Update

With talk of a new IcedTea release I thought I’d better commit what I had of Shark ready for it. I found a couple of what look like optimizer failures while testing (usually I build with optimization disabled, for debugging) but I managed to work around those this morning and get a set of DaCapo results:

  Status Detail
antlr FAIL too many open files
bloat pass 83178ms
chart pass 47227ms
eclipse FAIL one method miscompiles, one method won’t compile
fop pass 15762ms
hsqldb pass 21190ms
jython pass 67533ms
luindex pass 35567ms
lusearch pass 35633ms
pmd pass 60637ms
xalan pass 48422ms

These are still with a non-optimized LLVM, but the numbers are much closer to what I was hoping for than the previous sets.

10 thoughts on “Update

  1. These figures would mean more if you gave details of the machine the benchmarks were ran on. I’ve looked through your previous posts, and as far as I can see, you’ve never said anything beyond testing on ppc and ppc64. Apologies if you’ve given them, and I missed it…

  2. Robert, it’s a quad 2.5GHz G5, though that still doesn’t help much without something to compare them to. When I have all benchmarks passing I’ll do a proper run, with Shark vs Zero vs Cacao, and make some graphs or something.

    Hervé, nah, it’s just an optimized build against a debug one. I didn’t think it’d make such a difference, but it obviously spends more time in non-JIT code than I imagined.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.