"MI350P packs 144 GB of HBM3e and up to 4.6 petaFLOPS of FP4 grunt into a dual slot card AMD hopes to win over enterprise AI customers with a more affordable datacenter GPU that can drop into conventional air-cooled servers. Announced on Thursday, the MI350P is the House of Zen's first PCIe-based Instinct accelerator since the MI210 debuted all the way back in 2022."
"The 600-watt, dual-slot card is essentially a MI350X that's been cut in half. That means the CNDA-based GPU is packing 4.6 petaFLOPS of FP4 compute and 144 GB of VRAM spread across four HBM3e stacks delivering a respectable 4 TB/s of memory bandwidth. AMD supports configurations ranging from one to eight MI350Ps, though a lack of high-speed interconnects on these cards means it'll be limited to PCIe 5.0 speeds (128 GB/s) for chip-to-chip communications, potentially limiting its potential in larger models."
"AMD hasn't shared pricing for the cards just yet, but at least on paper, the MI350P is well positioned to compete with either Nvidia's H200 NVL or RTX Pro 6000 Blackwell PCIe cards. Compared to the 141 GB H200, the MI350P promises about 38 percent higher peak performance at FP8, while eking out a narrow VRAM capacity advantage. But the H200 does pull ahead when it comes to memory bandwidth."
"Nvidia's H200 also supports high-speed chip-to-chip communications over NVLink, while the MI350P doesn't use AMD's equivalent Infinity Fabric interconnect. However, all this assumes you can still find H200 NVLs in the wild."
MI350P is AMD’s first PCIe-based Instinct accelerator since MI210, designed to fit conventional 19-inch air-cooled server systems. The 600-watt dual-slot card is essentially a halved MI350X, providing 4.6 petaFLOPS of FP4 compute and 144GB of VRAM across four HBM3e stacks with 4TB/s memory bandwidth. AMD supports configurations from one to eight cards, but chip-to-chip communication is limited to PCIe 5.0 speeds because high-speed interconnects are not included. Pricing has not been announced. Performance positioning targets Nvidia H200 NVL and RTX Pro 6000 Blackwell PCIe, with higher FP8 peak performance but lower memory bandwidth and no NVLink-equivalent interconnect.
Read at theregister
Unable to calculate read time
Collection
[
|
...
]