Announcement

Collapse
No announcement yet.

The "Dirndl" On AMD Opterons Are Impressive

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

  • #16
    Originally posted by netrage View Post
    Sadly phoronix has become (or always was?) a tabloid. Who can take this site seriously with stunts like this? Boasting scoops and annoying people when the article hardly lives up to the headline. Always shamelessly advertising itself via links in articles back to phoronix articles (have you ever read an article here that contained fewer than 5 links back to other phoronix articles? I think not..). Always going on about the "test suite", etc etc.

    It's a shame this site is the only (sort of, there are others like osnews, ars technica, slashdot, etc. But there isn't really another place where almost everything is gathered in one place) site that gathers most linux news in one place. Until such a site appears (hint, hint) I shall be forced to visit this place every once in a week to see if i missed something off the other sites (if I can be bothered to scroll through the endless "does xxx boot faster than yyy" articles and similar garbage)... On the other hand if this tabloid/crap "benchmarking" can stop here then I would be happy to return. But I won't hold my breath.
    How is publishing benchmarks the equivalent of "tabloid" journalism?

    Comment


    • #17
      Originally posted by netrage View Post
      Sadly phoronix has become (or always was?) a tabloid. Who can take this site seriously with stunts like this? Boasting scoops and annoying people when the article hardly lives up to the headline. Always shamelessly advertising itself via links in articles back to phoronix articles (have you ever read an article here that contained fewer than 5 links back to other phoronix articles? I think not..). Always going on about the "test suite", etc etc.
      Whoa, let's not get carried away. Would I prefer it if Phoronix went for less 'sensationalistic' headlines? Sure. Would I prefer it if Phoronix weren't so prone to 'milk' their scoops for all it's worth (and probably then some)? Sure. But overall it's a great site, free (I ain't paying for it anyways, although I click on the adverts from time to time) and with the best overall technical coverage on Linux and it's surrounding technologies, not to mention the high level of technical knowledge amongst many of the forum members and even guys like xorg/ati devs here providing very interesting information on the development/infrastructure of Linux graphic drivers among other things. In short, Phoronix is fantastic in what it offers and it's FREE!

      As mentioned there are things I would prefer to be different in regards to the way certain articles are presented, but I can't understand how some people can be so negative when those 'gripes' pale compared to all the great stuff Phoronix offers, and again for FREE. Compared to 99% of the so called 'technology sites' covering Linux out there Phoronix is PURE WIN in my opinion, despite it's warts.

      Comment


      • #18
        Originally posted by jijitus View Post
        I'm hoping it's a CPU optimization; otherwise announcing results for Intel SB and AMD Opterons would be a deliberate attempt to fool us all.

        Maybe some geniuses developed a breakthrough C compiler which can automatically parallelize non-optimal code over 4 or 8 cores (like loop unrolling, but over multiple cores). Kudos if it uses SSE2 and/or finally forgets about 32-bit compatibility.
        I'd be happy to see that in the GCC, but it's more realistic to expect such an improvement on a competitor.
        If it's indeed the PathScale EKOPath compiler going open source, like some have alluded to, then your description of what it can do is probably not far from the truth. This kind of technology isn't entirely new; Intel's own C/C++ compilers have been claiming most of these features for a couple years now. What would be new is if we had a compiler like this that was free and open source.

        And hopefully its gcc compatibility is better than icc's, so all our favorite software that compiles with gcc will compile with EKOPath.

        Of course, all of this is speculation, but the story seems likely:

        *PathScale and Phoronix have a working relationship; PathScale representatives post here and Michael writes articles about pscnv
        *Amazing performance coming out of PathScale wouldn't exactly surprise me, it's to be expected (their whole company mission is to make compilers that produce high performance)
        *PathScale already writes open source software (they like the BSD license) in the way of pscnv and that C++ library for BSD
        *Someone found out that EKOPath used to cost $1795 USD for a single license back when it was a commercial product, and Michael separately said on his twitter feed that the big news is related to a piece of software that costed $1795
        *I haven't seen any posts on the forums recently from the PathScale guys; they are probably on a hush order or they are too busy getting their software ready for the big unveil

        The evidence points to it pretty strongly, but who knows, maybe the "news" is just that Michael learned about the -O3 and -flto options in gcc. (although that wouldn't agree with the very significant performance increases in the teaser benchmarks, since these two options tend not to affect the performance of your typical program in such a dramatic way!)

