Node-Level Performance Engineering @FAU
Topic outline
-
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 , Thomas Gruber, Jan Eitzinger and Gerhard Wellein from Erlangen National High Performance Computing Center
Course date: October 4-6, 2023 (9:00 am - 5:00 pm)
This course will be conducted in-person in room 2.135-113 (first floor, Blaues Hochhaus, Martensstraße 3, 91058 Erlangen). Details will be sent vie e-mail to registered participants.
Course Outline:
Introduction
- Basic architecture of multicore systems: threads, cores, caches, sockets, memory
- The important role of system topology
Tools topology and affinity in multicore environments
- Overview
- likwid-topology and likwid-pin
Roofline model: basics
- Model assumptions and construction
- Simple examples
- Limitations of the Roofline model
Tools: hardware performance counters
- Why hardware performance counters?
- likwid-perfctr
- Applications
Roofline case studies
- Stencil algorithms
- Tall & Skinny dense matrix-matrix multiplication
- Sparse matrix-vector multiplication
Basic skills in performance engineering
Optimal use of parallel resources
Extending Roofline: The ECM performance model
-
-
-
-
-
-
-
-
-
Excel 2007 spreadsheet
-
-
-
For publications of NHR@FAU (formerly the RRZE HPC group), see https://hpc.fau.de/research/publications
Important links:
LIKWID tool suite: https://github.com/RRZE-HPC/likwid
LIKWID documentation Wiki: http://tiny.cc/LIKWID
Online Layer Condition calculator: http://tiny.cc/LayerConditions
OSACA Open-Source Architecture Code Analyzer: https://github.com/RRZE-HPC/OSACA
Kerncraft automatic Roofline/ECM modeling tool: https://github.com/RRZE-HPC/kerncraft
MachineState system configuration script: https://github.com/RRZE-HPC/MachineState
-
