Page 2 of 2 FirstFirst 12
Results 11 to 18 of 18

Thread: GCC 4.8.0 vs. LLVM Clang 3.3 Compiler Performance

  1. #11
    Join Date
    Feb 2008
    Location
    Linuxland
    Posts
    5,130

    Default

    The openmp comparisons do have some merit. For example graphicsmagick here, it is less than 2x on the 8-core bulldozer: bad quality parallelization there.

  2. #12
    Join Date
    Feb 2013
    Posts
    66

    Default

    Quote Originally Posted by curaga View Post
    The openmp comparisons do have some merit. For example graphicsmagick here, it is less than 2x on the 8-core bulldozer: bad quality parallelization there.
    Nope, this means that clang compiled single thread perfomance equals 2-4 gcc threads.

  3. #13
    Join Date
    Feb 2008
    Location
    Linuxland
    Posts
    5,130

    Default

    That is another possible conclusion, yes.

  4. #14
    Join Date
    Jul 2011
    Posts
    73

    Default

    Quote Originally Posted by leonmaxx View Post
    I'm very surprised about FX perfomance in some tests.

    Clang: seems like next release will finally beat GCC, and be a good replacement for it (except OpenMP).
    Except that it only was faster in two tests (in one of them only on one single CPU out of 3) and slower in everything else… (I don’t count compile times as tests).

    But you summarized nicely how misleading the text of this article is - again

  5. #15
    Join Date
    Jul 2011
    Posts
    73

    Default

    Quote Originally Posted by leonmaxx View Post
    Nope, this means that clang compiled single thread perfomance equals 2-4 gcc threads.
    Nope: You cannot distinguish between a weakly parallelizable algorithm and compiler performance. To get good data, you would also have to provide a GCC run without openmp: That would show the speedup due to OpenMP.

  6. #16
    Join Date
    Feb 2013
    Posts
    66

    Default

    Quote Originally Posted by ArneBab View Post
    Except that it only was faster in two tests (in one of them only on one single CPU out of 3) and slower in everything else… (I don’t count compile times as tests).

    But you summarized nicely how misleading the text of this article is - again
    Under "next release" i mean Clang 3.4 or later... Sorry for my bad English.

  7. #17
    Join Date
    Feb 2013
    Posts
    66

    Default

    Quote Originally Posted by curaga
    That is another possible conclusion, yes.
    Or this:

    Quote Originally Posted by ArneBab View Post
    weakly parallelizable algorithm
    Thanks.

  8. #18
    Join Date
    Mar 2013
    Posts
    4

    Default compiler optimization

    (Sorry I didn't read too closely if it already does this, and didn't look in the source to check). Anyway one thought is "is this using gcc -march=native"? and another might be to use gcc's profile guided optimization for it. And/or clang's equivalent if it exists.
    Cheers.
    -roger-

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •