<div dir="ltr">Matt,<div><br></div><div>That's awesome, thanks for sharing. For the Broadwell system, it seems to take 2-3 microseconds in C-state 1. By any chance do you have numbers for C-state 0? I am curious what an IPI costs for a non-idle cpu, too. These numbers are interesting, though, I didn't realize wake-ups cost so much (or to think about whether to send an IPI to an idle core in the first place).</div><div><br></div><div>If cpu #16 is the neighbor SMT thread for cpu #0, wouldn't IPI latencies be minimal? I assumed both SMT threads couldn't be in different C-states since they share resources. Unless I am reading the data incorrectly...</div><div><br></div><div>-Alex</div><div><br></div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Aug 3, 2016 at 12:29 PM, Matthew Dillon <span dir="ltr"><<a href="mailto:dillon@backplane.com" target="_blank">dillon@backplane.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">I have some saved output from ./ipitest script runs that I've run on various cpus:<div><br></div><div><a href="http://apollo.backplane.com/DFlyMisc/ipitest01.txt" target="_blank">http://apollo.backplane.com/<wbr>DFlyMisc/ipitest01.txt</a></div><div><br></div><div><div><a href="http://apollo.backplane.com/DFlyMisc/ipitest02.txt" target="_blank">http://apollo.backplane.com/<wbr>DFlyMisc/ipitest02.txt</a></div></div><div><br></div><div><div><a href="http://apollo.backplane.com/DFlyMisc/ipitest03.txt" target="_blank">http://apollo.backplane.com/<wbr>DFlyMisc/ipitest03.txt</a></div></div><div><br></div><div><div><a href="http://apollo.backplane.com/DFlyMisc/ipitest04.txt" target="_blank">http://apollo.backplane.com/<wbr>DFlyMisc/ipitest04.txt</a></div></div><div><br></div><div><div><a href="http://apollo.backplane.com/DFlyMisc/ipitest05.txt" target="_blank">http://apollo.backplane.com/<wbr>DFlyMisc/ipitest05.txt</a></div></div><div><br></div><div>The numbers are in nanoseconds, so e.g. '2900' would be 2.9uS. '29000' would be 29uS. The originating cpu is #0. As an example, taking ipitest05.txt, due to the topological layout cpu #16 is the co-thread for cpu #0 and one can see it in the numbers (since cpu #0 is initiating the test, it's generally not running in a low-power mode regardless of the C state we use).<br></div><div><br></div><div>The results generally follow expectations. A cpu sitting in a deep C state can take over 30uS to respond. Minimum IPI latency is usually in the 1-2uS range.</div><div><br></div>-Matt</div>
</blockquote></div><br></div>