Remove info regarding old GPUs (1080TI,P100)

Author: grvlbit

docs/hardware/gpu.md

@@ -4,16 +4,14 @@
 [interconnect]: network.md
 [slurm-partitions]: ../runjobs/partitions.md
 
-The UBELIX GPU-based hardware partition currently consists of about 30 compute nodes. Due to their different architectures, their specifications differ as shown in the table below.
+The UBELIX GPU-based hardware partition currently consists of about 20 compute nodes. Due to their different architectures, their specifications differ as shown in the table below.
 
 | Nodes | GPUs                                               | CPU cores     | GPU Memory   | Network     |
 | :---: | :------------------------------------------------: | :-----------: | :------: | :---------: |
-| 7  | 8x NVIDIA GTX1080Ti | 24 (2x12) | 12 GB  | 40Gb/s |
-| 7  | 8x NVIDIA RTX3090 | 32 (2x16) | 24 GB  | 40Gb/s or 100Gb/s |
+| 6  | 8x NVIDIA RTX3090 | 32 (2x16) | 24 GB  | 40Gb/s or 100Gb/s |
 | 8  | 8x NVIDIA RTX4090 | 128 (2x64) | 24 GB  | 100Gb/s |
-| 2  | 8x NVIDIA P100 | 24 (2x12) | 12 GB  | 40Gb/s |
 | 1  | 6x NVIDIA A100 | 128 (2x64) | 80 GB | 100Gb/s |
-| 4  | 8x NVIDIA H100 | 128 (2x64) | 96 GB  | 100Gb/s |
+| 5  | 8x NVIDIA H100 | 128 (2x64) | 96 GB  | 100Gb/s |
 
 See the [Slurm partitions page][slurm-partitions] for an overview of options
 for allocating these nodes.
@@ -41,10 +39,8 @@ follows:
 
 | GPU Type | CPUs per GPU | Memory per GPU |
 | ---- | -------------| -------------- |
-| Nvidia GTX 1080 Ti | 3 | 30GB |
 | Nvidia RTX 3090 | 4 | 60GB |
 | Nvidia RTX 4090 | 16 | 90GB |
-| Nvidia P100 | 3 | 30GB |
 | Nvidia A100 | 20 | 80GB |
 | Nvidia H100 | 16 | 90GB |
 

docs/runjobs/partitions.md

@@ -9,7 +9,7 @@ We are currently operating the following partitions:
 | --------- | -------- | ---------- | ---------------- | ------------- |
 |**epyc2 (default)** | single and multi-core |AMD Epyc2 2x64 cores <br> AMD Epyc4 2x96 cores | 1TB <br> 1.5TB | 1TB |
 | bdw | full nodes only (x*20cores) | Intel Broadwell 2x10 cores | 156GB | 1TB |
-| gpu | GPU <br> (8 GPUs per node, <br> varying CPUs) | Nvidia GTX 1080 Ti <br> Nvidia RTX 3090 <br> Nvidia RTX 4090 <br> Nvidia Tesla P100 <br> Nvidia A100 <br> Nvidia H100 | 11GB <br> 24GB <br> 24GB <br> 12GB <br> 80GB <br> 96GB | 800GB <br> 1.92TB <br> 1.92TB <br> 800GB <br> 1.92TB <br> 1.92TB |
+| gpu | GPU <br> (8 GPUs per node, <br> varying CPUs) | Nvidia RTX 3090 <br> Nvidia RTX 4090 <br> Nvidia A100 <br> Nvidia H100 | 24GB <br> 24GB <br> 80GB <br> 96GB |  1.92TB <br> 1.92TB <br> 1.92TB <br> 1.92TB |
 | gpu-invest | GPU | *see gpu partition* |  | |
 | icpu-*investor* | single and multi-core | *see epyc2 partition* |  | |
 

docs/runjobs/scheduled-jobs/gpus.md

@@ -15,10 +15,8 @@ architecture and use one of the following `--gres` option to select it.
 
 | Type | SLURM gres option |
 | ---- | ----------------- |
-| Nvidia Geforce GTX 1080 Ti | `--gres=gpu:gtx1080ti:<number_of_gpus>` |
 | Nvidia Geforce RTX 3090 | `--gres=gpu:rtx3090:<number_of_gpus>` |
 | Nvidia Geforce RTX 4090 | `--gres=gpu:rtx4090:<number_of_gpus>` |
-| Nvidia Tesla P100 | `--gres=gpu:teslap100:<number_of_gpus>` |
 | Nvidia A100 | `--gres=gpu:a100:<number_of_gpus>` |
 | Nvidia H100 | `--gres=gpu:h100:<number_of_gpus>` |
 
@@ -46,10 +44,8 @@ In the past, we observed that GPU resources were often left unused because some
 
 | Type | CPUs per GPU | Memory per GPU |
 | ---- | -------------| -------------- |
-| Nvidia GTX 1080 Ti | 3 | 30GB |
 | Nvidia RTX 3090 | 4 | 60GB |
 | Nvidia RTX 4090 | 16 | 90GB |
-| Nvidia P100 | 3 | 30GB |
 | Nvidia A100 | 20 | 80GB |
 | Nvidia H100 | 16 | 90GB |
 

docs/software/packages/JupyterLab.md

@@ -121,7 +121,7 @@ Furthermore, if you use libraries, which implement threading: align the numbers
 
 OR requesting GPU resources on a node with a NVIDIA graphics card:
 ```
-jupyter-compute 15051 --ntasks 1 --time=01:00:00 --partition=gpu --gres=gpu:gtx1080ti:1
+jupyter-compute 15051 --ntasks 1 --time=01:00:00 --partition=gpu --gres=gpu:rtx3090:1
 ```
 
 ## Kernels