Are We Already in the HPC On-Demand Era?

By Miha Ahronovitz

July 23, 2010

Faith is the evidence of things not seen.

Therefore, under this definition, we must believe Amazon offering of a configuration made up of actual physical processor instances, not virtualized ones, that gets a #146 ranking on TOP500 for a cool $8M to $12M per year.

Quote:

“Each Cluster Compute Instance consists of a pair of quad-core Intel ‘Nehalem’ X5570 processors with a total of 33.5 ECU (EC2 Compute Units), 23 GB of RAM, and 1690 GB of local instance storage, all for $1.60 per hour.”

“We ran the gold-standard High Performance Linpack benchmark on 880 Cluster Compute instances (7040 cores) and measured the overall performance at 41.82 TeraFLOPS using Intel’s MPI (Message Passing Interface) and MKL (Math Kernel Library) libraries, along with their compiler suite. This result places us at position 146 on the TOP500 list of supercomputers.”

Are we already in the HPC on demand era? I contend that yes, we are getting there but that there are some details to fix. Robert Jenkins, co-founder CloudSigma comments on the Cluster Compute instance:

“The biggest bottleneck for high performance computing is disk performance…. Adding 10Gbps networking will help, but will not solve the constraint of having remote SAN storage from the computing. Infiniband is much lower latency than 10 Gbps networking if this really is your bottleneck.”

For now, the Amazon Web Services Compute Cluster Instances the offer is restricted geographically to the Northeastern US and Virginia. CloudSigma offers a similar configuration to customers in Europe.

 
Amazon
CloudSigma
Cluster Instance
– 23 GB of memory
– 33.5 EC2 Compute Units (2 x Intel Xeon X5570, quad-core “Nehalem”
architecture)
– 1,690 GB of instance storage
– 64-bit platform
– I/O Performance: Very High (10 Gigabit Ethernet)
API name: cc1.4xlarge
– 32GB of RAM
– 20GHz CPU (with user definable cores up to 10 for multi- threading)*
– 1,690 GB of persistent storage per drive with up to 4 drives per instance
– 64bit or 32bit with fully user controlled operating system
– local storage on fast 2.5inch disks in RAID6 (with battery backed hardware RAID cards)

* Based on AMD X4

Price
On Demand
(Burst)
$1.60 per hour
5 instances is $8:00 per hour
No discount for volume
Amazon Price List
$0.60 to $1.98 per hour
Price for 5 instances:
$3.02 to $9.92 per hour, low peak and high peak respectively
Subscription Pricing
$4,290 (1 yr) to 6,590 (3 yr) upfront plus $0.56 per hour
No upfront fees
$1.29 per hour,
Coverage
North East US and Virginia
Switzerland and Western Europe
Bandwidth
$0.15 per GB outgoing
$0.15 per GB data in
$0.06 per GB outgoing
Free unlimited bandwith data in

 

What is interesting here is that Amazon is a global behemoth company and CloudSigma is a recent startup. They are not unique, yet it is worth mentioning. For now they don’t even compete, as their services are in different geographies. One day they will, and it is nice to see that HPC customers have alternatives.

Chris Dagdijian from Bio-Team – the company that offers professional services to implement for their clients in bio-science and financial services HPC applications on Amazon, has this comment the AWS Compute Cluster Interface:

“Performance of the root/boot disk is way slower than any other type of block based storage. This is to be expected as the boot disk (even though it comes via an EBS-resident AMI) does not get the benefit of paravirtualization acceleration. The take home message is that the boot/root disk volume should not really be used for anything. This also means that this blog post showing how to increase the size of the local OS disk is useful only for playing around and not for anything serious.”

It seems the solution to slow boot disk access is adding para-virtualization drivers and the pressure from customers like bio-team may implement these changes on Amazon. Meanwhile Bio-Team possible remedy is described here:

“Future BioTeam cluster building practices may use the ~800GB of ephemeral storage to service a NFS or parallel file-system that offers input data to pipelines running on EC2 compute farms. Since we can’t trust ephemeral storage for anything unique we’d have a second shared file-system (backed by EBS) to handle capturing pipeline results.

Obviously there is one other comparison to make — how do these performance numbers measure against the 1-disk. 4-disk and 8-disk EBS RAID0 stripe sets that we’ve been testing all week?”

The possibility of double shared file system makes the use of Compute Cluster Instances not trivial and any company adopting the HPC in demand will contract expert independent services. Bio-Team makes this statement to differentiate themselves from web and database developers

We are bioinformatics and HPC types specializing in life sciences, not people trying to build the next Twitter or Facebook. What we care about when it comes to AWS performance may not be what YOU care about. In particular there is a ton of Internet information concentrating on methods for speeding up random IO access patterns on AWS. In our work, however, we seem to be more bound by the speed of long sequential reads (and sometimes writes). Parallel and serial scientific/HPC computing is different from building giant websites or databases.

Note that CloudSigma are offering fast RAID 6 storage in their bundle.

The availability of options available for Compute Cluster Instances is a positive aspect of the offering. Having some hiccups is part of the early adopters game, and final results will pay. All asperities will be nicely taken care of and probably the prices will come down.

What it counts in the end is how many customers use the solution implemented in AWS, Cloud Sigma and others. Allow me to paraphrase David Chernicoff blog from Zdnet:

“For the long term, everybody on the backend playing nice will be much more beneficial to cloud consumers than the same type of religious war that tends to crop up anytime you get Mac, Windows, and Linux users together in the same place. As much as zealots like to think that their personal opinion really matters, most of the business world just doesn’t care what operating system or application is being run, as long as it aids them in getting their work done and doesn’t impede them.

So whether the cloud application that is driving the business forward is running on OpenStack, Azure, VMware, RedHat Enterprise, or CP/M isn’t an issue to consumers of cloud services. Results are all that matter.”

This is the final reward for those – basically all readers of HPC Cloud – who had faith in HPC on demand.

Miha Ahronovitz is the Principal of Ahrono Associates. The company addresses the issues that 90% of the corporate software products fail to reach the initial goals. Ahrono specializes in cloud software products and business models. It manages the process to deliver products that users and clients really want. Miha was managing the Product Strategy and Business Development, HPC Grid and Cloud Computing at Sun Microsystems. He was also the executive product manager for Sun Grid Engine, now re-named Oracle Grid Engine. After Sun merger with Oracle in February 2010. he founded Ahrono Associates with two other Sun seasoned partners: Gregory Shirin and Kuldip Pabla.

Miha is also one of founders of Gridware, the start-up company acquired by Sun in 2000. Gridware flagship product was Codine, that later became, Sun Grid Engine. Miha’s blog, The Memories of a Product Manager is popular in the cloud computing community. His blogs on “Making big money with Hadoop” and “New HPC Compute cluster Instances” have resonated well with HPC cloud-oriented readers.

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