It is not fair, because many of us do deployments in other JVMs, but people keep waving the flag Java performance == Hotspot as if e.g. C++ performance == gcc.
Re:JVM JIT optimization techniques
by Alphasite_ on Sunday May 29, 2016 @09:43AM
(#11796331)
Hot spot is based on a relatively old paper at this point from what I remember and there are alternatives which purportedly perform better.
Re:JVM JIT optimization techniques
by sievebrain on Sunday May 29, 2016 @04:37PM
(#11798091)
Can you name one?
Re:JVM JIT optimization techniques
by chrisseaton on Sunday May 29, 2016 @05:46PM
(#11798377)
Partial escape analysis is one http://www.ssw.uni-linz.ac.at/Research/Papers/Stadler14/Stad...
Re:JVM JIT optimization techniques
by sievebrain on Monday May 30, 2016 @02:48AM
(#11799936)
Ah, I meant "alternatives to HotSpot" which is what the parent was implying.
I've read the Graal papers and part of the source code. So I am familiar with PEA. It's too bad that optimisation didn't make it into C2 yet. I wonder if it ever will.
Re:JVM JIT optimization techniques
by chrisseaton on Monday May 30, 2016 @08:09AM
(#11800886)
Someone told me that Zing also does PEA, but I don't know that to be a fact.
Re:JVM JIT optimization techniques
by chrisseaton on Monday May 30, 2016 @10:31AM
(#11801503)
Oh and I think JRockit might have done it as well.
The biggest constraint by far is the reliance on inlining. Inter-procedural escape analysis could potentially remove the need for value types in many places, but it doesn't seem like the JVM engineers believe that's feasible.