Node-Level Performance Engineering @ BU Wuppertal

Topic outline

• 

  Node-Level Performance Engineering

  Even in scientific computing, code development often lacks a basic understanding of performance bottlenecks and relevant optimization opportunities. Textbook code transformations are applied blindly without a clear goal in mind. This course teaches a structured model-based performance engineering approach on the compute node level. It aims at a deep understanding of how code performance comes about, which hardware bottlenecks apply and how to work around them. The pivotal ingredient of this process is a model which links software requirements with hardware capabilities. Such models are often simple enough to be done with pencil and paper (such as the well-known Roofline model), but they lead to deep insights and strikingly accurate runtime predictions.
  

  Lecturer:

  Dr. Georg Hager
  Erlangen Regional Computing Center
  Friedrich-Alexander University of Erlangen-Nuremberg, Germany

  Course dates:

  September 19-20, 2018

  
  

  
  

  • Agenda File
• 

  Day 1

  • Introduction File
  • Computer architecture File
  • LIKWID tools: topology, affinity, frequency File
  • Microbenchmarking for architectural exploration (and more) File
  • The Roofline model File
• 

  Day 2

  • Roofline case studies File
  • Hardware performance counters File
  • Optional: SIMD File
  • Optional: ccNUMA File
• 

  Exercises

  • Getting started with the Emmy cluster at RRZE Page
  •    

  • Exercise: Measuring the divide operation throughput Page
  • Exercise: General code optimization and modeling Page
  • Exercise: A 2D Jacobi smoother Page