Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
AMD Hardware

VIA K8T800 Chipset Preview - Dual Opteron in Action 258

Posted by timothy from the more-than-you-can-shake-a-stick-at dept.
Mr.Tweak writes "It has been a long time coming but we are finally reaching the beginning stages of 64-bit mainstream computing. AMD has been the first to bring a 64-bit processor to the market with any true support in the Opteron. VIA is one of the key chipset companies supporting AMD64 and today TweakTown takes a preview look at their new K8T800 chipset with AMD Opteron 242 and 244 processors. 64-bit computing is boarding - don't miss the train!"
This discussion has been archived. No new comments can be posted.

VIA K8T800 Chipset Preview - Dual Opteron in Action More

VIA K8T800 Chipset Preview - Dual Opteron in Action

Comments Filter:

  • Yes, but... (Score:5, Funny)

    by Sir Haxalot ( 693401 ) on Tuesday August 26, 2003 @06:55AM (#6792510)
    64-bit computing is boarding - don't miss the train!
    I'll get on the train when the fare is a bit less.

  • Well. (Score:5, Insightful)

    by JanusFury ( 452699 ) <kevin...gadd@@@gmail...com> on Tuesday August 26, 2003 @06:56AM (#6792511) Homepage Journal
    As much as I'd love to board the train, the ticket price is a bit expensive, especially because I don't know exactly where the train goes.

    I'm sure this is true for most other computer users as well. 64-bit on the x86 desktop is not really a 'mature' technology, even though it's been done before with Alpha and Itanium... I for one would hate to spend lots of money moving to an Opteron-based platform, to find out that one of my devices doesn't work or that one of my programs doesn't work. So I suspect that the risk involved (even though it's rather minimal, really) probably is going to keep a lot of people from moving to Opteron and co. for a while.

    • Re:Well. (Score:2, Interesting)

      by brokencomputer ( 695672 )
      I doubt that using a 64bit processor would cause one of your devices "not to work". I don't see why only one of your program's wouldnt work.

      • Re:Well. (Score:4, Insightful)

        by Electrode ( 255874 ) on Tuesday August 26, 2003 @07:00AM (#6792521) Homepage
        Because in 64-bit mode, the size of long is 8 bytes. Some programes have a major problem with that, as I've so painfully discovered...

        • Re:Well. (Score:5, Informative)

          by Ed Avis ( 5917 ) <ed@membled.com> on Tuesday August 26, 2003 @07:10AM (#6792568) Homepage
          For the relatively small number of programs (at least on Linux) that have trouble with 64-bit longs, just compile as i386 code. The Opteron is backwards compatible with 32-bit code and gets reasonable performance out of it.

          • Re:Well. (Score:2, Insightful)

            by cowbud ( 200323 )
            That is exactly why I won't even bother with this processor. If I have the source and it doesn't work with 64 I can compile it as 32 ok great. Now if I buy a game or something that I do not have the source for and it doesn't work what then? Companies will continue to distribute 32Bit applications, because they can support the most amount of platforms that way. As a result the 64 bit processor will just sit there doing 32bit operations.

            The train is a beast, but the desitinations are limited

            Great :)

            • Re:Well. (Score:2, Insightful)

              by eakerin ( 633954 )
              The original Intel 32 bit processors did exactly that, they sat for YEARS running 16 bit code on a 32 bit processor, because no one made 32 bit apps.

              Have patience, 64 bit apps will come, it's just a matter of time.
              • Ok, so I can buy hardware now that runs that code and can run the new stuff, or I can buy a dual 32-bit machine now (for less $$$) and then in 2 years when there's more software I can pust money on a dual 64-bit machine which will cost less then it does today and then I can really use the added feature. Why spend money today for a feature I can use if i buy the "right" software or compile my own? It's not worth it. I'll wait for the tracks to be built up a little more before I board this train.

