Slashdot Mirror
Intel To Pull Plug on RAMBUS, Use SDRAM?
Ratteau writes " Cahner's Group Electronic News, is reporting they have come across documents that Intel "has pulled the plug on plans to use Rambus direct memory in the mainstream PC market". " Given the troubled past with Rambus, this wouldn't surprise me - but it's a big move for Intel.
Intel's Desktop 2001 Roadmap Update indicates direct Rambus DRAM (RDRAM) will only be used in the high-end desk-top market I'd like to bring about a point. Consider the i815E. Its what Intel would consider a low-end SDRAM chipset. Is that why they put a 512 MB barrier on it? Even more bugging is the fact that Intel limits you to 2 PC133 DIMMS or 3 PC100 DIMMS. This statement only acknowledges that Intel finally knows that low-end customers are *probably* ;-> not going to shell out bigbucks for RDRAM. It still doesn't change their position to the market.
Ciao
-sush
RDRAM latency is a big issue, but with proper processor and chipset design, this can be avoided. Alpha's EV8 (?) is an example of this. If I remember right, the Rambus controller will be integrated into the processor core, and the architecture of the core is designed to minimize the RDRAM latency hit. In addition, the Alpha RDRAM controller is an 8-channel setup (8*1.6GB=12.8 GB max bandwidth). As for interleaving SDRAM, remember that SDRAM has a much higher pin count, which means more traces on the motherboard. Because of this, multi-channel SDRAM is more difficult and costly to implement. Though, with RDRAM prices the way they are, this is not too much of an issue. I believe ALi has a dual-channel SDRAM chipset (socket 7), though.
Written by a single drunk monkey in 30 minutes with a copy of MS Word 2000.
Don't they already coat the surface of new motherboards with some kind of stuff to keep my greasy little fingers from clawing on them? When I last was fscking around with my Tyan Tiger 100 it struck me that they had coated the top layer with a varnish-like finish.
RDRAM = RAMBUS Direct Random Access Memory
DDR = Double Data Rate
These are 2 different kinds of technologies, so no, its not common knowledge that the i815 chipsets will use this DDR RDRAM that you seem to know about, because DDR RDRAM doesn't exist. I believe what you meant was DDR SDRAM, which is what it will use as far as I know.
RAMBUS Info from www.pcaccelerate.com
Id go check out that site for info about RAMBUS, and you should see for yourself that there is no such thing as DDR RDRAM.
Snippet from the article:
The PC600 RDRAM bandwidth peaks at 1.2GB/sec--less than 20% faster than PC133. In real world applications there is no performance difference between PC133 and PC600. Sure RDRAM is fast, but has only a 16-bit data path. That's because with RDRAM only one 16-bit wide memory chip on the module is active at a time. When one chip is being addressed the other chips are in standby mode. With SDRAM eight 8-bit chips are active at once, giving a 64-bit data path.
That pretty much shows you some downfalls to a memory technology that is proprietary, and very expensive, versus one that non-proprietary, and very cheap (compared to RDRAM). RAMBUS worked great for the Nintendo 64, but for pc's it seems we are going to be using PC133, and DDR for a while. Thank god is all I can say, I mean $1000 bucks for a stick of 128mb PC800 RDRAM is a joke.
----------------------
Geist
The greatest trick the devil ever pulled was convincing the world that he doesn't exist.
I am not sure, but I believe Rambus stock is dropping quite a lot today. At this moment, it's down by some 5% compared to yesterday :-)
:-)
Of course, I may be mistaken. Look for yourself at Nasdaq:RMBS
Let's see wath a little slashdot effect can do to stock quotes now
Every expression is true, for a given value of 'true'
RAMBUS still pricey
Not meet performance hopes
Intel says "Oh, Shit!"
--
"It's tough to be bilingual when you get hit in the head."
"Never invest based on a 'tip' on the Internet without doing independent research"
-------
Warning: Slashdot may contain traces of nuts.
The writing is on the wall for RDRAM. All new designs are using SDRAM and DDR SDRAM.
