Difference between revisions of "New Nvidia RTX3090 GPUs"
From ScientificComputing
(→Introduction) |
|||
| Line 1: | Line 1: | ||
==Introduction== | ==Introduction== | ||
We added 10 GPU nodes with 8 Nvidia RTX3090 GPUs each to the Euler cluster. For the initial phase, we restrict the maximal run time of jobs for those nodes to 24 hours. | We added 10 GPU nodes with 8 Nvidia RTX3090 GPUs each to the Euler cluster. For the initial phase, we restrict the maximal run time of jobs for those nodes to 24 hours. | ||
| + | |||
| + | {| class="wikitable" style="width: 33%;" | ||
| + | !style="width:50%;" colspan="2" |Specs | ||
| + | |- | ||
| + | | Architecture | ||
| + | | style="text-align:right;" | Ampere | ||
| + | |- | ||
| + | | CUDA cores | ||
| + | | style="text-align:right;" | 10496 | ||
| + | |- | ||
| + | | Base clock | ||
| + | | style="text-align:right;" | 1.4 GHz | ||
| + | |- | ||
| + | | Boost clock | ||
| + | | style="text-align:right;" | 1.7 GHz | ||
| + | |- | ||
| + | | Memory | ||
| + | | style="text-align:right;" | 24 GB GDDR6X | ||
| + | |} | ||
==Compatibility with CUDA== | ==Compatibility with CUDA== | ||
Revision as of 15:18, 27 July 2022
Introduction
We added 10 GPU nodes with 8 Nvidia RTX3090 GPUs each to the Euler cluster. For the initial phase, we restrict the maximal run time of jobs for those nodes to 24 hours.
| Specs | |
|---|---|
| Architecture | Ampere |
| CUDA cores | 10496 |
| Base clock | 1.4 GHz |
| Boost clock | 1.7 GHz |
| Memory | 24 GB GDDR6X |
Compatibility with CUDA
The support for the Nvidia RTX30XX series of GPUs was added in CUDA 11.1, therefore you cannot use the RTX3090 GPUs with CUDA<11.1.
Access to the new GPUs
Please note that access to the new GPUs is restricted to shareholder groups that invested into GPU nodes in Euler.
