Close this search box.

TrinityX: a hugely scalable, Open Source management system for HPC, AI and Data cluster environments

ClusterVision’s TrinityX management software provides 24/7 oversight for your HPC&AI environments, offering a support system that is both dependable and SLA-compliant. This setup allows you to focus entirely on your research, leaving the monitoring and handling of complex technologies like Linux, SLURM, CUDA, InfiniBand, Luster, and Open OnDemand to us. 

In an era where AI and High-Performance clusters demand efficiency and effectiveness, facing challenges like GPUDirect and InfiniBand, TrinityX Cluster Manager emerges as a sleek, open-source (GPL3) tool crafted by ClusterVision. It streamlines the management of the cluster infrastructure, allowing you to add additional features and applications such as Kubernetes and Singularity in a user-friendly environment for the deployment, surveillance and scaling of HPC & AI clusters. Designed to cater to academic environments, startups, and large enterprises – scaling up to 1000s of nodes – TrinityX stands as a solid choice for managing your AI & HPC environment. 

TrinityX Cluster Manager Key Features

Seamless Secure Cluster Deployment

TrinityX streamlines cluster deployment through its intuitive interface, offering a straightforward setup process. It guides users with a step-by-step approach to configure clusters for diverse uses like container orchestration, traditional HPC, and InfiniBand/RDMA architectures. Leveraging the BitTorrent protocol allows rapid deployment of AI/HPC nodes, accommodating your setups in minutes. 

Centralized Cluster Monitoring & Reporting

Monitoring cluster health and performance is crucial for ensuring smooth operations. TrinityX offers a comprehensive dashboard that provides real-time insights into cluster metrics, resource utilization, and workload distribution. With this information at your fingertips, you can identify bottlenecks, optimize resource allocation, and proactively address issues before they impact your business.

Efficient Power Resource Management

TrinityX empowers you to manage cluster resources, optimize utilization, and minimize waste effectively. The manager enables dynamic resource scaling based on workload demands, ensuring your clusters always operate at peak efficiency. With TrinityX, you can easily allocate resources, set resource quotas, and automate resource provisioning, saving time and reducing administrative overhead.

Advanced Scheduling and Load Balancing

TrinityX incorporates advanced scheduling and load-balancing algorithms, allowing you to distribute workloads across your cluster effectively; the manager intelligently assigns tasks based on available resources, ensuring optimal performance and preventing resource contention. By intelligently balancing the load, TrinityX improves cluster efficiency and reduces response times, enhancing user experiences. TrinityX supports SLURM, (open)PBSpri & Moab.

Extensible and Open-Source

TrinityX is an open-source non-blocking cluster manager, providing the flexibility and extensibility you need to meet your unique requirements. With its modular architecture, you can easily customize and extend the functionality of TrinityX to integrate with other tools and systems in your tech stack. Additionally, the open-source community ensures continuous development and support, guaranteeing a reliable and evolving solution. 

Full Storage Monitoring & Managed Services

TrinityX supports all common HPC parallel file systems, such as Lustre, IBM Spectrum Scale (GOFS), and BeeGFS. TrinityX is also an enablement for a Management Spport frameworking enabling, SLA-driven, Remote System Administration, which enables you to focus on research fully, leaving the monitoring and handling of complex technologies like Linux, SLURM, CUDA, InfiniBand, Luster, and Open OnDemand to us.

TrinityX Cluster Manager Support Levels

Remote Sytem Administration by ClusterVisionTrinityX + Linux HPC/AI SupportTrinityX Support ++TrinityX
SupportProactive supportEnhanced supportStandard supportSelf-managed
Time to Respond4 Hours (BH)Next business dayNext business day1 week
Support & Discussion ChannelTicket portal, Microsoft TeamsTicket portal, Microsoft TeamsTicket portalGitHub
TrinityX Code SupportFully includedFully includedFully includedFully included
OnDemand TrinityX Cluster Management PortalFully includedFully includedFully includedFully included
OpenHPC & OpenOnDemand TrinityX IntegrationFully includedFully includedFully includedFully included
GPUs, InfiniBand & OpenHPC Tooling: CUDA, ROCm, SLURM & MPIFully IncludedFully includedLimited to 8h p/yCommunity Support
Expert Linux Support with ClusterVision Remote Login AssistFully includedFully includedLimited to 8h p/yNot included
Health-Check & Installation SupportFully includedFully includedFully includedNot included
Diagnostics, TroubleshootingFully includedFully includedNot includedNot included
Proactive / Pre-emptive Monitoring & Issue SolvingFully includedNot includedNot includedNot included
Monthly or Quarterly ReportingFully includedNot includedNot includedNot included
Parallel File System Installation, Tuning & SupportOptional service at extra costOptional service at extra costCustomerCustomer
End-User Application Integration, Tuning & TestingOptional service at extra costOptional service at extra costNot includedNot included
Data Backup Design, Integration & SupportOptional service at extra costOptional service at extra costNot includedNot included
In-depth Admin & User TrainingOptional service at extra costOptional service at extra costNot includedNot included
Capacity Planning / User Application BenchmarkingOptional service at extra costOptional service at extra costNot includedNot included

Our Open-Source Stack

luna 2019

Luna is a bare-metal provisioning tool that employs the BitTorrent protocol to provision nodes. As such, every booting node helps the others to boot. It delivers full images of operating systems and not a ‘recipe’ for configuring one. It also dramatically speeds up installation time and reduces administrative efforts. Within ClusterVision, we enable our engineers and developers to work on personal projects that often lead to new insights and innovative solutions. Luna was originally developed by one of our engineers in his free time and was later incorporated into TrinityX. We encourage this to advance the technology behind HPC further.

Ansible circle

TrinityX features Ansible for central configuration management and streamlines automation of tasks like software updates and implementation of services. A powerful tool to increase efficiency.

GitHub logo

TrinityX is a fully open-source HPC platform, At ClusterVision, we believe free exchange of ideas leads to a better result. In this spirit, we rely on open-srouce tools when building software features and have opened up our codebases for collabotration on GitHub. You can find the repository for TrinityX on GitHub

GitHub Repository