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

 


Forgot your password?
Close
typodupeerror
×
Hardware

The News From Computex, Including Non-Rambus P4s 74

Posted by timothy from the will-rambus-fade? dept.
M-Doggy writes: "With the festivities at Computex over in Taipei bringing in more out-of-towners than the Chinese New Year, a plethora of new product announcements and sneak peeks have hit the show floor. I noticed that AnandTech already has two articles up covering the action. The first one covers what was seen on the floor, including the AMD 760, NVIDIA's Crush chipset, and more. The second one has some interesting information regarding the non-RAMBUS solutions for the Pentium 4 and even includes some preliminary benchmarks. Both speak of the incredible politics behind the show; politics that rival even the recent events in the Senate." (Read below for another snippet on those non-Rambus P4s.)

And Tuzanor writes: "Yahoo is reporting that Intel is releasing the i845, the first P4 chipset that doesn't use 'fast but expensive' Rambus memory. Funny, the story says that they will be using the "current standard DRAM chips" but says nothing of DDR RAM."
This discussion has been archived. No new comments can be posted.

The News From Computex, Including A Non-Rambus P4 More

The News From Computex, Including A Non-Rambus P4

Comments Filter:

  • DDR isn't that expensive these days... (Score:1)

    by Anonymous Coward
    a friend of mine got 512meg (2x256mb) for about £120 on Saturday for a new system (on Tottenham Court Road in London). I think he would have gone for a full gig, but the mobo he's got only can only 3 sets.

    Mind you, he was sensible and is running an Athlon anyway. Hey wouldn't that make a much better slogan than "Intel Inside".
    reply: "don't worry mate, I've got an "Athlon Anyway :-)"

    Matt B
    (couldn't be arsed to dig out login details)

  • Re:It will be interesting to see... (Score:1)

    by Anonymous Coward
    Yes... But would you rather have RAM thats 1.25 times faster, or have 5 times as much RAM (or have the same amount and pay 5 times less)? I guess it depends on your application, but I think that for most people, RDRAM is just too darned expensive.

  • DDR vs. Rambus performance. (Score:1)

    by Anonymous Coward

    Anand's benchmark result isnt suprising. The P4 *NEEDS* massive bandwidth to perform halfway-decently.

    Most P4/Rambus PC600 show a fairly large performance decline compared with PC800.

    The result show P4 not performing all that well with DDR memory -- which seems to be why Intel is pushing for faster DDR (PC2700 and PC3200).

    DDR has about the same latency as SDRAM (slightly worse latency in some configurations), but twice the bandwidth. PC800 has about double DDR's bandwidth, but much greater latency -- at least partly because it's multiplexed and probably registered. Also, Rambus puts out enough heat to need a heat spreader -- a metal plate over the top of the chips.

    OTOH, P4 systems, while not selling well due to the economy, are outselling Athlon/DDRs and P3/DDRs. The buzz is that DDR isnt profitable at this point. The next iteration of DDR will probably need a different form factor -- i.e. not compatible with current motherboards -- they've been talking about mini-DIMMs that are half as wide as current DIMMs, and use fewer chips.

  • Re:DDR vs. Rambus performance. (Score:1)

    by Anonymous Coward
    *sigh* Normally I wouldn't even bother responding to a comment like this, but the ignorant ignore me. PC800 does *not* have twice the bandwidth of DDR memory! It doesn't even have more bandwidth than DDR memory. PC2100 DDR (that's 133 DDR, or "266", mhz) gives you 2.1 GB/s of bandwidth (hence the rating). PC800 Rambus gives you 1.6 GB/s of bandwidth. Yes, the bandwidth of Rambus is actually *less*. Now things are a tad more complicated than those theoretical bandwidth numbers. For one thing, Rambus memory tends to come much closer to its actual theoretical bandwidth than SDRAM does, but even so that's not nearly enough to account for the performance difference. The real reason the P4 performs better with Rambus is because it used *dual-channel* Rambus, giving it 3.2 GB/s of bandwidth. Dual-channel has nothing to do with the type of memory, it's a function of the motherboard and chipset. Yet all the numbers given are comparing dual-channel Rambus to single channel DDR. Theoretically, there is absolutely no reason why somebody couldn't make a dual-channel DDR chipset. There have been arguments about how the pin count of Rambus makes it easier to produce a dual-channel motherboard with it, but things changed today. You see, nvidia released something called nForce, perhaps better known as just "Crush". And do you know what that uses? Dual-channel DDR! And do you know what else? It's on a 4 layer board, while dual-channel Rambus boards are typically 6 or 8 layers, and it's targetted at the *low-end* market. That's right, it's actually easier and cheaper to produce than a dual-channel Rambus board! Now, Crush is an Athlon chipset so it may not be directly applicable to the P4 (And, unfortunately, the Athlon doesn't have the same chipset bandwidth as the P4 and it's not as bandwidth-hungry in the first place, so it won't benefit as much from the dual-channel memory. Even so, preliminary benchmarks show that if you don't use the integrated graphics Crush will absolutely kick-ass). Even so, this certainly opens of a possibility for the creation of dual-channel P4 boards in the future, in which case Rambus will have absolutely no advantage. AC

  • Re:Price Comparison of Rambus and SDR133 (Score:2)

    by Anonymous Coward
    You are indeed correct that the $15 stuff is really bad and for low end systems. For my own stuff I typically purchase Micron or Siemens RAM which is decent stuff. Runs really nicely =)

  • Actually, AMD 760-based boards have been available in upwards of a month already.

    The 760MP boards are what you're reading about just coming out now, in beta, etc. I've had my EPOX 8K7A board for a few weeks now already.

  • Re:Nanya (Score:1)

    by pod ( 1103 )
    And no, I'm not getting it confused with the spring water. (Hungry for swap, thirsty for Nanya?)

    You certainly are not confusing anything with water, the brand you're looking for is Naya [naya.com].

    --

  • Keep in mind the feature set of the Tyan board. (Score:3)

    by slothbait ( 2922 ) on Monday June 04, 2001 @09:01AM (#177581)
    $600 does seem steep until you consider the feature set.

    If memory serves, that board has 2 onboard SCSI controllers, 2 onboard ethernet controllers, and an onboard AGP graphics device. If you bought the MSI board, and then the seperate plug-in devices to bring it up to that functionality, it would come out to about the same price.

    So, the Tyan board is priced reasonably given its feature set. Of course, if you don't need all those features, then the less expensive board makes more sense for you.

    --Lenny
  • AMD 760 boards yes, AMD 760MP no. Big difference between the single-proc 760 and the dual-proc 760MP. FYI.
  • DDR is not much more expensive. 256MB stick of PC2100 DDR cost $65.69, exactly the same as 256MB stick of PC133 SDRAM. (see here for example: http://www.crucial.com/store/ListModule.asp?module =184-pin+DIMM&x=8&y=15). Now, considering that DDR has the same latency and double the bandwidth of SDRAM, I'd call it a good deal. That said, you will not notice anywhere near 2x performance increase overall if you go with DDR. As it stands, memory bandwidth is not a bottleneck right now. Only very few applications will benefit significantly from increased bandwidth.
    ___


  • Go to this page - http://www.ebns.com/printableArticle?doc_id=OEG200 10601S0063 - and you'll find that the SDRam price is wiling to a never before low level.

    128Mbit chips are selling for US$3.00 or lower in some market ! That means, a stick of 128MByte SDRam will only cost - to the manufacturer of the SDRam sticks - about USD 26 to priduce !

    I foresee that in the coming months - One or perhaps two months - we will see the price drops being reflected in the CONSUMER market.



  • According to this report

    http://www.ebns.com/printableArticle?doc_id=OEG200 10601S0063

    chip vendors are having a 6 to 8 week supply of chip in stock, and they are NOT very happy about this.

    So.... they flood the market with cut-throat price chips.

    In some spot market, 128Mbit chips can be had lower than $3 each. That essentially means, to get a 1GBYTE supply of RAM, you multiply $3 by 64, that means, for a palty $192, you'll get yourself your 1GBYTE memory.

    Even when you include the packaging, and stuffs, the price won't be going more than #220.

    But you better get the chips now, as when the oversupply is over, the price will go up.

  • Funny you should mention politics. Certainly RDRAM is better suited for the higher-bandwidth FSB of the P4 than the P3. However, when looking at DDR vs RDRAM performance on the P4, you should remember that Intel has no particular reason to make their DDR solution work very well, and a great deal of reason to show it performs worse than RDRAM. Just like their 815 (was that the one?) which performed worse than the ancient 440BX. No reason for it to do worse but for Intel not wanting it to perform well.

  • Re:Quite interesting..... (Score:3)

    by Chris Burke ( 6130 ) on Monday June 04, 2001 @09:30AM (#177587) Homepage
    Sure rambus is faster, but does it deliver a reliability+price/performance ratio that will attract corperate or even consumers?