            • Re:Well. (Score:3, Interesting)

              by mr3038 ( 121693 )

              Now if I buy a game or something that I do not have the source for and it doesn't work what then? Companies will continue to distribute 32Bit applications, because they can support the most amount of platforms that way. As a result the 64 bit processor will just sit there doing 32bit operations.

              Yes, not all applications are or will be 64 bit. You're practically guaranteed not to ever see 16 bit programs again because a 16 bit processor can address only 64 KB of memory without some hack like segmented me

              • Re:Well. (Score:2, Interesting)

                by Anonymous Coward
                "... because a 16 bit processor can address only 64 KB of memory ..."

                Uh... no.

                Traditionally, a 16 bit processor means a processor with a 16 bit databus.

                This doesn't restrict either register size or address space (ie number of address lines).

                My 68K was a 16bit CPU... with 32bit registers and a 24bit address space.

                My Z80 was an 8bit CPU ... with a 16bit address space.

                Likewise, it would be techically perfectly feasible to make a 32bit CPU with a 64bit address space - without hacks - or a 16bit CPU with a
            • It depends what you want to run. If you just want to run binary-only applications that are currently for i386 then there's not much advantage. By the same argument, when the 386SX came out a user running the currently available DOS software would be better off sticking with the 286, since it was slightly faster at the same clock speed for 16-bit code. (Yes I know the 386DX came out first... but it was very expensive.)

              Myself, I'd just buy a new Linux CD and get all my applications recompiled for Opteron

          • Ah, but can you link a 32-bit program with your 64-bit system libraries? Want two of every library?

            • Ah, but can you link a 32-bit program with your 64-bit system libraries? Want two of every library?

              Well, yes. I expect that OSes for Opteron will include two versions of every library for a while to come. I mean, Windows still provides all the 16-bit API calls.

              It wouldn't require every library - just enough libraries to run dodgy nonportable applications (such as the JDK) which are available only in 32-bit format. Such apps usually don't use many libraries beyond libc anyway

    • Re:Well. (Score:3, Informative)

      by selderrr ( 523988 )
      it's not the price that's holding me back (I'm considering a dual xeon for some serious SGML crunching) but rather the question of "what's the added value of 64bit for me here ?"

      I'm doing fine with my 3GB Ram. 6 would be nice, but so far I can stay out of thrashland at safe distance. So the potential speed gain would be minimal. Since it's an 1.4GB ASCII sgml, I don't need 64 bit numbers either...
      Honestly : there's no reason for me right now to go 64bit, and I consider myself a high-end desktop user. I

      • Re:Well. (Score:2, Interesting)

        by ynohoo ( 234463 )
        The only applications that would currently require this are fairly high-end scientific/business processing.

        Until the FPS/MMORG games start requiring it that is...

        • Re:Well. (Score:4, Interesting)

          by Anonymous Coward on Tuesday August 26, 2003 @08:27AM (#6792978)
          AI stuff can benefit, since Lisp on 64-bit architectures is especially nice. Lisp code on 64-bit architectures with 64-bit address space is significantly better performance than on 32-bit architectures, as you can implement many language primitive datatypes within the 64-bit quad, and still have a few high-bits for type-tagging, making a sort of virtual tagged memory architecture.

          That means a dynamically-typed language with comparable performance to statically-typed.

          Historically, one of the significant markets for Alpha processors was people running the Genera virtual lisp machine.

      • Re:Well. (Score:5, Informative)

        by hattig ( 47930 ) on Tuesday August 26, 2003 @07:30AM (#6792622) Journal
        The really useful thing about the Opteron isn't the 64-bit aspect, but the fact that in 64-bit mode you get a lot more registers, etc, to play with. This in turn means that code compiled for the 64-bit mode will run faster than the code compiled for the 32-bit mode. Also the on-die memory controller means that memory latency is much lower, which in turn means things run faster. I'd buy a dual Opteron machine over a dual Xeon machine anyday.

      • Re:Well. (Score:5, Informative)

        by Daniel Phillips ( 238627 ) on Tuesday August 26, 2003 @07:58AM (#6792749)
        it's not the price that's holding me back (I'm considering a dual xeon for some serious SGML crunching) but rather the question of "what's the added value of 64bit for me here ?"

