Great piece. Was wondering whether to get an NVLink bridge for $500+ for my two A4500s for inference. This pretty much confirms it only really rescues you if you have nonsensical PCI-E topology.
deflator 2 hours ago [-]
Very informative article. I was hazy on where NVLink sat in the local inference stack. This makes it very clear: to adapt consumer hardware that lacks multiple full x16 PCIe lanes.
causality0 2 hours ago [-]
I badly miss the days when I could buy a GPU and then three years later buy the same GPU for a hundred bucks and boost my framerate by 70%.
c-hendricks 2 hours ago [-]
Wasn't that actually a very short lived period of time? Especially with gains up to 70%, and you had to contend with new stutters?
thescriptkiddie 55 minutes ago [-]
nvidia supported it for 17 years and amd still supports it but only on older cards
reactordev 51 minutes ago [-]
Oh NV Surround, how we miss thee
ssl-3 44 minutes ago [-]
I don't miss it.
I got a pair of 9800GTs back in '08 to play with SLI. It only helped with some games, and despite having all those video output jacks the rig only supported two monitors.
By 2015, the essentially-free iGPU part of an i3 Skylake CPU was ~better than the SLI rig.
xiconfjs 3 hours ago [-]
Thanks
Rendered at 20:18:06 GMT+0000 (Coordinated Universal Time) with Vercel.
I got a pair of 9800GTs back in '08 to play with SLI. It only helped with some games, and despite having all those video output jacks the rig only supported two monitors.
By 2015, the essentially-free iGPU part of an i3 Skylake CPU was ~better than the SLI rig.