    Faster than what? Sure, a dual-channel solution has more bandwidth than a single-channel (rah nvidia) DDR, but the latency sucks. This is why the benchmarks swing so wildly with an apps dependence on b/w vs latency. You can't replace one with the other, regardless of rambusinc hype.

    Face it, today your bottleneck is the Video/Hard-drive (except for us using Ultra160 Scsi) and the bus to the outside world.

    Sorry, but even with your scsi disk is still the biggest bottleneck (unless scsi somehow magically turns seek times into nanoseconds). I don't care how much data you can get me in a second -- if I (the cpu) have to wait ten million clock cycles before the first byte of data shows up, then I'm screwed.

    Which I guess means I agree with you. :)
  • Usually you do, except for the P4 processor. The P4 will probably never be what you want. See previous /. articles for long descriptions of the P4 problems. Rambus was just the tip of the iceberg.
  • Nice example for consumer grade equipment. This is not the case for performance stuff.. Example. adaptech 29160 SCSi controller. Sharing an IRQ with this beast causes a significant decrease in performance, Linux drivers will fail to function when it is shared because the programmer knew that the hardware will choke by design. now, the motherboard gladly shares ide and other devices as a IDE is slow enough to have other things happening during a transfer/access. Video capture - example card: targa 2000+ PCI. it will crank out a data stream as fast as the PCI bus can handle... now share that IRQ and all of a suddent you have frame dropouts, jitter, etc.... Here's another device I have to force to it's own IRQ (and a low one as you cant move motherboard resources off of IRQ 14/15)

    If they would put all that damned integrated motherboard crap at IRQ 16,17,18 we wouldnt have that trouble..... disable USB you say? ok... funny how the IRQ really isn't released.

    the current PCI specifications are fine for consumer level junk... (and hell, they want us to only use USB anymore anyways...YUCK) but for anything that is professional grade or industrial grade... you cant have something wanting attention while using the high performace items.

    (Funny, the Compaq ML530's bios will force all devices away from the IRQ used by the SCSI raid controller... They know what I learned... you cant sucessfully share IRQ's on high performance SCSI devices.)

  • Quite interesting..... (Score:5)

    by Lumpy ( 12016 ) on Monday June 04, 2001 @09:11AM (#177590) Homepage
    Sure rambus is faster, but does it deliver a reliability+price/performance ratio that will attract corperate or even consumers? Rambus has recieved a ton of bad press over the past 6 months, and with SDRAM priced at insanely low levels (Hey, I remember buying 16 meg of ram for over $1000.00 for a customers server) only the truely retarted would go rambus. IBM isn't even using rambus in the AVID non-linear video editing suites (Got a new one here less than 8 months ago, Yup PC-133 SDRAM in there) The latest Compaq servers dont use it...

    Face it, today your bottleneck is the Video/Hard-drive (except for us using Ultra160 Scsi) and the bus to the outside world. (4 100BaseTX cards on a PCI bus is not living up to it's potential)

    I dont care about faster, Give me 32 IRQ'S, how about an expansion bus that doesn't suck? How about a bios that isnt a P.O.S. out of the box?

    my biggest gripe is the fact that we have been forced to use 16 IRQ's for way too damned long, they should have expanded it when they intorduced the PCI bus, now we have to wait forever to have a couple of free IRQ's on a new motherboard... (asus mobo's take 15 irq's out of the box)

    There was a nice turnaround in hardware 2 years ago, but it is heading back into that pit of crap that made the late 90's hell on hardware hackers.
  • RDRAM sucks lots when coupled with the P4 because it has high latency. Coupled with the very deep pipeline the P4 has, this means that a branch misprediction will cost LOTS. Rembmber that the P4 fares well in very predictable environments such as multimedia.

    From this point of view, SDRAM could help improve the P4's figures, since it has lower latency, thus branch mispredictions and random RAM accesses will be less penalized.

    I'll wait and see.
  • Checked their share price. Its trading at around $10, my dad asked about getting into this a year ago and I said don't - it was trading at about $80 (went to $100) and was a "hot tip" from a "friend."


    Since I am now an expert in the stock market I can offer stock market advice to the /. community.

  • The problem with the comparison is that you have to use Rambust in pairs of 2, so comparing 128 meg sticks is slightly misleading. You should compare 1 SDRAM 128 at $15 with 2x64 for the same amount of memory, which makes it cost $74 as opposed to $59. So Rambust is even more expensive than first reported.

    F.O.Dobbs

  • DDR has about the same latency as SDRAM (slightly worse latency in some configurations), but twice the bandwidth.

