According to SemiAnalysis, AMD has planned its first-ever rack-scale GPU cluster for the second half of 2026, when it shows its first rack‑scale accelerator, the Instinct MI450X IF128. Built on what's expected to be a 3 nm‑class TSMC process and packaged with CoWoS‑L, each MI450X IF128 card will include at least 288 GB of HBM4 memory. That memory will sustain up to 18 TB/s of bandwidth, driving around 50 PetaFLOPS of FP4 compute while drawing between 1.6 and 2.0 kW of power. In our recent article, we outlined that AMD split the Instinct MI400 series into HPC-first MI430X and MI450X for AI. Now for AI-focused MI450X, the company created both an "IF64" backplane for simpler single‑rack installs and the full‑blown "IF128" for maximum density. The IF128 version links 128 GPUs over an Ethernet‑based Infinity Fabric network and uses UALink instead of PCIe to connect each GPU to three built‑in Pensando 800 GbE NICs. That design delivers about 1.8 TB/s of unidirectional bandwidth per GPU and a total of 2,304 TB/s across the rack.

With 128 GPUs each offering 50 PetaFLOPS of FP4 compute and 288 GB of HBM4 memory, the MI450X IF128 system delivers a combined 6,400 PetaFLOPS and 36.9 TB of high‑bandwidth memory, and MI450X IF64 provides about half of that. Since AI deployments require massive density of rack systems, AMD plans to possibly outnumber NVIDIA's upcoming system known as "Vera Rubin" VR200 NVL144 (144 compute dies, 72 GPUs), which tops out at 3,600 PetaFLOPS and 936 TB/s of memory bandwidth—about half of what AMD's IF128 approach promises. AMD will have a possibly more powerful system architecture than NVIDIA until the launch of VR300 "Ultra" NVL576, which has 144 GPUs, each carrying four compute dies, totaling 576 compute chiplets.Huawei is also in the rack-scale race with CloudMatrix 384, combining 384 Ascend 910C chips across 16 racks using custom optical links. It delivers about 300 PetaFLOPS of BF16 compute while consuming roughly 560 kW, but it depends on export‑restricted optics and a domestic supply‑chain strategy. As demand for massive AI training clusters keeps climbing, AMD's MI450X IF128 will be a key test of whether Ethernet‑based rack‑scale GPU fabrics can deliver in real‑world data centers. Its production readiness and actual performance will be closely watched by hyperscale AI operators everywhere. With next-generation Ascend accelerators in the works, without exact timelines, we can expect the rack-scale system wars to become pretty intense in the coming months.