# System Hardware

## Oscar Specifications

|                     |       |
| ------------------- | ----- |
| **Compute Nodes**   | 330   |
| **Total CPU Cores** | 28608 |
| **GPU Nodes**       | 116   |
| **Total GPUs**      | 971   |

## Compute Nodes

Oscar has compute nodes in the partitions listed below.

* **batch** - The batch partition is for programs/jobs which need neither GPUs nor large memory.
* **debug** - The debug partition is for users to debug programs/jobs.
* **gpu** - The gpu partition is for programs/jobs which require GPUs.
* **gpu-debug** - The gpu-debug partition is for users to debug gpu programs/jobs.
* **gpu-he** -The gpu-he partition is for programs/jobs which need to access high-end GPUs.
* **vnc** - The vnc partition is for users to run programs/jobs in an graphical desktop environment.

Below are node details including cores and memory for all partitions.

| **Partition** | <p><strong>Total</strong><br><strong>Nodes</strong></p> | <p><strong>Total</strong><br><strong>Cores</strong></p> | <p><strong>Cores</strong><br><strong>Per Node</strong></p> | <p><strong>Total</strong><br><strong>GPUs</strong></p> | <p><strong>Memory Per</strong><br><strong>Node (GB)</strong></p> |
| ------------- | ------------------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------------- | ------------------------------------------------------ | ---------------------------------------------------------------- |
| batch         | 288                                                     | 12800                                                   | 24-192                                                     | n/a                                                    | 190-1540                                                         |
| gpu           | 64                                                      | 5000                                                    | 24-128                                                     | 519                                                    | 190-1028                                                         |
| gpu-he        | 12                                                      | 552                                                     | 24-64                                                      | 84                                                     | 190-1028                                                         |
| debug         | 2                                                       | 96                                                      | 48                                                         | n/a                                                    | 382                                                              |
| gpu-debug     | 1                                                       | 48                                                      | 48                                                         | 8                                                      | 1028                                                             |
| vnc           | 303                                                     | 13696                                                   | 24-192                                                     | 40                                                     | 102-1540                                                         |
| viz           | 1                                                       | 48                                                      | 48                                                         | 8                                                      | 1028                                                             |

## Hardware details

Hardware details for all partitions. The Features column shows the features available for the --constraint option for SLURM. This includes the available CPU types as well GPUs.

