Variations on an Opteron Theme

By Michael Feldman

July 14, 2006

This week Sun Microsystems, Inc. introduced three new AMD Opteron-based server products targeted to the high performance computing and enterprise space: the industry's first 4-16 way x64 (64-bit x86) server, a data server that can accommodate up the 24 terabytes of internal disk storage, and Sun's new blade platform.

The three new products are part of Sun's x64 strategy to use the AMD Opteron to expand its server offerings. Last September, Sun entered the x64 space with the introduction of their 2-socket Opteron-based Galaxy servers. Even then, the company was already planning for some of the follow-on systems announced this week.
 
The new Sun Fire X4600 server is the 8-socket big brother to the 2-socket Galaxy servers.  The Opteron-based X4600 also comes in a 4-socket configuration.  By choosing either single-core or dual-core Opterons, the server can scale from a 4-way to a 16-way machine within a single 4U chassis. The X4600 will accommodate 64 GB of shared memory (up to 128 GB in the near future).

“It really is the industry's first 16-way enterprise-class system in a single chassis,” said David Lawler, Director of Product Definition and Strategy at Sun Microsystems. “It's a 4U chassis, so it's relatively dense as well.”

Sun is entering some fairly uncharted territory with it's 8-socket offering for x86-based systems. In the past, most analysts believed that the market for machines like this were rather limited. Sun appears to believe they can position the X4600 at a price point that will be attractive for high-end server customers.

“Historically, 8-socket x86 servers were 32-bit machines (so only four GB of memory) using Xeon MP — which doesn't scale that great — and were priced at a premium,” said Lawler. “[The analysts] were right; there was no market for that. We're actually pricing ours at the 4-socket space, not at the premium price.”

No other Tier 1 vendors are in the x86 8-socket space right now. For example, HP will point customers to their Itanium-based Integrity line if they want something over 4 sockets. But Sun is willing to follow Opteron scalability right into the high-end SMP space. Currently, the architecture supports eight sockets, so that's where Sun is today.

Outside of high performance computing space, the server is destined for database and enterprise consolidation. Within HPC, the X4600 is targeted for Electronic Design Automation (EDA), CAD/CAM applications, and other compute-intensive workloads requiring that can make use of large amounts of shared memory.

It is also suited for scaled out supercomputer platforms. The Tokyo Institute of Technology TSUBAME machine, announced this past May, is actually made up of 655 X4600 servers. The TSUBAME achieves 38 teraflops (sustained), making it the 7th fastest computer in the world based on the Linpack benchmark. It has a total of 10,480 Opteron cores and 21 TB of RAM. All X4600 servers in the Tokyo Tech machine are 8-socket configured. Because Sun designed the CPU/memory modules as upgradable, the TSUBAME machine can expand its computational performance by plugging in quad-core Opterons when they become available next year. To learn more about the TSUBAME supercomputer, read the interview with Professor Satoshi Matsuoka, of the Tokyo Tech's Global Scientific Information and Computing Center, in this week's issue.

In addition to the 600-plus X4600 servers in TSUBAME, the Tokyo Tech machine also incorporates a number of X4500 Sun Fire servers. The X4500, which was also officially introduced this week by Sun, is characterized as a data server, combining Opteron computation with a large amount of integrated SATA storage.  Each 2-socket (4-way) server can accommodate up to 24 TB of data. The TSUBAME machine has 42 such servers for a total of 1.1 petabytes of storage.

Lawler said the X4500 was designed to consolidate the functionality of a server, a SAN switch and a large number of storage arrays. It boasts disk-to-memory sustained data rates of 2 GB/sec, which makes it suited for HPC applications requiring high levels of I/O throughput. In the enterprise it is targeted for data warehousing/business intelligence, digital media streaming and digital surveillance.

“We're calling it the world's first hybrid data server — admittedly a marketing term,” said Lawler. “But it is really a hybrid of server and storage technology.”

The third product announced this week by Sun is their new blade — the Sun Blade 8000 Modular System. The system supports up to ten 4-socket dual-core Opteron blades in a 19U chassis. Sun claims it is the only blade based on industry-standard PCI Express I/O, and the only one with hot-pluggable I/O.  Lawler said it is also designed to be used as a replacement for rackmount servers, offering better energy efficiency and serviceability. The Sun Blade 8000 is targeted for high-throughput computing, such as would be required in many HPC applications.

“Compared to other blade offerings on the market or even compared to other rackmount offerings on the market, we have vastly more I/O in the Sun Blade 8000,” said Lawler. “Each blade has 192 Gbps of I/O. Compared to even other rackmount servers today, that's a lot. It's 2x compared to any other blade offering on the market.”

According to Lawler, the system was designed to scale up to quad-core processors and beyond (along with the associated increase in memory capacity) when that technology becomes available. The rationale behind the upgradability is to give the system a certain amount of longevity not found in competing blades.

“We're going multi-core in a big way; the whole industry is,” said Lawler. “And when you get up to 8-core and 16-core you're going to need a lot more memory and a lot more I/O. Well, memory turns into real estate. If you don't have the real estate on your blade to be able to handle all those DIMMs, you can't put it anywhere, so it doesn't work. We have all that in the Sun Blade 8000. We will also be coming out with a denser chassis, just for HPC.”

The Sun Blade 8000 differs in one fundamental way from most other blade designs — there is no I/O on the individual blades. Other vendors have integrated Ethernet, Fibre Channel or InfiniBand into the blades themselves.  Sun's approach was to use raw native PCI express running right off the blade.

“So I/O becomes an attribute of the chassis,” said Lawler. “Any blade can go into any chassis and it simply works.”

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