However, they still cling to life by trying to extort royalties on all synchronous memory. They did "invent" synchronous DRAM after all, and got some patents. Despite the recent flurry of bad news for RMBS, their stock value is still worth >$6B. They are clinging to life on the hope that memory manufacturers will buy them off, rather than risk a jury trial. In the mean time, the RMBS insiders just keep selling, taking in the millions.
Some newer Geforce video cards come with heatsinks on the DDR SDRAM chips. My roommate has one without heatsinks, and I've noticed that the chips rarely get hot to the touch, so heatsinks may be overkill at this point (although some hardware sites I've read have claimed that the RAM can be clocked higher when cooled like this). Don't be surprised if next generations of DDR (or QDR) RAM get quite toasty, especially with constant heavy use.
---- I made the Kessel Run in under 11 parsecs.
DDR-DRAM is fundamentally bandwidth limited when compared to a DRDRAM implementation in the same technology. Servers need high memory bandwidth, and latency is not really an issue (BTW: a good RDRAM implementation has decent latency). You will see this in the next couple years.
This confuses me. I can see the need to have multiple 400MHZ channels from the RDRAM to the controller, but they shouldn't need 400MHZ from the controller to the CPU. It's 16bit vs 64bit, so they shouldn't need more than 100MHZ.
The traces from the memory to the controller shouldn't need to be that long, so I can't imagine that it's too terribly big of a problem.
-Michael
-Michael
From the article, this sounds more like a delay in implementation than Intel giving up on Rambus.
It's one small step on a long road that Intel must travel to win my confidence back. Their last year of gaffes has lost nearly all the goodwill they built up with me
SteveIt still sorta fits within the Intel/Rambus contract because it's not a 'new interface', merely a tweak of either the i810 or the BX. But it is a bit afoul because it exceeds 1GB/sec bandwidth, though just barely. OTOH, I doubt any controller can come within 6% of the theoretical max of a PC133 DIMM, so effective bandwidth is probably still low enough.
Lots of people have been looking at the publicly available portions of the Intel/Rambus contract, and speculating about the blanked out parts.
The living have better things to do than to continue hating the dead.
So it's not like Intel is giving up on RDRAM altogether - just on the lower-end machines. If they were switching because one is better, then they would just drop RDRAM totally.
I think the idea was to save face. If I understood the article correctly, RDRAM is expensive and buggy and there are alternatives that run just as well.
Investors and the general public tend to lose confidence in a company that says "We screwed up big time" so Intel has to find a way to gradually pull away from what they had heralded and "THE" RAM to use. They have gone from saying "we will use it in _all_ our PIV systems" to "we will use it in some PIV system that cost > $2000 sometime next year..." --quotes are my paraphrasing--
I would bet that Intel will ship very few, if any, systems with RDRAM. I think they will drop RDRAM from the roadmap for their high-end machines in six months or so and no one will notice/care.
This is supposed to be great art. So why does it look like a bunch of decapitated naked people? -- Calvin
I work closely with a DIMM engineer working with PC100 and PC133 memory systems. We've been watching all the lawsuits flying recently. Here's a few links about royalty and patent lawsuits:
e ws/OEG20000324S0022
u es/200004/rambus&page=1
6 1500.htm
7
Rambus asks ITC to bar Hitachi, Sega imports: (3/24/00) http://www.eet.com/story/industry/semiconductor_n
Will Rambus Go Bust?: (4/17/2000) http://www.32bitsonline.com/article.php3?file=iss
Toshiba Signs Patent License Agreement with Rambus
For SDRAM & DDR SDRAM Memory and Controllers: (6/16/00) http://www.rambus.com/general/press_releases/pr_0
Tech Report Analysis of Toshiba agreement: (6/16/00) http://www.tech-report.com/onearticle.x/881
RAMBUS using patent claims to lift RDRAM share: (6/25/00): http://www.ebnews.com/story/OEG20000623S0042
DRAM industry considers antitrust lawsuit vs. RAMBUS: (7/10/00) http://www.techweb.com/wire/story/TWB20000710S000
400 Mhz is a really big jump from the industry standard 100 - 133 Mhz. Minor impedance variations from board to board in production can cause significant phase and wave form changes in such fast signals.
