SciNet—University of Toronto

Overview

The University of Toronto's SciNet Consortium provides resources to the university's scientific researchers and ten affiliate research hospitals.

• 4,000-server IBM System x iDataPlex supercomputer
• 30,000 Intel Xeon 5500 cores
• 10 times more powerful than any other system in Canada

Challenge

SciNet had to show it could meet strict budgets for ongoing energy use and needed to provide multi-OS provisioning capabilities to meet the needs of its wide range of users.

Solution

Moab Adaptive HPC Suite™ from Adaptive Computing and open-source xCAT from IBM

Results

Moab's on-demand multi-OS provisioning capability allows users to choose their preferred OS on login or to make their OS choice part of their automated job template, and 10 or more flavors of Linux often run simultaneously in the system.

The Moab-xCAT solution delivers a two-to-three-times increase in performance while reducing power consumption by 30-40 percent.

View Complete Customer Case Study - PDF (8½x11) (A4)

View Press Release

Return to Menu of Customer Profiles