[zeromq-dev] Mb vs. MB in tests & on the Wiki

[Holger Hoffstätte]

Martin Sustrik wrote:
> Well, it would be interesting to find out what's so slow on the other
> box. Maybe single core is the cause. In fact, the P4 box I've tested it
> on has hyper-threading so it's not single-core box par excelence. Yuck,

My bet is definitely on single-coreness. If you compare your results to my
run "A" you'll see that your numbers are more or less exactly twice as
high (minus noise), so it's not caused by memory bandwidth or lock contention.

Holger