Page 1 of 2 12 LastLast
Results 1 to 10 of 17

Thread: GCC vs. LLVM Clang Is Mixed On The Ivy Bridge Extreme

  1. #1
    Join Date
    Jan 2007
    Posts
    15,133

    Default GCC vs. LLVM Clang Is Mixed On The Ivy Bridge Extreme

    Phoronix: GCC vs. LLVM Clang Is Mixed On The Ivy Bridge Extreme

    Our latest Linux benchmarks from the Intel Core i7 4960X Ivy Bridge Extreme Edition processor are compiler tests on this $1000 USD processor. The last two stable releases of GCC and LLVM's Clang C/C++ compilers were compared: GCC 4.7.2, GCC 4.8.1, LLVM Clang 3.2, and LLVM Clang 3.3.

    http://www.phoronix.com/vr.php?view=19192

  2. #2
    Join Date
    Feb 2013
    Posts
    82

    Default

    The Botan tests seem to be missing "-march=native".

  3. #3
    Join Date
    Oct 2009
    Posts
    845

    Default

    Quote Originally Posted by s_j_newbury View Post
    The Botan tests seem to be missing "-march=native".
    What's really bad with the Botan tests is that they use -O2 which makes those tests worthless when it comes to comparing compiler vs compiler code performance. As I've explained to Michael over and over, there are no rules for which optimizations a compiler should add at -O2, meaning that if compiler A decides to enable more optimizations than compiler B at that level, A will win which in turn says nothing of how the compilers compare when set to their HIGHEST optimization level which is what you use when you want the FASTEST code, which again is what all tests except the 'build time' test here was measuring.

    Again, this is why you compare the compilers at their highest optimization level (-O3, and when it was used GCC won all performance tests) because at this level the compilers compete on fair ground, which is to create the fastest binary they can. Now -O2 can be interesting as sometimes -O2 beats -O3 due to optimization heuristics failing, but only in the context of actually having -O3 results to compare with.

    I don't know why Michael persist at doing this, unless he is consciously trying to cook the results in order to get some pointless Clang/LLVM wins.

  4. #4
    Join Date
    Oct 2009
    Posts
    14

    Default

    I dont think Michael is cooking the books.
    Perhaps he went with o2 because most people use it as default?

  5. #5
    Join Date
    Oct 2009
    Posts
    845

    Default

    Quote Originally Posted by steverweber View Post
    I dont think Michael is cooking the books.
    Perhaps he went with o2 because most people use it as default?
    He is comparing the optimization between two compilers. Again, -O2 on one compiler has nothing to do with -O2 on another other than name and overall goal, it's just a loose balance the respective compiler developers choose between optimization and compilation time for -O2 on THEIR compiler, thus it's absolutely pointless to compare those when measuring the best performance the compiler can get out of a certain piece of code (which is what all tests but one did here).

    Meanwhile -O3 is standard highest optimization level between these compilers, here compilers say -'never mind compile time, enable all the appropriate optimizations to create the fastest code we can', which means that this option it the only one worth using when comparing code performance (again what is done here) UNLESS you compare both -O2 and -O3 to see if this particular test is one of the few where -O2 beats -O3.

    So as it stands this test is pointless in terms of which compiler can generate the fastest code for Botan, as we won't know that until he does this test using -O3.

    Unlike you I'm leaning more and more towards Michael's well known Clang/LLVM bias being the reason for throwing in tests using -O2, as I can't see any other logical explanation as to why he continues to do this.

    Now the Botan tests are worthless from a compiler vs compiler performance standpoint, which is sad because it would be interesting to see where CLang/LLVM stands against GCC in those tests aswell.

  6. #6
    Join Date
    Feb 2013
    Posts
    82

    Default

    Don't forget, for gcc there's also:
    -Ofast
    Disregard strict standards compliance. -Ofast enables all -O3 optimizations. It also enables optimizations that are not valid for all standard-compliant programs. It turns on -ffast-math and the Fortran-specific -fno-protect-parens and -fstack-arrays.

  7. #7
    Join Date
    Oct 2009
    Posts
    14

    Default

    s_j_newbury -Ofast sounds neat but unsafe as a default

    If o3 does not create unsafe code, I have to side with XorEaxEax.

