Optimizing Key Plasma Physics Code for Latest-Gen Nvidia GPUs Yields Threefold Increase in Processing Speed

By Thomas W. Overton

December 5, 2018

Experts at General Atomics (GA) have achieved a major improvement in processing speed for an important plasma physics code by working with experts from Nvidia to optimize it for operation on the latest GPU-based supercomputers.

This three-fold increase in processing time for the latest CGYRO code, used to simulate turbulent behavior of confined plasmas, was made possible by acquiring hardware similar to that used in the Summit supercomputer now being developed at Oak Ridge National Laboratory. Working on the system allowed GA researchers to test and validate their approach before deployment – an approach that could prove valuable for researchers in a variety of fields preparing for work on the next wave of supercomputing.

Early (left) and late (right) times in a simulation of multiscale plasma turbulence. At early times, short-wavelength electron-scale turbulence dominates, but is soon overtaken by long-wavelength ion-scale turbulence. Simultaneously capturing both scales is critical to the simulation realism but requires massive computational resources. (Source: General Atomics)

Physicists tend to be heavy users of Department of Energy (DOE) supercomputer resources. Those working on nuclear fusion rely heavily on modeling to predict plasma conditions inside a fusion reactor. An approach known as gyrokinetics has been used for nearly two decades to investigate turbulence in fusion plasmas because of its ability to model behavior of the ions and electrons in the plasma.

However, the extreme complexity of plasmas – which are heated to temperatures many times that of the sun to cause hydrogen isotopes to fuse into heavier elements – means that even limited simulations require enormous processing power. This is why all current models can simulate only portions of the plasma over limited timescales. As a result, physics researchers are constantly looking for ways to make their simulations more efficient.

Over a decade ago, scientists at GA – which operates the DIII-D National Fusion Facility for DOE at GA’s campus in San Diego – developed GYRO (a predecessor to CGYRO) to model the turbulent motion of confined plasma.

“In a toroidal containment device, the plasma fuel is confined by magnetic fields but suffers a very slow leakage due to turbulent behavior,” said Jeff Candy, manager of the Turbulence and Transport Group in GA’s Magnetic Fusion Energy Division. “GYRO has proved to be very accurate at simulating this complex nonlinear process in the core region of DIII-D and other tokamaks in the U.S. and Europe, but modeling the outside edge of the plasma is more challenging.”

Physicist Jeff Candy (front) and software developer Igor Sfiligoi (rear) of General Atomics worked together with their colleagues to optimize the CGYRO plasma physics code for Oak Ridge National Laboratory’s Summit supercomputer using a pair of nodes that mimicked Summi’s exotic processing environment. (Photo: Tom Overton/General Atomics)

The need to accurately model this more complex regime motivated the development of CGYRO. It was built from the ground up by combining the best algorithms from GYRO with new numerical schemes as well as a cutting-edge approach to parallelization that targeted the upcoming generation of multicore and GPU-based architectures.

“CGYRO was intended for operation on petascale systems,” said Igor Sfiligoi, a high-performance computer software developer at GA. “We’ve run it successfully on Titan for several years. But the original version of CGYRO was optimized for older GPUs, which means we weren’t using all the features of more modern GPUs.”

One goal in particular was optimizing CGYRO for use on Summit, Titan’s successor at ORNL. At the University of Colorado in Boulder GPU Hackathon in July, GA researchers worked with specialists from Nvidia to optimize CGYRO for the latest generation of GPU systems using the OpenACC programming model.

“A GPU-aware message passing interface is now used to move data directly between GPUs, without the need for staging first to the system memory,” Sfiligoi said. “Most of the remaining physics code execution has also been moved to the GPU, where it can now be efficiently executed without the excessive memory movement penalty.”

Since 2014, the Oak Ridge Leadership Computing Facility and its partners have held GPU hackathons to teach new GPU programmers how to leverage accelerated computing and help existing GPU programmers further optimize their codes. In 2018, there were seven such events at locations around the world, one of which was held at the UC Boulder. The GA team worked with Brent Leback and Craig Tierney from Nvidia at the hackathon.

In order to validate and benchmark the resulting code at the Hackathon, GA researchers needed access to Summit-like hardware. However, they did not have access to Summit nodes, and will not get it until 2019 at the earliest. In early 2018, to get around this problem, GA purchased two nodes that would mimic Summit’s fairly exotic processing environment.

The nodes comprise two IBM AC922 servers, each with two 16-core 4-hyperthread IBM Power9 CPUs and four Nvidia Tesla V100 with NVLink Volta GPUs, with 512GB of CPU RAM and 4x16GB of GPU RAM. GA was the first commercial user to acquire a setup like this.

Each Summit node uses six Nvidia Volta GPUs per two Power9 CPUs, tied together with Nvidia’s NVLink 2.0 technology (Image credit: Jason Richards/ORNL)

The result of the optimization efforts is a three-fold increase in processing speed on those nodes. The new version of CGYRO can thus be assumed to be optimized for use on Summit, where it will be able to run three times as many simulations in the same amount of time. Given how expensive and competitive supercomputer time is, a three-fold increase in the amount of work that can be done is an important achievement for GA’s plasma physicists.

“This improved computational efficiency on next-generation supercomputers will allow CGYRO to precisely compute plasma turbulence levels in the most challenging regions of the device operating space,” Candy said. “That opens up a new range of research that can help get us to commercial fusion power plants.”

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!

Energy Exascale Earth System Model Version 2 Promises Twice the Speed

October 18, 2021

The Energy Exascale Earth System Model (E3SM) is an ongoing Department of Energy (DOE) earth system modeling, simulation and prediction project aiming to “assert and maintain an international scientific leadership posi Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

NSF Awards $11M to SDSC, MIT and Univ. of Oregon to Secure the Internet

October 14, 2021

From a security standpoint, the internet is a problem. The infrastructure developed decades ago has cracked, leaked and been patched up innumerable times, leaving vulnerabilities that are difficult to address due to cost Read more…

SC21 Announces Science and Beyond Plenary: the Intersection of Ethics and HPC

October 13, 2021

The Intersection of Ethics and HPC will be the guiding topic of SC21's Science & Beyond plenary, inspired by the event tagline of the same name. The evening event will be moderated by Daniel Reed with panelists Crist Read more…

AWS Solution Channel

Cost optimizing Ansys LS-Dyna on AWS

Organizations migrate their high performance computing (HPC) workloads from on-premises infrastructure to Amazon Web Services (AWS) for advantages such as high availability, elastic capacity, latest processors, storage, and networking technologies; Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Eni Returns to HPE for ‘HPC4’ Refresh via GreenLake

October 13, 2021

Italian energy company Eni is upgrading its HPC4 system with new gear from HPE that will be installed in Eni’s Green Data Center in Ferrera Erbognone (a provi Read more…

The Blueprint for the National Strategic Computing Reserve

October 12, 2021

Over the last year, the HPC community has been buzzing with the possibility of a National Strategic Computing Reserve (NSCR). An in-utero brainchild of the COVID-19 High-Performance Computing Consortium, an NSCR would serve as a Merchant Marine for urgent computing... Read more…

UCLA Researchers Report Largest Chiplet Design and Early Prototyping

October 12, 2021

What’s the best path forward for large-scale chip/system integration? Good question. Cerebras has set a high bar with its wafer scale engine 2 (WSE-2); it has 2.6 trillion transistors, including 850,000 cores, and was fabricated using TSMC’s 7nm process on a roughly 8” x 8” silicon footprint. Read more…

What’s Next for EuroHPC: an Interview with EuroHPC Exec. Dir. Anders Dam Jensen

October 7, 2021

One year after taking the post as executive director of the EuroHPC JU, Anders Dam Jensen reviews the project's accomplishments and details what's ahead as EuroHPC's operating period has now been extended out to the year 2027. Read more…

University of Bath Unveils Janus, an Azure-Based Cloud HPC Environment

October 6, 2021

The University of Bath is upgrading its HPC infrastructure, which it says “supports a growing and wide range of research activities across the University.” Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer... Read more…

Enter Dojo: Tesla Reveals Design for Modular Supercomputer & D1 Chip

August 20, 2021

Two months ago, Tesla revealed a massive GPU cluster that it said was “roughly the number five supercomputer in the world,” and which was just a precursor to Tesla’s real supercomputing moonshot: the long-rumored, little-detailed Dojo system. Read more…

Esperanto, Silicon in Hand, Champions the Efficiency of Its 1,092-Core RISC-V Chip

August 27, 2021

Esperanto Technologies made waves last December when it announced ET-SoC-1, a new RISC-V-based chip aimed at machine learning that packed nearly 1,100 cores onto a package small enough to fit six times over on a single PCIe card. Now, Esperanto is back, silicon in-hand and taking aim... Read more…

CentOS Replacement Rocky Linux Is Now in GA and Under Independent Control

June 21, 2021

The Rocky Enterprise Software Foundation (RESF) is announcing the general availability of Rocky Linux, release 8.4, designed as a drop-in replacement for the soon-to-be discontinued CentOS. The GA release is launching six-and-a-half months... Read more…

US Closes in on Exascale: Frontier Installation Is Underway

September 29, 2021

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, held by Zoom this week (Sept. 29-30), it was revealed that the Frontier supercomputer is currently being installed at Oak Ridge National Laboratory in Oak Ridge, Tenn. The staff at the Oak Ridge Leadership... Read more…

Intel Completes LLVM Adoption; Will End Updates to Classic C/C++ Compilers in Future

August 10, 2021

Intel reported in a blog this week that its adoption of the open source LLVM architecture for Intel’s C/C++ compiler is complete. The transition is part of In Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Hot Chips: Here Come the DPUs and IPUs from Arm, Nvidia and Intel

August 25, 2021

The emergence of data processing units (DPU) and infrastructure processing units (IPU) as potentially important pieces in cloud and datacenter architectures was Read more…

Leading Solution Providers

Contributors

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

HPE Wins $2B GreenLake HPC-as-a-Service Deal with NSA

September 1, 2021

In the heated, oft-contentious, government IT space, HPE has won a massive $2 billion contract to provide HPC and AI services to the United States’ National Security Agency (NSA). Following on the heels of the now-canceled $10 billion JEDI contract (reissued as JWCC) and a $10 billion... Read more…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

The Latest MLPerf Inference Results: Nvidia GPUs Hold Sway but Here Come CPUs and Intel

September 22, 2021

The latest round of MLPerf inference benchmark (v 1.1) results was released today and Nvidia again dominated, sweeping the top spots in the closed (apples-to-ap Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make i Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire