0

I have Tesla M2070 cluster with 24 GPUs. I tried running simpleP2P SDK example but it is showing following error although my device supports UVA. OS; Linux 64bit.

Checking for multiple GPUs...

CUDA-capable device count: 3

GPU0 = " Tesla M2070" IS capable of Peer-to-Peer (P2P)

GPU1 = " Tesla M2070" IS capable of Peer-to-Peer (P2P) GPU2 = " Tesla M2070" IS capable of Peer-to-Peer (P2P)

Checking GPU(s) for support of peer to peer memory access...

Peer access from Tesla M2070 (GPU0) -> Tesla M2070 (GPU1) : No

Peer access from Tesla M2070 (GPU1) -> Tesla M2070 (GPU0) : No

Two or more SM 2.0 class GPUs are required for ./simpleP2P to run.

Support for UVA requires a GPU with SM 2.0 capabilities.

Peer to Peer access is not available between GPU0 <-> GPU1, waiving test.

PASSED

It is showing PASSED at the end but peer access from one GPU to another flag is showing No value.

username_4567
  • 4,737
  • 12
  • 56
  • 92
  • 1
    Peer to peer access requires that the GPUs are installed on the same PCI-e segment (so the same IOH/controller or switch). What is the topology of your system? – talonmies Aug 08 '12 at 19:07
  • 1
    That isn't what I am asking. How are the GPUs on a single node connected together? – talonmies Aug 08 '12 at 19:15

0 Answers0