Slashdot Mirror

1) When the IA-64 design first became public, it was clear that they'd made some incredibly poor decisions. For example, the architectural design was based on the assumption that the chip would not do out-of-order execution in hardware. Such deficiences were to be remedied by a god-like compiler that would emerge at some later date. Unsurprisingly, it never has.

The Intel fortran, C, and C++ compilers for the Itanium for Windows and Linux are pretty godlike in my experience. Look at AMD benchmarks and usually they are done with the Intel compiler. Intel has also licensed the compiler technology to at least Microsoft for VC++.

2) These predictions were borne out by the fact that Itanium performance has always sucked, especially considering the enormous die size, cost and heat dissipation.

Your definition of sucked differs from mine. Yeah, the Itanium1s did suck. Yeah, the Itaniums put out tons of heat, but much of the current work at Intel is not with uping the MHz game, but in lowering power consumption and heat dissipation. Currently available examples are the PentiumM and the low voltage Itanium2 processors which are only available at 1GHz now, but the whole line is supposed to be available in 2005.

3) It looked like Itanium might win in the market despite its technical limitations, just because of Intel's vast marketing budget, its momentum, and its monopoly leverage forcing OEMs to stay away from technically superior alternatives like AMD64.

Coke does the same thing over RC cola. Windows does this over OS X. It just comes from being the market leader. People buy what they are familiar and comfortable with and can afford.

4) Thankfully this hasn't happened. The technically superior, open solution is winning. Thanks AMD.

No comment.

If you want to learn more about future memory technologies which could replace today's SDRAM and flash-memory try searching for "MRAM", "FeRAM" and "PCRAM". The latter is probably the most promising one due to the (expected) ease of design and manufacturing ("Samsung says that it will enter full-scale production with the technology in 2006").

More information about phase-change (->PCRAM) materials can be found at E*PCOS website.

Actually, PBS has been ahead of the curve on digital broadcasting here in the U.S. It was the first network to do a national broadcast of a program fully produced and aired in hi-def. It was also the first to offer a 24/7 network of HD programming. In addition, it has worked to develop applications for interactive TV, and has worked to build various advanced broadcasting technologies. PBS.org is the most-visited .org Web domain in the world. So in a nutshell you're, like, wrong. PBS has decades of leadership in broadcast technology. But I know everyone loves to knock it, so go right ahead.

Secondly, EM64T processors are expensive, server-oriented Xeons.

It wouldn't make much sense to compared them with cheap desktop Athlon64s.

It would make perfect sense to compare socket 939 Athlon64s to EM64T Pentium 4s on 925X chipset, but I don't think EM64T P4s are easy to get without purchasing a whole workstation (oddly, boxed EM64T P4s are available in Japan). Can't Anandtech mooch a CPU from Intel for review purposes?

Who said there are only 2 compilers? He only tested 2, that's all. Here's a bit of a list - and notice that some of these are targeted specifically to scientific computing:

1. GCC
2. Intel compiler (Intel only)
3. Comeau
4. PathScale (Opteron only)
5. Portland Group (PGI)
6. Borland

Does anyone have a working EFI test PC yet?

I don't understand why legacy 16 bit code cannot be loaded on demand from a disk or flash for legacy boot while using new protected mode boot for a modern OS. Those who need the old code for compatibility simply turn it on in the bios menu.

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 - fjw

Most CPU manufacturers who also produce memory chips bed the next cpu tech level on memory chips first. This gives them experience of production on a slightly easier to produce product. I think you may find that INTEL already produce 90nm memory chips. Intel 90nm memory

If Intel's CTO really said that its time for him to be fired. Except that he didn't. What he really said is this

Planetlab isn't an alternative to anything. Its not even a network really. Its a research testbed, for people who want to evaluate their protocols on more realistic network conditions than the LAN in their labs. Its a good tool to help design the next generation Internet, but Plantlab in itself isn't going to do anything.

I know this because I happen to be one of the people who does network research on Planetlab, and one of those 429 happens to sit on a table across the room from me right now.

