Intel GPU D-Series Claims 5.9x Over Nvidia RTX PRO 6000 in Double-Precision Math on Less Bandwidth
AI-generated summary Intel reported that its GPU D-Series inference card reached up to 5.9 times the throughput of Nvidia products in financial simulations using double-precision math. Intel has named no price and no ship date for the card, which carries 160 GB of LPDDR5X memory and a power rating of 350 W.