Slashdot Mirror

"Intel(R) Extended Server Memory Architecture--expanded 36-bit memory support which allows operating systems and applications to utilize memory greater than 4 Gbytes" Intel

Um, there are plenty of vendors offering tested AMD dual CPU 1U setups. And NO AMD cpu's do NOT need more power than Intel, Intel Xeon MP 3.2GHz Themal Guidline is 92W from Intel, AMD Opteron 2.2GHz Thermal Design Power is 89W from AMD. And to give you an idea where Intel is headed their 90nm 3.4GHz P4 has a Thermal Guidline of 103.0W with industry people stating that the 90nm line will end up north of 150W!

Intel talked about this at the last developers conference. Its the ability to run OSes and applications in partitions that are protected from trashing each other. Here's a blurb from one of the keynote addresses (about halfway down):

You may remember at the last IDF, Paul Otellini in his keynote did a demonstration and introduced a new technology, a new star "T" called Vanderpool Technology or VT. In that demo, he was in a home environment where he demonstrated by creating different stations in a virtualized station. You are able to run your PVR in one partition and the games in another partition without interfering with each other.

VT has applications not just in the digital home but also in the digital office. What are some of these usage models? Let's take a look. VT, likewise, can be used in business computers to create different partitions, to provide an IT partition where the IT mission-critical applications are well protected and not compromised by the user. At the same time, it can create partitions that can provide legacy support. In other words, applications that may not run under the new operating system.

Now, this is the kind of thing that's actually fairly common encountered in both large enterprises as well as more medium business.

An example we see in accounting software or asset tracking software, they're written and validated on an old operating system that have not been reported or validated.

As an example, my sister is a dentist and she has a billing system on her computer. She wouldn't dare to upgrade it because there's no support of porting that billing system to a new OS. And as a result, she continues to run on old hardware, old OSs, that expose herself to productivity and security issues. Not a good situation.

So let's take a look at how this actually works. I'd like to invite Jason Davidson out here to show us how VT benefits the enterprise.

(Demo begins and ends.)

BILL SIU: So in the coming several years, we'll be working with many of our business colleagues, many of you present here, to develop this capability and bring this kind of improvement to the enterprise. We think this is of just great value to manageability, providing both end user benefits as well as IT value.



One assumes the demo shows them crashing an application yet the other application keeps on working.

Yes and no. I understand what you're saying but they could have easily bought a cheaper CPU for the job. Why not use a Mot 68000? Why not use an Intel i960? The Mot 68000 has been used in everything from Macs to Cisco routers. The Intel i960 is still used today in most manageable Ethernet switches. The printer drivers only need basc RS-232 capabilities. We don't need anything fancy. They aren't going to hook up an Epson Stylus Photo 870 to this thing. Using an existing consumer platform and OS like x86 and Windows will of course be easier (not cheaper) to implement a solution on but it will not be a better solution in the end. Security and stability problems will haunt you. That we've already seen. I really only wanted to point out the CPU info.

Intel Pentium M Thermal Design Power is listed as 24.5 Watt at 1.7 GHz, a FAR cry from the 7 Watt you claim

The 900 MHz and 1GHz ones are the 7 Watt models, but how those perform compared to an Efficeon I was unable to find.

Cooper
--
I don't need a pass to pass this pass!
- Groo The Wanderer -

...a laptop with a dedicated "portable" architecture. I can definately see Intel saying "More transistors, more power, more clock, and it'll be okay" -

Hi, welcome back to Planet Earth, I hope your trip to wherever-it-was for the last 2 years went well. Here's a URL that might help you catch up on what the world's been doing in the meantime:

Intel Centrino Mobile Technology

Basically it was an observation that the transistor density would double every few years... for a while.

But the gist of the parent may be right. Frankly I'd like to see the standard benchmark be porn related in some way.

Basically it was an observation that the transistor density would double every few years... for a while.