To accurately transmit 400 Mhz square waves it is necessary for the board traces to handle 4 Ghz sine wave signals. That is more of an Analog micro wave transmission problem than it is any kind of digital design problem. Evidently the board designers have had a great deal of trouble doing this.
The bottom line is that Rambus motherboards will need to be produced with tighter tolerance on both trace and board substrate thickness than current motherboards. Result: even more expense for a Rambus system compared to a DDR based system.
Intel's solution to fix the problem was to recall the board and replace my SDRAM with an equivalent amount of RAMBUS ram. That was cool considering that 128 MB of RAMBUS memory alone would have cost more than what I paid for the entire system.
If they are now discontinuing RAMBUS memory, I'm totally screwed into a computer I'll never be able to upgrade, as RAMBUS memory is already tremendously overpriced.
Thanks a lot Intel!
p.s. Anyone who wants to buy a CC820 with 128 MB of RAMBUS memory, let me know. :)- --------------
---------------------------------------------
---
Segmentation Fault ( core dumped )
Basically, RAMBUS has the theoretical capability to be significantly faster than SDRAM (not DDR, more later). However, the controllers have problems that prevent this. Basically, RDRAM can keep many pages open and many devices active at a time (more than SDRAM), but the i820 doesn't do this. So the chipset is crippling the RDRAM. Also, as soon as multiple devices are put on the bus, the latencies increase, so if too many chips are present things slow down. This is because of the longer wires needed. at 400MHz (not 800 - its DDR) that really matters. Also, RDRAM has been hindered by low yields and hence higher cost. It is now down to about double PC133 (see pricewatch). Also, the chips are more complex. However, the specs say that a good controller ought to be able to outperform PC133. Not by huge amounts, but by enough to matter. i820 is far from a good controller. Something to think about: the EV7 (maybe EV68, I can't remember) is going to use RDRAM. (also on Ace's hardware). However, it is going to increase performance by using 8 channels in parallel. So until there is a good desktop controller, and RDRAM is similar in price, AND the benchmarks say it's better, I'm using DDR SDRAM. But, the technology isn't inherently bad, just having more than it's share of problems.
---
It takes less power to run your CPU than a light bulb. On the desktop, power consumption doesn't matter so much as long as you can dissipate the heat. Transmeta already has a solution for reducing power use in mobile devices. Intel is doing the intelligent thing by occasionally devoting some time and R&D money toward developing lower power CPUs, but focusing on the biggest, best, and brightest.
In response to your core question, IE "who actually needs a processor this fast", the answer is, we all do. As higher-end CPUs get faster, lower-end CPUs get cheaper. As more processing power becomes available, we are able to predict weather more accurately, make more fuel efficient automobiles, and discover more about the cosmos in which we are only a tiny speck. Computers help us do everything, making products cheaper and giving a better way of life to all people (though admittedly there are billions for whom the benefits are slow to trickle down to.)
Next time you buy a car, stop a moment and marvel at the amount of processor time that went into modeling various aerodynamics characteristics, enabling you to get dramatically better gas mileage than the refinements made to the engine alone; Which are all designed and tested on the computer before they ever see metal. This is true of nearly every product with more than five moving parts, and many that have none at all. Be thankful for the race to technology, or get the hell off your computer and go plant some carrots or something.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
It is silly to use Rambus RAM, since SDRAM has lower latency. Rambus RAM has higher bandwidth, but if you need bandwidth you can always interleave memory. (the idea is similar to RAID striping. byte 1 comes from one ram chip, byte 2 comes from the other, so you have the same latency and twice the bandwidth. If you want more bandwidth, use more controllers and more chips. You can't do anything about latency except make each chip faster, though, which is why there's nothing you can do with Rambus to make it have SDRAM latency.)
I told you so.
The 'companies backing down from a bad decision' point is a very pertinant one for me. The company I worked for decided (without telling us) to sell the group I worked for, as it was only breaking even. 3 years later it was making a good profit, and we still got sold, completely screwing over the other groups which depended on our existance. The stupid bigwigs at the top _couldn't_ reverse/cancel the decision, as they were too proud to admit they were wrong (by being so short sighted).
