- Joined
- Aug 19, 2017
- Messages
- 3,044 (1.08/day)
AMD is gearing up to expand its Instinct MI family in the latter half of 2026 with two purpose‑built UDNA‑based accelerators. These new models, MI430X UL4 and MI450X, will cater respectively to high‑precision HPC tasks and large‑scale AI workloads. The MI430X UL4 is designed for applications that rely heavily on double‑precision FP64 floating‑point performance, such as scientific simulations, climate modeling, and others. It features a large array of FP64 tensor cores, ensuring consistent throughput for tightly coupled compute jobs. Because a dedicated UALink switch from partners like Astera Labs or Broadcom won't be available at launch, AMD has chosen a four‑GPU point‑to‑point mesh configuration for the MI430X UL4. This limited scale‑up approach keeps latency low and synchronization tight, making it ideal for small cluster deployments. On the AI side, the MI450X embraces Ethernet‑based Ultra Ethernet for scale‑out.
With UEC‑ready switches already on the market, this open‑standard networking solution lets users build expansive AI farms across dozens or even hundreds of nodes. By relying on established Ethernet technology instead of the new UALink ecosystem, AMD provides customers with immediate, hardware‑accelerated networking for both inference and training. While UALink promises an open, vendor‑neutral accelerator-to-accelerator fabric, its progress has been slow. Committee reviews and limited investment in switch silicon have delayed switch availability. Broadcom, viewed as the primary UALink switch supplier, has been cautious about its commitment, given expected lower volumes compared to Ethernet alternatives. AMD's acceleration segmentation addresses these realities. The MI430X UL4 delivers high‑precision compute in compact GPU meshes. The MI450X offers large‑scale AI connectivity via Ethernet. Should UALink switch development catch up in the future, AMD could revisit native GPU‑to‑GPU fabrics.
View at TechPowerUp Main Site | Source
With UEC‑ready switches already on the market, this open‑standard networking solution lets users build expansive AI farms across dozens or even hundreds of nodes. By relying on established Ethernet technology instead of the new UALink ecosystem, AMD provides customers with immediate, hardware‑accelerated networking for both inference and training. While UALink promises an open, vendor‑neutral accelerator-to-accelerator fabric, its progress has been slow. Committee reviews and limited investment in switch silicon have delayed switch availability. Broadcom, viewed as the primary UALink switch supplier, has been cautious about its commitment, given expected lower volumes compared to Ethernet alternatives. AMD's acceleration segmentation addresses these realities. The MI430X UL4 delivers high‑precision compute in compact GPU meshes. The MI450X offers large‑scale AI connectivity via Ethernet. Should UALink switch development catch up in the future, AMD could revisit native GPU‑to‑GPU fabrics.
View at TechPowerUp Main Site | Source
