Announcement

Collapse
No announcement yet.

Windows 7 & Windows 8 vs. Ubuntu 13.04 & Fedora 18

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

  • #31
    [QUOTE=jayrulez;324226]
    Originally posted by liam View Post

    I read OSNews but I wasn't aware there was an article on MobiCore. Do you mind linking to it?

    There are quite a few solutions available for running Linux as a task on microkernels. Some are Codezero, L4Linux, The Robin project, Solution from OK Labs now owned by General Dyamics.

    As to why I mentioned those microkernels, they could be ported to all the architectures that Linux runs on if one was motivated enough to do that.
    But fair enough since you mentioned that you are talking about what is available now and also a fair point that I did not mention that I was talking about "ideal" solutions.

    Just a note: QNX supports ARM, POWER, X86, SH and MIPS. Obviously not close to the range of architectures supported by Linux but shows that it could be done if desired.

    Most people I've had to deal with regarding these topics are actually fan boys that believe that Linux is the end all of operating system development so forgive me for pooling you with them initially.
    Here's the only link I could find that mentioned the l4 kernel and galaxy s3v(well, actually its a comment to an article...): http://www.osnews.com/thread?544120
    The press release linked to is completely useless, and that company's site has mostly ad-speak level descriptions of the tech. There are some links to some pdfs at their site but all returned the http 404 code.
    Don't forget about windriver. They are a pretty big player as well.
    QNX runs on several architectures, but that, of course, doesn't mean that it scales efficiently. I've looked for some numbers since it claims to scale well, but couldn't find any. I'd especially be curious how well it handles massive smp since that seems to have been a fairly late feature added to what has been a fairly old kernel. I would expect it to be damn good at horizontal scaling, though.
    BTW, no problem with the assumption. This is phoronix after all

    Comment


    • #32
      If anything this shows what a placebo effect Windows 8 has been having on people who said "Windows 8 is better for gaming than Windows 7!". It's pretty obvious almost nothing changed.

      As for the OpenGL drivers - let's just say Intel sucks at writing drivers. They have a decade of catching up with Nvidia and AMD. If even Nvidia and AMD drivers are not up to par yet because they haven't put too many engineers (or the best of them) on those OpenGL drivers, you can imagine it's even worse in Intel's case, where they have that much less experience writing drivers for the latest OpenGL 4.3 features.

      Comment


      • #33
        As i said before in these useless comparisons :
        1) its like comparing 1 game to thousands of thousands of games, plus it doesnt really show real performance, because linux doesnt have any aaa or aa games, so these comparisons are more like "100 year of history of oldest games in da world"...
        2) its intel graphics we are talking about, its made for longer battery life, not for performance, so...
        3) not to mention fact, that intel linux drivers is always under development, and on windows its "released and forgotten", linux drivers still is very bad.
        4) windows 8 is not made to be fastest, especially with intel graphics...

        And why the hell author of these stupid comparisons is so dumb ? Why he cant compare a real graphic cards, that were made for gaming, like geforce 690 gtx or radeon 7900 or something like that ????? Why oh why the hell did he choose to combine most useless things in this fkin world - linux + intel graphics + some useless old games... What was he smoking ????????? And even cheap nvidia or amd graphics cards are much much faster than intel graphics... Why he want to drive lada instead of ferrari ???
        Last edited by startzz; 04-06-2013, 04:43 AM.

        Comment


        • #34
          Originally posted by jayrulez View Post
          Linux (the kernel) is not good at everything because there are certain trade offs made so that it can be good at some things.
          It is, because you can tune it easily. Trade offs are everywhere, but in Linux you have control over them.

          Comment


          • #35
            Originally posted by Wilfred View Post
            He also showed results for fedora which does not use unity.
            It's a pity though that ms windows is faster. :-(
            What's pity is phoronix didn't mention Linux intel driver is much younger than their proprietary one.

            Comment


            • #36
              Originally posted by jayrulez View Post
              Well more power to you dude. Stick it to those "freedom-limiting proprietary-software-supporting" corporations.

