Techniques used in Hotspot compilation

Hi, I have been looking for some documentation or articles w.r.t what exactly this technology involves and unfortunately have not had much luck. The only source i have is the IcedTea project which requires I pour through source code to make a determination of what these techniques involve and whether they are applicable to the situations I am interested in. Does anyone know of resources which describe the basic motivation/ideas and algorithms that "hide" behind the hotspot umbrella? If anyone here had some insight into these technologies I would appreciate it.

Thanks in advance,

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.

Look up "trace trees" and

Look up "trace trees" and other papers on trace-based JIT, ie. YETI.

Thanks I will take a look.

Thanks I will take a look.

HotSpot

I'm confused as to what exactly you mean by the "hotspot umbrella". HotSpot is a trademark used by Sun to refer to two Java JIT compilers, HotSpot client and HotSpot server.

Here is a masters about HotSpot client: http://www.ssw.uni-linz.ac.at/Research/Papers/Wimmer04Master/Wimmer04Master.pdf
Here is a paper about HotSpot server: http://www.usenix.org/events/jvm01/full_papers/paleczny/paleczny.pdf

HotSpot Internals Wiki

There are a pile of links on the HotSpot Internals Wiki and on the OpenJDK HotSpot group website.