hpc clusters

HPC Clusters

At Aspen Systems, our primary business is building and supporting custom high-performance computational clusters and solutions. We have the knowledge and expertise to deliver different types of proven, turn-key clusters built for your needs.

Our Value

Decades of successful HPC deployments across multiple industries.

Custom Built

Like most HPC vendors, Aspen Systems offers a standardized build and package selection that follows HPC best practices. However, unlike some other HPC vendors, we also provide you the opportunity to customize your cluster hardware and software with options and capabilities tuned to your specific needs and your environment. This is a more complex process than simply providing you a “canned” cluster, which might or might not best fit your needs. Many customers value us for our flexibility and engineering expertise, coming back again and again for upgrades to existing clusters or new clusters which mirror their current optimized solutions. Other customers value our standard cluster configuration to serve their HPC computing needs and purchase that option from us repeatedly. Call an Aspen Systems sales engineer today if you wish to procure a custom-built cluster built to your specifications.

Turn-Key

Aspen Systems typically ships clusters to our customers as complete turn-key solutions, including full remote testing by you before the cluster is shipped. All a customer will need to do is unpack the racks, roll them into place, connect power and networking, and begin computing. Of course, our involvement doesn’t end when the system is delivered.

Expertise

With decades of experience in the high-performance computing industry, Aspen Systems is uniquely qualified to provide unparalleled systems, infrastructure, and management support tailored to your unique needs. Built to the highest quality, customized to your needs, and fully integrated, our clusters provide many years of trouble-free computing for customers all over the world. We can handle all aspects of your HPC needs, including facility design or upgrades, supplemental cooling, power management, remote access solutions, software optimization, and many additional managed services.

Superior Service

Aspen Systems offers industry-leading support options. Our Standard Service Package is free of charge to every customer. We offer additional support packages, such as our future-proofing Flex Service or our fully managed Total Service package, along with many additional Add-on services! With our On-site services, we can come to you to fully integrate your new cluster into your existing infrastructure or perform other upgrades and changes you require. We also offer standard and custom Training packages for your administrators and your end-users or even informal customized, one-on-one assistance.

Cluster Types

AMD EPYC™ Clusters


The Zen 3 AMD EPYC™ Milan Processor offers up to 64 cores, 8 channels of DDR4-3200 memory and 128 lanes of PCIe 4 per CPU providing exceptional performance, memory bandwidth, and I/O capability for all of your HPC needs.

Learn More

Intel® XEON® Clusters


3rd Generation Intel® Xeon® Scalable Processors offers up to 40 cores, 8 channels of DDR4-3200, 64 lanes of PCIe 4 per CPU providing exceptional integer, floating point, and memory peformance for all of your HPC applications.

Learn More
nvidia logo square

NVIDIA GPU Clusters


Accelerated clusters using the latest NVIDIA A100 and A30 GPUs provide massive floating-point computational power to perform general-purpose computing, artificial intelligence, and deep learning using NVIDIA's CUDA parallel computing platform.

Learn More

AMD INSTINCT™ Clusters


AMD Instinct Accelerators leverage AMD CDNA2 architecture and AMD Infinity Fabric to deliver extreme performance. AMD CDNA2 architecture uses AMD’s new Matrix Core Engines to optimize scalar and vector compute operations. AMD Infinity Fabric provides a high bandwidth communication fabric to scale up to multiple AMD Instinct Accelerators.

Learn More

Storage Clusters


Storage Clusters are used to service larger data space requirements or to facilitate faster access speed to your data. Often configured with parallel file systems, the storage cluster can serve your organizational data access needs or integrated into your HPC cluster solution.

Learn More

AMD EPYC™ CLUSTERS

Get the highest core count for your HPC Cluster using 3rd Gen AMD EPYC (Milan) Processors

When your application depends on the maximum number of CPU cores available and memory bandwidth, the AMD Milan processors are what you need. AMD Optimizing C/C++ and Fortran Compilers (AOCC) is also available to accelerate your x86 scientific applications in your HPC Cluster, boosting productivity.