    It would be nice to see the results of all 3 optimizations levels with benchmarks of performance/compile time.
    Last edited by steverweber; 10-13-2013 at 12:16 PM.

  8. #8
    Join Date
    Mar 2013
    Posts
    49

    Default

    Quote Originally Posted by s_j_newbury View Post
    Don't forget, for gcc there's also:
    -Ofast
    Disregard strict standards compliance. -Ofast enables all -O3 optimizations. It also enables optimizations that are not valid for all standard-compliant programs. It turns on -ffast-math and the Fortran-specific -fno-protect-parens and -fstack-arrays.
    XCode 5 also has a -Ofast (whose main effect is fast math, but also sets one or two other settings that I forget). I don't know if that has made it into mainline LLVM yet.

    [XCode's defaults are also now for new projects to be very aggressive about assuming that pointers don't alias. It's likely that this is an Apple developer mandate (they provide guidelines about how you should write your code to not make use of aliased pointers, eg through use of unions rather than pointer casting), and that mainline LLVM is not as aggressive. So this is an interesting point, but may not be relevant to the Phoronix community which, I am guessing, is more interested in having crappy old code compile properly than in following a company mandate about how to write better performant new code.]

    LLVM (and so XCode) also has link time (ie whole program) optimization, enabled by -O4. I imagine GCC has the same. It seems only sensible that this should be activated when both compilers are tested against each other. Apple slides showed that LTO made a substantial difference (5% to 20%) in performance, but of course that is against real world code that is split over a large number of files; it may have much less impact on these sorts of microbenchmarks.
    What's not clear to me is the extent to which either LLVM or GCC have fully optimized their LTO pass. Apple had (PPC specific) tools fifteen years ago that could run whole program optimization and rearrange the function layout so that functions that called each other were packed together (and so took up less TLB coverage and shared overlapping cache lines). They used heuristics in the absence of anything better, but could be run with a profiling pass to get a better understanding of the hot call chains. But as far as I know, the LLVM LTO does not (yet?) do this sort of thing, and I have zero idea about GCC.
    You can do even better with LTO (either heuristics or profile-directed). Rather than rearranging and repacking the code based on functions, you can do so based on basic-blocks so that if(!error){...}else(/*handle error*/...} moves the error handling code far away to the end of your binary. Now your actual binary (on disk and in RAM) looks like a series of basic blocks that jump between each other, not a series of functions --- looks weird yes, and more difficult to reverse-engineer from binary, but perfectly legit and not in any way fragile. Obviously this gives you even better utilization of both your I$ and your TLB. This has been done academically but I don't know if any commercial products (ICC? Dev Studio?) use it. You can also do the same sort of repacking with global/static data layout to try to get data that is frequently used together on the same cache line.

  9. #9
    Join Date
    Mar 2013
    Posts
    49

    Default

    Oh, one thing to add to my earlier comment.
    LLVM (and maybe GCC, but I don't know there) will not automatically vectorize many FP loops if fast-math is not enabled because getting the loop to vectorize requires re-ordering FP operations. This means that using fast-math, if your code allows it, can affect performance by quite a bit more than you might imagine.

  10. #10
    Join Date
    Jan 2011
    Posts
    207

    Default

    Quote Originally Posted by XorEaxEax View Post
    What's really bad with the Botan tests is that they use -O2 which makes those tests worthless when it comes to comparing compiler vs compiler code performance. As I've explained to Michael over and over, there are no rules for which optimizations a compiler should add at -O2, meaning that if compiler A decides to enable more optimizations than compiler B at that level, A will win which in turn says nothing of how the compilers compare when set to their HIGHEST optimization level which is what you use when you want the FASTEST code, which again is what all tests except the 'build time' test here was measuring.

    Again, this is why you compare the compilers at their highest optimization level (-O3, and when it was used GCC won all performance tests) because at this level the compilers compete on fair ground, which is to create the fastest binary they can. Now -O2 can be interesting as sometimes -O2 beats -O3 due to optimization heuristics failing, but only in the context of actually having -O3 results to compare with.

    I don't know why Michael persist at doing this, unless he is consciously trying to cook the results in order to get some pointless Clang/LLVM wins.
    Where in the wild do we actually see O3 though?

Posting Permissions

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