        I'm doing fine with my 3GB Ram...

        On a 32 bit architecture, the kernel has to use nasty, expensive tricks to address memory over 3/4GB (for the default 1:3 userspace/kernel memory split). These tricks require lots of TLB invalidations, which are painfully slow, since the cache has to be reloaded from main memory. 64 bit architectures can just directly address that high memory, so you get a speed boost. How much, I don't know yet, since I don't have an Opteron at hand to benchmark. It will be quite measurable.

      • Re:Well.Actual benchmark (Score:2, Interesting)

        by iva ( 672934 )
        I'm using a dual Opteron (model 240, 1.4 GHz) for intensive scientific calculations. Our program, on the Opteron system, works 1.5 to 2 times faster than the 32 bit version that runs on a double Athlon MP 1800+ (1.533 GHz), depending on the algorithm.
      • It's not going to come from 64 vs. 32 bit as much as from the 8 extra general purpose registers (GPRs). With 8 registers (x86 architecture) you can do very little register allocation, and consequently have to go to memory almost every time you do an operation. +8 registers changes this significantly. The register file is very fast to access and also has a fixed cost, whereas a memory operation can take a couple of hundred cycles (!!) if it misses in the L1, L2 and has to go to main memory.

    • Re:Well. (Score:2)

      by jpc ( 33615 )
      Well I thought I would get on, so I bought some Opterons. Cant get hold of any actual motherboards though.

      Lots of pins to admire though.

      Allegedly they might ship this week. It reminds me of when the athlon came out, there was little choice and availability of motherboards for ages.

  • AMD the first? (Score:5, Interesting)

    by LeninZhiv ( 464864 ) on Tuesday August 26, 2003 @07:00AM (#6792519)
    I think the distinction between PC and RISC is quickly becoming obsolete, and so perhaps one should be including the UltraSparc IIe that's in the SunBlade 100/150, which retail for less than most new PC's.

    By all accounts this is not the best of the current 64-bit chips, but I think it was the first to be offered in "PC-priced" systems.
    • so perhaps one should be including the UltraSparc IIe that's in the SunBlade 100/150, which retail for less than most new PC's.

      and with any luck, it can probably even reach the stellar performance of a PC that was mainstream 5 years ago.

      By all accounts this is not the best of the current 64-bit chips, but I think it was the first to be offered in "PC-priced" systems.

      And I bet some crackheads even bought it.

      Really, I have had the "pleasure" of dabbling with some (old, I admit it) 64 bit sun boxes and
    • I have a SunBlade 100 sitting under my desk that I've not logged into in a year... the thing was worthless from day one. Sure, it was a $1500 sun workstation, but it was slower than a $400 PC was two years ago. Not the best of the current 64-bit chips? Not even better than a lowly 700mhz PIII was... not even close.
    • Sun's management doesn't have the foresight or intelligent to bring their technology to the consumer market. And now I seriously doubt most consumers would consider it for compatibility reasons.

      Too little, too late.

      But if you want one I'm sure you can find them on eBay for next to nothing, which is what they're worth.
  • Where have you been? I've had a 64-bit machine [sun.com] for almost 5 years now. ;) It's even been EOLed since July 2002.

    • It could be said that the sun was not designed for mainstream computing, but the G5s are shipping as Dual 2Ghz 64 bit PPCs and this years Apple WWDC keynote went into the technical aspects (very high memory, IO, and processor bandwidth, or has Jobs put it, it can transfer a DVD from memory to processor in one second).
      The 64 bit AMD is also good but will still require a recompile. LinuxPPC-G5 or Linux-x86-Opteron are both different than the stock vanilla PC Linuicies.
      Apple/IBM and AMD have a very healthy co

  • Readable hardware reviews (Score:5, Insightful)

    by Ed Avis ( 5917 ) <ed@membled.com> on Tuesday August 26, 2003 @07:02AM (#6792528) Homepage
    Just once, it would be nice to have a link to a motherboard review that wasn't split over 15 different sections.

