… This is how you can lash together an AI supercomputer with traditional RoCE Ethernet using 800 Gb/sec ports on the 51.2 Tb/sec switches, which have 64 ports each: Each pod has 64 GPUs or XPUs, each with an 800 Gb/sec network interface. …
… However, Cisco is looking at this through its historically network-focused lens. “The other option – and this is borrowing from the paradigms that we have learned from cloud computing – is you can connect a whole bunch of these quantum computers together through a quantum network and make all of th… …
… Take a gander: The torus topology has multiple dimensions, as the name suggests, and have been popular in some supercomputer architectures – IBM’s BlueGene massively parallel machines used a 3D torus and the “K” and “Fugaku” supercomputers built by Fujitsu have a 6D “Tofu” interconnect, just to giv… …
… I am not sure how much of the overall networking business is Ethernet stuff, InfiniBand stuff, and NVSwitch stuff – I have been modeling InfiniBand versus Ethernet since the early days of Mellanox – but Nvidia has stopped talking specifically about how this networking business is carved up. …
… Hyperscalers and cloud builders, not to mention HPC centers, do not like when networking represents more than 10 percent of the cost of a distributed computing system, and they like it even less when they see the numbers drifting up towards 30 percent when you take into account the scale up network… …
… You will have 128 compute engines per rack, and need four racks for the compute, but it will take eight racks of networking. …
… The networking profits are helping, clearly. Looking ahead, HPE wants to use Juniper to capture more networking revenue. Speaking generally, the AI systems market might grow to $1 trillion a year by 2030 or so, and $200 billion of that might be for networking. …
… AI networking drove $2.78 billion, up 60 percent year on year, but down 51.5 percent sequentially. …
… We are experiencing a golden era networking with an increasing TAM now of over $100 billion in forthcoming years. …
… Add in the cost of the rack plus networking some from AMD, such as the Pensando DPUs and storage, you are probably talking $35 billion per gigawatt for the iron, with the rest going into facilities, power, and cooling. …