Solutions to Enterprise High Performance Computing Challenges
While all high performance computing systems (HPC) face challenges in workload demand, workflow constraints, resource complexity, and scale, enterprise HPC systems face more stringent challenges and expectations. Enterprise high performance computing systems must meet mission-critical and priority HPC workload demands for commercial businesses and business-oriented research and academic organizations. The Enterprise has requirements for dynamic scheduling, provisioning and management of multi-step/multi-application services across HPC, cloud and big data environments. Their workloads directly impact the revenue, product delivery and organizational objectives.
Enterprise HPC systems must process intensive simulation and data analysis faster, more accurately and most cost effectively to accelerate insights. By improving workflow and eliminating job delays and failures the business can more efficiently leverage data to make data-driven decisions to achieve a competitive advantage. The Enterprise is also seeking to improve resource utilization and management efficiency across multiple heterogeneous systems. To speed the time to discovery, user productivity must increase, making it easier to access and use HPC resources as well as to expand to other clusters as workloads demand.
Enterprise-Ready HPC Workload Management
Moab® HPC Suite – Enterprise Edition accelerates insights by unifying data center resources, optimizing the analysis process and guaranteeing services to the business. Through increased productivity, automated workload uptime, and consistent SLAs, Moab 8.0, for HPC systems and HPC cloud, continually meet enterprise priorities. It uses the battle-tested and patented Moab intelligence engine to auto¬matically balance the complex, mission-critical workload priori¬ties of enterprise HPC systems. Enterprise customers benefit from a single integrated product that brings together key Enterprise HPC capabilities, implementation services and 24/7 support. This speeds the time to discovery for the business with new use cases that including:
- OpenStack integration to offer virtual and physical resource provisioning for IaaS and PaaS
- Performance boost to achieve 3x improvement in overall optimization performance
- Advanced workflow data staging to enable improved cluster utilization, multiple transfer methods and new transfer types
- Advanced power management to reduce energy cost by 15-30% with clock frequency control and additional power state options
- Enhanced web-based graphical user interface for administrators to offer new reporting and monitoring capabilities
Moab® HPC Suite – Enterprise Edition accelerates insights by achieving more accurate results delivered faster from HPC resources at lower costs by increasing overall system, user and administrator productivity. Moab provides the scalability, 90-99 percent utilization and simple job submission that is required to maximize productivity, ultimately speeding the time to discovery aiding the enterprise in achieving a competitive advantage due to their HPC systems.
Enterprise use cases and capabilities include the following:
- Massive multi-point scalability to accelerate job response and throughput, including high throughput computing
- Workload-optimized allocation policies and provisioning to get more results out of existing heterogeneous resources and reduce costs, including tailored topology-based allocation
- Unify workload management cross heterogeneous clusters to maximize resource availability and administration efficiency by managing them as one cluster
- Optimized, intelligent scheduling packs workloads and backfills around priority jobs and reservations while balancing SLAs to efficiently use all available resources
- Optimized scheduling and management of accelerators, both Intel® Xeon Phi™ and GPGPUs for jobs to maximize their utilization and effectiveness
- Simplified job submission and management with advanced job arrays, self-service portal, and templates
Job and resource failures in enterprise high performance computing systems lead to delayed results, missed organizational opportunities, and missed objectives. Moab HPC Suite – Enterprise Edition intelligently automates workload and resource uptime in the HPC system to ensure that workload completes successfully and reliably, avoiding these failures and guarantee services are delivered to the business. The Enterprise benefits from these features::
- Intelligent resource placement to prevent job failures with granular resource modeling to meet workload requirements and avoid at-risk resources
- Auto-response to failures and events with configurable actions to pre-failure conditions, amber alerts, or other metrics and monitors
- Workload-aware future maintenance scheduling that helps maintain a stable HPC system without disrupting workload productivity
- Real-world expertise for fast time-to-value and system uptime with included implementation, training, and 24×7 support remote services
Moab HPC Suite – Enterprise Edition uses the powerful Moab intelligence engine to optimally schedule and dynamically adjust workload to consistently meet service level agreements (SLAs), guarantees, or business priorities. This automatically ensures that the right workloads are completed at the optimal times, taking into account the complex number of using departments, priorities and SLAs to be balanced. Moab provides:
- Usage accounting and budget enforcement that schedules resources and reports in line with resource sharing agreements and precise budgets (i.e. usage limits, usage reports, and dynamic fairshare policies)
- SLA and priority polices that make sure the highest priority workloads are processed first (i.e. Quality of Service hierarchical priority weighting)
- Continuous plus future scheduling that ensures priorities and guarantees are proactively met as conditions and workload changes (i.e. future reservations, pre-emption, etc.)
The benefits of a traditional HPC environment can be extended to more efficiently manage and meet workload demand with the multi-cluster grid and HPC cloud management capabilities in Moab HPC Suite – Enterprise Edition. It allows you to:
- Self-service job submission portal enables users to easily submit and track HPC cloud jobs at any time from any location with little training required
- Pay-for-use showback or chargeback soactual resource usage is tracked with flexible chargeback rates reporting by user, department, cost center, or cluster
- On-demand workload-optimized node provisioning dynamically provisions nodes based on policies, to better meet workload needs.
- Manage and share workload across multiple remote clusters to meet growing workload demand or surgesby adding on the Moab HPC Suite – Grid Option.
Managing the World’s Top Systems, Ready to Manage Yours
Moab manages the largest, most scale-intensive and complex high performance computing environments in the world. This includes many of the Top500, leading commercial, and innovative research HPC systems. Adaptive Computing is the largest supplier of HPC workload management software. Adaptive’s Moab HPC Suite and TORQUE rank #1 and #2 as the most used scheduling/workload management software at HPC sites and Adaptive is the #1 vendor used across unique HPC sites. [1,2]
 According to the IDC HPC End-user Study of System Software and Middleware in Technical Computing, 2013
 According to the 2012 HPC Site Census Survey: Middleware, December 2012, by Intersect360 Research