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.
They...[have]important patents, and they collect royalties
ERGO
RMBS DID contribute significantly to advances in memory technology
FALSE
Your argument shows that RMBS laid claim to advances and that, for whatever reason, others see it in their self-interest to respect that claim. Given the tenuous link from idea generation to legal claim, and then from legal claim to royalty payment, your argument simply does not suppport your conclusion.
I encourage you to be more skeptical as to the degree any given legal situation reflects reality.
"one treats others with courtesy not because they are gentlemen or gentlewomen, but because you are" --G. Henrichs
Well, so could have a brain-dead donkey.. but intel figured they'd cash in on the stock anyway.. it seemed like a PHB maneuver to me, in fact it reeks of PHB activity...
[Insert validity string] I work for a memory distributer [end validity string] We have recently been able to purchase RDRAM at a much lower cost than its initial offering. RDRAM is selling horribly in the end-user market. We have consulted with our manufacturer (not to be named here) and they have indicated that "someone in taiwan is dumping the stuff". I would tend to think if the memory is being "dumped" that it pretty much consitutes a flop. In the same time we've been offering RDRAM, we have gotten (at least) as many inquiry's about DDR DRAM, a product that has not even been released yet (to my knowledge).
--Ben
"AOL, CIA, NSA, whatever, they all collect information, and they are all out to screw the american public"
I've just gotten an Athilon Thunderbird which at it's current speed of 800MHz is about 1/4 faster than a P3 at the same clock speed. Since the FSB is at 200MHz (much faster than current SDRAM memory), Users of this chip won't have to deal with the losses resulting from using non-rambus technology. However, it would be kind of cool if RAMBUS actually did work 100% correctly.
-----------------------------------------
Perversely greped and groped by PowerPenguin
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.
SDRAM:
PC66: 66 MHz @ 64 bits = 4224 Mbit/s = 528 MB/s
PC100: 100 MHz @ 64 bits = 6400 Mbit/s = 800 MB/s
PC133: 133 MHz @ 64 bits = 8512 Mbit/s = 1.064 MB/s
DDR SRAM
PC1600: 100MHz x 2 @ 64 bits = 1600 MB/s
PC2100: 133MHz x 2 @ 64 bits = 2128 MB/s
RDRAM
700MHz @ 16 bits = 1400MB/s
800MHz @ 16 bits = 1600MB/s
RMBS will get their asses kicked by DDR, which is faster, cheaper, and has less latency.
I don't get how rmbs is still valued at $6B.
I don't get all this about Richard Stallman and patents. Doesn't he hate patents?
You can't just interleave memory to solve bandwidth problems...every type of memory does that. The only way to get higher bandwidth with SDRAM is to A) increase the speed, or B) use multiple memory buses going into the CPU (very costly pin wise). SDRAM has some nice properties, and I'm sure it's appropriate for the pc-world, but within a year or two it will be severly bandwidth limited for high-end systems.
but you're right, in the PC world it doesn't seem to be a good fit. Plus, Intel has done an extremely poor implementation of RDRAM for their initial offerings, which has handicapped it in the benchmarks.
Crucial (Micron's memory division) is already selling DDR memory. The prices are only slightly higher than SDRAM. They only have PC1600 listed, 100MHz bus.
Q.
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'
Did anyone notice how Intel was going to sell the higher performance computers with rambus?
Why stick junk RAM with high end products? Seems like a marketing scam to make the uneducated computer shoppers pay for Intel's initial mistake of pushing RDRAM.
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.
Quite frankly who gives a rats ass about RAMBUS anyway, unless you're running really powerful server class systems, home users wouldn't really benefit the use of it now. I can bet you the RAMBUS will go the way of the dinousaurs in maybe a year or 2... here is a brief genealogy of RAM for home PC users...
1975 - 1990 -- Good old standard DIP/SIP RAM chips (still used today in most electronic appliances)1990 - 1994 -- SIMM/DIMM RAM basically DIP RAM on slots.
