Powerful, Policy-driven Scheduling
PBS Professional accelerates job execution and selects optimal job placement across diverse, broadly distributed resources. It’s easy to create intelligent policies to manage distributed, mixed-vendor computing assets as a single, unified system. The PBS Professional scheduler is topology-aware and supports GPU scheduling.
Allocation and Budget Management
Manage budgets across your enterprise and for multiple clusters by allocating your users credits for PBS Professional workloads. Credits can be provided in one or more customizable currencies. To give you visibility into HPC usage, PBS Professional includes full reporting of credit consumption by groups and by individual users.
Forecasting and Simulation
The simulator included with PBS Professional gives you the ability to understand in detail why a job is currently queued rather than running, and to evaluate the effect of policy changes on job execution ordering. You can quickly evaluate situational issues and potential policy changes on workload execution.
Cloud Bursting and Dynamic Extension
PBS Professional comes with a built-in GUI that lets you extend your HPC resources to public and private clouds including Oracle Cloud Infrastructure, Google Cloud Platform, Microsoft Azure, and Amazon Web Services (AWS). Dynamic bursting makes it easy to manage peak-time workloads.
The hierarchical scheduler built into PBS Professional offloads the base scheduler to enable greater throughput and better license and resource utilization. Batches of short jobs are presented as one longer job while maintaining full visibility into each individual job, a common user need.
Startup is fast and reliable, even for huge MPI jobs. PBS Professional is tested at tens of thousands of MPI ranks and minimizes delays caused by faulty nodes. A highly redundant automatic failover architecture with no single point of failure means jobs are never lost, and they'll continue to run despite server failures, network failures, and even killing PBS daemons themselves.