    SDR and DDR both take about six cycles to set up the transaction, then SDR can do one transfer per clock and DDR can do two per clock. Virtually all motherboards have a 64-bit wide memory bus, so a Pentium 3's 32 byte cache line requires four transfers, an Athlon's 64 byte cache line requires eight transfers and an Pentium 4's 128 byte cache line requires sixteen. So, each SDR cache fill on a Pentium 4 should require 22 cycles (6 setup + 16 transfer), while each DDR cache line fill should require 14 (6 setup + 8 transfer), an improvement of 57%.

  • Rumour has it that there will be be a version without the two Ultra/160 SCSI controllers.

  • I wonder how long it will be until places like VA Linux and Penguin Computers have dual-athlon rackmount servers and deskside workstations for sale? :-)

    Good luck with VA Linux and AMD. As far as I can tell they are as intel-only as Dell. If you ask them publically about AMD you get tight-lipped "No Comment" comments.

  • The buckets only held one bit.

    You had bits? Why, in my day we only had zeros... none o' them fancy 'ones'! And we had to carry them by hand eight miles through the snow... up hill both ways! {shakes cane in the air}

  • Re:Nanya (Score:3)

    by csbruce ( 39509 ) on Monday June 04, 2001 @09:57AM (#177598)
    I hate to be one of those "Back in the day..." guys, but back in the day when I bought my first RAM upgrade for a PC, I payed more for 8MB than I would pay for 512MB today. Now that's fucking progress, mates.

    Yeah well I remember paying over $80.00 for 8 *K* of memory. And data had to travel over the memory bus uphill both ways! You young whippersnappers!

  • IRQs? (Score:2)

    by throx ( 42621 )
    The number of IRQs really isn't going to affect your performance. Remember most CPUs (x86 included) actually have only a single interrupt line going into them and they then handshake with an APIC to figure out what interrupt actually happened.

    If you are worried about interrupt chaining, then there still isn't much time lag there. Handling an interrupt is usually a matter of just determining if your device caused the interrupt, saving the state of the device and firing off a backgroud operation to actually deal with the data. The only delay is running down the drivers chained off the interrupt to find the one that actually caused it - usually a matter of each one simply checking a single PCI register (ie 20 clocks).

    Face it, the 'shared IRQ' is simply a non-issue any more (unless you have shitty drivers written by someone who learned to code in GW-BASIC and never read a design manual). Most RISC machines work happily with very few lines and the "16 Interrupts" idea is what is supported by the APIC and not the CPU anyhow, so get over it.
  • If you don't know much about hardware then you probably won't want the "bleeding edge" technology. Stick with PC133, even though the RAM is the same price, the mobos that support it are more expensive.

    ASUS is a good brand. I've had a number of them and they've always been rock solid with heaps of good features. They aren't the cheapest, but IMHO they are worth it.
  • What sort of performance metrics do you have to show that shared interrupts are the source of your problem? My current laptop has damn near everything on interrupt 9 (as have most machines I've seen lately), and I've not noticed any performance problems at all. Smooth mouse, smooth video, DVDs play just fine without dropping frames, transfers over fast ethernet at >8M/s etc.

    Most video capture problems are caused by disk latency or hitting a page fault at the wrong time, not interrupt latency. The average interrupt latency on most systems in somewhere under 1ms - if you are capturing at more than that rate then I suggest you need dedicated hardware. What model SCSI controller are you using? In many cases IDE is actually better value than SCSI - you can capture easily to an IDE drive at ATA/33 or better.

    If you really want to know the largest cause of bottlenecks then I suggest you look at register spilling on the CPU. The x86 is horribly register starved and therefore hits the cache a LOT. If that's not where you want to look, check out things like the actual transfer rate to your drives, where the CPU time is going (system or user space), how loaded your I/O busses are, what bandwidth you have between North and South bridges etc. Shared interrupts really haven't been a problem for a long time, especially on "proper" operating systems like Linux.
  • Part of the reason Rambus memory and the Pentium III processor didn't fare so well was that the Pentium III's front side bus was only 100/133Mhz (800MB/s and 1.06GB/s respectively) and it had to contend with a higher latency memory bus and mismatched speeds. The Pentium 4 resolves the problem by running the FSB to the same speed (but not really the same frequency) as the dual-channel Rambus memory bus.

