The HPC Triple Crown

By Gary Johnson

November 28, 2012

The semi-annual HPC “500 list” time and its attendant fall iron horse racing season are upon us. Thanks to the hard work of the list keepers, we currently enjoy three major ones to review, compare and contrast: TOP500, Green500 and Graph 500. Each focuses on a distinct aspect of HPC – number crunching, energy efficiency, and data crunching, respectively – and together they allow us to construct our own type of Triple Crown. Since new race results were recently announced, let’s take a look at the current standings.

In racing with real horses, a Triple Crown consists of a series of three races for three-year-old thoroughbred horses. Winning all three of these races is considered to be the greatest accomplishment of a horse’s career. Various nations, where thoroughbred racing is popular, each have their own Triple Crown series. Since HPC is a global sport, we enjoy the simplicity of only having one Triple Crown: our three 500 lists – the TOP, Green and Graph 500s. How do our HPC iron horses do in competing to win this Triple Crown? Let’s review the past year’s races and then look at the Fall 2012 competition.

Last fall, strictly speaking, there was no Triple Crown winner. No single machine occupied the top spot on all three rankings, but Tsubame clearly was the best all-around performer. Of those machines competing in all three races, Tsubame ranked closest to the top overall (see Number Crunching, Data Crunching and Energy Efficiency: the HPC Hat Trick). To refresh your memories, there’s a graphic below depicting the outcome. Also, you may wish to consult the three lists – TOP500, Green500, and Graph 500 – to learn more about the machines behind the nicknames used here.

Note that three of the fall 2011 top five TOP500 computers were missing from the comparison: K Computer (#1), Tianhe-1A (#2), and Nebulae (#4). This was because they were not included in the Graph 500. However, because of the relatively low ranking of those three machines on the Green500, the outcome of the comparison was not affected.

As discussed in the previously cited article, the constraint on this three-way comparison was the population of the Graph 500 list. While there is essentially complete overlap and obvious mapping between TOP500 and Green500 machine entries, for the Graph 500 this is not the case. The Graph 500 list was and is a work in progress. The fall 2011 version contained only 49 distinct computers and did not provide any mapping of these to either the TOP500 or the Green500 list. Nonetheless, it was possible to locate at least 19 Graph 500 computers on the other two lists – the ones named in the graphic above.

It would be nice to have not only a winner of our semi-annual iron horse races, but also a Triple Crown winner as well. Perhaps there are alternative definitions of the competition that would improve the odds of this happening.

Suppose we considered both “individual” and “team” competitions and a couple of “winning” categories within each competition. For example:

Individual Triple Crown

Class A Winner: Specific machine in first place on all three lists

Class B Winner: Specific machine present on all three lists & highest average rank

So, the individual competition looks as one might expect, except we admit the possibility of a Class B winner, based on highest average rank across all three lists. This pretty much ensures an individual winner even if one machine doesn’t glean the top spot on every list. In the fall of 2011, Tsubame would have been the Class B winner.

For the team competition, suppose we looked not for a specific machine (for example, Hopper) to win but instead for a type of machine (such as the Cray XE6)? Then, since the most attention is paid to the top of the lists, we might define “winning” a particular race to be having the greatest number of that machine type in the top 10 on that list. We could also then form aggregate scores for the winners in each list race by summing across all three lists.

Team Triple Crown

Class A Winner: Machine type present in the top 10 on each list & highest aggregate score

Class B Winner: Machine type present in the top 10 on at least one list & highest aggregate score

If we review the fall 2011 500 lists using our new definitions, we find:

Individual Competition

Class A Winner: None

Class B Winner: Tsubame

The input data for the team competition are summarized in the table below. The maximum number of occurrences of a particular machine type in the top 10 for each 500 list is shown in red.

Table1

These data yield:

Team Competition

Class A Winner: Tsubame (a team with one member)

Class B Winner: IBM Blue Gene/Q

If you think that just looking at the top 10 spots on the 500 lists is too restrictive, then use your own cutoff or include the whole of each list. Designing the competition is a game anyone can play. We’ve chosen the top 10 because that part of the 500 lists seems to draw the most attention from the HPC community.

Let’s see how events played out in the summer 2012 races.

Here once again we see that the small population of the Graph 500 constrains the comparisons. To be sure, the list is expanding. The summer 2012 version contained 89 entries, which was almost twice as many as the previous list, but we were still only able to clearly identify 19 of them as being included in the other two lists. Using those 19, the comparisons are shown in the graphic below.

Individual Competition

Class A Winner: None

Class B Winner: Sequoia (by a nose over Mira)

Once again, the input data for the team competition are summarized in the yable below.

