If you publish work processed using Hydra, please cite:

Wait, E., Winter, M. & Cohen, A. R. Hydra image processor: 5-D GPU image analysis library with MATLAB and python wrappers. Bioinformatics (2019). doi:10.1093/bioinformatics/btz523

  • White Facebook Icon
  • White Twitter Icon
  • White LinkedIn Icon

What you need for HIP to work

HIP functions can be easily used on either Windows or Linux computers with a Cuda capable device. See list of supported GPUs here. Apple computers are not currently supported.

I would recommend having twice the amount of RAM as vRAM. This means if you have a GPU with 8 gigabytes of GPU memory (vRAM), you should have at a minimum 16 gigabytes of system memory (RAM). For workstations or cluster nodes with multiple GPUs, ideally you should have twice the sum of the available vRAM. For instance, if you have a workstation with four V100 GPUs with 32 gigabytes each, that same workstation should have 256 gigabytes of RAM (32 x 4 x 2).

That's it. Now head over to the Quick Start guide to get your programming environment setup and you will be all set.