Re: Unusually high polymorphic dispatch costs?

2011-04-29 Thread Christian Thalinger
On Apr 28, 2011, at 9:58 PM, Charles Oliver Nutter wrote: I'm trying to figure out why polymorphic dispatch is incredibly slow in JRuby + indy. Take this benchmark, for example: class A; def foo; end; end class B; def foo; end; end a = A.new b = B.new 5.times { puts Benchmark.measure

Re: Coro in Java 8

2011-04-29 Thread Lukas Stadler
Am 2011-04-28 15:00, schrieb Mark Roos: Of course I would love to see the low level infrastructure in jdk7 binaries. Well, that would be cool, but I think the scope for JDK7 is very much fixed by now, and it's a much too short timeframe anyway... My thought was to use coroutines to emulate

hg: mlvm/mlvm/hotspot: meth-conv: recursive MHs

2011-04-29 Thread john . r . rose
Changeset: 3a27124ba8fa Author:jrose Date: 2011-04-29 03:59 -0700 URL: http://hg.openjdk.java.net/mlvm/mlvm/hotspot/rev/3a27124ba8fa meth-conv: recursive MHs ! meth-conv-6939861.patch ! series ___ mlvm-dev mailing list

hg: mlvm/mlvm/jdk: 2 new changesets

2011-04-29 Thread john . r . rose
Changeset: 931df9b18ac1 Author:jrose Date: 2011-04-29 04:00 -0700 URL: http://hg.openjdk.java.net/mlvm/mlvm/jdk/rev/931df9b18ac1 doc: apply more JSR 292 comments ! meth-doc-7014005.patch Changeset: 2471d29f121b Author:jrose Date: 2011-04-29 04:01 -0700 URL:

Re: Assembly output from JRuby 'fib'

2011-04-29 Thread Rémi Forax
On 04/29/2011 01:09 PM, Christian Thalinger wrote: On Apr 28, 2011, at 3:19 PM, Charles Oliver Nutter wrote: On Thu, Apr 28, 2011 at 5:16 AM, Christian Thalinger christian.thalin...@oracle.com wrote: I took a look at it. I used 64-bit x86 since the code is a bit smaller than with 32-bit.

Re: Unusually high polymorphic dispatch costs?

2011-04-29 Thread Rémi Forax
On 04/28/2011 09:58 PM, Charles Oliver Nutter wrote: I'm trying to figure out why polymorphic dispatch is incredibly slow in JRuby + indy. Take this benchmark, for example: class A; def foo; end; end class B; def foo; end; end a = A.new b = B.new 5.times { puts Benchmark.measure {

new macosx build of mlvm

2011-04-29 Thread Stephen Bannasch
I've uploaded a new build and all the jdk/test/java/lang/invoke test pass: http://www.concord.org/~sbannasch/mlvm/java-1.7.0-internal-mlvm-2011_04_29.tar.gz $ jtreg -XX:+UnlockExperimentalVMOptions -XX:+EnableInvokeDynamic -jdk:build/bsd-amd64/j2sdk-image -v:summary jdk/test/java/lang/invoke/

Re: Assembly output from JRuby 'fib'

2011-04-29 Thread Rémi Forax
On 04/28/2011 08:28 PM, Charles Oliver Nutter wrote: [...] * Fixnum overflow checks in + and - operations Do you specialize the overflow check depending on the callsite ? for fib(n - 1), you just have to check if n is different from Integer.MIN_INT, for fib(n - 2), if n is= to

hg: mlvm/mlvm/hotspot: 3 new changesets

2011-04-29 Thread lukas . stadler
Changeset: 76c1e87d8341 Author:Lukas Stadler lukas.stad...@jku.at Date: 2011-04-29 16:44 +0200 URL: http://hg.openjdk.java.net/mlvm/mlvm/hotspot/rev/76c1e87d8341 meth: small fix, distinct arg names ! meth-conv-6939861.patch Changeset: d3a3a7977609 Author:Lukas Stadler

Re: Unusually high polymorphic dispatch costs?

2011-04-29 Thread Charles Oliver Nutter
I think my strategy is going to be something like this: * Bind first method encountered straight through with a new GWT * Upon encountering nth new method, rebuild GWT chain to check first, second, nth PIC-style * For some N encountered methods, failover to a simple IC Some variation of these