Preparing for the Arrival of Aurora with CPU-based Interactive Visualization

By Rob Farber

October 30, 2018

In preparation for the arrival of Aurora, slated to be the first U.S. exascale supercomputer, Argonne National Laboratory is actively working to make techniques such as in situ and in transit visualization and analysis available to their user community plus the HPC community at large. The result is a DOE multi-institutional effort that includes Argonne, private companies, and other national labs to leverage SENSEI, a portable framework that enables in situ, in transit, and traditional batch visualization workflows that can use either ray tracing or triangle-based rendering back ends, for analysis and scalable interactive rendering.

In situ visualization has been identified as a key technology to enable science at the exascale[i]. In situ visualization means that the visualization occurs on the same nodes that perform the computation. In transit visualization is not as directly coupled to the simulation, and can help load-balance by using more nodes to support computationally expensive simulations like LAMMPs. Unlike in situ, in transit does incur some overhead when moving data across the communications fabric between nodes. Both methods keep the data in memory and avoid writing to storage.

Joseph Insley (visualization and analysis team lead at the Argonne Leadership Computing Facility) points out, “With SENSEI, users can utilize in situ and in transit techniques to address the widening gap between Flop/s and I/O capacity which is making full-resolution, I/O-intensive post hoc analysis prohibitively expensive, if not impossible.” Silvio Rizzi (assistant computer scientist, Argonne) highlights portability when he states, “the idea behind SENSEI is to write once and use anywhere.”

The Argonne team led by Nicola Ferrier as PI has adapted the popular LAMMPS (e.g. the Large-scale Atomic/Molecular Massively Parallel Simulator) code to demonstrate the benefits of the SENSEI framework. The integration of SENSEI made use of existing mechanisms in LAMMPS for coupling with other simulation codes.[ii]

Understanding the choice of LAMMPS as a SENSEI testbed

Paul Navrátil, director of Visualization at the Texas Advanced Computing Center (TACC), helps us understand the meaning and importance of in situ and in transit visualization to the general HPC community as well as the choice of LAMMPS by the ALCF team.

Just as Argonne will host the fastest U.S. supercomputer with Aurora, TACC will be home to Frontera, which will become the fastest academic supercomputer in the United States when it becomes operational in 2019.

Navrátil notes, “We expect in situ workflows to become increasingly necessary on Frontera and across all large-scale simulation science.” He believes that, “In transit analysis will also play an increasing role as simulations improve support for loosely-coupled in situ frameworks. With an in transit pathway, the simulation resources do not need to be shared for analysis tasks, which is favorable when analysis is compute-intensive, or when the simulation requires all available resources itself.”

LAMMPS is a compute intensive application plus it is a very popular simulation code, which makes it a natural testbed for SENSEI as it lets large numbers of users explore the benefits of in situ visualization plus the load balancing benefits of in transit visualization and analysis. SENSEI is also being used in multiple science domains, including molecular dynamics and materials science.

An in transit workflow using SENSEI and OSPRay is shown below.

Figure 1: LAMMPS using SENSEI to execute an in transit visualization and analysis work flow. (Image courtesy taken from Usher, et.al.[iii])
Choosing the right rendering back end

SENSEI is very flexible and allows researchers to perform analysis and use either OpenGL rendering or create photo real images. Jim Jeffers (senior director and senior principle engineer, Intel Visualization Solutions) notes that the interactive performance delivered by the Intel Rendering Framework and photorealistic rendering with the freely available OSPRay library and viewer, “addresses the need and creates the want” for photorealistic rendering. Succinctly, interactive ray tracing with its inherent lighting capability lets scientists get more from their data. Jeffers’ is famous for stating, “a picture is worth an exabyte.”

The ALCF team provided the following figure to illustrate what is possible when instrumenting LAMMPS with SENSEI. They used the Intel OSPRay library that is part of the Intel Rendering Framework and the libIS, a lightweight, flexible library to create this in transit visualization. However, SENSEI was designed[iv] work with other libraries in place of libIS such as catalyst (part of ParaView), ADIOS (from Oak Ridge National Laboratory), and LibSim (part of VisIt), as well as GPU-based software to perform in transit visualizations.

