[SushiHippie]

> 6x PCIe 4.0 x16 (64 GB/s)

Wikipedia [0] states that PCIe 4.0 x16 has a throughput of ~32GB/s, what does the (64 GB/s) indicate on the website, is this just a typo and you have 6x ~32GB/s or does it mean in total you can "only" expect a throughput of 64GB/s all lanes slots combined?

If so, wouldn't you also be bottlenecked by the PCIe bandwidth (when moving data between CPU and GPU)?

[0] https://en.wikipedia.org/wiki/PCI_Express#Comparison_table

[jasomill]

Most EPYCs have 128 PCIe lanes, so I'd expect a full x16 link for all six GPUs.

Pedantically, the combined bidirectional bandwidth of PCIe x16 is ~64 GB/s, as it's a full-duplex ~32 GB/s link, but that's an awfully misleading spec if this is the intent (akin to claiming Gigabit Ethernet is 2 Gb/sec).

[georgehotz]

It's the same way NVIDIA states bandwidth for PCIe and NVLink.

https://www.nvidia.com/en-us/data-center/h100/

[arder]

Well they're specifying the AMD EPYC and one of the things that the server line of AMD CPUs do that the consumer grade ones don't, is they have lots of connectivity. So for example an AMD EPYC 8324P is a 32 core CPU with 96 lanes of PCI Gen 5. Given that the 4090 GPU is PCI Gen 4, I think that's where you get the discrepancy. The 6 GPUS are connected in parallel to the CPU with 6 x16 connections (96 total lanes), the CPU could do this at Gen 5 (64GBs for each GPU) but the 4090 GPU is Gen4 only, so you'll only actually get 32GBps per connection.

[andersa]

It's 32GB/s in both directions. So when exchanging data two GPUs each can do this at 64GB/s. Is that a useful way to measure it? Who knows.