are the 384.66 drivers compatible with GP100?

Hi everyone!

So, at my molecular modelling group we have a SuperMicro Workstation, running Ubuntu 14.04 LTS, equipped with: 2 K80 cards and 2 K40 cards. We intent to replace the K40 cards with a GP100 card.
The latest drivers for the KXX cards which are compatible with cuda 8 are the 384.66 version and they list “Tesla P100” on the supported products list.
On the other hand, the latest driver compatible with GP100 is 410.93.

So, will a GP100 work (compute) with the 384.66 drivers? Its P100 cousin is supported… We don’t need it to have video output, just to run simulations/quantum calculations. Upgrading the operating system is not an option at the moment…

Many thanks!
Igor

All mentioned gpus are supported by the latest drivers (410/415)
General cuda install advice:

  • Don’t use the .run installers, use --uninstall to uninstall them
  • purge anthing nvidia/cuda
  • add the ubuntu graphics ppa
  • install the driver from that (sudo apt install nvidia-driver-415)
  • download the cuda .deb
  • add the repo to your system (first three steps from install instructions on download page)
  • don’t install cuda
  • instead, run sudo apt install cuda-toolkit-10-0

The 384.x driver also supports all mentioned gpus.

many thanks generix!
all the best,
igor

sorry to be bumping this.
what is the most suitable driver for Tesla K80 and Quadro GP100? I have 418.67, but I might have messed up something with OpenGL support, as I’m getting errors with other programs that need it and are unable to find it:

Cannot use native OpenGL. Using Mesa.
No OpenGL libraries found, using fallback MesaGL.

and, common to glxgears:

X Error of failed request: BadValue (integer parameter out of range for operation)
Major opcode of failed request: 148 (GLX)
Minor opcode of failed request: 3 (X_GLXCreateContext)
Value in failed request: 0x0
Serial number of failed request: 2858
Current serial number in output stream: 2859

thank you so much!