So micro-kudos to Intel. But they were damn suckers for signing the deal in the first place, it had bad news written all over it.
I hope to never hear the word RAMBUS again.
FatPhil
Also FatPhil on SoylentNews, id 863
Well, the other thing that killed RDRAM is the high price: US$500 or more per 128 MB RIMM module! (glyph of "Benjamins" sprouting wings and flying away at high speed)
Remember, today's PC-133 SDRAM modules cost about US$140 for 128 MB in most places; a DDR-SDRAM 128 MB module will probably cost around US$175-US$185. No wonder why people aren't so interested in RDRAM.
Raymond in Mountain View, CA
There are applications where throughput is more important than a significant amount of latency.
An example is context-switched highly-parallel processing, where the number of crunches per second on each piece is relatively low and fixed. You pipeline and context-switch, and get multiple virtual processors from one set of gates and a RAM. The higher your bandwidth the more virtual processors you get. This is important in many applications. Sometimes space for the box is more expensive than the box itself. Sometimes the cost per virtual processor is critical.
But some problems don't parallelize well. And even for those that do, parallizing them can be a real bitch. So your desktop or laptop (which tends to be doing only one or a few crunch-intensive things at a time) is organized to stick with a task for a significant time, then hop to another. RAMBUS isn't a match for that.
And it looks like it has some other kisses-of-death even for interleaved context-switched stuff. Oh, well...
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
If RAMBUS stock isn't worth anything, this won't matter.
1,000,000 shares time zero dollars per share is zero dollars.
I think Intel is starting to wonder if they have more to lose in market share than they have to gain in Rambus bribes.
Rambus won't quite go bankrupt, because they have big contracts with Sony and Hitachi for video games. But if I was someone with Rambus stock, I would sell it as soon as it shows the slightest sign of dropping.
--- "So THAT's what an invisible barrier looks like!" - Time Bandits
Don't forget though: the more over-priced a system is, the more your average manager will look at it and think he's getting something good.
When it comes to management decisions, "Expensive" is a good word, and "Cheap" is bad. (this is also why Linux isn't getting as much market share as it deserves).
(Spudley Strikes Again!)
Unless of course your doing disk access, in which case your far better off performance wise with PC133 and a SCSI Disk subsystem... which interestingly enough, can be done for still less money then 256MB of 800mhz RDRAM costs.
Yeah... you take your RDRAM, I'll take my Ultra160 controller and 10k RPM drive, and we'll see just who beats who as soon as you have to stop to access your good old IDE hard drive.
-- "So they told me that using the download page to download something was not something they anticipated." - Bill Gates
What happened is that Rambus was around 10% of the industry's memory production, but it never got anywhere near 10% of the industry sales. (the last figures I saw were more like 1%, but that wasn't very recent)
Its coming down like a rock now because people don't want to be stuck with mass inventories of it hanging around forever, not because its suddenly gotten cheaper. The success of motherboards like the Asus A7V (which is a great board) and in general anything that doesn't use Rambus has left the people holding stockpiles of it high and dry. They have to recoup at least *some* of what they originally thought they could make off it, and the way to do that is to sell it at a loss to simply get rid of it.
Don't be surprised if after they sell it all off (if they do), many places stop selling it entirely. There is simply no market for memory that expensive that doesn't do anything for my real world performance. (and all the theoretical stuff aside, its what it does to my real world speed that matters! I don't care if Rambus *might* be better when somebody makes a better memory controller or when they do this and that, I care what it does for me now. Paying 2-4x as much for something that does nothing useful for me is... well... stupid.)
-- "So they told me that using the download page to download something was not something they anticipated." - Bill Gates
due to a very massive drop in Rambus prices lately (probably due to nobody wanting to hold on to it anymore in inventory), you probably can't do it for the same price anymore. my bad.
We did work it out back when rambus was 4x the cost of PC133 SDRAM though, and we got some very interesting numbers. (on the price difference for 256mb, we found a way to store 16 weeks of 128kbps mp3 music)
-- "So they told me that using the download page to download something was not something they anticipated." - Bill Gates
Sorry, but RAMBUS _is_ a bad design for a next-gen memory technology.