Intel Outlines Strategy For Making The Internet Smarter, Safer, More Reliable And Useful
(...)
This would transform the Internet from a data transmission pipe into a vast platform for hosting a wide array of services available [add: for ________ $ / __ (+ your immortal soul where applicable)?, ed.] to the world's six billion inhabitants. Gelsinger referred to this approach as the ability to provide planetary-scale services.
(...)
we are confident that we now can begin deploying and testing revolutionary, planetary-scale commercial services that will change the way business is done on the Internet.
(...)
"A planetary-scale overlay of computational services would open the Internet up to a new era of innovation while complementing other Internet initiatives," Gelsinger added. "It would provide a platform on which Web services can run and a way to connect grid computing sites and utility data centers. It sits above the new physical infrastructure supplied by Internet 2 and above the networking layer where IPv6 functions, adding a new stratum of higher-level functionality to the Internet."

Intel's press release about the same speech has a little bit more information, although nothing technical.

http://www.intel.com/pressroom/archive/releases/20 040909corp.htm

Also interesting: a link to the open platform website:

http://www.planet-lab.org/

Interesting quotes:

"Applications run on PlanetLab are decentralized, with pieces running on many machines spread across the global Internet. They can also self-organize to form their own networks, and include some form of application processing inside the network (instead of at the edges), adding new intelligence and capabilities to the Internet."

"It would provide a platform on which Web services can run and a way to connect grid computing sites and utility data centers. It sits above the new physical infrastructure supplied by Internet 2 and above the networking layer where IPv6 functions, adding a new stratum of higher-level functionality to the Internet."

Why it has to replace the current TCP/IP-infrastructure is still unclear (apart from selling more hardware).

Question for the Kernel coders, what perctage of drivers are reverse engineered?? 60-70%

The percentage would be near 0% if not 0%. Plenty of hardware manufacturers have released open or open-enough programming specifications for their hardware. Intel, AMD and National Semiconductor are a few examples.

For example, here are the programming specifications for my network card, a Netgear FA312 - DP83815 10 100 Mb s Integrated PCI Ethernet Media Access Controller and Physical Layer (MacPhyter)

Companies like NVidia and ATi are the exception, not the rule.

Intel'sengineers posted this 2 weeks ago.

It's not too much difficult to get a 20 seconds boottime (from grub to GDM) in any machine using linux.

And you don't even need to rebuild custom kernels or hardcode anything, just launch GDM as soon as posible, then you load the other services in parallel just like windows do. Some other tricks explained in also help ;-).

8 out of the 20 seconds are used for the linux kenrel to load, and the rest are mainly Xfree loading and GDM & GTK loading....

Now imagine if you use a lightweight Xserver like kdrive and port kdrive to a fast-booting kernel such as FreeBSD: I bet you could get under 10 seconds boottimes. And there are still much more tricks:

• suspend on disk
• compressed second initrd for file needed for booting
• a more lightweight Display Manager like the one of Enlightenment guys
• Hardware Accelerated graphical server?
• DirectFB ?
• LinuxBIOS
• EFI (Extensible Firmware Interface) specification [2]

I'm thinking about building a new distro with some of these ideas and more, if you're interested, edulix@jabber.org ;-).

Cheers,
Edulix.

--- [1] http://forums.gentoo.org/viewtopic.php?t=131142&po stdays=0&postorder=asc
[2] http://www.intel.com/technology/efi/

From Dolby's press release:

Dolby Laboratories announced today that the Dolby® Digital Live encoder has been integrated into select 915 chipset-based Intel® Desktop Boards featuring Intel High Definition Audio. Dolby Digital Live is a real-time encoding technology which converts audio signals into a Dolby Digital bitstream for transport and playback through a home theater system via a single digital connection.

Using this technology, users can enjoy PC-based audio entertainment in thrilling surround sound through Dolby-equipped A/V receivers or other devices. PC-users simply connect a single digital cable (such as S/PDIF or optical cable) directly to the home theater system, thus eliminating the confusion and hassle of multiple cables and ensuring the quality of the audio signal.

Additionally, PCs featuring Dolby Digital Live technology enable PC gamers to enjoy realistic and exciting Dolby Digital 5.1-channel surround effects during interactive game play by reproducing the audio cues and effects to correspond with the onscreen action.