        If "real-world" performance gains for CPU-intensive tasks like encoders and decoders, physics engines and software renderers comes anywhere near the benchmark performance gains with EKOPath, this will be a huge benefit to the open source ecosystem -- provided their gcc support is compatible enough to compile things like libjpeg, libvorbis, libtheora, bullet, mesa, etc.

        Comment


        • #19
          Originally posted by XorEaxEax View Post
          Whoa, let's not get carried away. Would I prefer it if Phoronix went for less 'sensationalistic' headlines? Sure. Would I prefer it if Phoronix weren't so prone to 'milk' their scoops for all it's worth (and probably then some)? Sure. But overall it's a great site, free (I ain't paying for it anyways, although I click on the adverts from time to time) and with the best overall technical coverage on Linux and it's surrounding technologies, not to mention the high level of technical knowledge amongst many of the forum members and even guys like xorg/ati devs here providing very interesting information on the development/infrastructure of Linux graphic drivers among other things. In short, Phoronix is fantastic in what it offers and it's FREE!

          As mentioned there are things I would prefer to be different in regards to the way certain articles are presented, but I can't understand how some people can be so negative when those 'gripes' pale compared to all the great stuff Phoronix offers, and again for FREE. Compared to 99% of the so called 'technology sites' covering Linux out there Phoronix is PURE WIN in my opinion, despite it's warts.
          Agreed. It's unsightly the way the websites is designed to generate revenue (especially considering that hackers tend to get easily annoyed by adverts getting in their way), but once you dig through, you usually find a couple gems that you can't find elsewhere. Michael has a good nose for finding big news and capitalizing on it -- financially, that is.

          I'm not too fond of the news he generates by himself, though, with PTS and OpenBenchmarking.org -- I still think they are too difficult to use for the average user, and thus not something that everyone needs to know about. But Phoronix always manages to be the first to unveil pretty important news coming from the Linux hardware/gaming/enthusiast communities at large.

          At heart, Michael seems to really care about finding the kinds of stories that I personally find interesting (PTS exempted). The Unigine stuff was fun. News about the open source graphics drivers is always fascinating. I've bought all the HIBs directly as a result of them being advertised on Phoronix. I've even submitted a couple stories myself.

          If Phoronix is a tabloid, then I'm one of those people who buys trash magazines at the grocery store and sits down 10 minutes early to catch Inside Edition and Access Hollywood on TV every night.

          Comment


          • #20
            Originally posted by ahlaht View Post
            That's what i'm hoping too. Btw. what compiler AMD and NVIDIA use to compile the blobs? GCC?
            GCC 3.2 for AMD. And it seems that the current code state of the driver prevents it from being moved up to compile with GCC 4.x.

            Comment


            • #21
              Originally posted by gbeauche View Post
              GCC 3.2 for AMD. And it seems that the current code state of the driver prevents it from being moved up to compile with GCC 4.x.
              I doubt that they have any real motivation to use a better compiler, though. First of all, any compiler they use would have to be compatible with the idiosyncracies of the compiler they use for building the Windows drivers, since most of the code is shared. Maybe they use GCC 3.2 because they understand the limitations and language support status of this compiler so well that they can confidently train their staff to write code against a safe C/C++ subset that works on Microsoft's compiler as well as GCC 3.2. Basically they might have some 20 - 50 page handbook or wiki site (internally, of course) documenting the do's and don'ts of the syntax and semantics of the driver. And these rules were derived from careful observation of the compilers they use across their different platforms. Changing the compiler changes the rules of the game, which could mean code rewrites may be required.

              Aside from the engineering challenge of rewriting stuff to use a more strict compiler like gcc 4.x (let alone a less popular compiler like Intel's ICC or AMD's Open64 or PathScale's EKOPath), the other question is: would it provide a measurable performance benefit?

              The answer really depends on how CPU-limited most 3d rendering is within fglrx. From the benchmarks I've seen, the general idea is that fglrx is rather heavily GPU-limited in most cases, which is what it should be. Don't get me wrong, it eats CPU intensively while rendering -- but it's not like the code is egregiously inefficient, to the point that the GPU is sitting there waiting for a command but the CPU can't chew through inefficient code fast enough to feed the GPU. If those situations were being hit, then you'd be able to measure it by plugging in a faster GPU. If a more capable GPU doesn't provide a consequent increase in performance, then it's not GPU-bound, so it must be either memory-bound or CPU-bound. But I've seen enough fglrx benchmarks on Phoronix that it's pretty clear to me that bigger card == better FPS.