1994 - 1997 -- EDO RAM things start to get better with faster access RAM
1997 - 1998 -- SDRAM (PC66) this was meant for the first generation PIIs but could still be used with some Super Socket 7 chips.
1998 - 1999 -- SDRAM (PC100) Better mobos require faster RAMs for their faster processors
1999 - NOW -- SDRAM (PC133) Very few mobos support this type of RAM and demand is very low in comparison to the others
FYI before SDRAM entered the main stream market for the masses it was actually used on High End Servers (I know about this 'cos my components supplier for my PC said I was *NUTS* using SDRAM for my PC). Even when they came out for the masses I still paid a pretty penny for my 1st 64MB (about USD$5/MB) and that was back in 1997
The way I see it is that RAMBUS will probably make a hoo-haa in the PC market maybe in about 1 year from now and last about 6-8 months before being super suceeded by another breed of RAM. My suggestion is to stick with SDRAM until INTEL can solve the problem with the Data Bottleneck in their controller chips.
Hey INTEL! Take a few a few design pointers from AMD on their controller design-----
When it comes to management decisions, "Expensive" is a good word, and "Cheap" is bad.
Riiiiight... That's why everyone has Alphas on their desktop, right?
DrLunch.com The site that tells you what's for lunch!
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.
It would be a smart move, but generally industry hypes something and doesn't want to let go of the hype, regardless of it's destructive path.
Eh...
Well, the systems must cost >$2000 (USD)! Let's see - 128MB Stick of RAMBUS RAM, $780, Newest Pentium3-850, $530, that's $1310 before mobo, HD, CD, case, KB, Mouse, etc... Not to mention assembly, business overhead, some profit,and that requisite copy of Windows! Granted these prices are retail, so the cost to big manufacturers should be lower...
[NOTE: Pricing from Treasure Chest Computers
Roll Tide! For Bama headlines, check out Bamadog.
Well, this is another case of 'MHz uber alles'. Remember, MHz is not the end-all be-all of computer technology. RDRAM operates at 400 MHz DDR, but pushes that through a 16 bit bus (for 1.6 GB/s). PC133/DDR266 operates at 133 MHz, but uses a 64 bit bus (for 1.06/2.12 GB/s, respectively). So, what is really important in evaluating memory technologies is the amount of data being transfered per second. So, DDR SDRAM will keep that Thunderbird better fed than RDRAM. BTW, this doesn't take into consderation RDRAM's atrocious latency. For a more complete explanation, look at http://www.aceshardware.com and their RAM article for an explanation of how latency affects bandwidth. Very informative.
Written by a single drunk monkey in 30 minutes with a copy of MS Word 2000.
Now it's old news... jesus slashdot.. Try to keep up ok?
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.
RAMBUS might not be suck, but it isn't in the running for those who want best bang for the buck.
What is suck, is when vendors force RAMBUS on us. Want to buy a Dell? You can either by RAMBUS for $$$$ (notice the extra $), or get a lower end system with SDRAM but using the i820 MB, which combined with SDRAM, is of course suck
INTEL and its boyfriend Dell IS SUCK
According to things I have read about the Intel/Rambus deal, if Intel stops pushing Rambus as the number one memory option before 2003 or so, the licensing deal is voided. If this happens, then Intel would lose the ability to manufacture, or sell any chipset that has Rambus support. Since this includes the i810, i820, and i840 (even the MTH versions), it would leave Intel legally unable to support millions and millions of motherboards, and millions of customers. For this reason, I doubt Intel will drop Rambus soon, especially since most Rambus users are in the higher end of the price spectrum. (They'd pretty much have to be, given the price of the damn things.)
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
Did they just NOW figure out no one with brains will shell out the 1,000 bucks for ram thats not that big of an improvement over 150 dollar ram? Its a no value product they just figured out wasn't worth the push. I could have told them that a long time ago.
