Slashdot Mirror

LONDON -- Engineers from Advanced Micro Devices Inc., IBM Corp., Sony Corp. and Tohiba Corp. have developed a strained-silicon transistor technology called "Dual Stress Liner," which can improve the performance at a given power consumption, AMD said Monday (Dec. 13).

The team is due to present a paper on the topic at the International Electron Devices Meeting in San Francisco this week, and AMD said the company and IBM are both expected to deploy the technology at the 90-nm manufacturing node in the first half of 2005.

AMD did not say if or when Sony or Toshiba would make use of the technology. The process development allows transistor "speed" to improve by up to 24 percent at the same power levels compared to similar transistors produced without the technology, AMD said. This process makes AMD and IBM the first companies to introduce strained silicon that works with silicon-on-insulator (SOI) technology.

AMD said it intends to integrate the DSL strained silicon technology into all of its 90-nanometer manufacturing process technologies, including those used for future multi-core AMD64 processors. The first 90-nm AMD64 processors using the technology are expected to ship in the first half of 2005.

Similarly IBM plans to introduce the technology on multiple 90-nm processor platforms, including its Power Architecture-based chips, with the first products slated to begin shipping in the first half of 2005.

"This achievement with AMD demonstrates that companies willing to share their expertise and skills can find new ways to overcome roadblocks and help lead the industry to the next generation of technology advancements," said Lisa Su, vice president of technology development and alliances at IBM Systems & Technology Group.

In the 1980s, IBM opened representative offices in Beijing and Shanghai, followed in 1992 by establishment of the IBM China Company Limited, a wholly-owned subsidiary of IBM World Trade Corporation. The IBM China Research Laboratory was established in Beijing in 1995. Today, IBM China has offices in 11 cities and operates eight joint venture companies in China.
--PrimeUR

IBM built and operates a chip packaging plant in China (registration site), a Research Laboratory in China, and is eyeing upward of a 50 percent share of China's market for business computers. Even IBM mainframes are big in China

IBM is creating a chip ecosystem in China and expects that Asian manufacturers will represent the bulk of the new Power licensees

This is because Moore's law allows for increasing number of transistors. This means adding advanced functionality becomes cheap and process advancements reduce power, so what we consider fast will be on your watch in a few years. This leads to the notion of ubiquitous computing.

Its also interesting to note that the IC industry is easily matching our needs. This silicon strategies warns of the over capacity facing IC production.

This isn't free as in GNU, but cost. I assume he predicts that computers will become so powerful and accessable that the industry will follow a low-cost strategy like manufacturing. This would be instead of adding value through performance, since computers will be fast enough that its not extremely valuable.

Because the Germans guaranteed the necessary loans. AMD's balance sheet has been so bloody of years past, that there wasn't anyway that AMD would have been able to swing the loans without a consigner. Aren't a lot of parents out there who can co-sign a $2.4 Billion note. From the article...

Press reports quoted regional government sources in the state of Saxony as anticipating that AMD will receive a debt guarantee from the German governement by next week. Other sources report that the Saxonian government has already provided guarantees for 80 percent of the required loans.

It's neat that Vanu is doing this on Linux, but it's not like it's a revolutionary technology breakthrough.

There's still an analog RF radio involved; all the digital processing is at the IF frequency. Digital signal processing of raw RF in the gigahertz range is still a bit out of reach. (And it will require an A/D with huge dynamic range.)

It's not clear that it's a win to do this using commodity PC hardware. Most of the crunching is in tight signal-processing loops that don't use much memory. With custom boards, you can have more CPUs on a board. Squeezing the physical size down matters in this application. If you can put the gear in a box on the pole, instead of needing a little shed, that's a big win. PCs also tend to use more power, and thus generate more heat, than DSPs per MIPS. Cooling all the gear is a constant headache in the cellular business. It typically doubles the power consumption, and the air conditioners themselves are maintenance headaches. What the industry wants is gear that doesn't require air conditioning, at least for smaller sites. Qualicomm has been shipping pole-mounted CDMA base stations since 1997.

It's also not clear that introducing a network between the radios and the processors helps reliability. If the radios are flexible enough that one can take over the job of another, it's easier to fail out a radio/processor pair and switch in another one.

None of this matters all that much because the cellular base station equipment industry is in the tank. The industry overexpanded based on forecasts of huge needs for 3G gear, and that didn't happen.

Well if anything you can't fault VFX with the story. But yes each prequel had over 2000 VFX shots. You have to read the article though, last film Weta did about 800 VFX shots and for this they are doing upwards of 1200. As their technology matures (Massive, muscle dynamics, subsurface scattering) you can even throw more things at to the VFX.

