Great question! I've been wondering the same, and I've found great
answers here.
But here is how I was able to get some of the assembly (in normal JVM,
not debug), but for small portions of code - for example this is how I
was able to see the point-in-poly algorithm.
Basically I put a tight loop
On Jul 16, 12:58 am, Christian Vest Hansen
wrote:
> I haven't tried to look beyond the JIT to see what it does, so I
> wouldn't know which tools to use, but if you do not already know about
> it, you might find the HotSpot Internals wiki to be an interesting
> source of info:http://wikis.sun.com/
On Thu, Jul 16, 2009 at 11:00 AM, Glen Stampoultzis wrote:
> Apparently it's possible to see the assembly instructions if you're running
> a debug VM [1].
>
> -XX:+PrintOptoAssembly dumps to the console a log of all assembly being
> generated for JITed methods. The instructions are basically x86 a
I haven't tried to look beyond the JIT to see what it does, so I
wouldn't know which tools to use, but if you do not already know about
it, you might find the HotSpot Internals wiki to be an interesting
source of info: http://wikis.sun.com/display/HotSpotInternals/Home
On Thu, Jul 16, 2009 at 5:3
Apparently it's possible to see the assembly instructions if you're running
a debug VM [1].
-XX:+PrintOptoAssembly dumps to the console a log of all assembly being
generated for JITed methods. The instructions are basically x86 assembly
with a few Hotspot-specific instruction names that get replac
I see lots of discussion on this list about Clojure performance & how
to get it to Java speed. I am also interested in the next steps that
happen, how does the JVM convert byte code down to machine code and
how does one examine that?
The profiling tools I use for C code let me look at what the co