    I'm still holding out on the Pentium 4 solution until Northwood (ie: Pentium 4 in 0.13 micron and new packaging) proves itself and there is enough applications/server services that are optimized for the P4. Unfortunately, I'm stuck with a dual-channel Rambus setup at work :(

    So far, I'm relatively impress with the nVidia chipset and hope that it will help increase the acceptance of the AMD Athlon/Palimino processors.
  • $600 isn't so bad for such a motherboard, mostly when it's geared towards the server/workstation market rather than the consumer/enthuasists market. Dual Pentium III Socket-370 motherboards based on the ServerWorks chipsets (with on-board dual-channel SCSI, Ethernet, integrated ATI Rage video card, ATA/33 or ATA/66) from ASUS and Supermicro run for around $450+ (some even go for well over $550).

    It's also not really cheap to make 6 or 8 layer motherboards that are as large as the Tyan motherboard... the number of traces on the motherboard is also quite mind-boggling since you need a lot more traces to connect two processors using the EV6 bus than Intel's GTL+/AGTL+ bus scheme.
  • I personally haven't run into problems with the ServerWorks chipset... but I have only run Windows 2000 and FreeBSD on servers with that particular chipset. I haven't installed Linux onto that kind of server, since the servers that had Linux on them were 440BX based :)
  • ... But why not spend your money on a dual processor solution?
  • The article mentions that the full featured Tyan Thunder K7 is about $600, while the MSI MS-6502 will go for around $200. I would prefer the Tyan, but $600 is a bit steep, I hope they offer a more consumer priced solution.

    --
    microsoft, it's what's for dinner

    bq--3b7y4vyll6xi5x2rnrj7q.com
  • I'm buying a new mobo, athlon cpu, and memory in the next day or two. Should I get PC133 memory or DDR? It seems that DDR is much more expensive - is it significantly faster? I'm mainly using the workstation for PHP/HTML/SQL development, web surfing, and general office stuff.

    Also, my friend recommended that I get an ASUS mobo. Was he right that this brand offers good price/performance?

    As is probably obvious, I don't know jack about hardware. Any pointers about the above stuff would be greatly appreciated.

    --
  • "my biggest gripe is the fact that we have been forced to use 16 IRQ's for way too damned long, they should have expanded it when they intorduced the PCI bus, now we have to wait forever to have a couple of free IRQ's on a new motherboard..."

    This says two things 1) you don't understand what IRQ sharing/reentrant drivers are all about (which are NOT possible on the ISA bus, but are on the PCI bus/AGP port), and 2) that you seem to think you need to spend time configuring a PnP system. Don't try to configure a PCI system to force certain IRQs to certain devices, it won't work -- they do not need human intervention. You are obviously still scarred by the 1996 PnP implementations of ISA and OSes which are not samrt about resource allocation.

    I have yet to see a modern system require more IRQs than it has because every modern PCI device can share them. I have yet to see a modern system require manual IRQ assignment to devices.

    --
  • FWIW, I bought a Nanya 64mb RAM SIMM (DIMM? Nah.) 3 years ago that is still going in a server I have running.

    It didn't suck. It doesn't suck. I bought it when I lived in England, shipped it over and it's still serving up pages in Canada now.

    Then again, I don't have a Gig of RAM, so I can't tell you how well it would scale...

  • From the ip-weenies dept: (Score:3)

    by bflong ( 107195 ) on Monday June 04, 2001 @10:13AM (#177610)
    From the ip-weenies dept:

    In further news, Rambus, facing gallons of red ink in the 2nd quarter, have laid off 99% of their engineers. When asked for a reason for this perplexing move a Rambus spokesman stated, "The engineers were the cause of the whole problem! If we did not have to pay their salaries, we would all be millionaires! But now that Intel has violated our intellectual property by using DDR ram, we really need to tighten up and get to work." When then asked why Rambus kept their two lowest paid engineers the response was, "Well, we needed to keep them around in case one of our 500 lawyers has another annoying technical question. I hate those."
  • First of all, I can tell you that any 128MB sticks you get for $15 will be crap. The fact that you could get 512MB of crap won't make Doom run any faster. If you want increased performance, spend the dough on high-quality CAS2 Crucial, Mushkin, or Corsair PC133. Not only will it be faster and more stable, but the stuff is tested and certified.

    But hey, if you're running a cheap MySQL server and just want bucketloads of RAM, go ahead with the cheap stuff. MySQL is more likely to fail before the hardware will anyway.

    --

  • Memory bus? You had memory busses? We had to transfer data between system components with an elaborate system of miniaute pullies. And these weren't compound pullies, sonny, and we had to pull the little buckets of bits back and forth by hand, all the live long day. The buckets only held one bit. And yet I was able to code a fully functional space station in only five minutes! Sheesh, kids these days...

