Praktikum: Evaluierung moderner HPC-Architekturen und -Beschleuniger (IN0012, IN2106, IN4294)

Dieses Praktikum wird nur in englischer Sprache angeboten.

Experimental Evaluation of modern Computing Systems and Accelerators 

This lab course will be held in English.

Bachelor/Master practical course (IN0012, IN4294 IN0014, IN2107, IN4602).

 

The Course

This lab is organized in collaboration with LRZ and LMU.

It is provided seperately for bachelor and master students, but carried out as one event.

What you will learn from this course ?

The LRZ recently started building a testbed environment with novel architectures and accelerators called BEAST (Bavarian Energy, Architecture and Software Testbed). This will help in shaping future large LRZ systems (such as successors of SuperMUC-NG). In this lab you will gain hands on experience on the BEAST testbed.

You will:

  • have the chance to work on newest HPC technology such as CPUs or GPUs from Intel, AMD, NVidia, Marvell, Fujitsu (in particular A64FX - powers the fastest supercomputer in the world (Fugaku) by TOP500 rankings as of June 2020),
  • explore various features of novel technology on the node level,
  • learn about node level performance optimizations,
  • attend to vendor talks on their newest hardware,
  • learn various programming models on the node level for multicore CPUs and accelerators, such as OpenMP (for GPU), SIMD, synchronization,
  • - for later assignments - make use of OpenCL, SYCL, or CUDA.

Course Structure

The lab is split in two types of assignments:

  1. In the first assignments, students are expected to work on all architectures.
  2. For the second part, students work on specific architectures exclusively (assigned to student groups according to preferences).

Grading

Students will work in groups, doing reports for each task as well as short presentations of their evaluation results (2 groups will be selected every week to present their reports). Grading is done based on delivered reports and short presentations. This includes source code used for the evaluations, which has to be added to the reports.

Registration

Registration for the lab will happen via the matching system.

Expected Skills

  • Good knowledge of C or C++ on Linux
  • Understanding of terms in computer architecture: pipelining, SIMD, multi-core, SMT, TLB, processor caches, replacement policies (before registering in the matching system, ask yourself if you can explain these terms!)
  • Interest in computer architecture, benchmarking, and low-level code optimization

Schedule / Dates

Preliminary Meeting: (not this semester; if you want to signal your interest, please write a short email to J.Weidendorfer)

Weekly meetings during the semester: every Thursday 4pm - 6pm (warning: time change, was announced 3pm-5pm before), in-person, location FMI 01.06.020.

First date: April 18, 2024