Menu:




Latest News

07-Jun-2010 :
Two faculty members were invited to deliver a talk on "Early Experiences of GPU-enabling the Gadget-2 Simulation Code"...

08-Mar-2010 :
Director HPC Lab attended a three days workshop 22nd Feb to 25th Feb 2010 in Windsor, UK....

26-Jan-2010 :
MPJ Express Version 0.35 beta has been released....

15-Dec-2009 :
A research assistant presented his research paper at INMIC 2009....

21-Oct-2009 :
A research paper of a reserach assistant has been accepted in INMIC 2009....

Welcome to the High Performance Computing Lab

School of Electrical Engineering and Computer Science, National University of Sciences and Technology has established a High Performance Computing (HPC) Center, which is the first of its own kind in the Pakistani academia. This HPC center comprises of Sun's mainframe supercomputers like the Sun Fire V890 and clusters built with Sun Ultra and SunBlade workstations. An objective of this high performance facility is to conduct research, development, and evaluation of parallel programming libraries, languages, and paradigms. This high performance computing center aspires to support scientific computing ranging from forming cosmological structures like galaxies to modeling neurons that form the basis of a brain.

Aims and Objectives

High Performance Computing (HPC) is solving some of the most important problems in science today by pushing computer hardware and software technology to their limits. By definition the prime focus for HPC is performance---the ability to solve the biggest possible problems in the least possible time.

Keeping in view the important role of HPC in innovative science and engineering, the center is established with the following aims and objectives:

  • Support science and engineering
  • Conduct research, development, and evaluation of parallel programming languages, libraries, and paradigms
  • Produce HPC experts capable of pursuing innovative science and engineering efforts

Hardware Facilities

The center's main computational facility include the following:

  • A 32 processor compute cluster with 4 SunFire V890 compute nodes. Each node contains 8 microprocessors.
  • A 9 processor compute cluster with Intel Quad Core Xeon processors.
  • A 64 processor compute cluster with AMD Opteron processors.
  • Myrinet, which is a popular HPC interconnect, is used to connect the compute nodes.
  • 10 SunUltra45 workstations
  • 15 SunBlade workstations
  • 3 Sun V240 file servers
  • 1 Sun StorEdge with multiple terabytes storage
More details regarding hardware can be found here