Nvidia reprimands Intel over Xeon Phi processor claims

Intel (INTC -0.4%) published infographics used at a high-speed computing conference and Nvidia (NVDA -1.6%) is taking issue with the accuracy of some of the declarations. The dispute relates to Intel’s stated capabilities in the field of deep learning. Nvidia was primarily provoked by Intel’s claims its Xeon Phi processor is 2.3x faster than GPUs in training, that it provides 38% better scaling across nodes and registers scaling to 128 nodes while GPUs do not. Nvidia asserts Intel used outdated software versions and hardware data in its calculations and noted: “So it’s understandable that newcomers to the field may not be aware of all the developments that have been taking place in both hardware and software.” The post concludes: “It’s great that Intel is now working on deep learning. This is the…


Link to Full Article: Nvidia reprimands Intel over Xeon Phi processor claims