              Why would you then be interested in windows 8 performance results since there is no conceivable way you'll use it?
              Maybe because he wants to have full performance and use Freedom operating system? Maybe because he doesn't want his data to be sent to m$?

              Comment


              • #37
                Originally posted by jayrulez View Post
                Most people I've had to deal with regarding these topics are actually fan boys that believe that Linux is the end all of operating system development so forgive me for pooling you with them initially.
                There's nothing better, so they're right.

                Just a note: QNX supports ARM, POWER, X86, SH and MIPS. Obviously not close to the range of architectures supported by Linux but shows that it could be done if desired.
                And that's meaningless, because qnx is crap compared to Linux. Qnx supports arm, power, x86, but so what? It's damn slow, featureless crap.
                Last edited by kraftman; 04-06-2013, 05:00 AM.

                Comment


                • #38
                  Originally posted by jayrulez View Post
                  So can most if not all kernels. You just need to do the work to enable it right? This is not exclusive to Linux.
                  Nope. Most of the kernels aren't so flexible and when comes to proprietary ones you can nearly tune nothing.

                  There are various things that Linux cannot do without drastic changes that the developers probably wouldn't agree with.
                  Who cares? It's open source and you can take what you want and do what you want from it. I see your logic fails.

                  Comment


                  • #39
                    Originally posted by startzz View Post
                    And why the hell author of these stupid comparisons is so dumb ? Why he cant compare a real graphic cards, that were made for gaming, like geforce 690 gtx or radeon 7900 or something like that ????? Why oh why the hell did he choose to combine most useless things in this fkin world - linux + intel graphics + some useless old games... What was he smoking ????????? And even cheap nvidia or amd graphics cards are much much faster than intel graphics... Why he want to drive lada instead of ferrari ???
                    It's because of same reasons why moronix is advertising apple and llvm. I bet he gets money from ms and apple for his dumb articles and advertisements.

                    PS. I bet next benchmarks will be using catalyst and some other shitty games. Catalyst is known to be slower on Linux. He doesn't like to benchmark Nvidia, because it's the best Linux graphic driver, so windoze could lost.

                    Comment


                    • #40
                      Re float and S3TC questions, have some direct links:
                      http://openbenchmarking.org/system/1...013.04/glxinfo
                      http://openbenchmarking.org/system/1...a%2018/glxinfo

                      Both have s2tc it seems, only ubuntu has float.

                      Comment


                      • #41
                        The goal was to compare the performance of the Intel driver on Linux und Windows.

                        Originally posted by startzz View Post
                        it doesnt really show real performance, because linux doesnt have any aaa or aa games
                        "AAA" games with high end graphic effects would perform poor on intel graphics. It's useless to compare results of 3-5 fps.
                        Plus the games to test should run natively on Linux and use OpenGL render path on both systems...

                        Originally posted by startzz View Post
                        its intel graphics we are talking about, its made for longer battery life, not for performance, so...
                        Right, but comparing the performance can give us clues about the state of the driver development and potential to reach in the future...

                        Originally posted by startzz View Post
                        [..] linux drivers still is very bad.
                        As the results show, it's a little worse than on Windows, but not "very bad".

                        Originally posted by startzz View Post
                        windows 8 is not made to be fastest, especially with intel graphics...
                        The first test compared Ubuntu 13.04 (Unity) and Windows 8.
                        After some arguments, the test was extendet with Ubuntu 13.04 XFCE and KDE.
                        After further arguments, the test is now extendet with Windows 7 and Fedora.
                        It's impossible to cover every distribution, especially if you start tweaking. The most common default options seem to be covered...

                        Originally posted by startzz View Post
                        And why the hell author of these stupid comparisons is so dumb ? Why he cant compare a real graphic cards, that were made for gaming, like geforce 690 gtx or radeon 7900 or something like that ????? [..]
                        It's hard to compare Intel driver performance on NVIDIA or AMD hardware.
                        Maybe it's not the author...
                        ... but the reader?

