Re:Microsoft Pledges to Use ARM Server Chips, Threatening In...
by kartickv on Thursday March 09, 2017 @06:48AM
(#13828653)
So if my code is parallel enough to take advantage of all the cores, like a web server serving 96 requests simultaneously, one per core, would I get better performance than Intel? Better performance per watt?
Re:Microsoft Pledges to Use ARM Server Chips, Threatening In...
by Chyzwar on Thursday March 09, 2017 @08:28AM
(#13829058)
You would run 96 processes one for each core. Performance more depends on IO that CPU in reality.
What ARM will bring is competitive market and no Intel Tax. Average 1U in ARM will be massively cheaper. For servers OpenPOWER is more interesting[1]
[1]https://www.theregister.co.uk/2016/04/07/open_power_summit_p...
The ARM server ecosystem has been in the works for a few years. TechCon'16 we saw the announcement that the software is fully there: and this is not hype, all major distributions support all the major players out of the box. Download ISO, install, and use it.
HW-wise we are now in the 3rd gen of chips (QC Centriq, XGene3, ThunderX2) all of which compare with E5, not Atoms. First/Second gen were mostly proving grounds for the specs and software work, excepting for Cavium machines, which have some serious network I/O where the relative wimpyness of any one of the 96 cores simply doesn't matter for certain workloads. In a matter of two years we've seen private datacenters soak up XGene2 and Cavium chips. We've seen ODMs and OEMs get their shit together and start selling real kit (b2b.gigabyte.com).
It's funny, people expect these things to suddenly appear overnight everywhere and competitive with E7s and Power9. It takes decades, but the server guys managed to fit in nicely in about 5 years. I am excited.