    'Without dragging on anymore, let's see what VIA's K8T800 chipset is capable of' - well, without dragging on any more than going to the next page after about two paragraphs...

  • Memory (Score:5, Interesting)

    by I_am_Rambi ( 536614 ) on Tuesday August 26, 2003 @07:02AM (#6792531) Homepage
    The via board hinders the opteron. Instead of utilizing both on-chip memory controllers, it only uses one. You can see better results if you added a second set of memory banks for the second opteron to use.

    There are more dual boards also including Tyans Thuder K8W [tyan.com]. Rumor has it that nvidia will be coming out with a nforce chipset that will support dual opterons also.

    Benchmarks
    246 Benchmark [amdzone.com]
    Overclocked 246 [amdzone.com]
    • Use a second independant set of memory banks? Then how, in an multithreaded program, would two threads on two independant processors access the same structures on the the heap? What if the task switcher needs to change the processor a task is running on to balance the load? It seems to me what you're talking about is two seperate computers, not two processors operating in SMP.

      That said, you did make one good point 'via hinders the opteron'. VIA has the quality control of a three-legged sock monkey. D
      • Easily, you have an area of memory that is shared by both processors. When the process requests an area of shared memory for inter-process communication the kernel maps the memory from this area. This is what NUMA is all about.
        • Yeah, but why would we use NUMA on a dual processor setup if we've got a 64 bit addressable memory space (only a small percentage of which is actually used)?

          • Re:Memory (Score:3, Informative)

            by msgmonkey ( 599753 )
            NUMA is n't about utilizing memory space, it's purpose is to reduce the amount of contention on a bus, a 64-bit address space actually helps you. Contention is the the reason adding >2 processors on a board only gets you marginal spreed improvements since there is n't enough bandwidth on the bus for all the processors.

            With NUMA instead of sharing the memory and memory bus each processor has it's own local memory and a special bus for accessing other processors memory. Accessing local bus is always at 1

  • Pointless use of dual proc (Score:5, Interesting)

    by bgp4 ( 62558 ) on Tuesday August 26, 2003 @07:03AM (#6792535) Homepage
    While it's slick that they had a dual proc board and all... none of the tests they used used the dual proc-ness of the system. They even indicate in their results that the second proc just threw overhead into the system.

    They've asked for help getting some dual proc benchmarking software. It would be great if someone could help them out. I'm really curious what that box is ACTUALLY capable of. IT's a goodly amount of horsepower with a reasonable amount of L2 cache with 64-bits of data-y goodness. It could make a heck of a "workgroup" size database server.... for a lot less than Sun's workgroup servers.

    I think this next gen of procs (and their 64-bitness) is going to put another dent in Sun. First, lowend *NIX servers based on x86 put a huge dent in their pizza box market. Now, consumer grade 64-bit procs will probably start to eat heavily into their midrange market (like the 220R and that realm). In the big iron... well, that's contentious already. No need to to mess with them there ;)
    • They've asked for help getting some dual proc benchmarking software...

      make mrproper && time make bzImage
      • That should have been "make clean". Anyway, here's a more useful version that is actually a pretty good general benchmark for a dual processor system:

        make mrproper && cp ../config-2.4.21 .config && make oldconfig && make dep && time make -j2 bzImage

        The "mrproper" makes sure that a benchmark run can't take advantage of work done by the preceding one. The "j2" runs four make threads in parallel. To be fair, this should be "j1" when testing the single processor system, si

    • (dual) cpu benchmarking (Score:4, Informative)

      by ion++ ( 134665 ) on Tuesday August 26, 2003 @08:21AM (#6792935)
      one dual cpu test could be
      make -j bzImage
      on the linux kernel. -j spaws a new process when ever possible. It is possible to limit the number of processes, with a number right after the -j. This trick naturally works on other compilations than the kernel, so just find something big, and give it a test.