Not only was the nVidia SoundStorm APU the only sound solution capable of encoding Dolby Digital on the fly (which produces true and accurate 5.1 surround sound via either optical or digital coaxial cable to a set of computer speakers supporting these connections or to an external amplifier), it was also hardware accelerated meaning it does not chew up precise CPU cycles like other inferior onboard solutions which in turn reduces frames per second and do not have the ability to send separate digital signals to anymore than two channels. You'll get 5.1 sound using three analog cables but this type of setup is nowhere near as impressive or realistic as what the SoundStorm produces.

...the beauty of the nVidia SoundStorm APU is that it is capable of encoding Dolby Digital 5.1 on the fly via hardware acceleration and not software (CPU). This means that in any games you play and as long as you are using optical or digital coaxial cable with your surround sound speakers (anything above 2.1 channels), the hardware APU will do the intensive job of reproducing the sound from the game to Dolby Digital 5.1 or AC-3 so you get proper positional surround sound.

Onboard sound solutions utilizing their digital SPDIF output (whether it be optical or coaxial, depending on what the manufacturer chooses to go for) can only output to the front two speakers as without an encoded 5.1 signal from the computer end beforehand, what is being sent through your digital optical/coax cable is limited to stereo (two channels) of sound...

The only way you can achieve proper positional surround sound in gaming with all other sound solutions on the market apart from the mighty SoundStorm is to utilize their analogue outputs (centre/sub, front, & rear jacks) but then it is not digital so you don't get the true to life effects of proper digital.

Or did we all stop using P4's when I wasnt looking? Intel High definition Audio: http://www.intel.com/design/chipsets/hdaudio.htm?i id=ipp_desk+highdef&

Just to help avoid any confusion here, this is not some new clever transistor design or something. It's just another incremental step in process size reduction. It happens every few years. And it's not just Intel -- I know IBM and NEC are doing 65nm right now as well.

A significant milestone in developing next-generation chip manufacturing technology has been achieved by Intel Corporation. The company has built fully functional 70-megabit static random access memory (SRAM) chips with more than half a billion transistors using the world's most advanced 65 nanometer (nm) process technology.

Uh, that article was pre-release, and was for an AMD64 FX overclocked by about 15%. In fact, that was the power draw at the highest stable speed they could achieve with a -10C cooling system.

According to this, the AMD64 processors have a thermal design of 89W.

According to this the comparable P4 has a thermal design of 115W.

AMD has nothing to gain by recommending to OEMs that they be able to supply less power than the system requires, and to dissipate less heat. I purchased an AMD64 and find that it runs quite cool without any help besides the retail heat sink and fan (nothing special).

FYI - half of the CPUs in my home are Intel-based. I'm hardly biased for the sake of being biased. However, when I went to build my computer I checked the specs and the prices and found that AMD64 was the best bang for the buck. And in the 64-bit world it is essentially uncontested at this point if you care at all about x86-compatibility. (Granted, that will change, and I look forward to whatever Intel comes out with to compete.)

The actual Intel press release claims that:

"Intel's leading strained silicon technology, first implemented in its 90nm process technology, is further enhanced in the 65nm technology. The second generation of Intel strained silicon increases transistor performance by 10 to 15 percent without increasing leakage. Conversely, these transistors can cut leakage by four times at constant performance compared to 90nm transistors. As a result, the transistors on Intel's 65nm process have improved performance without significant increase in leakage (greater electrical current leakage results in greater heat generation)."

I submitted this earlier, but was rejected.

Anyway, here is the offical press release from Intel's website.

OK - how's this?

Back in April, Slashdot reported the announcement of a Universal 3D File Format by Intel, Microsoft & others - to be "as open as MP3". Of course, that's not all that open. And this turns out to be the sneaky part. There is a real open standard already - X3D is ISO-ratified, royalty-free, and has multiple open source implementations. U3D is "going to be submitted to ISO" - one day - but right now they're talking to ECMA, which allows royalty-bearing patents.
I found this article by Tony Parisi, co-chair of the X3D Working Group a fascinating insider's picture of the standards wars, along with insights into what it takes to release an online game, what really killed VRML, and why open standards do (and don't) matter.
I mean, a royalty-bearing, pseudo-open universal 3D format from Intel and Microsoft? Sorry, guys. That trick doesn't work anymore


BTW, I need to get a life.

Many PDAs, like the Dell Axim, use the 400mhz XScale CPU. It gets warm but never hot. More details can be found at Intel.

I am surprised they did not go with the 624Mhz XScale.