Benchmarks demonstrate that as processor speed increases, the performance gap between PC133 and RAMBUS increases (meaning RAMBUS does _worse_).
This makes complete sense to me. As processor speed increases, the number of CPU cycles that are wasted waiting for a critical piece of data to return from RAM increases. Latency becomes more important and more difficult to tolerate with clever architecture tricks. There's a reason new chips have 3 levels of cache, and it ain't bandwidth.
The only way this will change is if the _workloads_ change. RAMBUS does beat PC133 in some cases, mostly that involve streaming data from ram to the cpu from a contiguous buffer. Any small or random accesses are going to hurt with RAMBUS.
But that's why they made DDR. It has the low(compared to RAMBUS) latency, and better bandwidth than RAMBUS. As Pokey would say, HOORAY! ^_^
The enemies of Democracy are
it's because Rambus simply hasn't delivered. they keep saying it will enhance performance later on down the road when chips are faster, but in the benchmarks, the faster the chip, the better SDRAM is at slaughtering Rambus. wait until DDR. that's honest performance gain hopefully unlicensed by anyone. cheap, fast. just like the athlon. tswhat makes computer shopping so much fun.
Rambus is a design for a memory system from Rambus Inc. It is extraordinarily fast on paper. Intel chose their design and decided to support it on a lot of their new products.
The implementation took a long time to get around to getting around. It is now here. Intel bet a LOT on Rambus, because it would give them significant control over a lot of markets. (IE: They own rambus designs)
Rambus is significantly different from the DRAM used commonly today. It requires changes to how stuff is laid out on the motherboard. And it is manufactured differently, to very demanding tolerances.
It is now in production and is competing with DDR-DRAM, which uses existing manufacturing processes, generally works with existing chipsets, and is easy to support. And it doesn't require a fan setup for the memory alone. And runs far cooler. And gives almost as good performance when set up correctly as a RAMBUS setup. And is also capable of being manufactured in quantity, whereas RDRAM is extremely difficult to manufacture. DDRDRAM is also about a fifth of the cost of a RDRAM setup.
You do the math, and read up on it a bit.. I think you will agree that for all intents and purposes (read: mainstream pcs, servers, et al), Rambus is DOA.
Me? Oh... I bought AMD parts...
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
You hit the nail on the head, except...
RAMBUS gives almost as good performance as PC133, not DDR gives almost as good performance as RAMBUS, as you said.
Last year I had the priviledge of excersizing my masochism by working on an RDRAM mobo. While reading up on the architecture I said (aloud) "Gee, all this bandwidth is great and all, but the latency is so high won't that kill performance?" The Rambus Inc(tm) PowerPoint slides said no, bandwidth is all that matters, ignore the high latency. But the engineers I worked with were also skeptical. And it turns out we were right to be so, because RAMBUS sucks it up in real-world performance.
Other than that, though, you're right. And it is a sunovabitch to design for. When you have pico-seconds of margin to deal with at the _motherboard trace_ level, you know you're screwed.
The enemies of Democracy are
RDRAM as a technology on the pc platform has only been in production for maybe 9 months. From $1000 for 128 megs to $270 in 9 months is an incredible drop in price.
I dont have a
I do not remember where, but I heard about this last week. Intel had decided to stick with SDRAM for all general consumer level systems, since general consumers do not/will not stand for computers prices that have been dropping for years to suddenly sky rocket again.
The site with the Intel document said that they don't know wether they're going to use PC-133 or DDR. They have decided to use DDR. I don't remember if it was print or screen, but if I can find it again then I'll be back.
It looks like Intel was trying to back away from RAMBUS gracefuly after they hyped it for so long. Its good to see that they finaly came to their senses, but it seems like we could have been spared a lot of problems if they had been more farsighted.
Now if only all corperations could back away so gracefuly. [*caugh*]MPAA[*caugh*]RIAA[*caugh*].
------
Not a typewriter
Intel's Desktop 2001 Roadmap Update indicates direct Rambus DRAM (RDRAM) will only be used in the high-end desk-top market
So it's not like Intel is giving up on RDRAM altogether - just on the lower-end machines. If they were switching because one is better, then they would just drop RDRAM totally.
