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.
“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
Anton 1 Photo Credit: Matt Simmons