Figure 2: Interactive in situ visualization of a 172k atom simulation of silicene formation [6] with 128 LAMMPS ranks sending to 16 renderer ranks, all executed on Theta. (Image from Usher, et. al[v])
SENSEI is not the first code to provide easy access to both OpenGL and ray tracing back end and analytic capabilities. Both the popular VisIt[vi] and ParaView viewers make it simple to switch between or even combine triangle-based OpenGL rendering with Intel OpenSWR and photorealistic ray-traced rendering with Intel OSPRay.

Understanding Software Defined Visualization (SDVis)

The foundation of CPU-based in situ and in transit visualization is Software Defined Visualization. The core functionality are the freely available, open-source Intel OSPRay, Embree, and OpenSWR libraries. These libraries have been incorporated into the Intel® Rendering Framework stack as shown below.

Figure 3: Scientific and Professional rendering stacks using the Intel Rendering Framework (Image courtesy Intel)

Using CPUs for rendering has taken the HPC community by storm. Rizzi summarizes the interest at Argonne by noting, “We want to enable visualization on our supercomputers which are CPU-based”. Navrátil highlights TACC’s commitment by pointing out that, “CPU-based SDVis will be our primary visual analysis mode on Frontera, leveraging the Intel Rendering Framework stack.”

Scaling and the ability to run efficiently are two key ideas behind the OSPRay ray tracing and the OpenSWR OpenGL SDVis renderer.

Kitware, for example, performed trillion triangle OpenGL visualizations using the LANL Trinity supercomputer. David DeMarle, (visualization luminary and engineer at Kitware) observes that, “CPU-based OpenGL performance does not trail off even when rendering meshes containing one trillion (10^12) triangles on the Trinity leadership class supercomputer. Further, we might see a 10-20 trillion triangle per second result as our current benchmark used only 1/19th of the machine.” The ability of the CPU to access large amounts of memory is key to realizing trillion triangle per second rendering capability.

Meanwhile, OSPRay users have demonstrated the ability to render and visualize large, photorealistic images on everything from cosmological data sets to molecules and complex scenes. No special hardware is required for rendering, which can achieve interactive photorealism on as few as eight Intel Xeon Scalable 8180 processors or scale to high-quality rendering for in situ nodes. [vii] [viii] [ix] [x]

Viewing the rendered images

The “visualize anywhere” nature of CPU-based SDVis means that visualizing locally or remotely is possible on devices that can display from memory. Extraordinary display flexibility without device dependencies makes “visualize anywhere” even better. HPC users appreciate how they can view results on their laptops and switch to display walls or a cave.

SENSEI also supports existing batched save-to-storage workflows.

Summary

The HPC community has always been about pressing the limits of computation. For this reason, in situ and in transit visualization frameworks have been created to work with CPU-based rendering to eliminate data movement. In this way, visualization can scale and keep pace with simulation as the HPC community runs on petascale and anticipates the next generation exascale supercomputers.

Rob Farber is a global technology consultant and author with an extensive background in HPC and in developing machine learning technology that he applies at national labs and commercial organizations. Rob can be reached at [email protected].


[i] https://science.energy.gov/~/media/ascr/pdf/program-documents/docs/Exascale-ASCR-Analysis.pdf

[ii] https://lammps.sandia.gov/doc/Howto_couple.html

[iii] Will Usher, Silvio Rizzi, Ingo Wald, Jefferson Amstutz, Joseph Insley, Venkatram Vishwanath, Nicola Ferrier, Michael E. Papka, and Valerio Pascucci. 2018. libIS: A Lightweight Library for Flexible In Transit Visualization. In ISAV: In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization (ISAV ’18), November 12, 2018, Dallas, TX, USA. ACM, New York, NY, USA, 6 pages. https://doi.org/10.1145/3281464.3281466.

[v] https://doi.org/10.1145/3281464.3281466

[vi] https://tacc.github.io/visitOSPRay/

[vii] http://sdvis.org/

[viii] http://www.cgw.com/Press-Center/In-Focus/2018/Scalable-CPU-Based-SDVis-Enables-Interactive-Pho.aspx

[ix] https://www.ixpug.org/documents/1496440983IXPUG_insitu_S1_Jeffers.pdf

[x] http://www.techenablement.com/third-party-use-cases-illustrate-the-success-of-cpu-based-visualization/

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!

Goonhilly Unveils New Immersion-Cooled Platform, Doubles Down on Sustainability Mission

July 16, 2019

Goonhilly Earth Station has opened its new datacenter – an enhancement to its existing tier 3 facility – in Cornwall, England, touting an ambitious commitment to holistic sustainability as well as launching a managed Read more…

By Oliver Peckham

New CMU AI Poker Bot – Pluribus – Humbles the Pros Again

July 15, 2019

Remember Libratus, the Carnegie Mellon University developed AI poker bot that’s been humbling poker professionals at Texas hold’em for a couple of years. Well, say hello to Pluribus, an upgraded bot, which has now be Read more…

By John Russell

ISC19 Cluster Competition: Application Results, Finally!

July 15, 2019

Our exhaustive coverage of the ISC19 Student Cluster Competition continues as we discuss the application scores below. While the scores were typically high, some of the apps, like SWIFT and OpenFOAM, really pushed the st Read more…

By Dan Olds

HPE Extreme Performance Solutions

Bring the Combined Power of HPC and AI to Your Business Transformation

A growing number of commercial businesses are implementing HPC solutions to derive actionable business insights, to run higher performance applications and to gain a competitive advantage. Read more…

IBM Accelerated Insights

Smarter Technology Revs Up Red Bull Racing

In 21st century business, companies that effectively leverage their information resources – thrive. As it turns out, the same is true in Formula One racing. Read more…

Portugal Launches Its First Supercomputer

July 12, 2019

Portugal has officially inaugurated its first-ever supercomputer. The unassumingly named “Bob” supercomputer is housed in the Minho Advanced Computer Center (MACC) at the University of Minho.  Bob was announced i Read more…

By Oliver Peckham

Goonhilly Unveils New Immersion-Cooled Platform, Doubles Down on Sustainability Mission

July 16, 2019

Goonhilly Earth Station has opened its new datacenter – an enhancement to its existing tier 3 facility – in Cornwall, England, touting an ambitious commitme Read more…

By Oliver Peckham

New CMU AI Poker Bot – Pluribus – Humbles the Pros Again

July 15, 2019

Remember Libratus, the Carnegie Mellon University developed AI poker bot that’s been humbling poker professionals at Texas hold’em for a couple of years. We Read more…

By John Russell

ISC19 Cluster Competition: Application Results, Finally!

July 15, 2019

Our exhaustive coverage of the ISC19 Student Cluster Competition continues as we discuss the application scores below. While the scores were typically high, som Read more…

By Dan Olds

Nvidia Expands DGX-Ready AI Program to 19 Countries

July 11, 2019

Nvidia’s DGX-Ready Data Center Program, announced in January and designed to provide colo and public cloud-like options to access the company’s GPU-powered Read more…

By Doug Black

Argonne Team Makes Record Globus File Transfer

July 10, 2019

A team of scientists at Argonne National Laboratory has broken a data transfer record by moving a staggering 2.9 petabytes of data for a research project.  The data – from three large cosmological simulations – was generated and stored on the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF)... Read more…

By Oliver Peckham

Nvidia, Google Tie in Second MLPerf Training ‘At-Scale’ Round

July 10, 2019

Results for the second round of the AI benchmarking suite known as MLPerf were published today with Google Cloud and Nvidia each picking up three wins in the at Read more…

By Tiffany Trader

Applied Materials Embedding New Memory Technologies in Chips

July 9, 2019

Applied Materials, the $17 billion Santa Clara-based materials engineering company for the semiconductor industry, today announced manufacturing systems enablin Read more…

By Doug Black

ISC19 Cluster Competition: HPCC Deep Dive

July 7, 2019

The biggest benchmark the student warriors tackled during the ISC19 Student Cluster Competition was the colossal HPC Challenge. This is a collection of benchmar Read more…

By Dan Olds

High Performance (Potato) Chips

May 5, 2006

In this article, we focus on how Procter & Gamble is using high performance computing to create some common, everyday supermarket products. Tom Lange, a 27-year veteran of the company, tells us how P&G models products, processes and production systems for the betterment of consumer package goods. Read more…

By Michael Feldman

Cray, AMD to Extend DOE’s Exascale Frontier

May 7, 2019

Cray and AMD are coming back to Oak Ridge National Laboratory to partner on the world’s largest and most expensive supercomputer. The Department of Energy’s Read more…

By Tiffany Trader

Graphene Surprises Again, This Time for Quantum Computing

May 8, 2019

Graphene is fascinating stuff with promise for use in a seeming endless number of applications. This month researchers from the University of Vienna and Institu Read more…

By John Russell

AMD Verifies Its Largest 7nm Chip Design in Ten Hours

June 5, 2019

AMD announced last week that its engineers had successfully executed the first physical verification of its largest 7nm chip design – in just ten hours. The AMD Radeon Instinct Vega20 – which boasts 13.2 billion transistors – was tested using a TSMC-certified Calibre nmDRC software platform from Mentor. Read more…

By Oliver Peckham

TSMC and Samsung Moving to 5nm; Whither Moore’s Law?

