<![CDATA[Multi gpu peer to peer not available in vm]]>Hi everyone,
I am trying to get P2P communication working between two Nvidia L40s PCI GPU cards.
I did this in qemu/kvm by adding the "x-nv-gpudirect-clique=1" flag to each -device entry in the VM spec. Performance wasn't great (~13GB/s in the cuda p2pBandwidthLatencyTest), but the p2p function seems to work.
I can't achieve similar behavior in the latest xcp-ng 8.2 or 8.3 versions.

Is it possible in xcp-ng? Has anyone struggled with such a problem?

Thank you all in advance for your time and input!

]]>https://xcp-ng.org/forum/topic/11085/multi-gpu-peer-to-peer-not-available-in-vmRSS for NodeWed, 07 Oct 2026 19:46:15 GMTFri, 18 Jul 2025 08:07:33 GMT60<![CDATA[Reply to Multi gpu peer to peer not available in vm on Fri, 18 Jul 2025 08:43:10 GMT]]>Hmm I'm not sure it's even possible due to the nature of isolation provided by Xen 🤔

Let me ask @Team-Hypervisor-Kernel

]]>https://xcp-ng.org/forum/post/95496https://xcp-ng.org/forum/post/95496Fri, 18 Jul 2025 08:43:10 GMT<![CDATA[Reply to Multi gpu peer to peer not available in vm on Fri, 18 Jul 2025 08:42:31 GMT]]>exactly

]]>https://xcp-ng.org/forum/post/95495https://xcp-ng.org/forum/post/95495Fri, 18 Jul 2025 08:42:31 GMT<![CDATA[Reply to Multi gpu peer to peer not available in vm on Fri, 18 Jul 2025 08:18:31 GMT]]>Hi,

I'm not entirely sure to get it. You want P2P working with 2x GPUs via PCI passthrough AND inside a VM?

]]>https://xcp-ng.org/forum/post/95494https://xcp-ng.org/forum/post/95494Fri, 18 Jul 2025 08:18:31 GMT