-
Notifications
You must be signed in to change notification settings - Fork 10
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
71 additions
and
0 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,31 @@ | ||
+++ | ||
using Dates | ||
|
||
title = "Julia hackathon v6.0 2024 - Announce" | ||
date = Date(2024, 07, 13) | ||
reading_time = "1-minute read" | ||
|
||
tags = ["activities", "julia", "coding"] | ||
+++ | ||
|
||
The [GPU4GEO team](/team) and external collaborators will gather for the 6th Julia hackathon :tada:, **October 07 - 11 2024** to advance geoscientific Julia projects. | ||
|
||
## GPU4GEO Julia hackathon | ||
|
||
After five successful editions, we are happy to announce a 6th edition of the Julia hackathon, to be held in October 2024 in the Black Forest. | ||
|
||
**Save the dates: October 07 - 11 2024** | ||
|
||
During this event, we aim at moving forward with the various open-source Julia projects within ice-flow dynamics and geodynamics where collaboration with experts enables the fast track. | ||
|
||
Namely, we will focus on advancing Julia software engineering and high-performance, parallel, GPU-accelerated code development in following topics: | ||
|
||
- Work on [FastIce.jl](https://github.com/PTsolvers/FastIce.jl) large-scale application | ||
- Work on AD capabilities using [Enzyme.jl](https://github.com/EnzymeAD/Enzyme.jl) on GPUs | ||
- Further develop rheology and material parameter routines [GeoParams.jl](https://github.com/JuliaGeodynamics/GeoParams.jl) and use/implement that in existing codes | ||
- Advance several "differentiable modelling" projects | ||
- more... | ||
|
||
Participant will team-up among topics of interest and work on their selected challenges in small groups during the week. | ||
|
||
Stay tuned as more news will follow... |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,40 @@ | ||
+++ | ||
using Dates | ||
|
||
title = "GPU4GEO news - Extension and Follow-up project" | ||
date = Date(2024, 06, 10) | ||
reading_time = "2-minute read" | ||
|
||
tags = ["julia", "proposal"] | ||
+++ | ||
|
||
After the last progress meeting in Lugano in January 2024, GPU4GEO got granted a 1 year extension. 6 months later, we submitted a follow up project, ∂GPU4GEO, focussing on differentiable modelling with Julia on GPUs. | ||
|
||
## GPU4GEO extension | ||
*Ludovic Räss* | ||
|
||
After handing-in the final progress report, the GPU4GEO project got granted a 1 year extension to focus on topics such as: | ||
- GPU HPC CI (running continuous integration and packages' test suite on GPU HPC infrastructure) | ||
- Application readiness on Nvidia Grace-Hopper GH200 nodes CSCS' ALPS infrastructure | ||
- Large scale Geodynamics application readiness | ||
- Finalisation of the STREAM related large scale allocation | ||
|
||
~~~ | ||
<center> | ||
<img src="../../assets/images/gpu4geo_rev.png" alt="GPU4GEO overview" width="600"> | ||
</center> | ||
~~~ | ||
*Target application and related multi-scale challenges.* | ||
|
||
## Follow-up PASC project - ∂GPU4GEO | ||
|
||
On June 10, 2024, we submitted a GPU4GEO follow-up project to the [2024 PASC call](https://pasc-ch.org/projects/2025-2028/call-for-pasc-project-proposals/index.html). The project core team, composed of many GPU4GEO members, proposes to tackles differentiable modelling at scale using unique features of the Julia language, namely, close to native integration of the [Julia GPU](https://juliagpu.org) stack and outstanding automatic differentiation capabilities (of CPU and GPU code) with [Enzyme.jl](https://github.com/EnzymeAD/Enzyme.jl). | ||
|
||
~~~ | ||
<center> | ||
<img src="../../assets/images/dgpu4geo.png" alt="GPU4GEO overview" width="700"> | ||
</center> | ||
~~~ | ||
*Graphical abstract suggesting the next steps to be addressed in ∂GPU4GEO.* | ||
|
||
The proposed development will articulate around similar topics as developed in recent workshop such as the [NuTS workshop (https://github.com/PTsolvers/Julia-AD-NuTS)](https://github.com/PTsolvers/Julia-AD-NuTS). |