Node-Level Performance Engineering (Ansys 2022/23)

Topic outline

• General

  Collapse all Expand all

  This course covers performance engineering approaches on the compute node level. Even application developers who are fluent in OpenMP and MPI often lack a good grasp of how much performance could at best be achieved by their code. This is because parallelism takes us only half the way to good performance. Even worse, slow serial code tends to scale very well, hiding the fact that resources are wasted. This course conveys the required knowledge to develop a thorough understanding of the interactions between software and hardware. This process must start at the core, socket, and node level, where the code gets executed that does the actual computational work. We introduce the basic architectural features and bottlenecks of modern processors and compute nodes. Pipelining, SIMD, superscalarity, caches, memory interfaces, ccNUMA, etc., are covered. A cornerstone of node-level performance analysis is the Roofline model, which is introduced in due detail and applied to various examples from computational science. We also show how simple software tools can be used to acquire knowledge about the system, run code in a reproducible way, and validate hypotheses about resource consumption. Finally, once the architectural requirements of a code are understood and correlated with performance measurements, the potential benefit of code changes can often be predicted, replacing hope-for-the-best optimizations by a scientific process.

  Lecturers: Georg Hager, Jan Eitzinger, Thomas Gruber, Dominik Ernst, and Gerhard Wellein, Erlangen National High Performance Computing Center

  Course date: January 11-13, 2023 (8:00 am - 4:00 pm EST)

  This course will be conducted online as a Zoom event. Details will be sent vie e-mail to registered participants.

  Course program:

  Introduction

  Computer architecture for software developers

  Tools topology & affinity in multicore environments

  Roofline model: basics

  Tools: hardware performance counters

  Roofline case studies

  Optimal use of parallel resources: SIMD and ccNUMA
  
  Performance Engineering basic skills
  

  Extending Roofline: The ECM performance model

  
  

  • 

    Announcements Forum
  • 

    Agenda File
  • 

    Source code ZIP File

• Day 1
  • 

    Introduction File
  • 

    Basics of compute node architecture File
  • 

    Logging in and running a job (preparatory homework) Page
  • 

    Hands-on: The divide instruction Page
  • 

    LIKWID tools part 1: topology, affinity, frequency File
  • 

    Hands-on: topology, affinity, memory bandwidth Page
  • 

    Introduction to the Roofline model File

• Day 2
  • 

    Roofline case study: stencils File
  • 

    LIKWID tools part 2: hardware performance counters File
  • 

    Hands-on: Performance counters and memory bandwidth Page
  • 

    Performance Engineering Basics File
  • 

    Hands-on: Dense matrix-vector multiplication Page
  • 

    Roofline case study: Tall & skinny dense matrix-matrix multiplication File
  • 

    dMVM analysis (solution) File
  • 

    ccNUMA in depth File

• Day 3
  • 

    SIMD File
  • 

    Hands-on: Analyzing the MiniMD proxy app Page
  • 

    Analysis spreadsheet template File
  • 

    Solution for "Fritz" CPU (Ice Lake, Intel icc) File
  • 

    Roofline case study: Sparse matrix-vector multiplication File
  • 

    SpMV code for OpenACC and OpenMP for CRS and SELL-C-sigma File
  • 

    Hands-on: Matrix-free CG solver Page
  • 

    C source with instrumented hotspot: mfcg-marker.c File
  • 

    F90 source with instrumented hotspot: mfcg-marker.f90 File
  • 

    The ECM performance model File

• Miscellaneous information

  For publications of the RRZE HPC group, see https://hpc.fau.de/research/publications

  Important links:

  Intel Intrinsics Guide: https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html

  LIKWID tool suite: https://github.com/RRZE-HPC/likwid

  LIKWID documentation Wiki: http://tiny.cc/LIKWID

  Online Layer Condition calculator: http://tiny.cc/LayerConditions

  Kerncraft automatic Roofline/ECM modeling tool: https://github.com/RRZE-HPC/kerncraft

  MachineState system configuration script: https://github.com/RRZE-HPC/MachineState