Table2

This data yields:

Team Competition

Class A Winner: IBM Blue Gene/Q

Class B Winner: IBM Blue Gene/Q

The IBM Blue Gene/Q is the summer 2012 Class A and Class B Triple Crown team competition winner. Sequoia – an IBM Blue Gene/Q system at Lawrence Livermore National Laboratory – is the Class B Triple Crown individual competition winner and also finished first on both the TOP500 and the Graph 500. Another Blue Gene/Q system beat Sequoia out for the top spot on the Green500. Sequoia finished in 20th place on the Green500, having been beaten by 19 other Blue Gene/Q systems.

Another Blue Gene/Q system – Mira, located at the Argonne National Laboratory – was nosed out by Sequoia, in a photo finish, in the individual competition. So, machines from the IBM Stables dominated the Summer 2012 competitions.

Now, on to the current race results.

In November 2012, the population of the Graph 500 list expanded fairly substantially. This version contains 124 entries, almost 40 percent more than the previous one. While we were only able to clearly identify 41 of them as being included in the other two 500 lists, this is more than twice as many as our previous comparisons contained. For consistency with those previous comparisons, we’ve taken the top 19 of those 41 and compared their rankings on all three lists in the graphic below. We’ve also maintained the same vertical axis scale used previously, for ease in viewing across all three graphics.

Fall 2012 Graph

Individual Competition

Class A Winner: None

Class B Winner: JuQueen

The input data for the team competition are summarized in the table below.

Table3

These data yield:

Team Competition

Class A Winner: IBM Blue Gene/Q

Class B Winner: IBM Blue Gene/Q

The IBM Blue Gene/Q is the fall 2012 Class A and Class B Triple Crown team competition winner. JuQueen – an IBM Blue Gene/Q system at Forschungszentrum Jülich (FZJ) in Germany – is the Class B Triple Crown individual competition winner and thus becomes the first European winner of the Class B individual competition. Also notable is that every system in the Top 10 for this Triple Crown competition is an IBM Blue Gene/Q (JuQueen through Sakura). So, once again, machines from the IBM stables dominated the fall 2012 races.

Where, in all of this, is Titan, you might ask. Well, unfortunately, Titan, a Cray XK7 and the TOP500 race winner, did not compete in the Graph 500.

We’ve summarized the results of all HPC Triple Crown competitions in the table below and highlighted the row containing the new results.

Table4

So far, no machine has won the Class A individual competition and only two machine types have won the Class A team competition – Tsubame and Blue Gene/Q. Here’s a table of those machines which have come closest to winning the Class A individual competition.

Date

Machine

Ranking on “500 List”

Average Ranking

Top500

Green500

Graph500

Fall 2010

Intrepid

13

29

1

14.3

Summer 2011

Hopper

8

42

4

18

Jugene

12

40

2

18

Fall 2011

Tsubame

5

10

3

6

Summer 2012

Sequoia

1

20

1

7.3

Fall 2012

JuQueen

5

5

3

4.3

Will some iron horse win the Class A individual Triple Crown next time, or is placing first on all three 500 lists just too hard? Will the IBM stables continue to dominate or will Titan or some other machine steal some of the glory? Will the Graph 500 continue to grow and include more of the machines on the other two 500 lists? We’ll see what happens next summer.

In real horse racing, winning the Triple Crown accords prestige to horses, their humans and stables; adds economic value to the winners and their offspring; and provides entertainment for racing fans. Our iron horse races serve just about the same purposes. So, HPC racing fans, do your own analysis of the race results, take a look at the iron horses likely to race well next time, get ready to place your bets, and enjoy the upcoming summer 2013 races!

About the Author

Gary M. Johnson is the founder of Computational Science Solutions, LLC, whose mission is to develop, advocate, and implement solutions for the global computational science and engineering community.

Dr. Johnson specializes in management of high performance computing, applied mathematics, and computational science research activities; advocacy, development, and management of high performance computing centers; development of national science and technology policy; and creation of education and research programs in computational engineering and science.

He has worked in academia, industry and government. He has held full professorships at Colorado State University and George Mason University, been a researcher at United Technologies Research Center, and worked for the Department of Defense, NASA, and the Department of Energy.

He is a graduate of the U.S. Air Force Academy; holds advanced degrees from Caltech and the von Karman Institute; and has a Ph.D. in applied sciences from the University of Brussels.

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

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

March 18, 2024

Nvidia's latest and fastest GPU, codenamed 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…

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…

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…

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…

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…

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…

Leading Solution Providers

Contributors

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…

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…

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…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire