tutorial-multi-gpu
所属分类:GPU/显卡
开发工具:Cuda
文件大小:48315KB
下载次数:0
上传日期:2023-05-29 11:50:22
上 传 者:
sh-1993
说明: 用于Exascale的高效分布式GPU编程,SC ISC教程
(Efficient Distributed GPU Programming for Exascale, an SC ISC Tutorial)
文件列表:
.archive.mk (1019, 2023-05-25)
.etc (0, 2023-05-25)
.etc\.set-facl-permissions.sh (239, 2023-05-25)
.etc\deploy-material.sh (135, 2023-05-25)
.etc\deploy.sh (100, 2023-05-25)
.etc\instructions-header.md (295, 2023-05-25)
.etc\instructions-update-header.sh (235, 2023-05-25)
.etc\jsccourse-bashrc.sh (5333, 2023-05-25)
.etc\modules.sh (296, 2023-05-25)
.etc\printout.tex (2896, 2023-05-25)
.etc\sc22-titleslides (0, 2023-05-25)
.etc\sc22-titleslides\gen-titleslide.py (1242, 2023-05-25)
.etc\sc22-titleslides\prelude_slides.mk (2722, 2023-05-25)
.etc\sc22-titleslides\sc-background.png (924166, 2023-05-25)
.etc\sc22-titleslides\sessions.yml (521, 2023-05-25)
.etc\sc22-titleslides\title-slide.tex (689, 2023-05-25)
.template.json (388, 2023-05-25)
.zenodo.json (2795, 2023-05-25)
01-L_Introduction_Overview (0, 2023-05-25)
01-L_Introduction_Overview\slides.pdf (16490054, 2023-05-25)
01b-H_Onboarding (0, 2023-05-25)
01b-H_Onboarding\slides.pdf (12706373, 2023-05-25)
02-L_Introduction_to_MPI-Distributed_Computing_with_GPUs (0, 2023-05-25)
02-L_Introduction_to_MPI-Distributed_Computing_with_GPUs\slides.pdf (895326, 2023-05-25)
03-H_Multi_GPU_Parallelization (0, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master (0, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master\Instructions.ipynb (4192, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master\Instructions.md (2602, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master\Makefile (1637, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master\copy.mk (1578, 2023-05-25)
03-H_Multi_GPU_Parallelization\.master\jacobi.cu (22747, 2023-05-25)
03-H_Multi_GPU_Parallelization\solutions (0, 2023-05-25)
03-H_Multi_GPU_Parallelization\solutions\Instructions.ipynb (4192, 2023-05-25)
03-H_Multi_GPU_Parallelization\solutions\Instructions.md (2602, 2023-05-25)
03-H_Multi_GPU_Parallelization\solutions\Makefile (1637, 2023-05-25)
03-H_Multi_GPU_Parallelization\solutions\advanced (0, 2023-05-25)
... ...
# ISC23 Tutorial: Efficient Distributed GPU Programming for Exascale
[![DOI](https://zenodo.org/badge/409504932.svg)](https://zenodo.org/badge/latestdoi/409504932)
Repository with talks and exercises of our Efficient GPU Programming for Exascale tutorial, to be held at [ISC23](https://app.swapcard.com/widget/event/isc-high-performance-2023/planning/UGxhbm5pbmdfMTIyMDc5OA==).
## Coordinates
* Date: 21 May 2023
* Occasion: ISC23 Tutorial
* Tutors: Simon Garcia (SNL), Andreas Herten (JSC), Markus Hrywniak (NVIDIA), Jiri Kraus (NVIDIA), Lena Oden (Uni Hagen)
## 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).
Curriculum:
1. Lecture: Tutorial Overview, Introduction to System + Onboarding *Andreas*
2. Lecture: MPI-Distributed Computing with GPUs *Simon*
3. Hands-on: Multi-GPU Parallelization
4. Lecture: Performance / Debugging Tools *Markus*
5. Lecture: Optimization Techniques for Multi-GPU Applications *Markus*
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 *Lena*
10. Hands-on: Using Device-Initiated Communication with NVSHMEM
11. Lecture: Conclusion and Outline of Advanced Topics *Andreas*
近期下载者:
相关文件:
收藏者: