Announcement

Collapse
No announcement yet.

GCC 7.0 vs. LLVM Clang 4.0 Performance (January 2017)

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • GCC 7.0 vs. LLVM Clang 4.0 Performance (January 2017)

    Phoronix: GCC 7.0 vs. LLVM Clang 4.0 Performance (January 2017)

    LLVM Clang 4.0 is set to be released in February while GCC 7 will be released as stable in March~April. For those curious how both compilers are currently performing, here is our latest installment of GCC vs. LLVM Clang benchmarking on Linux x86_64.

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    WOW clang 4.0 has really improved a lot
    kudos to llvm developers

    Comment


    • #3
      What are the differences? When i use Clang, when GCC, or do they produce the "same result" with the same code?
      Or is GCC for "Code X" better and Clang for "Code Y" ?

      Comment


      • #4
        It seems, soon GCC will be irrelevant. All new tools are based on llvm and now it can beat GCC on many benchmarks.

        Comment


        • #5
          Originally posted by Pranos View Post
          What are the differences? When i use Clang, when GCC, or do they produce the "same result" with the same code?
          Or is GCC for "Code X" better and Clang for "Code Y" ?
          Most of the time they generate different machine code for the same source, but obviously if the program is well-formed what the program does should be the exact same.
          GCC is sometimes better than clang in certain cases, sometimes the opposite, it really depends on the project you are developing.

          Comment


          • #6
            I rarely compile C or C++ code nowadays, but I did use gcc last week to compile yad (yet another dialog), as I needed the latest version of yad. However, I used to use professional C compilers and linkers a lot (many years ago) and really the quality of the error reporting was one of the most important differentiators between compilers back then. Currently how important is coding rate versus other aspects of the compilers (I am thinking for 100K lines of code type programs).

            Comment


            • #7
              I wonder how clang++ compiled programs would perform with libc++ instead of libstdc++ which they now use.

              Comment


              • #8
                I like the win/loss report; it gives a nice quick overview and basically helps summarize results to add value above and beyond the "here's all the raw data"

                Comment


                • #9
                  Originally posted by Ray54 View Post
                  I rarely compile C or C++ code nowadays, but I did use gcc last week to compile yad (yet another dialog), as I needed the latest version of yad. However, I used to use professional C compilers and linkers a lot (many years ago) and really the quality of the error reporting was one of the most important differentiators between compilers back then. Currently how important is coding rate versus other aspects of the compilers (I am thinking for 100K lines of code type programs).
                  starting with gcc 6, the gcc folks have started paying a lot more attention to the error reports, CLANG is afaict still ahead there, but that might be in part because of bias (e.g. I use clang to see what error it gives only if I have a hard time with the gcc error, so it's not a clean statistical sample)

                  Comment


                  • #10
                    Originally posted by arjan_intel View Post
                    I like the win/loss report; it gives a nice quick overview and basically helps summarize results to add value above and beyond the "here's all the raw data"
                    With PTS7 git: phoronix-test-suite winners-and-losers <result file> if any other metrics/stats you would find interesting, can easily add. If it ends up adding more stuff to it, will probably rename from winners-and-losers.

                    Michael Larabel
                    https://www.michaellarabel.com/

                    Comment

                    Working...
                    X