Register to Node-level Performance Engineering course at CSCS

CSCS is pleased to be announce the following course:

Node-level Performance Engineering

to be held at CSCS in Lugano on May 15-16, 2014.

The instructors will be Prof. Gerhard Wellen and Dr. Georg Hager from RRZE, Germany

The 2-day training course aims to teach performance engineering approaches on the compute node level.
“Performance engineering”  is intended as developing a thorough understanding of the interactions between
software and hardware.

Course agenda and registration » (registration is open until May 8th, 2014)



  • Intel and AMD x86 architectures
  • ccNUMA
  • Performance modeling & engineering approaches
  • Our Approach

Practical performance analysis

  • The LIKWID tools
  • Typical performance patterns

Microbenchmarks and the memory hierarchy

  • Understanding the memory hierarchy
    • Data transfer between memory levels
    • Write allocate vs. NT stores
    • Modeling of cache hierarchies
    • Contention
  • NUMA effects – anisotropy and asymmetry

Typical node-level software overheads

  • Cost of synchronization
  • Work distribution

Example Problem: The 3D Jacobi solver

  • Core-level optimizations
    •  Blocking
    •  Non Temporal stores
    •  SIMD vectorization (SSE, AVX)
  • Multithreading – contention at different memory hierarchies
  • Temporal Blocking

Example Problem: The Lattice-Boltzmann Method (LBM)

  • Introduction
  • Roofline Model
  • Data layout
  • Non Temporal stores
  • Model  for in-cache data & multicore scaling
  • Sparse representation and options for propagation

Example Problem: Sparse Matrix-Vector Multiplication

  • Data layouts
  • Performance model – CPU vs. GPU
  • Bandwidth reduction

Example Problem:  A backprojection algorithm for CT reconstruction

  • The algorithm
  • Naïve analysis
  • Detailed analysis and performance model
  • Optimizations

Energy & Parallel Scalability

  • Energy consumption of modern processors
  • The energy-to-solution metric
  • Performance engineering == power engineering
  • Case studies