      Actualy when i read Toms and others test of the Opteron back when it was released i kind of missed tests that used OS tools and programs to test the system, using real programs.
      Source Compilation:
      Maybe you dont recompile kernels all day, but if you are a developper you compile source code, so for you a compile test is worth while.
      Gimp:
      Apple usualy does alot of photoshop benchmarks, so why not use gimp, a known image, and a known script for gimp to benchmark the system with that? Some people use imagemanipulation for work, so lets test real work.

      It might be an idea to test other programs, possibly some engineering tool, maybe blender, or some other tool that uses the floating point unit, rather than the integer part, and or possibly something that can use and test SMP, and/or tests that is cpu bound, memory bound, (or disk bound).
    • They've asked for help getting some dual proc benchmarking software. It would be great if someone could help them out.

      Or you could just let some professionals handle the professional benchmarks.
    • While it's slick that they had a dual proc board and all... none of the tests they used used the dual proc-ness of the system. They even indicate in their results that the second proc just threw overhead into the system.

      Those people do not have the faintest idea about what they are talking about.

      First, of all - a dual processor Opteron is not SMP. It is NUMA. (The difference: SMP="Symmetrical Multi Processing", NUMA="Non Uniform Memory Access").

      In an SMP system, multiple processors share access to the

    • While it's slick that they had a dual proc board and all... none of the tests they used used the dual proc-ness of the system. They even indicate in their results that the second proc just threw overhead into the system.

      They've asked for help getting some dual proc benchmarking software.

      It looked like, other than Sandra and some other synthetic benchmarks, all they did was run a few games on it. I couldn't care less how Half-Quake-Doom-Forever XLII runs on it, especially since your average game will

  • C'T Review (Score:5, Informative)

    by gmania ( 687303 ) on Tuesday August 26, 2003 @07:06AM (#6792547)
    There is a nice review in the latest german C'T too (issue 18 - page 36) of the MSI K8T Master2FAR board with dual opteron support, Via K8T800/VT8237 chipset and a lot of nice features (AGP, SATA, GBit Ethernet). Size constaints meant only a single memory-bus is implemented, a 5-10% speed bump on memory access. Another downside is no PCI-X slots.

    The nicest thing though is the price: 280 euros. Sounds like a good workstation board.

    • Re:C'T Review (Score:5, Informative)

      by DarkSarin ( 651985 ) on Tuesday August 26, 2003 @07:30AM (#6792621) Homepage Journal
      go for this the s2885 [tyan.com] from tyan. It has PCI-X, AGP, SATA, GBe, and hold 16GB RAM... Can't lose.
    • As yet, unless the nForce 3 boards are out, there weren't any Hammer boards that had 64 bit PCI/PCI-X _and_ AGP. I believe both are needed to truly be considered a workstation board now. I think that might change with nF3, but I forget if it is 2P capable, which is another thing that is needed now.

      As far as I can tell, Apple also has a problem of not being workstation class simply by not having ECC support. ECC was standard for workstation computers for at least five years.

      I really don't look that har

  • Overclocking, tweaking, overclock, tweak (Score:5, Funny)

    by dorlthed ( 700641 ) <mxc511&psu,edu> on Tuesday August 26, 2003 @07:06AM (#6792548)
    Does anyone else think this site is a little weird? "PGA or Pin Grid Array can be separated into two parts: the first being Pin, which in this case is the small metal pins we see coming from the bottom of the processor and the other is the Grid Array." Well bless my stars! Who knew?!
  • True support... such as developing their own motherboard chipsets, like Intel, instead of farming the task out to VIA??

    Don't get me wrong, AMD has done rather well relying on 3rd parties to develop mobo chipsets for them, but I'm not sure I'd call NOT having at least 1 in-house chipset solution "true support". If VIA and NVIDIA decided to dump AMD for some reason, they'd suddenly be in a pretty lousy position.

