Slashdot Mirror

← Back to Stories (view on slashdot.org)

Real Review of DDR Mobo

Posted by CmdrTaco on from the scraping-away-the-hype dept.

An anonymous reader sent us an overview of the AMD 760 chipset, and benchmarks to give some real numbers to DDR RAM. (10-15% speed increase over comparable SDRAM systems)

20 of 63 comments (clear)

  1. The hell with this... by the+Man+in+Black · · Score: 2

    ...I'm in the process of building out a machine for myself (and several web servers). I was planning on holding out until DDR SDRAM mobos were out, since they're supposed to be such hot$hit compared to the present SDR SDRAM. Removing the memory latency bottleneck sounded GREAT to me, and I was looking forward to having a sleek, sexy, swift machine.

    NOW (maybe I'm stupid), but it seems that, not only are halfway decent (read: fully working/compatible) mobos not going to be available for some time, but in order to fully exploit the new chipset, I need a NEW Thunderbird with a 266mhz FSB? Someone please let me know if I'm being a complete moron, reading the article wrong, whatever, but I'm going to be extremely upset if AMD plans on releasing a new version (faster front-side bus) of a chip I JUST bought in the next couple months.

    Sorry if I'm ranting...that's what I get for gut reaction posting, I guess.

    --
    El riesgo vive siempre!
    1. Re:The hell with this... by Goonie · · Score: 2
      ...I'm in the process of building out a machine for myself (and several web servers). I was planning on holding out until DDR SDRAM mobos were out, since they're supposed to be such hot$hit compared to the present SDR SDRAM.

      Somebody correct me if I'm wrong here, but I think you might have your priorities a bit wrong here for a webserver. Firstly, you don't stuff the very latest and greatest technology into a webserver, as it's just as likely to not be stable. Secondly, if you're serving static content, just about anything will do. Thirdly, stuffing your machine with lots of RAM and a fast hard disk is probably more important than absolute memory bandwidth.

      For your own machine, stuff it with the fastest CPU, RAM and graphics accelerator you can find to build a fast Quake machine, but for webserving the priorities are just a little different.

      --

      Any sufficiently advanced technology is indistinguishable from a rigged demo
      --Andy Finkel (J. Klass?)
  2. Re:Good chipsets on bad boards by AFCArchvile · · Score: 2

    That's exactly why I didn't fall for the DDR thing, because I knew it'd be crap at first. Take off those distance glasses and read a little closer next time.

    --
    "Ancillary does not mean you get to rule the world." --U.S. Circuit Judge Harry Edwards, speaking to the FCC's lawyer
  3. #4 is correct by RelliK · · Score: 2

    We are NOT, repeat NOT limited by memory bandwidth. This is why Rambus performs so crappy. Rambus has twice the bandwidth of 100MHz SDRAM but that does not mean computers with Rambus have twice the performance of the computers with SDRAM. In fact, in some cases computers with 800MHz Rambus are *slower* then the ones with 100MHz SDRAM because Rambus has higher latency.

    DDR does not have latency problem. It is basically the same as current SDR, but has double the bandwidth (hence Double Data Rate). So, computers with DDR will get a slight speed increase without incurring latency penalty. DDR machines will be faster than both SDR and Rambus, but still *nowhere near* twice as fast!
    ___

    --
    ___
    If you think big enough, you'll never have to do it.
  4. There was an earlier review of DDR at Anandtech by juggleme · · Score: 2
    Anand's article is actually better in my opinion. They use a different board (from FIC, if it makes a difference; it's still a DDR preview board) and got 5-20% better performance on various benchmarks. They also compare it to a PIII setup with an i815 and an i820 board.

    And don't forget, these are preview boards, hopefully the real thing should give us an even bigger boost. Go DDR! :)

  5. Re:My only complaint about the board is.. by HeUnique · · Score: 2

    Actually..

    The OSS drivers in kernel 2.2.16 are poor - very poor and they're actually YMFPCI drivers - with modification. Translation: bad OSS drivers which supports only up to (almost) 22Khz sound 8 bit stereo..

    But - grab ALSA and try their drivers - they are great! everything is supported (latest ALSA version added support for Bass/Treble)..

    So ofcourse, if you can afford to buy to your PC at work a sound blaster Live - then go ahead and be my guest..

    But these boards are for the main stream and for shops who sell white boxes. Without adding sound card - the seller can sell the maching cheaper..

    If you really don't like the VIA sound chip, and SB Live is too much for your office - I strongly suggest to buy the Yamaha DS-XG based cards, specially that now they are fully supported under Linux (with ALSA drivers and OSS emulation)

    --
    Hetz (Heunique)
  6. DDR? by Scott+Robinson · · Score: 2

    Is it just me, or does anyone else see DDR as "Dance Dance Revolution"?

    Scott.
  7. Re:why choose pc1600 ? by Tower · · Score: 2

    >but what about PC2100 (2*133) which is supposed to be available

    From the article...

    "The Tyan Trinity A762 motherboard we used sported 128MB of Micron PC1600 DDR SDRAM in one of its four slots. This matches up on bandwidth with the 1600MBps of the 200MHz FSB of the Athlon Thunderbird 1.1GHz we used for testing. You will likely need to have a 266MHz FSB Athlon Thunderbird or Duron in order to use DDR2100 memory with the AMD 760 chipset."

    --

    --
    "It's tough to be bilingual when you get hit in the head."
  8. Re:the real benefit by siokaos · · Score: 2

    No, the real benefit, I would say, is the fact that the bandwidth is soo much faster then it would have been. (Becasue of the fact that it can transmit data on both swings of the phase). This is a simple process actually, but I fear (with Quad Data Rate coming soon...) we may hit serious glass-ceilings with things such as doppler effect, signal bouncing, etc.

    --
    http://siokaos.org/
  9. Yay. by yawhcihw · · Score: 3

    Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith. Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket. It's a waste of time and money.
    Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM. Otherwise, we're gonna be running 2Ghz machines bottlenecked to 133Mhz bus. And that will not be cool.

    1. Re:Yay. by substrate · · Score: 5
      It would take more than a gentle or even vicious prod to RAM chip developers. Processor speeds are getting faster because of pipelining and architecture first and process technology second. The pipelining allows the CPU to trade off additional latency for a higher clock rate. It takes a little longer for the first result to come out but after that there is only an incremental delay before the next one. The performance gained by process improvement (improvements in silicon) are miniscule compared to the improvements due to architecture... except that process improvements have enabled the archictectual improvements (designers can cram more transistors onto a die, more wire etc)

      Unfortunately RAM doesn't work that way. People don't want to trade off latency for overall throughput. RAMBUS traded off latency for throughput. It has theoretically higher throughput than SDRAM but more latency, as a result in a certain class of performance measurements it does significantly worse than SDRAM.

    2. Re:Yay. by sethgecko · · Score: 3
      Let's look at what you said objectively.

      Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith.

      Actually, it's a 100% increase in speed over SDRAM. It delivers data twice as fast. 100MHz clock speed * twice the data. Or another way, it yields 1600MB/s bandwidth.

      Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket.

      Yes, it is a drop in the bucket. But you're comparing apples to commodores. It's a 10% system performance increase over systems that use PC100 RAM. That's quite respectable without changing the processor. Wouldn't you like to make your processor run 10% faster without buying a new one?

      Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM.

      Considering that Intel is pushing RDRAM running at 800 MHz and that still runs worse than DDR RAM, don't you think that this statement is a little off target? I understand that your and my idea of decent RAM is not Rambus. But as far as numbers on paper goes, RDRAM is quite fast.

      Also, I take issue with what you say about modern processors needing more speed/bandwidth in memory. I thought I agreed with you until I took a look at Tom's Hardware. A 533 PIII gets a 126 sysmark rating. A 1 Ghz PIII gets a 194 rating, nearly twice as fast when thechip is nearly twice as fast! If modern processors are really waiting for RAM so much, why is processor speed a linear progression up the performance chart? It would be tailing off, with performance gains of a 1GHz PIII only marginally faster than a 700 or 800Mhz at the top of the chart.

      It looks as if the fast cache on chip is the answer to slow RAM, and at least according to this chart, RAM speed does not make such a difference to fast processors.

      --
      Be ot or bot ne ot, taht is the nestquoi.
  10. DDR vs. SD by HighFlyer · · Score: 2

    We already have some good examples to compare DDR RAM vs. the old stuff:

    GeForce-based graphic cards.

    They give us some idea of how much performance increase we can expect. 100% speed boost would be ridiculous. Expect something in the range of 20-30%. And that's still very good if you look at the comparatively small price tag.

    Happy happy, joy joy!

    --

    -- Truth suffers from too much analysis.
  11. Real PREview by levendis · · Score: 3

    This is not a review, its a preview. The distinction is important, because many initial revs of chipset and mobos have numerous performance and compatibility bugs. I wouldn't be suprised if memory throughput increases by 10-15% after a few "mature" revs of the BIOS and chipset. (Didn't something similar happen with the AMD750 "super-bypass" feature, as well as new BIOS revs on Via KX113 based boards?) At any rate, I'm glad to see some improvement in memory bandwidth without a disproportionate increase in cost. Running with an 11x multiplier (on Athlon 1.1ghz chips) is just way too ridiculous.
    ----

    --
    ---- I made the Kessel Run in under 11 parsecs.
  12. I really don't think this is a real test. by c.r.o.c.o · · Score: 2

    Is it just me, or for each of the tests the reviewer had a little comment to make? Like they didn't have ATA100 drives on the SDRAM system, or they had to turn off the sound in quake, or the DDR system was running at AGP 1X...

    I don't know about you, but this doesn't seem to be even a remotely accurate test. And when you're talking about a 10-15% difference, you really do need accuracy.

    So if anybody is planning on buying a DDR mb based on this test alone, they're making a big mistake, IMHO. I know I'm not (either planning or buying). I'll be sticking with SDRAM for a while... :P

  13. Good chipsets on bad boards by AFCArchvile · · Score: 2
    Lately, the trend throughout the motherboard business is to put on a sub-standard AC97 onboard audio chip, a really bad video subsystem, and deny the user the option to disable it. This is obviously a tactic by companies to force your system to have bugs (two big examples: the VIA 4-in-1 driver revision 4.24 [IDE Busmaster 2.1.49, VIA AGP Driver 4.03, IRQ Routing Driver 1.3a, and the VIA INF Driver 1.02, revised umpteen times for nagging problems, and yet they don't seem to go away] and the infamous Intel 810 video chipset).

    I think it'll be about a year before we see some legitimate DDR motherboards; and not these turds that look like they got ganked out of a Gateway. I'm still waiting for something legit to replace my trusty 440BX. After all, that chipset has withstood the test of time, and even holds up to 133MHz. Mine's at 100MHz, so it will last much longer than these Athlons going up in flames left and right.

    --
    "Ancillary does not mean you get to rule the world." --U.S. Circuit Judge Harry Edwards, speaking to the FCC's lawyer
  14. Meaningless article by MobyDisk · · Score: 4

    The final results here look like the old RDRAM tests - slower sometimes, faster other times, with no real conclusion. People gave up on RDRAM because it didn't deliver what it promised, results varied, and price was too high.
    But these results make no sense. DDR has the same latency, higher bandwidth, but results in speed increases from -5% to +6%? It should be consistently faster, never slower

  15. Cache Hit Ratio by K-Man · · Score: 2

    There's already a simple number to determine if memory bandwidth is a limiting factor: the percentage of memory accesses which are satisfied by the cache. Just about every database uses this statistic (for memory vs. disk accesses, not cache vs. RAM) as a measure of how well-tuned the installation is. For DDR, if 90% of the memory accesses are found in the cache, that leaves only 10% for the RAM to show its stuff on.

    Given a sequence of memory accesses (e.g. in a memory benchmark), and the sizes of L2 and L1 caches, it's straightforward to calculate which will require main-memory reads, and which will not. For instance, if your cache size is 512kb, and you're getting a memory location that isn't among the 512k most recently accessed addresses, then you're going to incur a RAM hit (with slight alterations for associative caches, but the idea is the same).

    Big scan or copy operations, where each address is only accessed once, will reduce the cache hit ratio to zero (and fill up the cache with useless data).

    I suspect that these benchmarks are getting a cache hit ratio in the 80-90% range, which would explain the lack of dramatic improvement. But since the testers don't state this number, it's difficult to see if DDR is giving the improvement expected.

    The benchmarks that I've seen for DDR on video cards have usually been able to highlight where DDR gives a big improvement, eg Quake at 1600x1200, and where it doesn't, such as 640x480 with 16-bit color.

    --
    ---- "If we have to go on with these damned quantum jumps, then I'm sorry that I ever got involved" - Erwin Schrodinger
  16. My only complaint about the board is.. by Talonius · · Score: 2

    "With an AGP slot, six PCI slots, four memory slots for up to 2GB of RAM, onboard AC'97 audio and ATA/100, this 4-layer board is aimed directly at the high-end, Socket A, Athlon Thunderbird desktop user."

    Onboard audio? Does anyone actually use onboard audio in their high-end desktop? I HATE onboard audio and video. It'd be a different story if the motherboard manufacturers would support the friggin' thing after release, but most of the time they don't.

    SB-Live Platinum, thank you. I'll keep it versus onboard audio.

    -- Talonius

    --
    My reality check bounced.
  17. Either this mb is POC or... by marat · · Score: 3
    ... or I understand nothing in modern computers. Look: for a long time (since ~200 MHz) I was told that current computers are limited by memory bandwidth. Every improvement in CPU speed gave too little gain in real life performance (even while not limited by disk io). Finally we've got amazing memory technology that should be twice as fast as before. If we have really had bottleneck in memory IO, we should have experienced at least 50% performance increment. What we see? Nothing. Only real difference in their benchmark caused by better IDE interface and hd.

    So, I conclude that:

    1. This motherboard is a piece of crap, or
    2. DDR SDRAM idea is bullshit, or
    3. This report is bullshit, or
    4. We are not actually limited by RAM bandwidth but, say, by real instructions per second (as opposite to tics per second) CPU speed, or
    5. I missed something, or
    6. All of the above.

    ---
    Every secretary using MSWord wastes enough resources