    --

  • Slightly offtopic, but we are talking about RAM, after all. What is the deal with Nanya chips? I recently bought 1GB of Mushkin PC133 which was labeled as having "Nanya" chips, with a little star* and everything. I take it that Nanya is a maker of "value" (ie LAME) modules, but the price was right ($250!) so I bought the stuff anyway. Can anyone tell me if Nanya does not suck?

    And no, I'm not getting it confused with the spring water. (Hungry for swap, thirsty for Nanya?)

    PC RAM has gotten just as cheap as CPU cycles and IDE disks, it seems. This is of course due the the new market for DDR RAM and RAMBUS, but even DDR RAM is remarkably inexpensive. I hate to be one of those "Back in the day..." guys, but back in the day when I bought my first RAM upgrade for a PC, I payed more for 8MB than I would pay for 512MB today. Now that's fucking progress, mates.

    --

  • As others have said, the Tyan board is so expensive because of the integrated SCSI and other goodies. In case you're wondering why we'd want the integrated components (which on consumer-level mainboards are usually undesirable), it is because this is a server-class board, and will very likely be rackmounted. If you're trying to stuff a MP board into a 1U case and only have two PCI risers available, having integrated SCSI, video, and networking is a huge plus.

    But make sure that you're buying good integrated components, since you'll be keeping them for a while. Like the Intel STL2 (a dual-PIII board), which retails for about $600 but includes an Adaptec U160 controller, ATI video, and the oh-so-sexy Intel PRO 10/100 NIC. You may be able to do as well for less, but please research -- one "simiarly spec'ed" ASUS board does indeed include a SCSI controller, but it's a no-name SCSI2 controller, for fuck's sake.

    $600 is very reasonable for a the first-available SMP Athlon board. People will pay for this board, trust me -- especially when they realize that they'll be saving major dough on higher-performing CPUs.

    --

  • Yeah, that was a brain fart, I meant the 760MP. If you follow the search link you will indeed find that the Tyan board is dual cpu. :-) Word on the grapevine is that Tyan will be the first manufacturer of these beasts.
    --
    News for geeks in Austin: www.geekaustin.org [geekaustin.org]

  • Seems the 760 chipset is already available on the street: ugly pricewatch.com search query for the Tyan S2462 [pricewatch.com]. Price is about 580 give or take 20 it seems. (Of those shops I've actually directly dealt with essencom.com a few times; they seem to be a nice, reputable shop.)

    (This suprised me as I thought what I've been seeing around the past few days were just beta boards.)

    I wonder how long it will be until places like VA Linux and Penguin Computers have dual-athlon rackmount servers and deskside workstations for sale? :-)


    --
    News for geeks in Austin: www.geekaustin.org [geekaustin.org]
  • I vaguely recall (most Rambus stories go in one ear and out the other for this reader, as with most /.ers I imagine) that the RDRAM bus is severely limited compared to DDR (??)

    Then again, maybe that's just FUD. Tit for tat then, eh Mr Litigious Rambus Bastard.

  • I remember talking with my fellow co-worker about a year ago as well, and how he was excited about Rambus stocks. I've told him their technology isn't clearly superior, and difficult to manufacture. that guy is not longer in a company so can't ask him what has happened with his Rambus stocks.

  • Actually, AMD 760-based boards have been available in upwards of a month already.

    Over two months actually:

    uptime
    9:59pm up 65 days, 3:32, 24 users, load average: 2.06, 2.06, 2.01

    This machine has Asus A7M266 motherboard (which works very nicely ;) The 760MP boards are certainly interesting, but I guess that a single-CPU TB is enough for me right now.

  • Just the other day I found a site through Pricewatch [pricewatch.com] that purported to be selling Nanya PC2100 DDR memory with CAS latency of 2 for CHEAP (like $60 for 256MB). It's hard to believe, so maybe it's not legit... but I did a little searching on Nanya, and an article I found indicated that they want to have some double-digit percentage of the DDR market going forward.

    Does this suggest low-end or high-end? Dunno... but thought I'd mention it.

    - Leomania

  • Mind you, he was sensible and is running an Athlon anyway. Hey wouldn't that make a much better slogan than "Intel Inside". reply: "don't worry mate, I've got an "Athlon Anyway :-)"

    Well, I've got an Intel Outside [ucam.org].

    Seriously though, do we really need a cheesy slogan for AMD processors? People who choose AMD over Intel have more sensible reasons. IMHO even when AMD wasn't a serious competitor, I found the 'intel inside' logo as repulsive as *cringes* 'Designed for Windows 95'.

    --

  • the really cheap ram is using high density chips. as for the comment about needing a BX133 chipset to run pc133, i run pc133 quite happily in my celeron 466, at 66fsb.

