RDMA Changes For Linux 5.12 Add DMA-BUF Support For Peer-To-Peer Transfers With GPUs

[phoronix]

Phoronix: RDMA Changes For Linux 5.12 Add DMA-BUF Support For Peer-To-Peer Transfers With GPUs

The changes within the remote direct memory access (RDMA) subsystem for Linux 5.12 are deemed "quite small" but there is one interesting addition courtesy of Intel...

http://www.phoronix.com/scan.php?page=news_item&px=RDMA-DMA-BUF-P2P-Linux-5.12

[pegasus]

So this is now the third implementation solving the same problem? As far as I know Mellanox was the first with GPUdirect. Seems like a good scenario for Linus to share some sharp wisdom with the world

[agd5f]

So this is now the third implementation solving the same problem? As far as I know Mellanox was the first with GPUdirect. Seems like a good scenario for Linus to share some sharp wisdom with the world

GPUDirect/PeerDirect is not upstream.

[mppix]

Sounds exciting. This, pci4/5 (..6) smart access memory, oneAPI and the like may really start a new compute model where the CPU is only one of many compute nodes in a system.

[tildearrow]

RDMA just makes me think of RDNA...

(even though I know they are separate things)

[You-]

This is interesting and just goes to show how much of a behemoth intel is in relation to opensource.

I would suggest this is also useful to AMD and something they could have worked on, but by having a smaller team, a lot of this type of work is done by intel.

The sales and marketing side of intel may sometimes be evil, but its OSS Side is amazing.

[agd5f]

This is interesting and just goes to show how much of a behemoth intel is in relation to opensource.

I would suggest this is also useful to AMD and something they could have worked on, but by having a smaller team, a lot of this type of work is done by intel.

FWIW, AMD did the GPU side of this (i.e., added peer to peer support to dma-buf in general).

[mppix]

This is interesting and just goes to show how much of a behemoth intel is in relation to opensource.
I would suggest this is also useful to AMD and something they could have worked on, but by having a smaller team, a lot of this type of work is done by intel.

Early AMD exascale supercomuter reports suggests that they are doing something like infinity fabric over pcie interfaces. This may come down to a very similar concept..

[agd5f]

Also, HMM doesn't currently handle Peer to Peer access.

[You-]

FWIW, AMD did the GPU side of this (i.e., added peer to peer support to dma-buf in general).

Cool, with cooperation there is less chance that one party wants to take its toys home (or rather, not bring them out to play).

Thanks for correcting me on this.