  • This is great news for us (Score:5, Insightful)

    by Rosco P. Coltrane ( 209368 ) on Tuesday August 26, 2003 @07:08AM (#6792557)
    ... the majority of people who want to pay less for the same computers. Whenever a new super-duper computer comes up, a minority fringe with too much money (that I was once part of) blows ungodly amounts of money to get it, driving down the cost of perfectly serviceable, good, fast, but older computers for the rest of us.

    So I say go AMD64 and go KIA, so I can buy those Athlons 2000+ based-machines I need even cheaper.
    • So I say go AMD64 and go KIA, so I can buy those Athlons 2000+ based-machines I need even cheaper.

      Actually, 2600+ is at 100EUR at the moment. It's not going to go much lower, percentually... they just phase out products that are 70EUR. And motherboards, older generations don't really plummet in price, they just disappear. But the CPU-mobo combo costs something like 200EUR if you go with AMD, so who cares?

      Obviously you can buy the stuff second hand, which is a different matter altogether.

  • Spooky Slashdot tagline... (Score:3, Funny)

    by Zocalo ( 252965 ) on Tuesday August 26, 2003 @07:10AM (#6792566) Homepage
    Just got to the bottom of the thread and what do I found for the Slashdot tag:

    #if _FP_W_TYPE_SIZE < 32 #error "Here's a nickle kid. Go buy yourself a real computer." #endif -- linux/arch/sparc64/double.h

    So, the Slashdot Oracle is endorsing Sparc over Opteron? To hear is to obey, Master! ;)

  • 64 bit processors running 32 bit software (Score:5, Insightful)

    by mkosmul ( 673296 ) on Tuesday August 26, 2003 @07:13AM (#6792578) Homepage
    Sure, the benchmarks are impressive, but it would be nice to see more benchmarks using 64-bit-optimized software (eg. an optimized gromacs [gromacs.org]). 32 bit software just doesn't use all the power these chips have.

  • "Finally"? (Score:5, Informative)

    by mblase ( 200735 ) on Tuesday August 26, 2003 @07:24AM (#6792599)
    It has been a long time coming but we are finally reaching the beginning stages of 64-bit mainstream computing.

    I guess you didn't hear about the Apple PowerMac G5 [apple.com] when it was announced months ago and began shipping last week, then....

    • Re:"Finally"? (Score:2, Informative)

      by hattig ( 47930 )
      I don't call a computer system 64-bit when the OS it is running is 32-bit. Sure, the CPU is 64-bit, but it looks like the only 64-bit OS that will be running on those PowerMacs in the near future will be Linux. :D
    • I guess you didn't hear about the Apple PowerMac G5 when it was announced months ago and began shipping last week, then....

      I guess you didn't read the word "mainstream" in the comment you replied to.

    • Re:"Finally"? (Score:5, Informative)

      by FatherOfONe ( 515801 ) on Tuesday August 26, 2003 @08:02AM (#6792782)
      Well I have had my dual Opteron system for about three weeks now, AND I ordered a G5 over a month ago.... The G5 still hasn't shipped to me (I ordered the 1.8GH model). Even if it did the Opteron was out more than a month ago.

      Now granted the article should say something like, this is the first somewhat affordable x86 chip to provide 64 bit computing.

      There are many other links that have excellent benchmark results of the Opteron. Specifically, toms hardware has a great review, but to sum most of the review up...
      The dual Opteron 244 kicks the crap out of a dual Xeon in most linux server type benchmarks. This is WITH 32 bit code. The next step is to get code that is still 32 bit but compiled for the Opteron. i.e. Oracle wich is out now. This gives you another small gain in performance and then lastly you can test again with pure 64 bit compiled programs. The last "MAY" give you some performance increase over 32 bit programs recompiled, but that depends on the program. An example would be a simple "hello world" would not run any faster, but a database that needs more than 4GB of memory should perform better.

      So for our company we didn't compare the Opteron to a Itanium, but to a Xeon and the dual Opteron smokes it.

