Search:

Type: Posts; User: pszilard; Keyword(s):

Search: Search took 0.16 seconds.

  1. GROMACS 4.6 does not compile

    Just tried to compile GROMACS with AVX-256 CPU acceleration, but the 02-11 nightly choked on our SIMD intrinsics kernels:



    $ make
    [ 0%] Generating version information
    [ 0%] Built target...
  2. irrelevant benchmarks!

    What the hell do computational benchmarks tell about a platform targeted at web servers!? Correct me if I'm missing the point, but IMHO not a freakin' thing.

    Yet again, content mill smell. Dude,...
  3. yet another content-mill-style post

    FFS, I'm so fed up with these misguiding "benchmarks". Michael, if you want to run a one man content-mill, would you mind doing it on Windows instead of Linux. Let's face it: the Linux community has...
  4. Replies
    3
    Views
    2,712

    multi-process programming???

    article-factory fail!
  5. Not really - unless you are a Fedora fanatic. :D ...

    Not really - unless you are a Fedora fanatic. :D

    It's more like: Fedora 16 has better graphics performance than Ubuntu 11.10 because the former uses X v1.11.1, while the latter only 1.10.4....
  6. Exactly! A technology-oriented website should...

    Exactly! A technology-oriented website should strive for giving insights through analysis. Also, fragmenting a single topic - in this case analysis of the Bulldozer architecture - into multiple...
  7. Replies
    22
    Views
    4,652

    more stupid conclusions

    Unless you were referring to home users only that's not entirely true.

    There are quite many scientific (and some non-scientific) applications that make use of CUDA/OpenCL, a great number of them...
  8. Replies
    22
    Views
    4,652

    Agreed, that was a weird comment - unless using...

    Agreed, that was a weird comment - unless using servers and high-end workstations is not considered "use".

    We have quite a few Supermicro file and compute servers and they all have the Matrox...
  9. Replies
    37
    Views
    11,229

    Excellent! Another minor issue, reproducible...

    Excellent!

    Another minor issue, reproducible with both Chromium and Google Chrome version 14.0.835.202, see screenshot: http://dl.dropbox.com/u/239841/openbenchmarks.org_chromium_14.png
  10. Replies
    37
    Views
    11,229

    gcc is far from ideal for Bulldozer

    Nope! I'd share a document with you, but I don't want to get my butt kicked, so I found some public info on the home page of the Swiss National Supercomputing Center (they are just getting their...
  11. Replies
    37
    Views
    11,229

    Ummm, if you google for for "-march=bdver1"...

    Ummm, if you google for for "-march=bdver1" you'll find all the information you need! ;) Most important piece of info is this: http://goo.gl/LXkBr.
  12. Replies
    37
    Views
    11,229

    Thanks, still haven't taken the time to figure...

    Thanks, still haven't taken the time to figure out the OpenBenchmarking.com interface, it might be only me, but I find it a little confusing...

    Btw, the CC info lines (most notably the...
  13. Replies
    37
    Views
    11,229

    What compiler and compiler options were used? It...

    What compiler and compiler options were used? It really does matter!

    From what I've seen until now, only Bulldozer-based CPUs get a hefty performance boost with new kernels and compilers which...
  14. Replies
    37
    Views
    11,229

    You've obviously just jumped at defending Michael...

    You've obviously just jumped at defending Michael without actually thinking through what I said. I'm not going to do you a favor by continuing the smart-ass style discussion you started.

    I was not...
  15. Replies
    37
    Views
    11,229

    another incomplete article! why?!

    Michael, I personally don't really like that you are pumping out articles with bits and pieces of information instead of doing all benchmarks and writing proper performance analysis in a single,...
  16. Cheers for that! I really hope you're not...

    Cheers for that!

    I really hope you're not joking, though, because that wouldn't be a really bad joke... :D
  17. The segfault seems to be caused by -march...

    The segfault seems to be caused by -march (running on Ubuntu 10.04 X86_64, AMD X6 1090T).
  18. Got Gromacs 4.5.4 compiled without -ipa...

    Got Gromacs 4.5.4 compiled without -ipa (-march=auto -O3 -OPT:Ofast -fno-math-errno -ffast-math). I was hoping that the conclusions will be straightforward, but they're not:

    some parts of the...
  19. Compiling Gromacs fails in the linking phase with...

    Compiling Gromacs fails in the linking phase with -Ofast.


    Signal: Segmentation fault in Assembly phase.
    Error: Signal Segmentation fault in phase Assembly -- processing aborted
    [backtrace...]...
  20. As in Gromacs the great majority of the run-time...

    As in Gromacs the great majority of the run-time is spent in hand-coded assembly kernels (SSE/SSE2 on X86/AMD64/X86_64), I doubt that EKOPath can give much speedup wrt gcc. For the same reason there...
Results 1 to 20 of 20