AMD EPYC vs Intel Xeon-W: "Clean kill for AMD"

Discussion created by black_zion on Aug 29, 2017
Latest reply on Aug 29, 2017 by wkcook

As we mentioned before, workstations have a >1:1 GPU attach rate with many common workloads being bound by GPU performance. AMD has a multiple of what Intel can offer on GPUs per 1S and a useful two additional slots on a 2S machine. If you are GPU limited as many large markets are, chances are you are not CPU bound, the CPUs tend to be glorified I/O controllers. If you buy Intel CPUs you need to buy 2x Xeon-Ws for less supported GPUs than a single Epyc-P 1S device. It isn’t just a clean kill for AMD, Intel isn’t in the game and they can’t fix it for at least 3 years.


Overall Intel’s Xeon-W launch today shows exactly how deep a hole Intel is in. They are reacting to AMD’s every move but doing so late, ham-handedly, and with significantly inferior products at a significantly higher price. This is significant in case you didn’t catch it last sentence. With Epyc you get more cores, more performance per socket, more memory capacity, more PCIe lanes, and all for notably less money. Intel still wins, barely, on single threaded performance, something that has no place in the workstation market. In short Intel wins on nothing with the Xeon-W and SemiAccurate’s talks with large OEMs confirm this is reflected in sales figures. AMD wins this round, Intel didn’t even show up to fight