---

Why AWS for HPC & Supercomputing?

Researchers and businesses alike have complex computational workloads such as tightly coupled parallel processes or demanding network-bound applications, from genome sequencing to financial modeling. Regardless of the application, one major issue affects them both: procuring and provisioning machines. In typical cluster environments, there is a long queue to access machines, and purchasing dedicated, purpose-built hardware takes time and considerable upfront investment.

With Amazon Web Services, businesses and researchers can easily fulfill their high performance computational requirements with the added benefit of ad-hoc provisioning and pay-as-you-go pricing. The AWS cloud computing platform allows organizations to:

• Eliminate the cost and complexity of procuring, configuring and operating expensive in-house compute clusters.
• Increase the speed of innovation and output by accessing compute resources in minutes instead of months.
• Scale compute resources up to the size and time appropriate for each workload, then shut them down when no longer needed.
  
  

---

AWS Solutions for HPC

Amazon EC2 provides resizable compute capacity in the cloud with the flexibility to choose from a number of different instance types to meet your computing needs. Each instance provides a predictable amount of dedicated compute capacity and is charged per instance-hour consumed. There are no up-front fees or long-term commitments.

Cluster Compute Instance:

The Amazon EC2 Cluster Compute instance types are specifically designed to combine high compute performance with high performance network capability to meet the needs of HPC applications. Unique to Cluster Compute instances is the ability to group them into clusters of instances for use with HPC applications. This is particularly valuable for those applications that rely on protocols like Message Passing Interface (MPI) for tightly coupled inter-node communication. Cluster instances provide low latency, full bisection 10 Gbps bandwidth between instances, they also provide specific processor architecture in their definition to allow developers to tune their applications and achieve optimal performance.

Cluster Compute Eight Extra Large specifications:

• 88 EC2 Compute Units (Eight-core 2 x Intel Xeon)
• 60.5 GB of memory
• 3370 GB of instance storage
• 64-bit platform
• I/O Performance: Very High (10 Gigabit Ethernet)
• API name: cc2.8xlarge
• Price: Starting from $2.40 per hour
  

Cluster Compute Quadruple Extra Large specifications:

• 33.5 EC2 Compute Units (2 x Intel Xeon X5570, quad-core “Nehalem” architecture)
• 23 GB of memory
• 1690 GB of instance storage
• 64-bit platform
• I/O Performance: Very High (10 Gigabit Ethernet)
• API name: cc1.4xlarge
• Price: Starting from $1.30 per hour (Linux)
  
  

The Amazon EC2 Cluster GPU instance type adds to the capabilities of the Cluster Compute instance by including two Nvidia Tesla GPUs per instance for very high computing capability using the CUDA or OpenCL programming models.

Cluster GPU Quadruple Extra Large specifications:

• 22 GB of memory
• 33.5 EC2 Compute Units (2 x Intel Xeon X5570, quad-core “Nehalem” architecture)
• 2 x NVIDIA Tesla “Fermi” M2050 GPUs
• 1690 GB of instance storage
• 64-bit platform
• I/O Performance: Very High (10 Gigabit Ethernet
• API name: cg1.4xlarge
• Price: Starting from $2.10 per hour
  
  

Cluster Compute and Cluster GPU instances are available today for Linux operating system use in the US – N. Virginia Region. If you wish to run more than 8 Cluster GPU instances, please complete the Amazon EC2 instance request form. There is no similar limit specific to Cluster Compute instances.

Cluster Compute and Cluster GPU instances require booting from an EBS-backed Amazon Machine Image (AMI) using Hardware Virtual Machine (HVM) virtualization. Information on how to create an HVM AMI and how to launch instances as a cluster can be found in the concepts sections of the Amazon EC2 Developer Guide and User Guide.

---

Get Started

1. Sign up for Amazon EC2

2. Read the Amazon EC2 Developer Guide and User Guide (see Concepts Section) to learn how to create an Amazon Machine Image (AMI) using Hardware Virtual Machine (HVM) virtualization

3. Launch instances and run your application. If you need more instances than the default (8 instances providing 64 cores), please complete the Amazon EC2 instance request form or get started by simply using one of our partner’s web-based software tools: Cycle Computing, Univa, Bright Computing, and StackIQ.

---

Related Resources

---

Customer Quotes

“Cluster Compute Instances give MATLAB users the opportunity to test and run their high performance computing problems for data-intensive applications in the cloud at a price and performance level that allows us to continually innovate and meet customer needs.”
– Silvina Grad-Freilich, Senior Manager Parallel-Computing, MathWorks

“For years we’ve helped customers build and manage the world’s most complex large-scale computing clusters, and now with Cluster Compute Instances, customers can leverage Adaptive Computing’s familiar automation software tools to manage HPC resources on Amazon’s leading cloud infrastructure.”
– Michael Jackson, COO and President, Adaptive Computing

“The high-performance networking of Cluster Compute Instances for Amazon EC2 fills an important need among scientific computing professionals, making the on-demand and scalable cloud environment more viable for technical computing”
– David Patterson, co-inventor of RAID, RISC, and several other computer innovations

The Laboratory for Personalized Medicine (LPM) at Harvard Medical School took the power of Oracle and the flexibility of AWS to develop innovative genetic testing models in record time. “The combination of Oracle and AWS allowed us to focus our time and energy on simulation development, rather than technology, to get results quickly.”
– Dr. Peter Tonellato, Center for Biomedical Informatics at Harvard Medical School