NetworkComputer™ : High-Performance Job Scheduler

NetworkComputer™ is an enterprise-grade high-performance job scheduler, otherwise known as a batch processing system or a distributed resource management system (DRMS). NetworkComputer™ provides a cost-effective solution for distributing an IT workload over any compute farm (cluster) topology.

NetworkComputer™ is capable of managing farms with many thousands of processors, with instantaneous workloads in excess of 2 million jobs, and throughput of millions of jobs per day. At such high loads, the response time of the scheduler remains below one second and the memory footprint of the central server remains below 2GB.

Powerful Capabilities

  • Extremely fast: event-driven design provides sub-second latency for scheduling jobs; very efficient for short jobs
  • Built-in integration with a variety of license managers(e.g. FLEXlm™, RLM™, IBM LUM™, etc ...)
  • MultiQueue: supports the sharing of licenses across multiple geographical sites
  • Preemption (including over MultiQueue)
  • Job profiling (see how a job uses computing resources over its life span)
  • Monitors out-of-queue license usage by users, and adjusts in-queue license availability accordingly
  • Comprehensive description of resource requirements for each job, including detailed license and hardware requirements
  • Environment management mechanism for setting up projects and tools
  • Comprehensive reporting of workload, waiting times, unmet demand
  • Visualization of compute farm and job status and utilization
  • Web browser UI (integrated web server), CLI, and GUI provide flexible ways of using NC
  • Full-access Tcl-based extension language provides scriptability and automation

Maximize License Utilization

Impact of NetworkComputer on license utilization A chip design company had a farm with about 100 cpus and 100 simulator licenses and could not get the overall utilization of their license above about 80% using their conventional scheduler.  After moving to NetworkComputer™ , they immediately reached close to 100% utilization of those licenses, thus justifying further investments in both hardware and software. They now run in excess of 1,000 licenses on a much larger farm, with sustained utilization of those licenses above 98.6%.

See a real world use of NetworkComputer

SANDisk has recently published a white paper on their usage of NetworkComputer

HPCWire Interview at SuperComputing 2011

Migration to NetworkComputer™

While there are other commercial-grade job schedulers on the market, we claim ours provides the most cost-effective, feature complete solution, with excellent support included. The advantages of NetworkComputer™ over other schedulers are:

  • Higher throughput due to event-driven scheduling design
  • Easy installation, configuration, and management
  • Natural integration with license managers
  • More complete fairshare and preemption support
  • MultiQueue (allocation of licenses across multiple sites)
  • Dynamic visualization of workload


NetworkComputer™ datasheet