      Note, that I always say dual Opteron, because a single Opteron doesn't perform any better than the current 32bit X86 chips. In most cases it performs worse. One of the key factors with the Opteron is the way the chips talk to the front side bus. This is currently the bottleneck in most dual/quad processor x86 systems. AMD has somewhat handled this bottleneck by allowing both chips to have a separate path to "some" RAM and providing a larger amount of data to pass from processor to RAM. I can't speak for the quad and eight way systems, but for the dual processor systems this makes a HUGE difference.

      In our environment, a dual Opteron 1.8GH beats a QUAD 2.8GH Xeon in performance (with Oracle). Given that Oracle charges us 15k per CPU + 4k a year, that is a huge savings, and we are not forced to go to a pure 64 bit system today.

      Intel addresses the front side bus issue to RAM by increasing the on die cache of the Xeon. So they released a 1MB version of the Xeon 3GH (they had a 512MB version before), to combat the Opteron. The problem is that it didn't help that much. Intel's solution would be to include X86 code, "done well, not the crappy way it is done now" in the Itanium, and lower the price to under a grand. I doubt they will do that any time soon, so it looks like this will give AMD a good path to the small server market. Factor that in with IBM and SUN wanting to use their stuff in new server, things look ok for the Opteron.

      I still don't know how well the AMD Athlon 64 will be though. That chip isn't due to be released until next month. That is the replacement for the current Athlons, and for AMD's sake it better beat a P4 in most Windows stuff.

      • Is Oracle already available in 64 bit mode for the Opteron?
        • Yes. It came out a few weeks ago. You have to download it.

          I am currently loading RedHat ES 3.x BETA and hope to try it out.

          I don't expect it to work with the BETA of RedHat, but I want to test it out.

          Oh yeah, the RedHat version is also for the Opteron.

          I started the load last night...

      • Re:"Finally"? (Score:2, Informative)

        by jaywee ( 542660 )
        [QUOTE]
        but a database that needs more than 4GB of memory should perform better.
        [/QUOTE]

        I believe any reasonable database will perform much better on 64bit than 32bit even 4GB. For one simple reason - databases are internally using 64bit counters for everything and 64bit int on 64bit cpu is perfect fit :)
      • >Well I have had my dual Opteron system for about three weeks now, AND I ordered a G5 over a month ago....

        I hate you :-D

        *hate in the envy sense of the word

  • enough already (Score:5, Interesting)

    by BenjyD ( 316700 ) on Tuesday August 26, 2003 @07:30AM (#6792620)
    Repeat after me: 64 bit processors aren't new. There's no new "computing fad" leaving the station. No new architectural wonder.

    They aren't even new in desktop machines. I just threw out an Alphastation4 with a 64 bit 21064 from 1996 or something (nearly put my back out lugging the thing down the stairs. They built computers to last in those days). That was a competitor with the Pentium Pro IIRC. Many of the machines where I work were 64 bit ultrasparc before we started to go 32 bit x86.

    That said, the new athlon does look pretty damn fast.

  • I allready rode the train. (Score:5, Funny)

    by jgarland79 ( 665188 ) on Tuesday August 26, 2003 @07:59AM (#6792763) Homepage
    I allready rode the 64bit train to DEC Alphaville and back.

  • Server software (Score:4, Insightful)

    by BenjyD ( 316700 ) on Tuesday August 26, 2003 @08:00AM (#6792764)

    The benchmarking software that would give us the opportunity to test the SMP Opteron platform to its fullest extent costs many thousands of dollars (Ed. Note - If any company wishes to sponsor us with this type of software, you are most welcomed!).

    Thousands of dollars? Can't they just run Apache or something on it and show transactions per second comparisons serving some complex dynamic page?

  • How could you? (Score:2, Insightful)

    by skwog ( 101252 )
    ...64-bit computing is boarding - don't miss the train!

    Miss the train? Miss the train? How could you possibly miss the train? As 64 bit computing comes into the market, 32 Bit will gradually move out (not unlike 8 and 16 bit have previously done). So when you need buy new systems, you're gonna eventually end up buying into the 64 bit thing.