Aspen Systems is an AMD Elite partner and HPC Specialist. Let Aspen Engineers architect the best AMD EPYC cluster for your application and budget.

INTEL® XEON® CLUSTERS

Get the performance based on the 3rd Generation Intel Xeon Scalable (Ice Lake) Processors.

Intel’s Ice Lake CPUs deliver the highest performance with base clock speeds of up to 3.9GHz, and processors with up to 60MB of L3 Cache. Clustering these servers together with a high-speed, low latency interconnect and compiling with Intel’s OneAPI compiler suite will give you the performance you need for your research. In fact, Intel’s 3rd Generation Intel Xeon Scalable (Ice Lake) Processors can even run your AI and Machine Learning applications. Intel also offers Speed Select Technology (SST), Optane memory, and Virtual RAID on Chip (VROC) with these CPUs for all of your HPC needs.

Aspen Systems is an Intel Titanium partner and Intel Data Center and HPC Specialists. Let Aspen Engineers architect the best Intel Xeon cluster for your application and budget.

Nvidia GPU Clusters

Accelerate HPC and hyperscale data center workloads.

Data scientists and researchers can now parse petabytes of data orders of magnitude faster than they could using traditional CPUs, in applications ranging from energy exploration to deep learning. NVIDIA’s accelerators also deliver the horsepower needed to run bigger simulations faster than ever before. Plus, NVIDIA GPUs deliver the highest performance and user density for virtual desktops, applications, and workstations. NVIDIA A100 SXM4 systems, with NVLink and NVSwitch, enable high GPU densities to process workloads. NVIDA PCIe GPU cards, with optional NVLink, enable the flexibility to start with a limited number of GPUs and grow according to the workload.

Aspen Systems is an NVIDIA Elite Partner and GPU accelerated HPC specialist. Let Aspen Engineers architect the best NVIDIA GPU compute cluster for your application and budget.

AMD INSTINCT™ MI CLUSTERS

AMD Instinct Accelerators were built from the ground up with HPC in mind.

With the AMD CDNA2 architecture and AMD Infinity Fabric technology, the latest AMD Instinct MI200 Series Accelerators deliver the highest performance from a single server solution to your data center. The latest AMD Instinct Accelerators are the first multi-die GPU combining the power of two GPUs on one chip. Clustered together with AMD EPYC CPUs leading the way, you can have an entire cluster utilizing these Accelerators for your HPC and AI workloads.

Aspen Systems is an AMD Elite partner and HPC Specialist. Let Aspen Engineers architect the best AMD EPYC and Instinct MI cluster for your application and budget.

HPC Storage

Storage is often an afterthought in many HPC designs.

When processor speed, memory, and interconnect considerations are the only design considerations for your next purchase, you run the risk of undermining the efficiency and reliability of your HPC solution by teaming it with an inadequate or poorly matched storage solution that becomes the performance bottleneck and limiting factor in system productivity.

To that end, Aspen teams with some of the best storage providers in the business to offer you the best solution for your specific storage needs. We partner with storage solution providers who provide distinct advantages, and are the industry leaders in their specialty areas.

Our Storage Partners

Networking

Cluster Networking is the backbone of a high-performance cluster solution.

If your cluster design requires a high-speed interconnect, either InfiniBand or Ethernet can provide network solutions with higher bandwidth and low latency, providing reliable, blazing-fast performance.

HPC clusters can utilize a single Ethernet network for administrative traffic, data sharing, and application processing traffic. If your applications are bandwidth or latency- sensitive, using an additional high-speed interconnect like InfiniBand for your cluster network is preferred to ensure that critical computational and data traffic is not hampered by other traffic.

InfiniBand networking is an industry-standard, channel-based, point-to-point switched fabric interconnect for high-performance networks. InfiniBand networks provide high-bandwidth, low-latency, and reliability with failover in a scalable, high-performance network with built-in security and quality of service. InfiniBand provides a high-speed interconnect from compute nodes to storage systems.