Get paid to code OSS
DDR SRAM requires 4x as many pins as RDRAM. If you use 4 RDRAM channels (for same pin count as DDR SRAM), all of a sudden you are talking 6400MB per second, or thereabouts. And guys!, the latency is not that bad.
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
SteveI've said it before and I'll say it again. Intel's initial crack at RDRAM is a poor implementation and shouldn't be used to judge Rambus. In a year or so you will see some legitimate hardware wrapped around RDRAM, and then you will see the truth.
It 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.
now if we had SMP althons in 64 bit mode clocked at 1+GHz i'd be *really happy*....hey amd, wheres my 2/4/8 CPU mobos ?
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 )
If thats the case, then Rambus Inc. have come of pretty well, while Intel are dead in the water to a tune of $400M. I can see some Intel suit's head rolling....
Syllable : It's an Operating System
Honestly, I just feel that the industry is moving toward narrow and fast technologies (like DRDRAM) and that it will just take time for these things to set in. However, I do NOT like the idea that one company owns all of the intellectual property associated with it. But, Rambus appears to be taking out royalties on non-RDRAM solutions, so it may be that DDR wins, and so does Rambus, and intel just looses horribly...
Not that I would like Intel to dissapear (they won't) as I love the price competition between them and AMD, but I think that the next 18 months are going to be quite rough in terms of getting beaten in performace and price by AMD and Rambus alternatives.
IMHO, Intel's best move right now would be to release a CPU with the DRDRAM controller built into the IC, so that they effectively OWN the Northbridge market (they don't now, look at VIA and Ali and Sis...) for Intel proccessors and so as to get some real performace from a technology that will make them money (RDRAM).
Just a thought....
I dont have a
True, to achieve parity, DDR needs 4x the pins.
But the flip side is that for the same parity, Rambus needs 4x the speed.
Today, having a 64 bit data bus is no sweat. But having a 700+MHz bus is a big deal. Hence RMBS's low yields and high costs.
If Rambus had designed their stuff to use the same number of pins and tried for 1.5-2x the speed, they might have had something.
Regarding RDRAM's latency, it may or may not be that bad. I don't know. But in any event, RDRAM contains a great deal of additional circuitry, which drives the cost up even more. Face it. RDRAM is dead.
Hmmm...1.4GHz processor hey. Don't get me wrong - this sounds fast and would be impressive to own, but who actually needs a processor this fast. Surely (especially since the race to break 1GHz is over) they would be better off trying to produce more efficient chips that everyone would benifit from and stop producing this gargantuan devices which probably require a heat sink the size of my current machine to run. After all - who's going to notice the difference.
...and it is not really an issue.
when it is done right. The peak theoretical bandwidth of that system is reported to be 12.8GB/s--which is almost 6 times better than the second place contender (also an Alpha, incidentally, 21264). And the latency of a dedicated DRDRAM implementation (using on-chip controllers) is much lower than a chip-set implementation.
Check it out yourself at pricewatch.com.
2.27x is a significant premium, IMHO.
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.
---
Intel stops RAMBUS and goes to SDRAM.
And in other new, the heating oil prices in hell reach an all time high. Hell has gome through the third straight day of bellow freezing temperature.
is a big move for Intel.
Moral of the story: Don't buy stock until their product has been proven better.
Vote Naked 2000
A feeling of having made the same mistake before: Deja Foobar
The ironic part is that the high-end market is that which would benefit most from DDR SDRAM. The low end will never approach the bandwidth limits of DDR (twice that of normal SDRAM) anyway.
On top of that, PC133 SDRAM has almost the same bandwidth as "PC800" RDRAM. PC133 DDR-SDRAM (which runs at 266mhz) has far greater bandwidth than RDRAM (mostly because RDRAM transfers two-byte words at a time, and SDRAM does eight bytes at a time, with lower latency (10ns total as opposed to the 12.5-30ns of RDRAM.) We've been over all this before, of course.
