LLVM Clang 16 vs. GCC 13 Compiler Performance On Intel Raptor Lake

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts
  • brad0
    Senior Member
    • May 2012
    • 1000

    #31
    Originally posted by Volta View Post
    Does clang compile kernel yet? If not it can lick GCC boots.
    It does and with LTO. GCC is the one licking Clang's boots.

    Comment

    • Weasel
      Senior Member
      • Feb 2017
      • 4422

      #32
      Originally posted by discordian View Post
      TBH this whole ELF interposition should've never been the default but an explicit opt-in. Its not used anywhere outside of hooking stuff into libc
      It's due to ELF's garbage global symbols. PE in contrast can't even store them. You can still hook there, it just requires more effort, and who cares? Most people who hook are experienced enough for it to not matter, unlike 99.999% of users who will suffer because of ELF's stupid design decisions.

      Comment

      • berolinux
        Phoronix Member
        • Jun 2014
        • 104

        #33
        Looks like OpenMandriva's idea of switching the entire OS to building with clang will finally pay off in terms of performance.

        Comment

        • brad0
          Senior Member
          • May 2012
          • 1000

          #34
          Originally posted by berolinux View Post
          Looks like OpenMandriva's idea of switching the entire OS to building with clang will finally pay off in terms of performance.
          It already has for some time.

          Comment

          • DanglingPointer
            Senior Member
            • Nov 2013
            • 146

            #35
            When are we getting this... ???
            11.4 vs 12.2 vs 12.3 vs 13.1 vs llvm-15 vs llvm-16
            with:
            • O2
            • O3
            • O2 -flto
            • O3 -flto
            • O3 -flto=thin (llvm)
            • march=native O2
            • march=native O3
            • march=native O2 -flto
            • march=native O3 -flto
            • march=native O3 -flto=thin (llvm)
            ​with AMD​

            Comment

            • akostadinov
              Junior Member
              • Jan 2018
              • 11

              #36
              Wanted to see what compiles faster, ont the resulting binaries...

              Comment

              Working...
              X