SchedMD is the core developer and services provider for Slurm providing support, consulting, configuration, development and training services to accelerate workloads and results across cloud and on-prem clusters with proven best practices and innovation. SchedMD offers 5-10x more complex HPC & AI scheduling expertise, including half of the biggest systems in the TOP500, to optimize the speed, throughput and resource consumption for organizations unique workload mix so public sector organizations can focus on getting to results faster and easier.

Slurm is a free open-source workload manager designed specifically to satisfy the demanding needs of high performance computing (HPC), high throughput computing (HTC) and AI. Slurm® is the industry-leading workload manager for large-scale, complex workloads in the cloud with faster processing and optimal consumption of the specialized resource capabilities needed for each workload. Slurm maximizes workload throughput, scale, reliability, and results in the fastest possible time, managing workloads across cloud and on-prem clusters.

SchedMD and AWS have collaborated to optimize Slurm for AWS HPC infrastructure, integrating it with AWS ParallelCluster so you can leverage its ease of deployment, autoscaling, and management for HPC clusters. Slurm manages all your large, complex workloads across cloud and on-premise resources. The combined Slurm and ParallelCluster solution enables migration of existing HPC workloads to AWS with little or no modifications and provides streamlined bursting and hybrid workload management across on-prem and cloud environments for the most cost-effective operations. Slurm workload manager for AWS is optimally deployed via AWS ParallelCluster using the easy install and configuration instructions provided in the user guide, see the cluster section scheduler area for Slurm information.

Annual services subscription includes:

• Consulting and implementation support expertise to increase throughput 5-10x and consumption efficiency 30-40%, especially for massive scale workload and resources.
• Support services to ensure cloud cluster workload management configuration continually processes workload at peak levels as mix and scale evolves, delivering 20-30% improved uptime for critical workloads.
• Unique support expertise spanning software engineering, Slurm development, computer engineering, systems administration, and cloud experience to improve issue resolution speed and quality 3-5x.
• Tailored Slurm and cloud workload expertise training that empowers users on harnessing Slurm capabilities, including new robust innovations driven by the strong Slurm community and industry partnerships, helping to speed cloud-based projects and increase adoption. A 2-day remote training package is included with the option to purchase an upgrade to a 3-day onsite training package if that better fits organizational needs.