The bottom line is that RDRAM could be improved, it probably IS being improved now. Updated RDRAM will require a different chipset though; If they're smart they'll broaden its bus so it can transfer 4 bytes at a time, which would jack the price up considerably but also make it the fastest ram around, even faster than DDR SDRAM, in the best case. I'll overlook for now the interleaved access problem.
Of course, we'll end up seeing 300mhz DDR SDRAM before too many moons go by, I think, which would put it slightly ahead of 4 byte read RDRAM...
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Face the facts, Mr. Brannon.
RDRAM failed. If their design doesn't work properly or can't be manufactured cost-effectively, they are to be blamed.
They want it both ways. They own the intellectual property, and presumably did the design work, but when it doesn't work, it's Intel's fault.
RMBS will be lucky if RDRAM makes it into any PCs in 2001, including high-end machines.
Intel is smart to dump their asses. If I recall correctly, though, their deal with RMBS prohibits from using non-RMBS memory at >1GB/s for another year or two. That probably explains why they state their future use of SDRAM, not DDR. But they'll need to use DDR to stay competitive. It'll be interesting to see how it plays out.
Yeah, but it is hardly $1000 vs. $150, as the original poster said.
ok, in the last analysis it's about money...but Intel's interest in RAMBOOST goes way way beyond a direct financial stake in RAMBOOST equity. With a successful imposition of RDRAM on the industry, Intel has a wickedly powerful club to beat OEMS and the likes of VIA. Had they succeeded with their initial plans to shove it down all our throats, I would have had to travel to D.C. and pitch a tent outside Joel Klein's office 'til he brought an Antitrust action against Intel/RAMBUS.
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
With PC133 RAM you're ok now, but stuck with potential problems down the road. I don't mean to be hypocritical: I use PC100 in my Athlon system. But I really don't think that old RAM is the way of the future.
- I don't care if they globalize against free speech. All my best free thoughts are done in my head.
When in the motherboard with the micron k7 MP chipset going to be available?
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
I see this as Intel's attempt to foul the Alpha 21364. From what Compaq/DEC has release the Alpha is supposed to only use RAMBUS. If Intel says 'Hey this sucks' They could possibly bring down the new Alpha's. And Intel is probably only doing this because they can't do as well with RAMBUS as Compaq/DEC has with the Alpha and RAMBUS.
Itanium will support SDRAM, at least at first.
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
You asked:
Do you really think Moore's law would be holding up if there wasn't a shitload of money in it for the people who produced the silicon?
The companies that produce the silicon are entitled to make money and fuel Moore's law. However, RMBS doesn't produce anything except a stack of patent applications.
BTW, I am a practicing EE and earn my living every day working with traces and picoseconds. I learned in EE school years before RMBS existed about synchronous communication and PLLs and DLLs and DRAM circuits. If you were really an EE, you would agree that the concept of "syncronous DRAM" is obvious and therefore not patentable.
From what I read, intel were claiming they were going to use RAMBUS in high end systems costing more then 2000 dollars. This doesn't seem like intel dropping RAMBUS. This seems like intel admiting that you can't build a useful system based around RAMBUS for less then 2000 dollars. I think they will still try. They just won't sell that many.
Bob.
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
Why can't they just pull an RIAA and claim they never promised to use RDRAM?
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
well.. The main reason why Toshiba agreed to pay the loyalty to RAMBUS is that it is "the" RDRAM supplier for Sony Playstation 2. Toshiba is banking on it. Joonbug
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
I believe that Intel merely has options to buy up to 10% of the company at something absurdly low, like $2/share. The only money they've given them thus far is just in royalties for making their chipsets Rambus compatible (though maybe not? Maybe the royalties are just on memory manufacturers making RIMMS?).
So in the end, all intel will lose is a lot of face, a few hundred million dollars from the 820 motherboard fiasco, and a couple years of R&D. But that's all spent already, so they might as well brush themselves off and continue on...
