optimizing acmp in L-World

Tobias Hartmann tobias.hartmann at oracle.com
Mon Sep 3 08:59:53 UTC 2018


Hi Sergey,

On 01.09.2018 19:26, Sergey Kuksenko wrote:
> I've checked performance here.
> 
> Cool, I like that patch. It provides better performance now.
> 
> I have to say that always locked mark word pattern  with old acmp provides the performance which
> quite close to before-valhalla-world.
> Even it's better than klass bit test (didn't expect that, will discover the reason later).
> You can find all results here:
> http://cr.openjdk.java.net/~skuksenko/valhalla/acmp1/acmp_charts_0831.png

That looks great, thanks!

> If you execute that benchmark ('Trivial') by default or "-wm INDI" - you'll get case when the only
> one branch is working and all others are cut of by C2.
> If use "-wm BULK" - also the only one branch is working, but  all others branches are NOT cut of by
> C2, because of they were working at warm up.

Okay, thanks for the clarification!

I'll follow up with a RFR for this.

Best regards,
Tobias


More information about the valhalla-dev mailing list