June 12, 2019

With reports that Taiwan Semiconductor Manufacturing Co. (TMSC) and Samsung are moving quickly to 5nm manufacturing, it’s a good time to again ponder whither goes the venerable Moore’s law. Shrinking feature size has of course been the primary hallmark of achieving Moore’s law... Read more…

By John Russell

Deep Learning Competitors Stalk Nvidia

May 14, 2019

There is no shortage of processing architectures emerging to accelerate deep learning workloads, with two more options emerging this week to challenge GPU leader Nvidia. First, Intel researchers claimed a new deep learning record for image classification on the ResNet-50 convolutional neural network. Separately, Israeli AI chip startup Hailo.ai... Read more…

By George Leopold

Nvidia Embraces Arm, Declares Intent to Accelerate All CPU Architectures

June 17, 2019

As the Top500 list was being announced at ISC in Frankfurt today with an upgraded petascale Arm supercomputer in the top third of the list, Nvidia announced its Read more…

By Tiffany Trader

Top500 Purely Petaflops; US Maintains Performance Lead

June 17, 2019

With the kick-off of the International Supercomputing Conference (ISC) in Frankfurt this morning, the 53rd Top500 list made its debut, and this one's for petafl Read more…

By Tiffany Trader

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Intel Launches Cascade Lake Xeons with Up to 56 Cores

April 2, 2019

At Intel's Data-Centric Innovation Day in San Francisco (April 2), the company unveiled its second-generation Xeon Scalable (Cascade Lake) family and debuted it Read more…

By Tiffany Trader

Cray – and the Cray Brand – to Be Positioned at Tip of HPE’s HPC Spear

May 22, 2019

More so than with most acquisitions of this kind, HPE’s purchase of Cray for $1.3 billion, announced last week, seems to have elements of that overused, often Read more…

By Doug Black and Tiffany Trader

A Behind-the-Scenes Look at the Hardware That Powered the Black Hole Image

June 24, 2019

Two months ago, the first-ever image of a black hole took the internet by storm. A team of scientists took years to produce and verify the striking image – an Read more…

By Oliver Peckham

It’s Official: Aurora on Track to Be First US Exascale Computer in 2021

March 18, 2019

The U.S. Department of Energy along with Intel and Cray confirmed today that an Intel/Cray supercomputer, "Aurora," capable of sustained performance of one exaf Read more…

By Tiffany Trader

Announcing four new HPC capabilities in Google Cloud Platform

April 15, 2019

When you’re running compute-bound or memory-bound applications for high performance computing or large, data-dependent machine learning training workloads on Read more…

By Wyatt Gorman, HPC Specialist, Google Cloud; Brad Calder, VP of Engineering, Google Cloud; Bart Sano, VP of Platforms, Google Cloud

Why Nvidia Bought Mellanox: ‘Future Datacenters Will Be…Like High Performance Computers’

March 14, 2019

“Future datacenters of all kinds will be built like high performance computers,” said Nvidia CEO Jensen Huang during a phone briefing on Monday after Nvidia revealed scooping up the high performance networking company Mellanox for $6.9 billion. Read more…

By Tiffany Trader

Chinese Company Sugon Placed on US ‘Entity List’ After Strong Showing at International Supercomputing Conference

June 26, 2019

After more than a decade of advancing its supercomputing prowess, operating the world’s most powerful supercomputer from June 2013 to June 2018, China is keep Read more…

By Tiffany Trader

In Wake of Nvidia-Mellanox: Xilinx to Acquire Solarflare

April 25, 2019

With echoes of Nvidia’s recent acquisition of Mellanox, FPGA maker Xilinx has announced a definitive agreement to acquire Solarflare Communications, provider Read more…

By Doug Black

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This