Google puts Intel on notice, they are not using Intel chips within its cloud
For those of you interested in datacenter architecture this is a good article to look over. As we know Intel has been a dominate force in the market and with the downturn in the PC space it is servers that have kept Intel happy. It would seem that Google is looking for a better way to run their datacenters and is not planning to use Intel hardware anymore.
Instead they are looking towards what OpenCAPI is planning and with names like AMD and NVIDIA on the list you can guess what they may come up with. As PC enthusiasts most of us recognize that Intel has the faster CPU and while ARM and AMD might have more power efficient solutions it is raw power we "want"
The goal of these new interconnect initiatives is to challenge Intel’s dominance in this space. OpenCAPI is a project Nvidia has prominently planned to support with the enterprise version of its Pascal architecture, and AMD has its own reasons for cooperating with such efforts. If it wants to win back space for Zen, it may have decided throwing its own lot in with competitors working on new interconnects is the right way to do that. There’s precedent for doing this — back in 2003, it was AMD’s HyperTransport bus and its support for “glueless” multi-socket systems that gave the company a prominent advantage over Intel in the multi-socket server market. Even after dual and quad-core chips were available, Opteron continued to outperform some of its Core 2-equivalents in multi-socket configurations, at least for a little while.
The majority of servers run either Windows, Linux or Unix based operating systems and the nature of a server OS is to run a variety of applications usually at the expense of NOT running any one of them extremely fast. In the past the hardware drove OS development and with more powerful hardware it has made OS developers lazy, Well lazy might be too harsh of a word, Developers have added more features to the point where you needed "more" hardware to run just the base OS. (eg: Windows 8 and Windows 10) If the OS was more efficient or specialized you could get away with running ARM in a datacenter, scale with more CPUs and still draw less power than anything else currently in production. The trick is to make it fast.
Power is expensive and I suspect that is part of the reason Google is looking for an alternative and it will be interesting to see what they come up with.
Related Web URL: http://www.extremetech.com/computing/237734-google...