<table><thead><tr><th width="105">Partition</th><th width="70">Nodes</th><th width="77">CPUS/ Node</th><th width="77">Total CPUs</th><th width="58">GPUs/ Node</th><th width="72">Total GPUs</th><th width="84">Memory (GB)</th><th>Features</th></tr></thead><tbody><tr><td>batch</td><td>100</td><td>32</td><td>3200</td><td>n/a</td><td>n/a</td><td>190</td><td>32core, intel, scalable, cascade, edr</td></tr><tr><td>batch</td><td>122</td><td>48</td><td>5856</td><td>n/a</td><td>n/a</td><td>382</td><td>48core, intel, cascade, edr</td></tr><tr><td>batch</td><td>40</td><td>32</td><td>1280</td><td>n/a</td><td>n/a</td><td>382</td><td>32core, intel, scalable, cascade, edr, cifs</td></tr><tr><td>batch</td><td>10</td><td>192</td><td>1920</td><td>n/a</td><td>n/a</td><td>1540</td><td>192core, amd, genoa, edr</td></tr><tr><td>batch</td><td>4</td><td>64</td><td>256</td><td>n/a</td><td>n/a</td><td>514</td><td>64core, intel, icelake, edr</td></tr><tr><td>batch</td><td>2</td><td>24</td><td>48</td><td>n/a</td><td>n/a</td><td>770</td><td>24core, intel, e5-2670, e5-2600, scalable, skylake, fdr</td></tr><tr><td>batch</td><td>10</td><td>24</td><td>240</td><td>n/a</td><td>n/a</td><td>382</td><td>24core, intel, e5-2670, e5-2600, scalable, skylake, fdr</td></tr><tr><td>bigmem</td><td>4</td><td>32</td><td>128</td><td>n/a</td><td>n/a</td><td>770</td><td>32core, intel, scalable, cascade, edr</td></tr><tr><td>bigmem</td><td>2</td><td>192</td><td>384</td><td>n/a</td><td>n/a</td><td>1540</td><td>192core, amd, genoa, edr</td></tr><tr><td>gpu</td><td>2</td><td>32</td><td>64</td><td>5</td><td>10</td><td>382</td><td>intel, gpu, titanrtx, turing, skylake, 6142</td></tr><tr><td>gpu</td><td>1</td><td>24</td><td>24</td><td>5</td><td>5</td><td>190</td><td>intel, gpu, titanrtx, turing, skylake, 6142</td></tr><tr><td>gpu</td><td>1</td><td>48</td><td>48</td><td>10</td><td>10</td><td>382</td><td>intel, gpu, quadrortx, turing, cascade</td></tr><tr><td>gpu</td><td>10</td><td>32</td><td>320</td><td>10</td><td>100</td><td>382</td><td>intel, gpu, quadrortx, turing, cascade</td></tr><tr><td>gpu</td><td>13</td><td>64</td><td>832</td><td>8</td><td>104</td><td>1028</td><td>amd, gpu, geforce3090, ampere</td></tr><tr><td>gpu</td><td>4</td><td>48</td><td>192</td><td>8</td><td>32</td><td>1028</td><td>amd, gpu, geforce3090, ampere</td></tr><tr><td>gpu</td><td>7</td><td>128</td><td>896</td><td>8</td><td>56</td><td>1028</td><td>amd, cifs, gpu, a5500, ampere</td></tr><tr><td>gpu</td><td>10</td><td>64</td><td>640</td><td>8</td><td>80</td><td>1028</td><td>amd, cifs, gpu, a5000, ampere</td></tr><tr><td>gpu</td><td>10</td><td>128</td><td>1280</td><td>8</td><td>80</td><td>1028</td><td>amd, cifs, gpu, a5000, ampere</td></tr><tr><td>gpu</td><td>1</td><td>64</td><td>64</td><td>2</td><td>2</td><td>1028</td><td>amd, gpu, a5000, ampere</td></tr><tr><td>gpu</td><td>2</td><td>128</td><td>256</td><td>8</td><td>16</td><td>1028</td><td>amd, gpu, a5500, cifs, ampere</td></tr><tr><td>gpu</td><td>3</td><td>128</td><td>384</td><td>8</td><td>24</td><td>1028</td><td>amd, gpu, cifs, a5000, ampere</td></tr><tr><td>gpu-he</td><td>3</td><td>48</td><td>144</td><td>8</td><td>24</td><td>1028</td><td>amd, gpu, a40, ampere</td></tr><tr><td>gpu-he</td><td>3</td><td>24</td><td>72</td><td>4</td><td>12</td><td>190</td><td>intel, gpu, 4gpu, v100, volta, skylake, 6126</td></tr><tr><td>gpu-he</td><td>4</td><td>64</td><td>256</td><td>8</td><td>32</td><td>1028</td><td>amd, gpu, a6000, ampere</td></tr><tr><td>gpu-he</td><td>2</td><td>40</td><td>80</td><td>8</td><td>16</td><td>512</td><td>intel, cifs, gpu, v100, volta, haswell</td></tr><tr><td>debug</td><td>2</td><td>48</td><td>96</td><td>n/a</td><td>n/a</td><td>382</td><td>48core, intel, cascade, edr</td></tr><tr><td>gpu-debug</td><td>1</td><td>48</td><td>48</td><td>8</td><td>8</td><td>1028</td><td>amd, gpu, geforce3090, ampere</td></tr><tr><td>vnc</td><td>100</td><td>32</td><td>3200</td><td>n/a</td><td>n/a</td><td>190</td><td>32core, intel, scalable, cascade, edr</td></tr><tr><td>vnc</td><td>134</td><td>48</td><td>6432</td><td>n/a</td><td>n/a</td><td>382</td><td>48core, intel, cascade, edr</td></tr><tr><td>vnc</td><td>1</td><td>64</td><td>64</td><td>8</td><td>8</td><td>1028</td><td>amd, cifs, gpu, a5000, ampere</td></tr><tr><td>vnc</td><td>2</td><td>128</td><td>256</td><td>16</td><td>32</td><td>102</td><td>amd, gpu, a2, ampere</td></tr><tr><td>vnc</td><td>40</td><td>32</td><td>1280</td><td>n/a</td><td>n/a</td><td>382</td><td>32core, intel, scalable, cascade, edr, cifs</td></tr><tr><td>vnc</td><td>10</td><td>192</td><td>1920</td><td>n/a</td><td>n/a</td><td>1540</td><td>192core, amd, genoa, edr</td></tr><tr><td>vnc</td><td>4</td><td>64</td><td>256</td><td>n/a</td><td>n/a</td><td>514</td><td>64core, intel, icelake, edr</td></tr><tr><td>vnc</td><td>2</td><td>24</td><td>48</td><td>n/a</td><td>n/a</td><td>770</td><td>24core, intel, e5-2670, e5-2600, scalable, skylake, fdr</td></tr><tr><td>vnc</td><td>10</td><td>24</td><td>240</td><td>n/a</td><td>n/a</td><td>382</td><td>24core, intel, e5-2670, e5-2600, scalable, skylake, fdr</td></tr><tr><td>viz</td><td>1</td><td>48</td><td>48</td><td>8</td><td>8</td><td>1028</td><td>amd, gpu, geforce3090, ampere</td></tr></tbody></table>

## GPU Features and GPU Memory

<table><thead><tr><th width="333.3333333333333">GPU Features</th><th>GPU Memory</th></tr></thead><tbody><tr><td>b200</td><td>192 GB</td></tr><tr><td>h100</td><td>80 GB</td></tr><tr><td>a100</td><td>80 GB</td></tr><tr><td>l40s</td><td>48 GB</td></tr><tr><td>a6000</td><td>48 GB</td></tr><tr><td>a40</td><td>45 GB</td></tr><tr><td>v100</td><td>32 GB</td></tr><tr><td>a5000</td><td>24 GB</td></tr><tr><td>quadrortx</td><td>24 GB</td></tr><tr><td>titanrtx</td><td>24 GB</td></tr><tr><td>geforce3090</td><td>24 GB</td></tr><tr><td>p100</td><td>12 GB</td></tr><tr><td>titanv</td><td>12 GB</td></tr><tr><td></td><td></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.ccv.brown.edu/oscar/system-overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.