I have tested times using computed goto in the interpreter and here are the results:
# ./test_prog mops.pbc Iterations: 100000000 Estimated ops: 300000000 Elapsed time: 8.604721 M op/s: 34.864582 # java -Xint mops Iterations: 100000000 Estimated ops: 300000000 Elapsed time: 9.692999958992004 M op/s: 30.950170356876555 And I'm sure that you are going to write better code than me. Just for the records, this is with the current interpreter: # ./test_prog mops.pbc Iterations: 100000000 Estimated ops: 300000000 Elapsed time: 22.623212 M op/s: 13.260716 On Tue, 30 Oct 2001, Dan Sugalski wrote: > At 09:46 AM 10/30/2001 -0500, Ken Fox wrote: > >Kevin Huber wrote: > > > This is a comparison of mops running on Parrot (-O6 on an Athlon 700) > > > versus Java JDK 1.4.0 beta 2 jitted and interpreted. You can see that > > > Parrot performance is very comparable to Java in interpreted mode. > > > >I have an Athlon 700 too. With these compiler flags: > > > >PERL-CFLAGS = -O3 -fomit-frame-pointer -pipe -s -march=pentium -ffast-math \ > > -fexpensive-optimizations -fno-strict-aliasing \ > > -D_LARGEFILE_SOURCE -D_FILE_OFFSET_BITS=64 > > > >I'm seeing 24 mops which puts Parrot even closer to Java. Do those > >flags improve your times? > > I really want to see the times when we get computed goto and switch based > cores. Hopefully we can soundly trounce Java when interpreted, and dodge > the slow bits when its JITted. (Since we're unlikely to rally enough > expertise to build a Java-class JIT system for Parrot, unless IBM & > DEC^WCompaq^HP's engineering folks kick in some talent) > > Dan > > --------------------------------------"it's like this"------------------- > Dan Sugalski even samurai > [EMAIL PROTECTED] have teddy bears and even > teddy bears get drunk > >