    With my previous celeron 300 at 450, i ran some old pre-pc66 class ram at 100, it worked fine. Nothing like buying quality ram in the first place. Got many years out of that ram.
  • The problem is that the P4 was made to have a huge memory bandwidth. SDRAM and DDR SDRAM both have a lower bandwidth than Rambus. SDR DDRAM will probably have a 20% (or greater) performance hit. So... the question isn't about price/performance of only the RAM, but of the entire system. Save $70, lose 20%!

    steve
  • The best source for news, computer and otherwise, is the Taipei Times. Check: http://www.taipeitimes.com/news/2001/06/05/dept/bi zfocus

  • Re:DDR isn't that expensive these days... (Score:3)

    by JCCyC ( 179760 ) on Monday June 04, 2001 @09:20AM (#177625) Journal
    "AMD Anytime" sounds better. <delusion-of-grandeur>Consider this a modest gift from me to the marketing department of AMD. Use at will. Trademark it. Create dancing funny-clad people to go along with it. No strings attached.</delusion-of-grandeur>
  • True, the Rambus is not exactly the first thing on my wishlist. But i dont think this change will change that much. All benchmarks has already told us what a crappy CPU the P4 is.. why would i like it just because we got better ram ?

    Sure its better then earlier, but the T-bird and DDR still kicks butt :)

  • Seriously, I wonder what they were smokin' and I also would like to try that shit! I wouldn't use Ramsux RAM if I meant my life.

    WTG Intel on sobering up! Now pass dat bong around!

  • if it's not an open and free market, then how can AMD and VIA exist and succeed? intel has no more power than microsoft or even redhat to determine what we buy. heck, if other chipset companies wanted to "improve" intel chipsets they'd be sell like hotcakes. intel can't and will never be able to do anything about it except make a better product.
  • It takes awhile to produce a new product. Rambus promised Intel the hottest thing in new memory and got it set as a standard. Intel's R&D department in partnership with Rambus got blindsided. It has high power, high price and didn't compete with the advances in DDR RAM. SDRAM went beyond PC100 with lower prices to boot. This left Intel with a committment to something stillborn and playing catch-up with the field. Look out. With the new memory hub chip, they got the train on the right track now. They know the overall cost of the system does affect the ability to sell cutting edge chips. They are not sitting still on this one. They need the market share back and they won't let Rambus problems hold them back.

    Those who ride the cutting edge often get cut by it.

  • My next system will be a dual tbird, fastest I can get my hands on, with as much and as fast DDR RAM as I can aquire
    I can no longer justify a single-processor solution, the disadvantages of UP far outweigh the disadvantages of SMP (of which there are few, cost and compatability are the biggest ones)
  • With regards to i815 and 440BX..

    i815 has a one way asynch. memory controller, i.e. supports a 133MHz front side bus processor with 100MHz PC100 memory.

    440BX has a synch. memory controller.

    What does this mean?

    Synch. memory controllers can be made with fewer gates in series, i.e. the memory controller has less latency.

    That account for most of the 0 to 5% difference in performance.
  • Your head is stuck in the PCI specification manuals.

    The reality is that *some* (possibly most) PCI devices..
    a) from a hardware prespective don't like to share IRQ's
    b) from a software prespective have crappy drivers that don't (for some devices can't) follow the specification close enough.

    For any time critical application (video editing, server type stuff) shared IRQs can be a problem
  • Remember how when RDRAM first came out and it's benchmarks were abysmal? Rambus said that it was designed for the P4 moreso then the P3. I remember thinking that was a bunch of bs but it turns out to be true, not only that but the 10% performance difference (btwn RDRAM AND DDR)in that benchmark [anandtech.com] sounds about right if recall my impressions from some of Tom's comparisons.

    I wouldn't go near a RDRAM based system but now that they have a viable platform for their product they'll never see the market penetration they now need. If I didn't hate Rambus so much I woulda considered an i850 RDRAM.

    Anyone agree/disagree?
  • Seriously, I had to keep myself from yawning. The problem is that chip speed is far less important nowadays than it was 2 years ago. The bus speed matters a little bit, and it will be nice, but with recent Intel fiascos, I just don't see the point.

    Perhaps I'm wrong, but I was recently pricing computers over at Gateway, since I got my son a copy of Black & White and I can't run it on any of my Linux boxen, so I decided to donate my old Win98 box to a friend and pick up WinME on a box that matches the demand specs of the game. And I looked at all the nice 1.1 GHz Intel chips and then saw that I could buy an 850 MHz AMD chip in a box for about $800 instead of shelling out $1600 for the "faster" Intel chip that I knew wasn't really faster.