                        @ Michael: Thanks for the comparisons. And don't let the unjustified criticism discourage you.

                        Comment


                        • #42
                          [QUOTE=liam;324234]
                          Originally posted by jayrulez View Post

                          Here's the only link I could find that mentioned the l4 kernel and galaxy s3v(well, actually its a comment to an article...): http://www.osnews.com/thread?544120
                          The press release linked to is completely useless, and that company's site has mostly ad-speak level descriptions of the tech. There are some links to some pdfs at their site but all returned the http 404 code.
                          Don't forget about windriver. They are a pretty big player as well.
                          QNX runs on several architectures, but that, of course, doesn't mean that it scales efficiently. I've looked for some numbers since it claims to scale well, but couldn't find any. I'd especially be curious how well it handles massive smp since that seems to have been a fairly late feature added to what has been a fairly old kernel. I would expect it to be damn good at horizontal scaling, though.
                          BTW, no problem with the assumption. This is phoronix after all
                          Thanks man, I somehow forgot that I read that comment.

                          I have some numbers for QNX compared to Linux and another Kernel on ARM and x86. I will post for you when I can locate them.

                          Current QNX is not that old though. Stuff was rewritten for a more modern era, I think that was around QNX 6 Neutrino (not quite sure I recall correctly). It handles SMP well and is really good for distributed computing(see qnet).

                          Comment


                          • #43
                            Originally posted by kraftman View Post
                            It is, because you can tune it easily. Trade offs are everywhere, but in Linux you have control over them.
                            How do you easily tune Linux for transparent distributed computing or fault isolation?

                            It is not easy, and it cannot be done without massive breaking changes.

                            Maybe because he wants to have full performance and use Freedom operating system? Maybe because he doesn't want his data to be sent to m$?
                            Can the man speak for himself?

                            There's nothing better, so they're right.
                            I see you are one of those fan girls... sorry, I meant fan boys.

                            And that's meaningless, because qnx is crap compared to Linux. Qnx supports arm, power, x86, but so what? It's damn slow, featureless crap.
                            Based on your previous comment, I think it would be a waste of effort to try to correct you.

                            Nope. Most of the kernels aren't so flexible and when comes to proprietary ones you can nearly tune nothing.
                            I know quite a few kernels that are quite flexible and allows such changes to be made without being invasive. Whether it's proprietary or open source doesn't matter. The developer of the kernel can make it do what he wants it to do. I don't suppose you yourself are making massive changes to the linux kernel to get it to do what you want to do.

                            Who cares? It's open source and you can take what you want and do what you want from it. I see your logic fails.
                            What was the point of that comment? We all know Linux kernel is open source and with enough effort, you could get it to do what you want.

                            However, say you want a kernel that enables transparent distributed computing(even across architectures): It would be much easier to use another kernel that already enables this rather than try to tame Linux for this. If you managed to change Linux to do that, it wouldn't even be Linux anymore.
                            Last edited by jayrulez; 04-06-2013, 11:48 AM.

                            Comment


                            • #44
                              Originally posted by Michael View Post
                              If you are on a modern web-browser (anything supporting SVG, a.k.a most anything in past few years aside from IE), you get the SVG graphs that all have links to the OpenBenchmarking.org results... But if you're using AdBlock or similar, it seems to think that result graphs are ads, so it might be blocking you from seeing it.

                              Yes, on OpenBenchmarking.org are all of the key system log files.
                              Hum. I can see SVGs, I'm not using AdBlock, and yet I can't find the links. I'm probably just looking at the wrong place, though. Where exactly is that link placed at?

                              Comment


                              • #45
                                Originally posted by Michael View Post
                                What's your HTTP user agent string there?
                                Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.43 Safari/537.31

                                Edit- and headers that work:
                                Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0
                                Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)
                                Last edited by smitty3268; 04-06-2013, 04:15 PM.

                                Comment

                                Working...
                                X