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
For decades, Aspen Systems has delivered customizable, turnkey HPC solutions backed by expert engineering and industry-leading support. From fully integrated clusters to long-term infrastructure management, we provide reliable, scalable systems tailored to each customer’s unique performance and operational needs.
Aspen Systems designs high-performance AMD EPYC HPC clusters powered by 5th Gen AMD EPYC processors, delivering exceptional core density, memory bandwidth, and optimized application performance. As an AMD Elite Partner and HPC Specialist, we build scalable solutions tailored to your workload, performance goals, and budget.
Aspen Systems delivers Intel Xeon HPC clusters powered by Intel Xeon 6 processors, combining high core counts, fast clock speeds, and advanced technologies for AI, machine learning, and research workloads. As an Intel Partner and HPC Specialist, we engineer scalable cluster solutions optimized for your performance needs and budget.
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 H200, B200, and B300 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 Accelerators were built from the ground up with HPC in mind.
With the AMD CDNA3 architecture and AMD Infinity Fabric technology, the latest AMD Instinct MI300 Series Accelerators deliver the highest performance from a single server solution to your data center. The latest AMD Instinct Accelerators support a broad range of precession capabilities from INT8 and FP8 to FP64 for HPC. Clustered together with AMD EPYC CPUs leading the way, you can have an entire cluster utilizing these AMD for your HPC and AI workloads.
For HPC Storage, remove the IBM Spectrum Scale logo and have them in this order (to match our storage page) DDN, VAST, BeeGFS, Weka, VDURA
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
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.
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 Base Command 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.
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.
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.
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.
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.
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.
The Future of HPC Is Liquid Cooled
Here at the dawn of Exascale, HPC components are running hotter than ever, increasing energy requirements across the board to match the demand for ever-greater performance and density.
Today, liquid cooling technologies are more robust than ever before, providing incredible efficiency, serviceability, and temperature control at scales and price points that most data centers can’t afford to ignore anymore. You no longer need to build a completely new data center to experience the benefits of liquid cooling – new developments in cold plate and in-rack CDU technologies have made liquid cooling more accessible than it has ever been.
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.
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.
The latest chassis models from industry-leading providers like Gigabyte, ASUS, Tyan, and SuperMicro.
The most common plug/receptacle types you will encounter in North America are:
CoolingTo figure out which size unit is best for your cooling needs:
