You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
-23Lines changed: 0 additions & 23 deletions
Original file line number
Diff line number
Diff line change
@@ -29,26 +29,3 @@ Curriculum:
29
29
9. Lecture: Device-initiated Communication with NVSHMEM *Jiri*
30
30
10. Hands-on: Using Device-Initiated Communication with NVSHMEM
31
31
11. Lecture: Conclusion and Outline of Advanced Topics *Andreas*
32
-
33
-
## Onboarding
34
-
35
-
The supercomputer used for the exercises is [JUWELS Booster](https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html), a system located at Jülich Supercomputing Centre (Germany) with about 3700 NVIDIA A100 GPUs.
36
-
37
-
Visual onboarding instructions can be found in the subfolder of the according lecture, `01b-H-Onboarding/`. Here follows the textual description:
38
-
39
-
* Register for an account at [JuDoor](https://judoor.fz-juelich.de/login)
40
-
* Sign-up for the [`training2232` project](https://judoor.fz-juelich.de/projects/join/training2232)
41
-
* Accept the Usage Agreement of JUWELS
42
-
* Wait for wheels to turn as your information is pushed through the systems (about 15 minutes)
43
-
* Access JUWELS Booster via [JSC's Jupyter portal](https://jupyter-jsc.fz-juelich.de/)
44
-
* Create a Jupyter instance using `LoginNodeBooster` and the `training2232` allocation on JUWELS *(see slides for screenshots)*
45
-
* When started, launch a browser-based Shell in Jupyter
46
-
* Source the course environment to introduce commands and helper script to environment
47
-
```
48
-
source $PROJECT_training2232/env.sh
49
-
```
50
-
* Sync course material to your home directory with `jsc-material-sync`.
51
-
**Recommended*: Install [Nsight Systems profiler](https://developer.nvidia.com/gameworksdownload#?dn=nsight-systems-2022-4) for third session (also available via [package managers](https://developer.download.nvidia.com/devtools/repos))
You can also access JSC's facilities via SSH. In that case you need to add your SSH key through JuDoor. You need to restrict access from certain IPs/IP ranges via the `from` clause, as explained [in the documentation](https://apps.fz-juelich.de/jsc/hps/juwels/access.html#ssh-login). We recommend using Jupyter JSC for its simplicity, especially during such a short day that is the tutorial day.
0 commit comments