RTX 3090 Testing

From ScientificComputing
Jump to: navigation, search

Introduction

We have received an nVidia GeForce RTX 3090 for evaluation.

Initially only jobs with a runtime up to 4 hours can use this GPU.

Usage

To run a job on this GPU, request a single GPU and specify the exact model:

bsub -R "rusage[ngpus_excl_p=1] select[gpu_model0==NVIDIAGeForceRTX3090]" ./my_gpu_program

Of course, other options options, such as more system memory or CPU cores can be included:

bsub -n 16 -R "rusage[ngpus_excl_p=1,mem=4096] select[gpu_model0==NVIDIAGeForceRTX3090]" ./my_gpu_program

You should avoid using any other GPU options for this evaluation, such as selecting GPU memory.

Notes

Please note that support for the RTX 30XX series of GPUs was added in CUDA 11.1. When using an older CUDA version with the RTX3090 GPU, then warning messages such as

W tensorflow/stream_executor/gpu/asm_compiler.cc:235] Your CUDA software stack is old. We fallback to the NVIDIA driver for some compilation. Update your CUDA version to get the best performance. The ptxas error was: ptxas fatal   : Value 'sm_86' is not defined for option 'gpu-name'

are to be expected.

Support

We can only provide limited support for running software on this evaluation GPU. However, do not hesitate to contact us in case of problems submitting jobs or accessing the GPU.