... double the FLOPS of an Opteron ...

A couple months after AMD said they had taped out their dual core Opteron, Cray and others said they would be upgrading to that in 2005. Putting two Opterons next to each other with their hypertransports talking to each other is so easy that I suspect AMD's first silicon worked. I suspect dual-core Opterons will be in production way ahead of dual-core Itanics, since they are so much smaller. And we will see 8-core Opterons before we see 4-core Itanics. A number of people have working 8-way Opteron motherboards and I have not heard of anyone getting more than 2 Itanics on a motherboard. All the while AMD production volumes will be far higher than Itanic volumes.

If SGI wants to stop loosing money, they should come out with an Opteron CPU-brick fast.

"Won't be safe for long" means Itanic is sinking. Really.

My Intel PC Camera Pro has a nice shutter that you can slide over the lens. I always use it, kind of automatically. IMHO most webcams should have something like that but it seems many don't.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

Intel had, by then, hired away some of the Alpha designers and began to adopt its performance enhancing strategies.
Yes!
Google "alpha director site:intel.com" and you get 6 different web pages for guys who were working on Alpha design, but are now with Intel.
http://www.intel.com/pressroom/kits/bios/plowney.h tm
http://www.intel.com/pressroom/kits/bios/rgrove.ht m
http://www.intel.com/pressroom/kits/bios/jemer.htm
http://www.intel.com/pressroom/kits/bios/pbannon.h tm
http://www.intel.com/pressroom/kits/bios/wgrundman n.htm
http://www.intel.com/pressroom/kits/bios/dbhandark ar.htm
2 of these guys work specifically on Itanium stuff, the rest seem more generic.

So much for Intel's Commitment to LCOS and the Future of HDTV.

But seriously, what does this mean for LCOS? Manufacturers (e.g., Philips and Fujitsu) are still making and selling LCOS TVs or working on the technology. Does it just mean that they won't get as cheap as fast?

Depending on the technology (small mirrors or liquid crystal), the silicon switches pixels on or off when the color is aimed at it. Intensity of the color is handled by cycling the pixel on or off (only possible at semiconductor speeds). Light is reflected from the small mirror or substrate underneath the liquid crystal pixel and shines on the screen. The combination of the RGB colors together at high speed creates the image.

To add 1-3 colors to the color wheel and add support for that color to the silicon should not be too much of a technology hurdle. All you need is a faster color wheel and faster switching silicon to handle the additional colors without slowing the refresh rate.

Intel is currently working on a flash replacement called OUM (Ovonic Unified Memory). You can see their presentations here (bottom of page). STMicroelectronics is also working on the technology (among several others) and has announced a preliminary version of the technology that has 10^11 cycle endurance. This is 5 orders of magnatude greater than flash. Intel is shooting for 10^15 or higher in order to get DRAM equivalence for "most" PCs and servers. That is, "most" PCs and servers aren't flipping a single bit more than 1,000,000,000,000,000 times in their lifetime.

Intel makes a compiler. AMD does not. Intel's compiler HAMMERS gcc and MSVC. Like 20% in some cases.

You can try it for 30 days free here. Note Linux is there too.

Ugh, why would you want to?

Now, Solaris on an XServe... That makes sense... Server class hardware that doesn't suck, yet doesn't cost an arm and a leg, running perhaps the best multiprocessor Unix ever... Mmmmm.

The ironic thing in my view is that this is sort of what CHiRP was supposed to be - a happy universe where you could buy an RS6000 and run MacOS on it, or a Mac and run Solaris on it, or whatever. But then His Steveness decided that the clones had to go...

It's pretty astounding that major jump from 32-bit to 64-bit processing isn't even mentioned by Intel.

Not really. They are actually embarassed by it. They had to abandon their 64-bit Itanium processor and instead make their processors compatible with AMD's 64-bit processors.

You'll probably find little "64-bit enabled" stickers on the computers and logos like that in the ads, but aside from that they're going to be as quiet about this as they can. When the 64-bit version of XP starts shipping, they'll say something like how their processors have been compatible with it since August 2004, and how all their current processors are compatible, and leave it at that.

Though Xeon-Nocona has been available for more than a month it seems there there are no substantial reports on 64-bit performance of Nocona. Is there anyone here who can report anything about the 64-bit performance of Nocona?

