Announcement

Collapse
No announcement yet.

Is Fedora 15 Faster Than Ubuntu 11.04?

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

  • #16
    Michael,

    One severe short coming of this test is that it used only CPUs from intel. There are architectural differences between intel and AMD cpus that could effect performance and power consumption differently.

    Comment


    • #17
      Originally posted by Obscene_CNN View Post
      Michael,

      One severe short coming of this test is that it used only CPUs from intel. There are architectural differences between intel and AMD cpus that could effect performance and power consumption differently.
      Right, but blame AMD for not sending out CPUs to Phoronix...
      Michael Larabel
      http://www.michaellarabel.com/

      Comment


      • #18
        Originally posted by Michael View Post
        Right, but blame AMD for not sending out CPUs to Phoronix...
        But as these tests were done with laptops its not like you swap out the CPUs in them anyway. I don't think intel sends you whole laptops do they?

        Comment


        • #19
          Originally posted by Obscene_CNN View Post
          But as these tests were done with laptops its not like you swap out the CPUs in them anyway. I don't think intel sends you whole laptops do they?
          I just got a Sandy Bridge laptop from Intel last week as a Software Development Platform to use for driver testing...
          Michael Larabel
          http://www.michaellarabel.com/

          Comment


          • #20
            It doesn't matter if Ubuntu 11.04 is faster, Fedora 15 is just better and the Shell goes a long way to do prove that.

            Comment


            • #21
              Originally posted by gilboa View Post
              Michael,

              Is PTS still self compiling the tested software?
              If so, have you considered adding, whenever possible the built in version to the mix?

              - Gilboa
              I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution. Thus it makes much more sense to benchmarks those binaries, not your own compilations. Otherwise, these tests show the performance of the supplied kernel + glibc + gcc, not the full system.

              Comment


              • #22
                Originally posted by eduperez View Post
                I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution. Thus it makes much more sense to benchmarks those binaries, not your own compilations. Otherwise, these tests show the performance of the supplied kernel + glibc + gcc, not the full system.
                I fully agree.
                Hence the reason for my question
                DEV: Intel S2600C0, 2xE52658V2, 32GB, 4x2TB + 2x3TB, GTX780, F21/x86_64, Dell U2711.
                SRV: Intel S5520SC, 2xX5680, 36GB, 4x2TB, GTX550, F21/x86_64, Dell U2412..
                BACK: Tyan Tempest i5400XT, 2xE5335, 8GB, 3x1.5TB, 9800GTX, F21/x86-64.
                LAP: ASUS N56VJ, i7-3630QM, 16GB, 1TB, 635M, F21/x86_64.

                Comment


                • #23
                  Originally posted by Michael View Post
                  Right, but blame AMD for not sending out CPUs to Phoronix...
                  Why not use some of the billions in ad revenue you make from this website to purchase a few AMD processors?



                  I keed.

                  Comment


                  • #24
                    Originally posted by eduperez View Post
                    I guess that the vast majority of users are NOT going to compile their own software, but use the binaries provided within the distribution.
                    Gentoo users will.

                    Comment


                    • #25
                      I wonder if Fedora 15 (KDE) will still be faster than Kubuntu 11.04?

                      Comment


                      • #26
                        Default LVM partitions

                        One of the annoyances of Fedora, is the LVM-by-default install pattern that is used, which is great for desktops, and possibly basic servers, but generally sucks arse for laptops.

                        And LVM will always kill performance.

                        I am fairly sure removing LVM would even the disk performance numbers up to minimal differences.

                        Comment


                        • #27
                          Hmm. LVM vs non-LVM, as well encyprtion vs non-encryption would be really interesting benchmark. (remember to use some hardware with harware support for AES, like some newer core2 cpus).

                          Comment

                          Working...
                          X