First Details Emerge from Cray on Trinity Supercomputer

By Nicole Hemsoth

July 10, 2014

Note – 7:32 p.m. Eastern: We have full details from Los Alamos about the system in a detailed update article.

Cray has been granted one of the largest awards in its history for the long-awaited “Trinity” supercomputer. This morning the company announced a $174 million deal to provide the National Nuclear Security Administration (NNSA) with a multi-petaflop next generation Cray XC machine, complemented by an 82 petabyte capacity Cray Sonexion storage system. The goal of the new super is set to contend with the agency’s nuclear stockpiles, simulating everything from continued maintenance, degradation, and even destruction of the vast reserves, as well as hosting a wealth of classified national security applications.

The original proposal for the system suggest a need for a machine capable of up to 30 petaflops, and it looks like this might not be unrealistic given what we know about the architectural choices and the amount Cray inked into their revenue for the year today—causing a decent uptick in their stock price and tipping them into billion-dollar valuation territory.

The system will be powered by what sounds like a relatively balanced combination of future-generation Haswells (we’re guessing between 14-18 cores) and future Knights Landing processors (60+ cores), which represents a strategy that’s driven by a clear sense of NNSA application and simulation goals. We’ll do some speculative math in the coming week or so about what this system might actually look like since nothing has been released FLOPS or otherwise, but given so many unknowns in terms of final core counts of the Haswell and Knights Landing as well as pricing, we want to take our time on those guesses. But the early look we got with the formal announcement and our conversation with Cray denotes this is going to be core-heavy, FLOPS-centric powerhouse, even if it doesn’t meet the high-end 30 petaflop target.

Following a conversation this morning with Cray’s Barry Bolding, we learned there are two major phases in the deployment leading up to the acceptance testing late next year or into the following year, which is likely determined by Intel’s delivery of the new Xeons and Knights Landing chips versus any delays on Cray’s part. What’s interesting is that it sounds like it’s a balanced system between the two core types.

Bolding says that the processor updates are a defining factor in the next generation of their XC rather than an entirely new system set driven by custom engineering of the entire system’s interconnect, cooling, or other components. He does note that in the new generation of XC machines there has been extensive work done to support the large number of new Intel cores within the software stack, and ostensibly in their Sonexion storage to support the tiered storage demands for using burst buffers in novel ways. The idea, he says, is to make machines that are ready to roll into large deployments like this and the NERSC system instead of custom engineering systems based on particular user requirements.

“It’s hard to build these reproducible products at this scale that multiple sites agree they can all use. Our philosophy is to create these massive production systems and it’s good that we don’t have to custom design each one. There’s going to be an evolution of the software stack and new features we’re not talking about today, but there will be innovations—and that’s another reason it’s a multi-phased approach.”

“Each phase is significant in size—the first will predominantly be the next-generation Haswell processors, followed by the Knight’s Landing piece in a later phase.” They’re both major parts of the installation, one isn’t much larger than the other.

Other systems that are set to come online in the next year and a half may be reliant on more novel, diverse architectures, but with a very specific, known set of users and projects, it’s clear that the NNSA had a direct sense of how the additional cores (and presumably on-package memory of Knight’s Landing) would translate directly into meaningful results.

The system choice was driven by the need to secure a mixed workload system, hence the processor choice of both Knight’s Landing and Haswell cores (compared to the NERSC “Cori” supercomputer that Cray is building which is predominantly next-generation Knight’s Landing based). “The binary compatibility in their Xeon line is a Knight’s innovation when you want to do heterogeneous types of problems across different types of processors. It’s not super-unique, but it’s interesting that they want to do this at such large scale,” said Bolding.

NERSC’s system and Trinity are both XC systems, but these are different workloads with different mandates. NERSC has a broad user base as an open science DoE system serving thousands of applications and hundreds of users. The Trinity system will be used for more targeted weapons stockpile-related workloads.” He says it shows that the XC systems can be diverse enough to support both distinct user types and beyond.

Aside from the sheer core thrust from the Intel processors, one of the more interesting elements of the upcoming machine is the storage. Bolding says they wanted a very large, powerful Lustre environment and Sonexion met those requirements. We’ll be bringing more details on the burst buffer and general storage component later today following a conversation with one of the leads on that front at Los Alamos but for now, we have some initial details from Cray.

“Tiered storage (and burst buffers are a particular tier) will be more important for customers like this in the future but there is real interest in more than just Lustre at other tiers. We are working to develop this in multiple tiers to support these needs,” said Bolding.

This is among the largest deals in Cray’s history. The company had a multi-year DARPA contract valued initially at $250 million in 2006, although the final contract was closer to the amount of the Trinity system. The Blue Waters procurement, as tangled as it might have been in 2011, was around $200 million, and at Oak Ridge, other similar deals in terms of dollar value were secured. Still, this represents one of the top contracts for Cray—and we’re just getting into swing with procurement news, which will pick up now that there is clarity around when the latest Intel processors will roll out—something that undoubtedly is driving procurement timelines across the board.

The new supercomputer will be housed at Los Alamos National Laboratory and is part of a joint effort between the New Mexico Alliance for Computing at Extreme Scale (ACES), based at LANL, and Sandia National Laboratories’ NNSA Advanced Simulation and Computing Program (ASC).

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!

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…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

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…

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