Processors
More power for artificial intelligence
The new scalable Xeon processors from Intel are aimed at companies for which computing-intensive tasks such as real-time data analysis, virtualized infrastructures and high-performance computing are important.
According to the provider, users benefit from an average 1.652-fold increase in performance compared to the previous generation. The processors also offer platform innovations - for example in the area of artificial intelligence: compared to the previous generation, the system delivers deep learning training and inferences that are 2.2 times faster. In combination with software optimizations that additionally accelerate AI applications, the performance of deep learning increases by a factor of 113 compared to a three-year-old, non-optimized server system, according to the manufacturer. In the area of networks, the IPSec forwarding rate for important network applications increases by a factor of 2.5 compared to the previous generation. Compared to a four-year-old system, up to 4.2 times more virtual machines can be operated. For high-performance computing, the flow operations (FLOPS) per clock have been doubled thanks to Intel AVX-512 and integrated ports for the Intel Omni-Path architecture.










