AMD Instinct™ GPU Training

This course will be provided ONLINE via Zoom.

This course will deep dive into the AMD Instinct™ GPU architecture and its ROCm™ ecosystem, including the tools to port or/and migrate their application (HPC/AI) on AMD GPU through HIP (Heterogeneous-computing Interface for Portability) as run them in a multi-node environment. An introduction to RocOps, the AMD software stack for AI, will be provided to attendees, including optimized execution engine for deep learning neural networks.

After this course, participants will

  • have gained knowledge about software enablement on AMD GPU using HIP
  • be able to port simple code from CUDA to HIP
  • have gained knowledge about optimized execution engine for deep learning neural networks.

Location

Online course
Organizer: HLRS, University of Stuttgart, Germany

Start date

Sep 29, 2022
08:45

End date

Sep 30, 2022
16:15

Language

English

Entry level

Intermediate

Topics

Code Optimization

Deep Learning

GPU Programming

Machine Learning

Back to list

Prerequisites and content levels

Prerequisites

Some knowledge in GPU programming, e.g., CUDA, and AI/Deep Learning

See also the suggested prereading below (resources and public videos).

Content levels

Basic: 1 hours
Intermediate: 4 hours
Advanced: 6 hours

Learn more about course curricula and content levels.

Resources
Public videos

Instructors

Essam Morsi, Adil Lashab and Philipp Samfass (AMD)

Agenda

All times are CEST.
Day 1

08:45 - 9:00 Drop in to Zoom

  • 9:00 - 10:30 Introduction AMD GPU
    • GCN/CDNA Overview
    • Memory Hierarchy
    • HIP GPU Compute Terminology
    • Compute Units
  • 10:45 - 12:45 HIP
    • Introduction to HIP & Core HIP API
    • Memory Management in HIP
    • Asynchronous Computing with HIP
    • Tips & Tricks
  • 12:45 - 13:45 Lunch Break
  • 13:45 - 15:15  ROCm
    • Introduction to ROCm
    • Multi-GPU RCCL/MPI with ROCm
    • Debugging
    • Profiling
  • 15:30 - 16:15  AI
    • RocOps introduction (AMD AI SW Stack)
    • Training
      • Single GPU training with TF and PY for all models
      • mGPU training with TF and PY
      • Distributed mNode training with TF and PY
    • Inference
      • MLPerf MIGraphX & TVM Backend
Day 2 (Hands-on)

08:45 - 9:00 Drop in to Zoom

  • 9:00 - 9:45 ROCm setup
  • 10:00 - 12:00 Hipification: CUDA To HIP
    • Square
    • RTM TTI
  • 12:00 - 13:00 Lunch Break
  • 13:00 - 14:30 HIP
    • Profiling HW counters 
    • Example with bank conflicts on shared memory / how to profile / resolve it
    • RocProfiler RocTracer ISA code
  • 14:45 - 16:00 AI
    • Distributed Training Demonstration
  • 16:00 - 16:15 QA

Registration information

This course is already fully booked.

Fees

This course is free of charge.

Contact

Khatuna Kakhiani phone 0711 685 65796, kakhiani(at)hlrs.de
Lorenzo Zanon phone 0711 685 63824, zanon(at)hlrs.de

PRACE PATC and bwHPC

HLRS is part of the Gauss Centre for Supercomputing (GCS), which is one of the six PRACE Advanced Training Centres (PATCs) that started in Feb. 2012.

HLRS is also member of the Baden-Württemberg initiative bwHPC.

This course is also provided within the framework of the bwHPC training program. This course is not part of the PATC curriculum and is not sponsored by the PATC program.

Further courses

See the training overview and the Supercomputing Academy pages.

Related training

All training

December 05 - 09, 2022

Online


February 13 - 17, 2023

Online