2u Blackbird Build with 18 cores?!

[deepblue]

Re: the xz compression behavior, can you tell if you are memory bandwidth starved?  Lots of cores vs. Blackbird's meager DIMM capacity isn't a very balanced combination. 

I did add a swap disk to this server, and I am wondering if that would that impact the performance of my XZ transfer? I am also curious if that would impact my testing as well, after doing some searching I ran into the package 'mbw' which suggests to disable swap during testing.

BTW, I looked at your awesome graphs up above more carefully and you can see how current & voltage are moving around --> that looks like the processor is indeed dynamically boosting/dropping frequency to manage within it's power limit.

Its strange to see it go 'invisible' during testing. I am wondering if the reporting just stops and the board takes over?

[ejfluhr]

How do you mean "invisible?"   Are you referencing the "Current" field of the bottom chart?

That looks to me as a plotting problem, where the processor is going to a range of 125-130A VDD which for some reason goes off the top of the chart.  If the chart was scaled to, say, 150A then we could see where the current really rests.

I am not sure which of the blue or green Voltage curves is representative of processor VDD.   Maybe the blue is the regulator setpoint and the green is VDD at the processor given loadline loss?    If so, then given current is 125A at processor-VDD=0.85v, the processor is consuming at least 125A * 0.85v = 106W of VDD power.   VDN is 15.6A * 0.69v = 10.8W.   I cannot tell how much VIO power is being used, let's just guess 30W?   That would put the processor in the ballpark of 106W + 10.8W + 30W ~=147W.

When you compare that to the idle data, which shows VDD current of ~30A at about 1.0v, that would be 30W VDD power versus the 106A fully-loaded.

One line that seems worrisome is the "VR" temp which appears to go to 115C.  That seems pretty extreme.  I don't know what that regulator is rated for but other server designs I know about have long-term reliability limits around 90C.  This may be an example of how the Blackbird design is not built to handle a high-core-count processor, as those tend to run much lower voltages and higher currents at the same power as a low-core-count processor.    It would be nice to have comparison data of an 8-core processor running at max power for comparison, but I haven't seen anyone else post any characterization results like you have.