    So, what I'm saying is - so what? Until Intel finds some way to deliver faster Net access, it's all a bunch of hype about meaningless benchmarks that have no connection with my reality. And I'll still buy Linux for my servers, so I really just don't care.

    But it is a cool trade show, I'll give you that.

  • if you already have enough money to spend to buy P4's rather than AMDs for that slight gain in performance

    You mean for that slight gain in brand-name recognition? From everything I've read, heard, and seen, the fastest Athlon system on the market still equals or beats the fastest P4 system on the market in just about everything (leaving SMP machines out of the comparison, obviously). All Intel really has to offer over AMD now is the name, and even that is becoming fairly tarnished with all the recalls and such in the past few years.
  • I could be wrong but the name sounds very familiar, I seem to remember reading about them on Hardocp recently and they are a division of the bizarrely named Corp that also owns Via. [hardocp.com]
  • >And to check to make sure that it is a geometic expression... Geometric progression.. I think you mean exponential increase.. perhaps we could model the prices with something along the lines of: Price_of_Rambus = Ae^-t/size_of_ram (Where A is very very large..) forget Moores law.. we have Digimax's law!!
  • well if you guys would put your money where your mouth is you could have made a killing by buying the Puts on the Rambus Options or even just sold short on the stock. I've sold short on VALinux and I've made a killing. Linux stocks can keep drying up for all I care...I keep making more money.
  • The performance difference between the RAMBUS version and the DDR version.
  • Memory at rock bottom prices, dual Athlons/Tbirds/Palamino's (just hope consumers aren't left out in the cold for long).

    Two words: "Chubby Gooood!".

    'slashdot, hardocp, tech-report, macslash, macsurfer, arstechnica --phew! no wonder I'm so damn tired all the time'
  • The problem, of course, is that ram is a major bottleneck... if you already have enough money to spend to buy P4's rather than AMDs for that slight gain in performance, then you might as well spend the extra money on RDRAM too...

  • There's this guy making whoopass inside athlon decal/stickers (the thing you put on the front of the case)... they are available as auctions on ebay. I need to get one or two of those myself... ^_^
  • buy another stick of ram with that 70 bucks :op
  • ...the first P4 chipset that doesn't use 'fast but expensive' Rambus memory.

    I wouldn't touch Rambus with a 20 ft pole. Is it me, or do we always have to wait for the second generation of the Intel processor (ie P4 Northwood, P3 Cumine) before we even get remotely what we want?

    People aren't demanding Rambus. They want something that's worth the cost!

  • With prices like that, I'll be buying RAM rather than candy from the vending machines that Aramark provides in all government buildings.
    Then again, knowing Aramark, they would at least quadruple the price of it just to make a profit. . .
  • To all of those that are not sporking this. . . All prices are subject to change without notice ;-) These prices come from our happy friends over at Pricewatch.com
    Rambus - 64mb stick - $37
    Sdram 133 - 64 mb stick - $9
    Hmmm, that's odd, it would seem that it's nearly four times as much. And to check to make sure that it is a geometic expression. . .
    Rambus - 128 mb stick - $59
    Sdram 133 - 128 mb stick - $15
    So what do we learn from this class? Essentially that we are going to be able to have a lot more more memory running in our P4's :-) I like the prospects of that. For the price of One Rambus stick, I can put in nearly half a gigabyte of RAM. . . just think of how fast Doom will run. . .
  • "This is exactly the kind of behaviour that makes me hate Intel & Microsoft. This is not politics, it is clearly abuse of power, clearly the attitude of a monopolist that can't stand a bit of competition." Since when is politics NOT about abuse of power? Don't you watch the news? In any case, actually hating MS and Intel is simply ridiculous. They are merely behaving like any other major player in an "open and free market economy." This is what the market economy is all about, the companies provide a needed service or product, and the people buy from the company that gives them the best product at the most reasonable cost. To believe that this situation in the motherboard market is in any way unique, and a sign that it is a closed market, is ludicrous. It occurs any time one or two companies dominate a market for any length of time. Recall with me the late 70/early 80s, when people discovered that the Japanese could provide them with cars that got better gas mileage than Detroit even dreamed of offering. The shakeup that resulted therein led to a massive paradigm-shift in the domestic auto industry, and a readjustment to the demands of the consumer. Any time a corporation ignores the needs of the consumer for too long, it pays the price in the marketplace.

Slashdot Top Deals

"Why should we subsidize intellectual curiosity?" -Ronald Reagan

Close