    It's all good, but it's not like you need to buy now, or forever miss the train!

  • PlayStation 2 CPU was not first, but earlier. (Score:3, Informative)

    by Junks Jerzey ( 54586 ) on Tuesday August 26, 2003 @08:33AM (#6793024)
    Putting the various other 64-bit processors aside (and remember, there have been > 32-bit processors since the 1970s), don't forget about the 64-bit MIPS processors. There's one in each and every PlayStation 2. Yes, there's only 32MB in a PS2, but the processor is still truly 64-bit. Integer registers are all 64-bits wide. Actually, they're 128-bits wide, but there's a limited number of operations that can be performed on 128-bit values

    • Re:PlayStation 2 CPU was not first, but earlier. (Score:4, Funny)

      by Glonoinha ( 587375 ) on Tuesday August 26, 2003 @09:34AM (#6793577) Journal
      Bah! I had a Commodore 64 in the early 80's and not only was it a Commodore 64 (note : the earliest use of the numbers 64 in a computer name) it also had 65,536 bytes of memory. 65,536 - you see that? Big numbers. Way bigger than anything I have seen in this whole thread. I have seen some 244's, some 1.8's, some 2.4's, some 32's and some 128's, but this machine was a monster with 65,536. Connected to other computers at 300 baud. Not the puny 28.8 or 33.6 or even 56.7 you read about today, or even the dedicated 128 or 256 lines - or even the wickedly overpriced 1.544 T1 lines that everybody dreams about ... a hard core 300!

      Also held the record for most machines ever sold, at the time anyways. The biggest, and the mostest. Commodore 64. Accept no substitutes.

  • I can't wait... (Score:5, Informative)

    by djeaux ( 620938 ) on Tuesday August 26, 2003 @08:48AM (#6793131) Homepage Journal
    Let's see ... 64-bit WinXP is due some time next year. Longhorn some (ambiguous) time after that. I know /. is the home of the *NIX faithful, but that's a very small percentage out in the real world.

    Are we about to enter 18 months to 2 years of mostly running 32-bit apps on 64-bit hardware? (Or even longer than that, if we recall that "32-bit Win95" was really 16-bit in sheep's clothing.) And what's a "generation" for hardware? 2 years?

    There will probably be some nice bargains on 32-bit boxen later this year & next, I'm sure. And they're gonna run those old 32-bit apps just fine. Then, when they wear out in 2-3 years, you can upgrade to 64-bit hardware to actually run 64-bit apps.

    In other words, that first train trip is going to take you to an amusement park that's still under construction.

  • VIA again? The steady rain of Linux problem reports tracked back to odd behavior from VIA chipsets has kept me from trying out any of AMD's newer designs, since the only boards I can find for them are always lumbered with VIA parts.
  • I think Nvidia should bring to the market an NForce chipset not only supporting dual Athlon64 chips, but also the AthlonXP/MP series. With 64bit WindowsXP delayed until next year, they [Nvidia] could really score with gamers with the dual XP chipset rig...perhaps AMD should give them a call...And please, Nvidia, go Apple's route and drop the legacy support. Drop the floppy port, the serial/PS2 ports, the parallel port, etc. The market needs USB2, Firewire, Wifi, Ethernet (some might wish for Gigabit)Blue
  • The train hasn't even left the station. Or are you attempting to tell us that 64-bit computing will be bug free from its inception?

    I'm going to wait until the second generation of this technology emerges before I put my money on anything.
  • 4GB isn't very much once you start running a number of virtual machines for production use.

    I also wonder if AMD has talked with the vmware and virtual pc people regarding what sort of instructions would be helpful and actually implemented them.
  • These benchmarks were done in 32 bit mode. Win XP Professional Edition Service Pack 4 doesn't run in 64 bit mode. There are operating systems which can run in 64 bit mode but they're not official Microsoft software.

Slashdot Top Deals

"There is no statute of limitations on stupidity." -- Randomly produced by a computer program called Markov3.

Close