tutorial-multi-gpu - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #golang #go #android #rust #deep-learning #docker #java #nodejs #kubernetes #vue #mcp #open-source

tutorial-multi-gpu

(★ 382)

Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial

파일 탐색기

최종 버전 다운로드 (.zip)

- - .set-facl-permissions.sh
  - deploy.sh
  - jsccourse-bashrc.sh
  - modules.sh
  - README.md
- .gitignore
- .update-scripts.sh
- deploy-material.sh
- env.sh
- instructions-header.md
- instructions-update-header.sh
- printout.tex
- - ci.yml
- slides.pdf
- slides.pdf
- slides.pdf
- - copy.mk
  - Instructions.ipynb
  - Instructions.md
  - jacobi.cu
  - Makefile.in
- - Instructions.ipynb
  - Instructions.md
  - jacobi.cu
  - Makefile
- - Instructions.ipynb
  - Instructions.md
  - jacobi.cu
  - Makefile
- slides.pdf
- slides.pdf
- - copy.mk
  - Instructions.ipynb
  - Instructions.md
  - jacobi.cpp
  - jacobi_kernels.cu
  - Makefile.in
- - Instructions.ipynb
  - Instructions.md
  - jacobi.cpp
  - jacobi_kernels.cu
  - Makefile
- - Instructions.ipynb
  - Instructions.md
  - jacobi.cpp
  - jacobi_kernels.cu
  - Makefile
- slides.pdf
- - copy.mk
- slides.pdf
- - copy.mk
- slides.pdf
.archive.mk
.gitignore
.template.json
.zenodo.json
CITATION.cff
LICENSE
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/FZJ-JSC/tutorial-multi-gpu

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd tutorial-multi-gpu

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Make

보통 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Make Linux/macOS는 보통 기본 설치되어 있습니다. Windows는 별도 설치(예: MSYS2, WSL)가 필요합니다.

⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.

cd 03-H_Multi_GPU_Parallelization/solutions

이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.

make

생성된 빌드 설정을 바탕으로 실제 컴파일을 진행해 실행 파일을 만듭니다.

✅ 에러 없이 끝나면 성공입니다. 생성된 실행 파일을 직접 실행해보세요.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# ISC26 Tutorial: Efficient Distributed GPU Programming for Exascale

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5745504.svg)](https://doi.org/10.5281/zenodo.5745504)

Repository with talks and exercises of our Efficient GPU Programming for Exascale tutorial, to be held at [ISC26](https://app.swapcard.com/event/isc-high-performance-2026/planning/UGxhbm5pbmdfNDM5MDIyMg==).

## Coordinates

* Date: 22 July 2026
* Occasion: ISC26 Tutorial (Full Day)
* Tutors: Andreas Herten (JSC), Laura Morgenstern (NVIDIA), Lena Oden (Uni Hagen)
* Support: David Appelhans (NVIDIA), Simon Garcia de Gonzalo (SNL), Markus Hrywniak (NVIDIA) and Jiri Kraus (NVIDIA)

## Setup

The tutorial is an interactive tutorial with introducing lectures and practical exercises to apply knowledge. The exercises have been derived from the Jacobi solver implementations available in [NVIDIA/multi-gpu-programming-models](https://github.com/NVIDIA/multi-gpu-programming-models).

Walk-through (only possible on-site at ISC26!):

* Sign up at JuDoor
* Open Jupyter JSC: https://jupyter.jsc.fz-juelich.de
* Create new Jupyter instance on [JUPITER, using training26XX account, on **LoginNode**](https://jupyter.jsc.fz-juelich.de/workshops/isc26mg) [^1]
* Source course environment: `source $PROJECT_training26XX/env.sh`
* Sync material: `jsc-material-sync`
* Locally install NVIDIA Nsight Systems: https://developer.nvidia.com/nsight-systems

1. Lecture: Tutorial Overview, Introduction to System + Onboarding *Andreas*
2. Lecture: MPI-Distributed Computing with GPUs *Lena*
3. Hands-on: Multi-GPU Parallelization
4. Lecture: Performance / Debugging Tools *Laura*
5. Lecture: Optimization Techniques for Multi-GPU Applications *Lena*
6. Hands-on: Overlap Communication and Computation with MPI
7. Lecture: Overview of NCCL and NVSHMEN in MPI *Lena*
8. Hands-on: Using NCCL and NVSHMEM
9. Lecture: Device-initiated Communication with NVSHMEM *Laura*
10. Hands-on: Using Device-Initiated Communication with NVSHMEM
11. Lecture: Conclusion and Outline of Advanced Topics *Andreas*

[^1]: JUPITER is the default. In the case the tutors tell to move to the backup (JUWELS Booster), launch a [new Jupyter instance here](https://jupyter.jsc.fz-juelich.de/workshops/isc26mg-juwels).