But the gist of the parent may be right. Frankly I'd like to see the standard benchmark be porn related in some way.

The centrino tests/comparisons were heavily rigged (using 16 meg video ram for the comparison processor)...I recently tried to help a young friend buy a laptop, and while researching came across Intel notebook comparisons with what appear to be rigged tests. I was amazed at the obviously crappy centrino selling everywhere... why are they using 16 megs of video ram? This seems to be their common practice, as the tests they have up now seem to be a newer version of the ones I saw a few months ago.

... since your computer will be shaped like a guitar and kill pirates, it will be totally fuckin' sweet.

Surprise, Microsoft releases .Net for Unix, and the entire effort is null and void. Your pride and joy is now a footnote, and a deprecated one at that.

Moore's Law says that the numbers of transistors per integrated circuit increased exponentionally.

A Marketing major heard it and thought that too drery, and declared speed doubled every 18 months.

It goes here, which is a page saying that they're working on it.

>BTW: Don't forget to sign the Intel Support of Centrino Under Linux Petition.

Check this out. Closed-source, but it's better than nothing

Parrot will perpetually be 6 months from doing anything useful. [...] Parrot is too complex and bloated for what little it does. It already has over a thousand opcodes - talk about simplicity! What moron designed this thing?

By the terms of the lawsuit described in that article, AMD cannot clone intel chips. They can (and do), however, implement intel patents, the latest I can think of being SSE2 instructions in their athlon-XP processor. They renewed their cross-licensing agreement in 2001 for ten years, and it cannot be broken without mutual consent.

This is a long standing agreement, dating from 1976.
intel press release

Listen to how they weasel their way into admitting that they implemented the AMD64 instruction set:

Q9: Is it possible to write software that will run on Intel's processors with 64-bit extension technology, and AMD's 64-bit capable processors?

A9: With both companies designing entirely different architectures, the question is whether the operating system and software ported to each processor will run on the other processor, and the answer is yes in most cases. However, Intel processors support additional features, like the SSE3 instructions and Hyper-Threading Technology, which are not supported on non-Intel platforms. As such, we believe developers will achieve maximum performance and stability by designing specifically for Intel architectures and by taking advantage of Intel's breadth of software tools and enabling services.

So, "in most cases, yes" you can write software that will run on both processors (implying that they're implementing AMD64), but be sure to use Intel-specific features such as SSE3 so as to maximize "performance and stability" (i.e., Intel's market dominance).

this page is probably what you are looking for.

Here, #9

Q9: Is it possible to write software that will run on Intel's processors with 64-bit extension technology, and AMD's 64-bit capable processors?
A9: With both companies designing entirely different architectures, the question is whether the operating system and software ported to each processor will run on the other processor, and the answer is yes in most cases. However, Intel processors support additional features, like the SSE3 instructions and Hyper-Threading Technology, which are not supported on non-Intel platforms. As such, we believe developers will achieve maximum performance and stability by designing specifically for Intel architectures and by taking advantage of Intel's breadth of software tools and enabling services.

The campaign launched with the 486 in 1991 and Intel considers the real pay off to have been in 1993 with the Pentium and then Pentium Pro in '94.

I guess the implication is that the proper thing Intel should have done is develop its own set of 64-bit extensions, making it absolutely incompatible with AMD's offering.

You mean like Pentium?

From Intel's 64 bit extensions faq

Q9: Is it possible to write software that will run on Intel's processors with 64-bit extension technology, and AMD's 64-bit capable processors?
A9: With both companies designing entirely different architectures, the question is whether the operating system and software ported to each processor will run on the other processor, and the answer is yes in most cases. However, Intel processors support additional features, like the SSE3 instructions and Hyper-Threading Technology, which are not supported on non-Intel platforms. As such, we believe developers will achieve maximum performance and stability by designing specifically for Intel architectures and by taking advantage of Intel's breadth of software tools and enabling services

That sure sounds PRETTY FORTHCOMING TO ME.