Being with you, it's just one epiphany after another
Everybody loves "RAMUS".
--
Linux MAPI Server!
http://www.openone.com/software/MailOne/
(Exchange Migration HOWTO coming soon)
The release of their 815i chipset already pointed in this direction (Rambus didn't really like that move :)
Also, the 815i chipset seems to be faster then the 820i chipset (which uses expensive Rambus memory). Now, it looks like they're indeed going to drop it. Look at some of these articles:
Every expression is true, for a given value of 'true'
Good question! I think it's because of:
1) Area. Putting a reasonable amount of RAM (128 MB) onto a CPU core would make the chip huge. Die area is a big concern. That's why until recently the L2-caches were off-chip.
2) Process. DRAM uses a special process that allows for vertical capacitors to achieve maximum density. Using this same process in a chip core would be expensive and wastefull.
3) Effectivness. Putting the memory on chip wouldn't necessarily increase the speed that much. Powering the huge arrays of RAM still takes time. The delays on the traces and going on-off chip aren't the dominating factors.
4) Upgradeablitily. You can't go to Best Buy and get another 64MB when your ram is on-chip.
Eventually, you might see this. More likely to me, though, is just expanding cache hierarchies. You'll have a 128MB L5 cache to go with your 32GB of RAM. ^_^
The enemies of Democracy are
Now all we need is for Intel to pull out of the consumer market and were set.
This comes as no major surprise, Intel announced not too long ago that it would include support for :), and the fact that the Tbird Athlon is already, IMHO, a better processor than the Pentium 3, Intel really needs to get rid of some of it's crazy ideas and get back down to business. Comparing the Sledgehammer with the Itainium, it doesnt look all that great for Intel either (of course, Itainium has been hyped forever already, and were just now starting to learn about Hammer, so who knows).
SDRAM with the Pentium 4 (where as the article stated, was originally going to only support Rambus). Considering AMD's push with DDR SDRAM with the Athlon, which is considerably cheaper than Rambus (duh
IIRC, Rambus is still going to be used solely for Itainium--of course in 20 years when Itainium is finally ready to ship (but only to Intel's bedbuddies like Dell for the first 6 months), maybe Rambus will finally be affordable.
It is silly to use Rambus RAM, since SDRAM has lower latency. Rambus RAM has higher bandwidth, but if you need bandwidth you can always interleave memory. (the idea is similar to RAID striping. byte 1 comes from one ram chip, byte 2 comes from the other, so you have the same latency and twice the bandwidth. If you want more bandwidth, use more controllers and more chips. You can't do anything about latency except make each chip faster, though, which is why there's nothing you can do with Rambus to make it have SDRAM latency.)
#define X(x,y) x##y
#define X(x,y) x##y
Peter Cordes ; e-mail: X(peter@cordes ,
The hot Sun is a red ball glazing behind the electrically darkened window glasses. The office is covered with shiny chrome and black marble.
-"Our business is going to hell. We oughta do something."
-"Yeah. Like what?"
The Fat guy takes a puff of his cigar.
-"You know that guy RAMUS?"
There is a moment of silence.
-"Yeah."
-"A class-A freakin' pencil-neck geek. Can't even use a spell checker. Let's pull the plug on him."
Well this isn't a bad move on intels part since they really dont need their high end systems having a $800 price difference from AMDs. Certainly they've wasted a TONNE of money and time over rambus and i'm sure they wouldn't be loosing out to AMD now if they had better directed all that effort.
:) Without the burden on rambus this should give intel a fighthing chance against amd and bring prices down more :)
However as I see it the current big looser is toshiba who I think are one of the few DRAM manufacturers that agreed to pay rambus royalties on DIMMS, in order to continue their license to produce RIMMs.
For those of you that dont remember this, rambus turned round and claimed that they had also patented regular SDRAM as well as their funky rambus. They started putting pressure on companies who already licensed rimm technology to pay up for dimm tech also. Toshiba (i think) were one of the few that complied, scared of loosing lucrative rambus contracts.
Now they are stuck paying royalties to rambus for dimms... and without the big return on rimms they could seriously dent their business.
AMD on the other hand got it right and i'm well pleased