It certainly is a big setup, they are adding 1,176 new processors to what they already had (which was stated in an article some time ago). Probably ILM and Imageworks have a bit more though. The article says that they have the largets Intel deployment, but places like ILM and Imageworks, besides their Intel/Linux machine still have quite bit of SGI hardware around. An article on the SGI websitye a couple years back stated ILM had an 800 CPU Origin 2000 machine, and around 500 O2s. Since then a lot of the TDs, animators and compositors have gotten Dell Linux workstations and several of them keep the 2 machines side by side (the O2 and the Dell). ILM and Pixar also recently added to their renderfarm via RackSaver:

Pixar switches from Sun to Intel
Racksaver testimonials
AMD debuts server processor, readies 'Barton'
SGI Powers 5 Summer films

It certainly is nice that New Line is paying for this though. I'm sure other studios are envious ;-).

Any litigator knows that you don't want to go to trial--you want to force a settlement.

I think that is only true only if the other side has assets you want and that they are reasonably likely to surrender, like cash, and still survive. If your intent is to destroy them, you go to trial, especially if you are certain that you will win.

If SCO's real target is Linux, with the idea being to remove Linux from the market and pick up the residual commercial business, then going to trial is in their interest.

Not many companies willingly self-immolate at the suggestion of contract, patent or copyright infringement.

Just for reference I will point out two cases involving theft of intellectual property (source code) in EDA (Electronic Design Automation) land:

Cadence vs Avanti - result: Company execs go to jail, $465million in damages awarded.

Silvaco vs Circuit Semantics - ongoing.

Low-k? Welcome to the ballgame. IBM rolled out low-k, SOI, and Cu three years ago ... on 0.13 micron. See here and here. So did Intel.

Not quite what you are talking about.. but here it is anyway.

in late 2003 or early 2004 they are completely switching memory to DDR2, but since DDR2 is as hard to come by as Jesus in a Bottle

DDR2 on eBay

Oh, that DDR2.

Read this. They know more than I do.

1000 clients sounds incredibly small to me when you're talking about feeding a large residential area networking, especially given the bandwidth of 802.11g spread out over all those users...

Here's a snippet from the article on what it offers:

In an ideal world, Marks said, 802.16a can serve as a backbone for 802.11 hot-spots. Still, some wireless LAN advocates promote 802.11's use as a MAN, even though its medium-access control protocol is fundamentally optimized for shorter-range topologies. At the same time, Marks said, others have talked of using 802.16a within the enterprise as an adjunct to 802.11a or 802.11g. If the 802.11e working group has trouble providing true quality-of-service prioritization for wireless LANs, then it might make sense to take 802.16a directly to an end user, Marks said. Otherwise, "it's more efficient and more cost-effective to look for the ways 802.11 and 802.16 complement each other."

This article posted today at Silicon Strategies is probably just a rehashed press release pointing out that Motorola has made some nifty new nano-crystal flash with its 90-nm process technology. But if anyone's interested in it, it's those of you who've read this far.

This article posted today at Silicon Strategies is probably just a rehashed press release pointing out that Motorola has made some nifty new nano-crystal flash with its 90-nm process technology. But if anyone's interested in it, it's those of you who've read this far.

This article has a bit more information about who is likely to start selling stuff with this chip. FYI.

Allow me to bring you up to speed:

Nintendo's future

The X-Box's woes, and the price of Microsoft's sacrifices.

Heck, a quick search on Google has yielded this, and that's just scratching the surface.

As for relationships, this is a good article to start.

I'm certain a bit more hunting around Google News will yield what you're looking for.

Xilinx and IBM are teaming up to make an 10 million gate FPGA with multiple PowerPC cores on it (see this story) in ADDITION to the 10 million gates.

So, 1 chip and you could have an SMP PDA - do all the interfacing logic as part of the FPGA core. I suspect that is what this device is.

(Granted, the cores aren't floating point cores, more like what the Series 1 TiVO has, but still....)

I work with a lot of Taiwanese engineers. They don't consider forwarding stolen information to China to be stealing. They all believe that helping the Motherland is their duty.

It's funny that the U.S. is so vociferous about protecting Taiwan when the Taiwanese are already helping China out. Once Taiwan is folded back in to China, all those fancy weapons and huge investments in Taiwanese industry will benefit their biggest enemy.

The Kodak one is a indeed single chip one. For more details, see this article at Silicon Strategies.

Funny, you've been asked twice now and declined to provide links.

Here's mine:

FreeBSD Driver Initative
Announcement of collaboration between NVIDIA, SGI, and VA Linux
NVIDIA press release
And another release
Tom's Hardware discussion

Oh, and SGI isn't the only proprietary code either. There's also a cross licensing agreement with S3 for the S3TC (S3 Texture Compression) algorithms that NVIDIA doesn't have the right to disclose.

NVIDIA and SGI drop lawsuits

Anyone with enough data to answer?

It says here that Intel's Fab 24 is now slated to support a .09um/300mm process by end of 2003. Although no dates were indicated for IBM, they may indeed beat Intel to 0.1um. So why is IBM going for .1um when Intel is going to .09um?

http://www.siliconstrategies.com/story/OEG20020118 S0081

You can sign up to become a Beta tester for the Xbox Live here

What I really wanted to say was Sony has decided to release the PS2 Linux kit in Europe. Sign up Linux Play
Looks like Sony is covering all their based. Look at the deal they just made with IBM about Setbox technology that I am sure will find its way into PS3 related stuff.

http://www.siliconstrategies.com/story/OEG20020417 S0077, as linked to by the Reg article. Rehashed rehash, that's slashdot!

--j

Things have changed. Micron (Boise, Idaho) is taking over the industry. They bought Toshiba's DRAM business, they bought TI's business, they bought KMT's business, and are negotiating to buy Hynex, which is in trouble. They and Samsung are in a race for the #1 spot now; if the the Hynex deal goes through, Micron will be far bigger than Samsung in DRAM.

In 2001, there was a huge DRAM glut, which pushed prices down. Micron, instead of cutting back, used its advantage as the lowest-cost producer to squeeze out the weaker players. Here's an overview of the industry.

It looks like that when the dust settles, Micron will have about 40% market share, Samsung (S. Korea) about 22%, Elpdata (Japan) somewhere under 20%, and minor players the rest. The era of brutal competition in DRAM may be ending. The number of players is much smaller now. We may see more "stability" in DRAM pricing.

That article always left a funny taste in my mouth.

Why was he comparing next-gen DDR (DDR333), which isn't officially out yet, to the OLD PC800 RDRAM? Wouldn't it make more sense to compare PC1066 RDRAM (see the AcesHardware benchmarks)?

PC1066 RDRAM and DDR333 will both come out officially around the same time in official chipset support.

In other words, next-gen DDR performance for the P4 is about 1.5 years behind the RDRAM performance. Tom didn't mention that part...

In other news, Samsung is sampling PC1200 RDRAM now, too. 4.8GB/s in a dual channel config.

While it's wonderful that they can create a 300fs inverter, you also have to consider that they have yet to prove that they can actually mass-produce these structures to get adequate yields. This is not a trivial operation. Bell Labs, IBM, Intel, and AMD have all announced ultra-small and/or ultra-fast transistor structures, but they all admit that they are far from mass-producing them on a wafer/die.

Also - the rest of the componentry in a computer or other electronic structure, and how it will all communicate all of these calculations, will also be a problem. Already, integrated circuit I/O circuits are having trouble transporting data back and forth on a PCB.

ALSO, consider that the photolithography tools that are supposed to support the next generation of smaller structures are already off-track. 157nm lithography tools have been delayed due to development and financial difficulties. See SiliconStrategies.com). My personal guess is that the vertical MOSFETs will be the winners in the short term because, until they get other factors in line, they will have to make do with what they've got, though *again* the additional processing required for the wafer will impact yields, so it will be an expensive technology to implement either way.

What we must not forget is that limited liability corporations are an invention of government. Before the LLC was invented by government, owners of a business were personally liable for all wrongdoings done by their business. The LLC grants the owners immunity from prosecution, thus allowing the LLC to gather funds from greater numbers of investers, thus allowing companies like Dolby to exist. And that's good. But let's not forget that Dolby is a creation of the government, and is the direct result of government intervention in our economy (i.e., the granting of immunity to the owners of businesses in direct contradiction of a thousand years of common law).

It's amusing the the boosters of capitalism turn a blind eye to this blatant interference of government into our own economy, all the while condemning other nations' governments' control over their own economies. But not surprising. Hypocrits never see the beam in their own eye when they turn to condemn the splinter in another's. The fact of the matter is that we practice "corporate socialism" rather than capitalism here in the United States. We give certain businesses special immunities or priviliges (such as their owners not being sue-able) in exchange for the benefits of that arrangement (being able to better concentrate capital to do things like, e.g, build multi-billion dollar fabs). The benefits have been enormous in terms of the ability of this country to muster resources and apply them to leading-edge technologies. This does not render it any less socialism, though.

-E

...lots of research just as interesting as this gets published all the time. ZnO is a wide-bandgap material enjoying a renaissance of interest, and might compete with SiC, DLC, and GaN, but I'm not sure this is worthy of a full-blown /. article. Now combinatorial MBE to explore the TiO2:Co system, that was /. worthy ;-)

Sorry myamid, but you're the one who screwed up this time. :)

The Register: At the high end, ClawHammer will be AMD's first implementation of its 8th generation architecture. ClawHammer will feature the x86-64 technology aimed at rivalling Intel's IA-64 McKinley. Sampling in Q4 2001, ClawHammer will be SMP capable and go into production at the beginning of 2002.

Silicon Strategies: AMD also looks forward to bringing the 64-bit microprocessor generation to the desktop. A previously undisclosed version of AMD's 64-bit Hammer chip, Clawhammer, will begin sampling at the end of 2001 for desktops and server appliances and enter production in the first quarter of 2002. Sledgehammer, a 4- and 8-way capable part for servers, will sample in the first quarter of 2002 and ship a quarter later.

I'd link to more, but it's all reprintings of the same press release, more or less.