I've always wanted to say this. RTFA, Linus!

And, please apply lameness filter to michaels comments. Thank you.

no, but you can download the SDK and drop in the eval verison of intel's compiler.

actually, Intel recommends against using HyperThreading with Win2K (all flavors)

Intel.com

it will run but performance sucks

Do you remember when the "Intel Inside" logo came out?

1991, according to Intel themselves

There was no real competition. (it was the Pentium days) There were other processors, but the Pentium pretty much blew them away.

The Intel Inside marketing program started two years before the Pentium came out. At that time AMD was competing very effectively with the 486. So much so that Intel wanted a new marketing campaign to try to bring people back. Even in the early Pentium days AMD continued to compete effectively. Their 5x86 120MHz chips were very competitive with the Pentium 60 and Pentium 66, and even the 75MHz Pentium chips. It wasn't really until '94 or '95 that Intel really started leaving AMD in the dust, mainly because AMD was WAY late at releasing their K5 processor and when it did come out they had so many problems manufacturing it that it was clocked much lower than initially hoped for. Cyrix continued to offer some competition for Intel during this time, but they were plagued by crappy motherboards which gave them a poor reputation (it was a bit of a self-fulfilling prophecy thing: reputation for being cheap crap meant that they were put on cheap crap motherboards which resulted in a poor quality system).

it will be [better] because it is cheaper

And that is somehow an invalid reason for a product to be better?

This will be a binary only release, pretty much hands down, pretty much precluding the more esoteric and non US centric distros getting a driverset. Still the big deal for me isn't distro, OS lockin because of drivers is no news to me.

I sit here typing this on my Presario X1000 which would not agree to function with the DriverLoader hack. The only way I'll be able to get reliable support for mini-PCI wifi will be to replace the intel card with something like this.

Hell I'm not even worried about the wifi drivers until I can actually get decent battery life. Maybe if the speedstepping was 100% complete and verfied by an intel OSS coder then I'd take this to heart. Until then, this is just more of the same empty promises Linux drivers are "under development" and have been for nearly a year for the wifi, from intel's page anyways.

though it wasn't a cpu per se, but a gpu, the i740, if i recall correctly, was a pretty big flop when it was trying to compete against the likes of 3dfx as a low cost alternative onboard graphics chip...

64 Bit Extensions

From the Intel FAQ Site:

Q9: Is it possible to write software that will run on Intel's
processors with 64-bit extension technology, and AMD's 64-bit capable
processors?

A9: With both companies designing entirely different architectures, the
question is whether the operating system and software ported to each
processor will run on the other processor, and the answer is yes in
most cases. However, Intel processors support additional features, like
the SSE3 instructions and Hyper-Threading Technology, which are not
supported on non-Intel platforms. As such, we believe developers will
achieve maximum performance and stability by designing specifically for
Intel architectures and by taking advantage of Intel's breadth of
software tools and enabling services.

On Intel Xeons, noless. That said, they built it signficantly before the G5 Desktop and the G5 XServe were available. No offense, but much as I want a G5 and like the look-and-feel of Mac OS X, you have to admit that a bunch of overheating 1GHz G4's were significantly less cost effective than a similar bunch of P4 Xeons at the time the render farm was built.

Ah, this stuff has been around for like 4 years, at least. We were using this kind of technology at the University of Chicago back in 1999 with WindowsNT images. (The department I worked in was responsible for supporting all of the public-use workstations throughout campus, and we naturally relied on disk imaging technologies.)

If you buy a product like Altiris LabExpert or Norton Ghost and are very clever, you can jury rig an entire operating system environment onto a CD.

Oddly enough, we stumbled on how to do this kind of thing while researching Wake-Over-LAN and PXE technologies. Apparently, the system BIOS just needs to be smart enough that it can look at something other than a PCI/IDE/SCSI hard drive for information with which to load a kernel into memory. If your BIOS is PXE enabled, it's smart enough to tell the system bus to look for a kernel on the network card (in the case of a Wake-On-LAN network boot) or on a CD drive (in the case of a CD boot).

FYI, PXE is Intel's Preboot Execution Environment specification, and is therefore working at the hardware level underneath Microsoft PE (Preinstallation Environment).

Nonetheless, the hardware capabilities which have allowed Windows to be booted from a CD have been around since 1999, at least, as they are part of Intel's PXE specification.

Just my two cents...

Here is a link to the Nature article (sorry if this is a repost). You can't print the article, so you must use your PDF cracking skills to turn on the print ability.

Intel researchers have developed a silicon-based optical modulator operating at 1GHz an increase of over 50 times the previous research record of about 20MHz. Their technological breakthrough was announced in a paper," (.pdf, 233KB), in the prestigious scientific journal Nature. Fabricated in an Intel Fab using Intel's existing high-volume manufacturing processes, the device incorporates a transistor-like structure to encode data onto a wavelength of light.

The original report on this research was published in Nature, Volume 428 dated 12 February. A copy of the paper and more information about Intel's silicon photonics research can be found here.

Here is a link to the Nature article (sorry if this is a repost). You can't print the article, so you must use your PDF cracking skills to turn on the print ability.

Intel researchers have developed a silicon-based optical modulator operating at 1GHz an increase of over 50 times the previous research record of about 20MHz. Their technological breakthrough was announced in a paper," (.pdf, 233KB), in the prestigious scientific journal Nature. Fabricated in an Intel Fab using Intel's existing high-volume manufacturing processes, the device incorporates a transistor-like structure to encode data onto a wavelength of light.

The original report on this research was published in Nature, Volume 428 dated 12 February. A copy of the paper and more information about Intel's silicon photonics research can be found here.

I know it's lame to answer my own post, but for a possible demo setting, you can put a DVD ISO image at a webpage and get it to the demo computer.

Mathematically speaking, let's say DVD's content is 9.4 GB, which is equivalent to 75.2 GBits. Divide this by 2.5 GBit/sec = 30.08 secs. Since "typical" TCP/IP utilization is roughly 70%, divide this number with 0.7, so the estimated transfer time is roughly 43 seconds, plus some delay if the source is pretty far away from the demo place.

Transfering a full DVD content in less than 1 minute is damn impressive. Just let them taste the "raw" power of the 2.5 GBit link.

If you want to use streaming, make sure you have a high end CPU to back it up. Note that Ethernet is poor in contention management. It would exacerbate multi-client performance, but you can avoid this using FDDI based cards, which some clients find it not desirable. But it can be a good demo if their main motive is for tele-conferencing or whatnot.

If you want to gain more insights, here's an article by Intel. It's their advertisements for IXP, but nevertheless a good read with nice statistics.

Here is the official patent from the USPTO. It was originally filed in 1998, but IC's have been around much longer than that, so I'm sure there's some prior art somewhere. This next quote could almost have come from the depths of the SCO complex:

"'Our Main focus is the IP [intellectual property] business now,'" he [CEO Jeff Wallin] said."

Kinda sounds like Rambus and look where they've gone.

Amigori

Real programmers buy silicon in bulk and make their own CPUs and Assembly languages instead of sending a check to the man.

Anyway, I'd recommend doing a google search for 386intel.txt. This is Intel's documentation for the 386 chip, including systems programming stuff. This is the file Linus used. The modern version of this documentation is available here for the Pentium III, split up in three. You'll need all three, but the third in the series is most relevant.

After you get booting, you'll need some documentation for various devices when writing drivers. I used "The Indespensible PC Hardware Book" by Messner and it was pretty good. I guess there are also good websites available and you can always look at how Linux or *BSD does it.

Anyway, you might be able to skip the Intel documentation if you use someone else's bootloader, but I don't recommend this. One of the points of this project should be to understand the machine inside and out from boot, so write your own bootloader and object code loader. Once it can run your C code, you'll get a feeling of satisfaction, which should be another of this project's goals.

