeing single digit microseconds to tens of microseconds of simulation. Some investigators would study one system for a very long time and then they might get up to 100 microseconds, but most do several simulation on the scale of 10 microseconds,” said Blood.

Using Anton 2 Blood expects investigators will be able to routinely simulate tens of microseconds up to hundreds of microseconds of biological time. “You start to get really close to that millisecond scale where a lot of interesting biology happens,” he said.

The Anton 1 supercomputer that has been in use at PSC since 2010 has so far enabled 277 simulation projects by 127 different PIs across the US and resulted in more than 120 peer-reviewed research papers. Three of these studies appeared in the scientific journal Nature, one of the international scientific community’s premier publications.

Development of the Anton systems (named for the legendary microbiologist Anton van Leeuwenhoek) is part of David Shaw’s impressive work. Shaw, a computational scientist turned hedge fund manager, famously made a fortune on Wall Street and then turned his efforts and resources to computational biochemistry and biology. He is founder and chief scientist of DESRE and a senior research fellow at the Center for Computational Biology and Bioinformatics, Columbia University. Anton 1, developed by his group, broke important new ground in specialized supercomputing.

PSC expectations are high for Anton 2. A fairly detailed look at Anton 2’s architecture, detailing improvements relative to Anton 1, is presented is in a 2014 paper, Anton 2: Raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer. The work was presented at SC14 and is available from the ACM digital library.[i] Here is the abstract and a brief except: presented below.

“Abstract: Anton 2 is a second-generation special-purpose supercomputer for molecular dynamics simulations that achieves significant gains in performance, programmability, and capacity compared to its predecessor, Anton 1. The architecture of Anton 2 is tailored for fine-grained event-driven operation, which improves performance by increasing the overlap of computation with communication, and also allows a wider range of algorithms to run efficiently, enabling many new software-based optimizations. A 512-node Anton 2 machine, currently in operation, is up to ten times faster than Anton 1 with the same number of nodes, greatly expanding the reach of all-atom biomolecular simulations. Anton 2 is the first platform to achieve simulation rates of multiple microseconds of physical time per day for systems with millions of atoms. Demonstrating strong scaling, the machine simulates a standard 23,558-atom benchmark system at a rate of 85 μs/day—180 times faster than any commodity hardware plat- form or general-purpose supercomputer. “

Excerpt: “We have designed and built Anton 2, a special-purpose supercomputer for MD simulation that outperforms Anton 1 by up to an order of magnitude and outperforms currently available general-purpose hardware by two orders of magnitude, while simultaneously presenting a simpler, more flexible programming model than Anton 1. Like its predecessor, Anton 2 performs the entire MD computation within custom ASICs that are tightly interconnected by a specialized high-performance network. Each ASIC devotes a quarter of its die area to specialized hardware pipelines for calculating interactions between pairs of atoms, and also contains 66 general-purpose programmable processor cores that deliver data to these pipelines and perform the remaining computations required by the MD simulation.

“Improvements in VLSI chip fabrication technology provide Anton 2 with more computational units than Anton 1, but due to the overheads of distributing work to and coordinating a larger number of units, this alone is insufficient to deliver proportionally better performance. A key component of the Anton 2 design is thus a set of new mechanisms devoted to efficient fine-grained operation. The resulting architecture more aggressively exploits the parallelism of MD simulations, which fundamentally consist of a large number of fine-grained computations involving individual atoms or small groups of atoms. By providing direct hardware support for fine-grained communication and synchronization [20, 52], Anton 2 allows these computations to be distributed across an increased number of functional units while maintaining high utilization of the underlying hardware resources.”

Blood notes that programming is usually challenging for first-time Anton users. “The system is different from anything they are used to working with; it isn’t using any molecular dynamics code people have used before, at least in terms of the general research community. They are not going to run NAMD or GROMACS or Amber on Anton. The most computational intense parts of the MD algorithms are expressed directly in hardware. We always have the investigators come to a workshop at the beginning of the year,” said Blood.

Details of the Anton 2 deployment and what exactly will happen to Anton 1 are still being discussed according to Blood. Anton 1, like the new machine, still belongs to DESRES. NIH supported that effort with a $2.7 million grant.

“Sometime in the spring we will release a request for proposals for the new Anton 2 system. Current allocations on the Anton 1 will finish at the end of July so sometimes between the end of July and beginning of the new round of allocations in late fall, we will de-install the current Anton 1 system and install the Anton 2,” said Blood. More information on the Anton project at PSC can be found at https://www.psc.edu/index.php/computing-resources/anton

[i] LINK to paper http://dl.acm.org/citation.cfm?id=2683599

Anton 1 Photo Credit: Matt Simmons

Subscribe to HPCwire's Weekly Update!

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

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from its predecessors, including the red-hot H100 and A100 GPUs. Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. While Nvidia may not spring to mind when thinking of the quant Read more…

2024 Winter Classic: Meet the HPE Mentors

March 18, 2024

The latest installment of the 2024 Winter Classic Studio Update Show features our interview with the HPE mentor team who introduced our student teams to the joys (and potential sorrows) of the HPL (LINPACK) and accompany Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the field was normalized for boys in 1969 when the Apollo 11 missi Read more…

Apple Buys DarwinAI Deepening its AI Push According to Report

March 14, 2024

Apple has purchased Canadian AI startup DarwinAI according to a Bloomberg report today. Apparently the deal was done early this year but still hasn’t been publicly announced according to the report. Apple is preparing Read more…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimization algorithms to iteratively refine their parameters until Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimizat Read more…

PASQAL Issues Roadmap to 10,000 Qubits in 2026 and Fault Tolerance in 2028

March 13, 2024

Paris-based PASQAL, a developer of neutral atom-based quantum computers, yesterday issued a roadmap for delivering systems with 10,000 physical qubits in 2026 a Read more…

India Is an AI Powerhouse Waiting to Happen, but Challenges Await

March 12, 2024

The Indian government is pushing full speed ahead to make the country an attractive technology base, especially in the hot fields of AI and semiconductors, but Read more…

Charles Tahan Exits National Quantum Coordination Office

March 12, 2024

(March 1, 2024) My first official day at the White House Office of Science and Technology Policy (OSTP) was June 15, 2020, during the depths of the COVID-19 loc Read more…

AI Bias In the Spotlight On International Women’s Day

March 11, 2024

What impact does AI bias have on women and girls? What can people do to increase female participation in the AI field? These are some of the questions the tech Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Analyst Panel Says Take the Quantum Computing Plunge Now…

November 27, 2023

Should you start exploring quantum computing? Yes, said a panel of analysts convened at Tabor Communications HPC and AI on Wall Street conference earlier this y Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Leading Solution Providers

Contributors

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Training of 1-Trillion Parameter Scientific AI Begins

November 13, 2023

A US national lab has started training a massive AI brain that could ultimately become the must-have computing resource for scientific researchers. Argonne N Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire