Follow Slashdot stories on Twitter

 


Forgot your password?
Close
typodupeerror
×
Technology

Real Review of DDR Mobo 63

Posted by CmdrTaco 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)
This discussion has been archived. No new comments can be posted.

Real Review of DDR Mobo More

Real Review of DDR Mobo

Comments Filter:
  • ...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.
  • 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.
  • Or. . .

    7. Memory bandwidth is a big bottleneck, but very fast caching technology built on chip masks the slowdown caused by the memory bus.

    Seriously, I was astounded when I saw that a PIII/1000 benchmarks nearly twice as fast as a PIII/500.

    See for yourself at: http://www.tomshardware.com/cpu/00q2/000511/pentiu miii-11.html

  • lick my scrotum. please.

  • If you can't figure out why these benchmarks don't fit your understanding of the world, then you don't know what preproduction on hardware terms really means...
  • 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!
    ___
  • AMD keeps turning out crappy motherboards (can you say Irongate?). Via supports the 133 FSB with via's KX133 chipet. There is NO REASON why AMD can't build in the same funtionality for DDR2100. Via will do it. Shoot it'll probly take Via to get a multiple processor motherboard out too!
  • Yes, You could use your PC100 SDRAM with the current Tbirds. the current Athlon runs on 100Mhz FSB.

    but SDR SDRAM and DDR SDRAM have different pinouts. so if you want to use your old SDRAM in the new DDR MB, you'll need to buy the MB that has both SDR and DDR slots... but there might not be a lot of those around.

  • The reason why memory bandwidth is not a a problem right now is precisely because of caching.
    Only very few applications (like large databases) will get a significant speed boost from greater memory bandwidth. 99% of other applications (even games) will get only a marginal increase.

    ___
  • This is good news. I would definitely buy AMD boards if they had SMP boards. But they don't. So I'm still buying Intel. It's that simple.
  • Yes, You could use your PC100 SDRAM with the current Tbirds. the current Athlon runs on 100Mhz FSB.

    But the 100 MHz fsb doesn't matter. The athlon's memory bus is asynchronous to the cpu bus speed. That's why it's so easy to support either pc100 (cheap upgraders like me) or pc133 (getting a new system?) ram speeds.

    The good old Intel BX chipset, on the other hand, uses the cpu's bus speed and some ratios to figure out how fast the agp, pci and ram clocks should go. That's a bit annoying for overclockers which cheap components, and is one of the reasons that the Athlon was well-received by the overclocking community.
  • ...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.

  • Not much to add here except that this post is excellent and should be modded up accordingly. Insightfully describes the use main memory has in a system in conjunction w/the roles various levels of cache play. Great job.

  • While their practices may well be unethical, you're overlooking the fact that unlike Microsoft, Creative Labs has consistently put out products that are among the best in their field.

    WinNT vs. Linux as a web/ftp/mail/samba server
    SBLive! vs. Vortex2 as a soundcard

    one of those matchups is a lot closer than the other.

    chris

    full disclosure: chris uses a sound blaster live! value under win98, win2k, and linux.
  • 10-15% is a small speed increase, replacing my CPU for a 30% speed boost would be cheaper and more effective than buying 256MB of new RAM.
  • I'm still looking for something to replace my 430HX chipset machines. The PPro FX chipsets weren't bad by comparison to the later stuff, but my BX chipset machines are all non-server worthy.

    Look through the older stuff being sold on ebay; the pentium 200's that are going for more than modern machines are often actually worth the money.

    The motherboard makers are screwed by the chipset makers; why shouldn't they throw marketing trash like built in audio on; they board's never going to be worthwhile 'cuz the chipset sucks and there's very little they can do about it.

  • Memory does slow a system down, but that's why cpu's now have ondie (& before that off-die) cache. Cache allows you to have really high #'s of clock cycles without beign slowed to a crawl by ram...

    Out of order execution & some other cpu tricks help as well... If you could give a P3 a mobo with an EV6 bus, you'd see a smaller increase than the athlon more from caching then anything else... athlons have very good cache structures...
  • Anand's article [anandtech.com] 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! :)

  • DDR? (Score:1)

    by kimmop ( 121096 )
    The Brand for modern technology. For example the Trabant was a car with no competitor in the west. The Trabant was the only car in the world that didn't need a metaljob. (Because it was made of plastic)

    --

  • Probably because you are too young. The DDR ("GDR" in English) ceased to exist more than 10 years ago...
  • 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)
  • Well as I see it, the chipsets VIA has produced so far seems to be relatively problem prone (with the exception of the KT133 which is only slow). The KX133 which supports PC133 SDRAM had trouble running some power hungry GeForce cards stably. They also don't seem to be able to run Thunderbirds/Durons stably (with the possible exception of the Asus and Abit boards). The Irongate will run Thunderbirds on the get go. Also the Irongate boards perform on par using PC100 RAM vs a VIA board using PC133 RAM. You'd almost think that the Irongate was released after the KX133. And considering that VIA must have had engineering samples of Thunderbirds, Athlons and Durons before they released their much delayed KX133 and considering that they had a lot of help from AMD, I don't see them making a chipset superior to AMD's 760 anytime soon. From what I hear, VIA is delaying the release of the their DDR SDRAM supporting chipset. In the past, AMD has publicly announced that they do not plan to produce their own chipsets as a mainstream product. And they have tried to keep their word. Thus many motherboard makers did not even make an Irongate board. I would guess that the only reason their chipsets are somewhat lacking in features is because they plan to produce chipsets only as a temporary measure so that sales of their cpus will not be as badly effected by the lack of chipsets (in this case the lack of DDR SDRAM supporting chipsets). If VIA had its act together and actually produced a working chipset on time, I don't think either the 750 or the 760 chipsets would have been released.

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

    Scott.
  • Maybe I wasn't super clear...the bleeding edge hardware was for my personal machine. My webservers are Duron 700s with 256mb of ram and IDE RAID. Trust me, I know the need for stability in a webserver.
  • karmawhore
  • And what is more I think that this test should have tested DDR and SDRAM in the same system if this was supposed to test the speed increase from DDR.

    OTOH if this was supposed to be MB test both boards should have used SDRAM. I'm afraid that current test has no real information whatsoever because pre-production MB is slower - but DDR memory is faster.

    I would have wanted to see at least test where AMD760 was running SDRAM to have real results about DDR being faster.
    _________________________

  • You crunch numbers much better than me. Took more time too I see.

    1. I understood the original poster's intent by saying that SDRAM only gives a 10% system boost. The point I was trying to make was that a ten percent system boost by using DDR RAM (and a supporting motherboard), all else being the same, is quite respectable. What did he want, a system to run twice as fast by changing the RAM? It's still gonna run in the same general neighborhood of preformance (due to efficient caching was my second point).

    2. You're right. I ambiguously claimed that you could get a 10% increase without buying a new processor. I still think it was clear enough. I didn't say you didn't have to buy a new mobo. And besides, buying a new mobo is much cheaper than buying a new processor. But I said nothing about cost-free.

    3. I will be the last one to claim that a new PIII/1000 is twice as fast as a PIII/500. My point was that it is much closer to double the speed on Sysmark than one wold expect. If you adjust PIII/533 =126 to the expected PIII/500 = 118, then you get that a PIII/500 gets around 100 sysmark (rounding grossly) and a PIII/1000 gets around 200, rounding less grossly.

    Your number crunching is much more precise than mine. In reflection it should really be more like 60% difference between 500 and 1000. You got me there.

    At the top of the charts, you really do see it waiting for the RAM. But not as much as one (e.g. I) expected.

    And I would think that DDR RAM would bring the stats more in line with double the SYSMARK speed.

  • the real benefit to using DDR RAM is that you won't have to sell your car/kids/blood/sperm/organs in order to pay for your RDRAM habit. That's a plus if it've ever heard one. And besides, we all know that RAMBUS is "the man"
  • At first I read "interview of the AMD chipset" :-)
  • >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."

    --
  • 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.

  • Yay. (Score:3)

    by yawhcihw ( 171760 ) on Monday September 25, 2000 @03:28AM (#756979)
    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.

  • Re:Yay. (Score:5)

    by substrate ( 2628 ) on Monday September 25, 2000 @04:03AM (#756980)
    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.

  • But I won't be looking at anything like that for a while. You can get plenty of performance these days for a pretty good price. Until there are a few DDR boards that are proven, I'm not interested.

    Spooon!

  • Waste of time/money? The only things that drive technologies up is innovation, caused by cash flow. Without it, you'd !have ur x86 bro...

  • 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!

  • hmmm....
    <a href="http://nothing.nothing.com/why _oh_why_does_it_count_binary_as_caps/i_will_never_ know></a>Q:01010000100101001000010111101 01101010101001111111110101101010100101010010010001 00111 0111 1011010111110001110101?

    <a href="http://nothing.nothing.com/why _oh_why_does_it_count_binary_as_caps/i_will_never_ know></a>A:01010100101010010010001011010 10101001111100001001010010000101100111010001011110 10110 1010 10100111110100001001010101101010100101010010010001 001110111.
    --

  • Real PREview (Score:3)

    by levendis ( 67993 ) on Monday September 25, 2000 @03:34AM (#756985) Homepage
    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.
    ----
  • ...but Creative Labs is one of the crappiest companies out there, to the point where I'd call a general boycott for their totally unethical behavior. Look at how long they basically sold the same equipment (SoundBlaster 16 ISA series) until Ensoniq brought out their hardware, at which point Creative just BOUGHT them, then re-released their hardware at a higher price point. Oh, and look at how they handled a company that offered better sound and performance - Aureal, and their A3D 2.0. After suing Aureal and forcing a developing company to spend all it's finances on litigation, they lost the suit, but ended up buying Aureal in bankruptcy proceedings.

    (I know that the Diamond Monster MX300 caused a performance hit, but apparently that was caused by a poor implementation of the Vortex2 chipset by Diamond - apparently the later versions put out by Aureal actually offered a smaller performance hit than the Sound Bastard Dead! card did.)

    Creative Labs is just about as bad as Microsoft in my book.
  • 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

  • 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.

  • Yes, motherboards based on the KT133 chipset (Via's chipset for Durons & Thunderbirds) can use PC-133 or PC-100 just fine.

  • Never ceases to amaze me.. (Score:1)

    by Anonymous Coward
    Well, it sure seems that someone FINALLY realised what held RDRAM systems back.. I mean gee, comparable to PC133, 133mhz bus... hmm.. A little suspicious eh? Well, All you people hoping for DDR Intel chipsets for their P3s, forget it. It will have the same effect as RDRAM - practically none. As for the AMD guys, of course it will have a nice effect, i mean, you bust up to 200mhz bus, and have the same performance of a 133mhz bus P3.... 133mhz memory... 133mhz fsb performance... hmm.. Susupicious again. As for the review saying that there isnt much of a performance increase, well, that's how everything starts huh? Remember back when the P3 came out? "New P3, oh hey, shit performance over the P2, im not buying one of those." Anyway, for all you people dogging on sharkyextreme, stop it. Same benchmarks as they always use. Look at the other articles before you state biased opinions. Remember, this is the first released board. Someone always has to do it first, and it never comes out perfect in the first fell swoop now does it? And as usual, DOES NOONE READ THE ARTICLE BEFORE SAYING STUFF? Sheesh, just look at the conclusion part.
  • That would be the case if the ram was the only thing that was variable in this experiment. ASUS consistently makes faster motherboards than the competition. Also, it's a comparison of two completely different chipsets which adds even more variance to the results. Just wait for a KT133 to K?266 comparison with the same motherboard manufacturer and im sure there wont be a time when the KT133 outperforms the 266 model.

    You Like Science?
  • "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."

    Sysmark ratings use a small enough working set that the memory isn't overly taxed (L2 cache is a big help). For some things, raw integer or fp power overwhelms the memory speed, but in a lot of real world situations, that memory speed does hold you back. The more multi-tasking that you plan to do, larger working sets (for db apps, etc), and faster through-data that you work with (streaming, virus scans, etc) the more important the memory speed becomes... Most benchmarks are greatly aided by L2 cache (as well they should for proc benchmarks), and it would be nice to see some other numbers.

    The 'stream' numbers would be interesting, to see if the memory/chipset can really deliver close to the rated throughput. Run the same tests with the L2 disabled (yes, yes, then it isn't a real world example, but it isn't anyway) for 'normal' and DDR SDRAM - it would be interesting, if not revealing. A nice kernel compile (which is assumed to be CPU-bound) might reveal some interesting things.

    RAM speed may not make a difference to fast processors, but it makes a difference to a fast system...
    --

  • Meaningless article (Score:4)

    by MobyDisk ( 75490 ) on Monday September 25, 2000 @04:18AM (#756993) Homepage
    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
  • OK, now let's step back and take a look at what you have said....

    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.

    OK, yes, in theory it is supposed to be 100% increase in speed. So, where is that increase?? I think that is his point, this great new memory isn't too efficient if you double its performance window but only see a 10% improvement when actually trying to use it. That definitely says to me the wrong problems are being addressed at the system level!

    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?

    Whoa! Hang on a second. Yes, a 10% improvement without any cost would be nice...but you seem to have forgotten that in order to get this increase, you have to change your MB and your memory (or just build the new system with these parts). This isn't a costfree speed gain here. I don't know if you intended to imply that, but that was the way I read it. I will admit that if you are building a new system, going the DDR route is probably the wise choice in terms of cost/price, but if you already have a system, the cost could definitely be deemed prohibitive!

    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.

    OK, here is where I really question some things. First off, 194 is only a 54% increase over 126, that is hardly "nearly double" in my book (of course, the author of my book may be different than yours). To get this 54% increase in this benchmark, we cranked the CPU speed up by 88%! So, if the CPU isn't waiting around...what is it doing with those extra cycles it is clicking through??? Again, we have a very poor return on our investment in speed. Any engineer should be cringing at these numbers, I know I am. As for why we have a "linear" progression, linear doesn't mean 1:1, so yes, the wait time is still there, but the CPU time is getting smaller and smaller and we see the overall score go up. Finally, let's look at the data from Tom's Hardware and see if I am right, that things are flattening out....Using the BX chipset at 133MHz (since it was on top of the charts):

    CPU speed Score
    1000 (+7.2%) 194 (+4.3%)
    933 (+7.7%) 186 (+5.1%)
    866 (+8.4%) 177 (+5.4%)
    800 (+9.1%) 168 (+7.0%)
    733 (+10%) 157 (+6.1%)
    667 (+11.2%) 148 (+8.0%)
    600 (+12.6%) 137 (+8.7%)
    533 126

    (My apologies to Tom for using his data without permission, I hope he does not mind too badly)

    So, we see that we cut the performance gain by more than half, while cutting the CPU speed gain by less than half. Sure looks to me like we are losing the benefits of speeding up the CPU. Perhaps the original poster wasn't so far off base?

    My apologies as well if this post seems a harshly worded, I was just a bit put off by statements that lack backing from the stats they claim back them!
  • I bet your opinion would be different if you were a stockholder. I still like Intel CPU's, but I put most of my money into AMD last two days. After Intel took them down 20% it was a great buy op. And when earnings come out next month it should be even better. Business is business. A company's board has a duty to their stockholders and that is to be the best in their industry/sector and run everyone else out of business.

  • Huh? (Score:1)

    by TheMCP ( 121589 )
    East German communist RAM?
  • You could always go look at the timing diagrams, and figure that out for the best case. Of course, most people aren't that concerned with the real technology, and are just concerned about how soon they can get 200fps at 1600x1200x32b 8^)

    Seriously, though, the x86 architecture (the bus structure most notably) isn't the best optimized for memory transfers, though the I/O is much worse (the whole x86 addressing scheme is due for a rewrite). </rant> Oh well, that's another topic for another day.
    --
  • Ge-Force2 is a totally different case than CPU's. The Ge-force2 is almost *totally* bandwidth bound in most cases, so that 20-30% increase you are seeing is probably the maximum a CPU will ever see.

    This is obvious if you look at benchmarks. Crank up the core clock on a Ge-force2 and you get little to no improvement. Crank up the memory clock and you get measureable improvement.

    For CPU's dropping in a 1Gig compared to a 800 gives you a noticable improvement. So obviously CPU's aren't bandwidth bound nearly as badly as the Geforces are, so they won't see that high of a performance increase.

  • Well, your POC comment isn't too far off - this is not release-level hardware. It took a couple tries with the SDR chipset to get things performing correctly 750->751->751b. Once everything gets worked out on this one, we should see a more consistent improvement.

    #4 is also pretty accurate, and can be further alleviated with better memory access management (think RISC) and pipelining (aka, P4). We are only RAM limted in certain situations, for much of what we do, a great deal is held in the L2 cache, so the accesses to main store are far less frequent.

    --
  • Well, I hate to break it to you, but maybe you should take a look at this [anandtech.com].

    It seems AMD has been planning to release a 266MHz FSB processor in 2000 for a while (Note the slide is from Comdex in the Fall of '99). Now, whether or not this will actually happen is up for discussion.

    Oh, and by the way, this preview was on Anand's web page on the 14th of this month... how do things slip through the cracks so often here?

  • 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.

  • we got some real information on these things. I'm wondering however how this will affect my purchasing.
  • doh! damn preview!

    --

  • Re:Yay. (Score:1)

    by AleT ( 51575 )
    Lets look at this objectively. A 10% speed increase using buggy/prerelease chipset and drivers which can't even manage to turn on AGPx4 isn't too shabby at all. Especially if it doesn't cost any more!

    For comparison, how much extra do people pay for a 10% increase in processor clock?

    And when these DDR boards come out, AMD will release its 133/266MHz FSB processors, which should give performance another significant nudge upwards.
  • Why dont they just show us raw units of how fast it can read/write with proprietary machines? Then it wouldn't matter (accept, of course, for caching differences)
  • "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

  • Either this mb is POC or... (Score:3)

    by marat ( 180984 ) on Monday September 25, 2000 @04:19AM (#757007) Homepage
    ... 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

  • why choose pc1600 ? (Score:1)

    by Anonymous Coward
    the test uses PC1600 ddr sdram, (2*100Mhz) but what about PC2100 (2*133) which is supposed to be available at the same time for approximately the same price ???

    I think this tests shows some bias against ddr by not featuring the fastest (and probably the most used in some months) type of ddr sdram.
  • I'm just curious, if I wanted to pick up an AMD Thunderbird 1 Ghz CPU and motherboard, would I still be able to use my PC100 SDRAM, even though I will experience a bit of a bottleneck with it? At one point, I would upgrade the RAM, but since I only bought what I have about a year ago, I'm not ready yet. Suggestions?

  • Re:Yay. (Score:3)

    by sethgecko ( 167305 ) on Monday September 25, 2000 @04:27AM (#757010)
    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 [tomshardware.com]. 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.

Slashdot Top Deals

If you want to put yourself on the map, publish your own map.

Close