              PathScale EKOPath, for its part, doesn't seem to have anything to do with a GPU; it's just a very efficient C/C++ compiler for the CPU. So if fglrx isn't CPU-bound, then increasing the efficiency of the parts of fglrx that run on the CPU is not going to result in a noticeable performance increase -- especially with less-capable graphics cards, where more than likely the CPU will sit there waiting for the GPU to finish processing, rather than the reverse.

              Still, it's good information. I find it intriguing, but not surprising, that they use GCC 3.2. And I don't think there will be a whole lot of pressure to use something different.

              The gallium3d drivers, on the other hand, tear through CPU like nobody's business. Reducing the CPU-boundedness of the open source graphics stack would be a huge win.

              Comment


              • #22
                Originally posted by allquixotic View Post
                Aside from the engineering challenge of rewriting stuff to use a more strict compiler like gcc 4.x (let alone a less popular compiler like Intel's ICC or AMD's Open64 or PathScale's EKOPath), the other question is: would it provide a measurable performance benefit?
                My point was not to provide performance but code fixes and new features to help them fix some of their bugs. Some time ago, there was a memory allocation problem for XvBA/Catalyst. A solution to avoid clashes (XvBA used the wrong allocators and then was leaking memory) was to use visibility attributes and not expose certain symbols, or use linker scripts to filter out the necessary ones. By then, another "solution" was chosen as it provided least effort. e.g. wrt. fix the code for C++ conformance and then regression testing.

                In your wiki model (of do's and don'ts), you are probably talking of a C++ subset. If that was to be used, then any compliant compiler would still compile this subset. If this is not the case, this means that subset was probably not compliant in the first place.

                PathScale EKOPath, for its part, doesn't seem to have anything to do with a GPU; it's just a very efficient C/C++ compiler for the CPU.
                Well, it probably evolved but some time ago, Pathscale was not a so efficient compiler as it was marketed. Michael's figures tend to say "yes" nowadays though. Anyway, they did a great job at making it more GCC compatible (newer C++ ABI at that time) than what the original Pro64/Open64/ORC/whatever was. I still wish ENZO is going open source instead of EKOPath. IIRC, for the latter, sources were already available to some research institutions.

                Comment


                • #23
                  If it is EKOPath, I'm going to regret not using Gentoo :P

                  Anyhow, the PKGBUILD for mesa will get a tweak, that's for sure ^^

                  David

                  Comment


                  • #24
                    waste of time

                    so why are you wasting my time with results of "dirndl" without telling me what it is?

                    Comment


                    • #25
                      Originally posted by Linuxhippy View Post
                      so why are you wasting my time with results of "dirndl" without telling me what it is?
                      You're kidding right? If not, be ashamed of your self and read the article one more time.

                      Comment


                      • #26
                        I am genuinly excited.
                        Here's hoping it makes normal software go faster too (Firefox? Kernel? JRE?)

                        J.

                        Comment


                        • #27
                          They already released some of their code under BSD licence,

                          http://www.prweb.com/releases/2011/5/prweb8464380.htm

                          It would be nice if this code dump would be BSD too.

                          Comment


                          • #28
                            Originally posted by kuse View Post
                            You're kidding right? If not, be ashamed of your self and read the article one more time.
                            I read the article several times, and still have no idea what "dirndl" is, other than some kind of magic sauce that makes stuff go faster....

                            Apparently it somehow involves GPUs; a compiler/infrastructure for running traditional CPU tasks on GPUs maybe? I dunno, because the article simply doesn't say.

                            This kind of stuff does make phoronix look bad.

                            Comment


                            • #29
                              Originally posted by snogglethorpe View Post
                              I read the article several times, and still have no idea what "dirndl" is, other than some kind of magic sauce that makes stuff go faster....

                              Apparently it somehow involves GPUs; a compiler/infrastructure for running traditional CPU tasks on GPUs maybe? I dunno, because the article simply doesn't say.

                              This kind of stuff does make phoronix look bad.
                              Then apparently you didn't read the article, i'll help you so you don't look so stupid here on the forum:

                              Those that follow my Twitter feed know a big software announcement is pending after being set back multiple times over the past week. Here's one graph illustrating the real-world impact of this yet-to-be-announced open-source move for open operating systems.
                              In the graph below, "Dirndl" is the codename for this new project that we shall use until the official announcement is made, as the results are just so irresistible. The Ubuntu 11.04 result is the value of a stock Ubuntu Natty installation.

                              Comment


                              • #30
                                Originally posted by snogglethorpe View Post
                                Apparently it somehow involves GPUs
                                Where in the article does it say 'GPU'? Which test is testing the GPU?

                                Comment

                                Working...
                                X