🎨 Add figure explaining NVIDIA GDS and currently supported files (#6)

* 🎨 Add figure explaining NVIDIA GDS and currently support files

Illustration of NVIDIA GPUDirect Storage (GDS) from NVMe storage drive to Graphical Processing Unit (GPU) with and without GDS. Path with GDS is shorter, only passing through a PCIe switch. Path without GDS involves going through the PCIe switch, CPU, System RAM, then back to the CPU and PCIe switch before going to the GPU.

Further on the right, the figure shows current (2023) support for filesystems, file formats (via cuFile) and Zarr compression (via nvCOMP). Also linking to the Excalidraw files/URLs (for future editing) to the figures/README.md file, and added references to the NVIDIA GPUDirect Storage blog post and DevSeed's FOSS4G SotM Oceania 2023 blog post.

* 🔍 Add NVIDIA GPUDirect Storage schematic to main README.md

More eyecandy on the main README.md file. Also linking the PNG images to the Pull Requests that has links to the actual Excalidraw file and URL.

README.md

@@ -1,6 +1,6 @@
 # [FOSS4G SotM Oceania 2023 presentation](https://talks.osgeo.org/foss4g-sotm-oceania-2023/talk/YP3KPT)
 
-![Pangeo Machine Learning Ecosystem 2023](https://github.com/weiji14/foss4g2023oceania/assets/23487320/f91941a8-80c5-48b1-841a-1265bec1eed6)
+[![Pangeo Machine Learning Ecosystem 2023](https://github.com/weiji14/foss4g2023oceania/assets/23487320/f91941a8-80c5-48b1-841a-1265bec1eed6)](https://github.com/weiji14/foss4g2023oceania/pull/5)
 
 The ecosystem of geospatial machine learning tools in the
 [Pangeo](https://pangeo.io) world.
@@ -37,6 +37,7 @@ data pipelines. Learn more as the Pangeo community develops tutorials at
 about the challenges and ideas on scaling machine learning in the geosciences
 with the [Pangeo ML Working Group](https://pangeo.io/meeting-notes.html#working-group-meetings).
 
+[![NVIDIA GPUDirect Storage schematic](https://github.com/weiji14/foss4g2023oceania/assets/23487320/b339605a-492b-4c5c-8a06-b14ebcd258b7)](https://github.com/weiji14/foss4g2023oceania/pull/6)
 
 # Getting started
 
@@ -129,6 +130,8 @@ Ampere generation (e.g. RTX A2000) NVIDIA GPU.
 ## Links
 
 - https://xarray.dev/blog/xarray-kvikio
+- https://developer.nvidia.com/blog/gpudirect-storage
+- https://developmentseed.org/blog/2023-09-20-see-you-at-foss4g-sotm-oceania-2023
 
 ## License
 

figures/README.md

@@ -2,6 +2,11 @@
 
 Folder to store all the figures used in the presentation.
 
+## Excalidraw files
+
+- [Pangeo ML Ecosystem 2023 diagram](foss4g2023oceania_pangeo_ml_talk.excalidraw) | https://excalidraw.com/#json=Z0T6mFgNZnFSjN3rs349O,YdPkNNwey7rS5OtWgvSkyQ
+- [NVIDIA GPU Direct Storage](nvidia_gpu_direct_storage.excalidraw) | https://excalidraw.com/#json=PBEuODqMxdJFVxGrgLzkP,ZAGNmAF2OJmxeq_nIDbPEA
+
 ## Logos
 
 Sources of logos (as of Oct 2023):