Doesn't intel have a lot of money invested in Rambus? As far as I know (from stock quotes etc) Rambus is not an up and coming company so mabye that has something to do with it.
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.
problems as Rambus, then (tight tolerances, etch resistance, etc.). If the fast bus isn't exactly twice as fast as the two slower ones, then you have to do some kind of multiplexing and bus arbitration outside the CPU--which creates all kinds of livelock and starvation problems, probably.
Do we really care if Intel stops using RAMUS?
wouldnt it be better if they just pulled the plug on RAMBUS instead?
Stop over-analyzing your analizations
that what Intel did was add a single rambus channel to a chipset and hack that in to an existing processor. No wonder it doesn't work well! If you put the controller on-chip (as DRDRAM intends), then you can have relatively low-latency to memory, and you can use multiple channels to get extremely high bandwidth.
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.
Why are you using a 32 bit architecture? Get an Alpha or something. No matter what tricks RDRAM may have, it's hard to beat proessing 64 bits at once compared to 32.
I'm one of those computer researchers, and I think that memory latency is not that big a deal. For single-thread performance, sure, a TLB miss can idle your processor. But when you are a server, you just swap contexts and continue working--with no problem at all. You are right that latency is important, but really more of latency to L1 & L2 caches, not memory latency. Let's play some games with scale:
L1 cache hits 95% of the time at 1ns a pop.
When L1 misses, L2 hits 90% of the time at, say, 15ns a pop.
When L2 misses, memory satisfies requests at between 40 & 100ns (SDRAM/RDRAM roughly)
So, you're average memory latency time for a SDRAM system is:
(95% * 1ns) + (5% * (90% * 15ns + 10% * 40ns)) = 1.825ns
And for a RDRAM system, it is: (95% * 1ns) + (5% * (90% * 15ns + 10% * 100ns)) = 2.125ns
Now, your SDRAM, or DDR-SDRAM, system might have less than half the latency of RDRAM (40ns vs. 100ns) (and believe me, that is a conservative ratio as SDRAM isn't that fast and RDRAM isn't that slow), but the average memory latency is only about 16% worse. This is because the average memory latency is largely controlled by the cache latencies, since caches have such high hit rates.
Now factor in that RDRAM can supply three or four times as much bandwidth as SDRAM or DDR-SDRAM for an equivalent pin-count, and you have a much, much faster computer with RDRAM.
The problem is that Intel did a high latency and low-bandwidth implementation of Rambus, and therefore you haven't seen it perform yet. They're next version should be better. Otherwise, just wait for EV7.
It's that you need four of them to match the bandwidth you can get with RDRAM from a 64bit bus. How many processors do you know of with 4 SDRAM busses?
BTW: What 700Mhz bus are you talking about? As far as I know, the spec for RDRAM is 2x (yes DDR) on a 400Mhz bus.
Actually, RDRAM simms are pretty simple, the additional circuitry is in the controllers--which is, admittedly, more complex than what's necessary to make a DDR-SDRAM work, but not that big a deal when compared to the complexity of modern processors. It's expensive because it is new. Plus, RDRAM is for higher-end systems, not your grandma's PC, at least not yet.
This has the same text as my message (below), which was posted half an hour before the one above. Nice try, AC, but you've been busted.
#define X(x,y) x##y
#define X(x,y) x##y
Peter Cordes ; e-mail: X(peter@cordes ,
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?
Stop it, you're killing me. I am the nitewatch for the IS dept. and my shift just started. (Sober and bored.)
"..don't you eat that yellow snow."
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
Someone moderate this up, it has more information than any 5 posts ont his article so far.
If you think education is expensive, try ignornace
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.
Just without the chutzpah to try.
"If one is really a superior person, the fact is likely to leak out without too much assistance" -- John Andrew Holmes
Apparently by spelling it 'RAMUS' they're implying 'ram us' as in 'God forbid we make a spelling error.'
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.
I should have seen through you, but this whole RMBS thing pisses me off.
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