Software Stack

Aspen Systems has decades of experience installing high-performance computing software stacks. Aspen Systems offers our proprietary command-line-driven cluster management software, Aspen Cluster Management Environment (ACME). We also provide NVIDIA’s Bright Cluster Manager, a commercial product, and many other open-source solutions such as xCAT2, Warewulf, and OpenHPC with configuration management software, monitoring capabilities, containers, and package management tools for scientific software found in supercomputers. We are very flexible and can customize these environments to fit your needs.

Operating Systems

Aspen Systems installs and integrates the latest operating system into your high-performance cluster environment. With our expertise, we can build your solution precisely to your needs, with complete reliability and recoverability. If you’re unsure which OS would be optimal for you, our staff can provide the information you need to help you choose the operating system that best fits your requirements.

red hat os
rocky linux
centos
ubuntu
suse

Cluster Management

Aspen Systems offers our proprietary command-line-driven cluster management software, Aspen Cluster Management Environment (ACME). We also provide NVIDIA’s Bright Cluster Manager, a commercial product, and many other open-source solutions such as xCAT2, Warewulf, and OpenHPC with configuration management software, monitoring capabilities, containers, and package management tools for scientific software found in supercomputers.

acme software
xcat
warewulf
bright computing nvidia
openhpc

Applications

HPC Applications are specifically designed to take advantage of the parallel nature of high-performance computational computing systems. Algorithmically designed to take advantage of high-performance architecture, these applications can be run on your compute cluster with only minor customization. Some software packages will benefit from custom compilation, but most are commercial releases and don’t allow their source code to be distributed.

Aspen can install your choice of applications onto your cluster before it ships. We will install, configure, and performance tune your applications so that you can rest assured that you get every bit of performance from your cluster. Many factors affect how your specific applications will perform, such as your choice of interconnect and processor architecture. Your Aspen sales engineer can help you discover the optimal choices for your solution.

hpc cluster applications

Compilers

High-performance cluster solutions work best when the software takes full advantage of the cluster environment. HPC optimized compiling tools are designed to optimize software for parallel-computing environments, so choosing the proper compiler is crucial to achieving optimal results. HPC technology has achieved excellent results through open-source operating systems. However, commercial compilers often offer the best possible performance results in cluster environments because these compilers are specifically suited to the processor and the architecture used in your operating environment. Our experts can help you choose the best option for your particular needs.

Schedulers and Tools

Cluster batch control systems are used to manage jobs on the system. They are essential for sequentially queuing jobs, assigning priorities, distributing, parallelizing, suspending, killing, or otherwise controlling jobs cluster-wide. SLURM is the most commonly used open-source job scheduler today. We also offer OpenPBS, Grid Engine, and other open-source solutions to fit your needs. Commercial products such as Adaptive Computing’s Moab-Torque and Altair’s PBS Professional and Grid Engine are also available. Aspen Systems has the knowledge and expertise to configure your scheduler of choice to get the uttermost efficiency out of your HPC cluster.

Managed Services

HPC Managed services for upgrades and maintenance

Managed HPC Services are a suite of professional upgrade and maintenance services we provide to our clients. Our highly trained, certified engineering team will help you manage, update and service your systems whenever and wherever you need us. Aspen Support VPN is an installable service that enables Aspen Systems HPC specialists to remote into and provide support for your cluster. Aspen Systems managed services are available in 3 packages: Standard, Total, and Flex. Additional add-on services include the following: Onsite Maintenance, Priority Shipping, Onsite Spares Service, Disaster Recovery, Vacation Service, and “Firefighters” Service. For more detailed information select the button below.

Get a Quote for a Custom Cluster

System Architecture

Compute Nodes

Storage

Interconnect

Software

Budget

Submit Inquiry

Complete the brief form below to submit your inquiry.
























    Technology Partners

    Aspen Systems Inc. maintains a close working relationship with the industry’s most innovative hardware manufacturers. We exclusively design and sell systems that use the latest and greatest components that money can buy.

    nvidia elite partner
    intel titanium partner
    amd elite partner

    Our Chassis Partners

    The latest chassis models from industry-leading providers like Gigabyte, ASUS, Tyan, and SuperMicro.

    supermicro
    gigabyte
    asus
    tyan