I used an older version of VMWare for testing, but I highly recommend bochs nowadays. Bochs seems designed exactly for this stuff, so you can run a debugger right away and you don't need to go through the older debugging route which was to write a serial port driver as soon as possible and get a remote debugger working over that (easiest way to do remote debugging in VMWare and real hardware).

I'd recommend nasm for the assembler bits. It can do 16-bit code for the bootloader and it can spit out unadorned object code so you don't have to bother with parsing ELF and extracting what you need (although you'll need to do this eventually when you get to C, but you can at least delay that until after you start booting).

One last thing - ignore the naysayers. It seems lots of people thought it important to post that you shouldn't be doing this but should instead be contributing some drivers to another project or something like that. Whenever someone in the open source community says this, they're almost always non-developers. Most of us write code on our own time because we find it satisfying and this is one of the most satisfying projects you can undertake. This project is also a kind of "coming-of-age" experience (for lack of a better word), like writing your own compiler or creating a GUI API or window manager. Users won't understand. That's OK. We understand.

If you can visit Santa Clara USA then Intel's museum has a nice introduction to the process of turning sand into chips.

Intel mentions (about the "Security" phase) here that:

The objective is to ensure that the first code executed by the processor is trustworthy and that this code has sufficient resources in and of itself to determine the trustworthiness of any subsequent code. What "authenticate" and "trustworthy" mean can evolve over time and across platforms

Trustworthy computing anyone?

To relieve the slashdotted server, a similar review:
The actual spec (PDF!):
Intel's info about it:

Here's a few other links to similar data:

http://www.anandtech.com/showdoc.html?i=1876
http://www.dvhardware.net/article.php?sid=1894 Has PDF's of the Spec.
http://www.intel.com/update/contents/dt10031.htm

Some info on BTX can be found here. Presumably Intel's server can handle some additional traffic.

More info, greater bandwidth, fewer ads, etc at Form Factors and, of course, Intel.

Search for Prescott New Instructions Software Developer's Guide on Intel's site.

Do you mean a Tualatin core, or the P6 core that is the basis of the Pentium Pro, Pentium II, Pentium III, and Pentium M (and Celeron counterparts)

Well, when I was writing this, I was only thinking of the PIII/Tualatin. You're right about the Pentium M... but it does have some major design changes. For example, up to the PIII, the core uses micro-ops (uops). According to this, the Pentium M uses macro-ops. This says so too, even though they don't specifically call it a macro-op. I tend to think of the Pentium M as somewhat "loose" implementation of the P6 core.

Rose: I'll never let go Jack...
Jack: Are you smoking crack woman? I'm getting off this POS! You can stay with Craig!

According to the article, it uses an Intel PXA255. The creator has plans to open source the thing, so if you are truely interested, read the article and contact him. (His name is Gordon.)

Ugh. That does not even remotely resemble Moore's Law, "the doubling of transistors every couple of years". Further, Moore's Law does not apply to the embeded domain. Whereas the driving motivation for desktops and supercomputers is nearly exclusively computation power, a huge motivation for wireless embeded devices is energy consumption and lifetime. Moore's Law makes no assertion about the power efficency of computers, and yes, they're getting more hungry, not less -- go look at the size of your heat sink (!) and fan (!!) on your CPU and imagine putting those in your phone (!!!).

You can't abstract Moore's Law to "falling prices" and apply it to embeded devices. Fewer transistors and less memory consume less energy than their more beefy counterparts. When designing and selecting the hardware and software in this domain, device lifetime must be considered and balanced against the processor power and available memory.

Perhaps they plan to move that logic into a future mobile CPU chip.

yes they do. and into everything

I thought EFI was Microsoft's implementation of BIOS. They just picked a well known hardware vendor to introduce their plan.
http://www.intel.com/technology/efi/efi.htm