Did someone just say that the DMA implementations are different enough that device drivers will not be compatible? Tell me more about that.

Tell me, is EM64T truly identical to AMD64 or are there small differences? I'm curious.

Intel® Extended Memory 64 Technology is one of a number of innovations being added to Intel's IA-32 Server/Workstation platforms in 2004. It represents a natural addition to Intel's IA-32 architecture, allowing platforms to access larger amounts of memory. Processors with Intel® EM64T will support 64-bit extended operating systems from Microsoft, Red Hat and SuSE. Processors running in legacy* mode remain fully compatible with today's existing 32-bit applications and operating systems.

why would somebody link to a forum reposting the official press release? (well ok I think I know)

New Server Platforms
EUV Lithography

why would somebody link to a forum reposting the official press release? (well ok I think I know)

New Server Platforms
EUV Lithography

The Celeron is a severly crippled chip, unlike the Duron, which is a respectably performing budget processor. It only has 128KB cache, which is CPU sucide on a P4 core...One would be much better of with an Athlon XP, Duron, or a slow P4 as a budget processor.

Tom's Hardware reviewed a Celeron M notebook and, unlike the old P4-based desktop Celeron (128KB L2 cache), it is not at all crippled. Here's a link to the review: Does Everything Have To Be A Centrino? Intel says "No"!

Unfortunately, Celeron M notebooks aren't as cheap as notebooks with cheap desktop chips. The HP Compaq nx9020 (1.3GHz Celeron M) "starts at" $800, but that's with Intel integrated graphics, CD-ROM, and 128MB of shared memory. But for those that want a budget laptop with high performance, low power, and thin-and-light dimensions, a Celeron M is probably well worth the extra money.

For all those people that think "Intel screwed themslelves with the MHz myth", and "they should follow AMD's number scheme", they are already doing this. Read it for yourselves:

http://www.intel.com/products/processor_number/

And...

For all those people that think Intel is just doing this to clear out inventory, that is also not true. How many people do you know go for the top of the line, most expensive processor anyway? How much % of the population outside of the US could even afford anything near the top of line. US sales can't be more than 40% of Intels global sales. They will be able to sell any excess inventory without a problem in Asia/India/MiddleEast.

The most likely reason for this is that yeilds are so low that the cost for the chip would be out of line with current prices. The delay will give the fabs enough time to improve their process steps and get wafer yields inline with the other processors.

Actually, Bluetooth is not explicitly 2.4GHz. It frequency hops a band around 2.4GHz. It only keeps the same frequency for a few ms, before switching to another, which makes it rather noise immune: if a frequency is noisy, it just skips over to the next clear one. It's run by a special interest group (SIG) made up of several leading technology companies. More information on Bluetooth specifications.

I think that something with one of these (Intel PXA27x), 64MB RAM, one of these (Cornice Storage Element, 2.0GB in the highest-end model, 1.5 in a mid-range model, 1.0 in a low-end model), a digital camera, and a WiFi card would sell QUITE nicely, especially with a nice 320x480 color display (maybe OLED will be cheap enough by the time Apple would get around to engineering one) - it wouldn't be a resolution increase, though - the MP2x00 used a 320x480 16 gray display.

Of course, this is not the same as saying they are the widest used graphics card or that they will sell a large amount of standalone cards but still.

Most people don't buy external sound cards any more but once upon a time everyone did. So those cheapo AC97 based things are ALL over the place - OK Intel don't make them all but they did come up with the AC97 codec.

Here's a Register story which mentions that Intel have 31.7% of the graphics card market.

I've talked to people of various importance who feel that in a certain number of years the graphics card market will go a similar way to the sound card market. The impression I was given was that only people wanting high end quality/speed will go for an extra card but most others will be satisfied by onboard.

Could this be an attempt to stay competitive now that Intel's High Definition Audio is coming?

With this advanced audio appearing on most of Intel's new boards, it would seem to me that Creative's market is disappearing.

I believe that Intel has already stated that they want to make some radical changes to the way the BIOS works.

They are ditching the BIOS in favor of EFI.

Does the system have on-board hardware RAID?

Sadly, no. It uses the ICH6R chip which has some Raid functionality on the chip itself, but the ICH6R requires software drivers, and only supports Windows.

So it's not true hardware RAID.