Slashdot Mirror

First of all, wtf is with that name? All it needs is a few more Xs for Xtreme.

Anyway, thanks for a bunch of pictures of the PSU without actually telling me anything. If you want a real review of PSUs, head over ot X-bit labs. All of their reviews contain actual power data with power draw vs rated voltage graphs and scope readings of rail fluctuations. And one picture of the PSU if you actually care.

First of all, wtf is with that name? All it needs is a few more Xs for Xtreme.

Anyway, thanks for a bunch of pictures of the PSU without actually telling me anything. If you want a real review of PSUs, head over ot X-bit labs. All of their reviews contain actual power data with power draw vs rated voltage graphs and scope readings of rail fluctuations. And one picture of the PSU if you actually care.

Well flash media doesn't have seeking like harddrives.

It'd be silly for it not to be. It would just increase the latencies for graphics reading, and you wouldn't be able to use the full system bandwidth.

Of course it doesn't need the frame in eDRAM to work on it, but the fact that you basically can't store the frame in eDRAM should tell you that it's quite small. It's not a texture cache. At least, not for next-generation textures.

The Xbox was not a good design. It was a poor design that competed solely by brute force. The unified memory architecture was panned greatly when it was announced.

Besides, it's important to remember that the Xbox 360 is a scale up from the Xbox. Latencies that wouldn't hurt the Xbox much will hurt the Xbox 360 much more.

Yah, basically. Guess I'm just demanding.

The X-Bit link from this post has a good picture of the card. It looks like a monster of a 2-slot card. And its got 2 huge fans on it, to boot. Passive indeed. If they got it running with no fans then they'd have something to talk about.

Boiling point over 2000C, so it must really be metallic, not a solution as I was thinking. Hopefully someone will crack one open and find out what it really is soon.

Geeze, why does /. keep on linking to physorg, which has crappy articles and no links to real information about stuff.

Here's a more in depth article on X-bit [xbitlabs.com]. NanoCoolers has a pretty in depth description [nanocoolers.com] of the product. It's basically a watercooling loop but using a molten metal. The really cool part is that because the metal is obviously electrically conductive, they're using a DC current combined with some magnets to take advantage of Lorentz force [gsu.edu] to propel the fluid.

Here's a little bit more info, no word on T1000's involvement.

However, I wouldn't be surprised to hear that owners of this new "metal liquid cooling" at a LAN party ending quite horribly.
I can see it start with a few leaks, the liquid metal all joins together... T1000 lives again...

Geeze, why does /. keep on linking to physorg, which has crappy articles and no links to real information about stuff.

Here's a more in depth article on X-bit [xbitlabs.com]. NanoCoolers has a pretty in depth description [nanocoolers.com] of the product. It's basically a watercooling loop but using a molten metal. The really cool part is that because the metal is obviously electrically conductive, they're using a DC current combined with some magnets to take advantage of Lorentz force [gsu.edu] to propel the fluid.

Here's a little bit more info, no word on T1000's involvement.

However, I wouldn't be surprised to hear that owners of this new "metal liquid cooling" at a LAN party ending quite horribly.
I can see it start with a few leaks, the liquid metal all joins together... T1000 lives again...

Geeze, why does /. keep on linking to physorg, which has crappy articles and no links to real information about stuff.

Here's a more in depth article on X-bit. NanoCoolers has a pretty in depth description of the product. It's basically a watercooling loop but using a molten metal. The really cool part is that because the metal is obviously electrically conductive, they're using a DC current combined with some magnets to take advantage of Lorentz force to propel the fluid.

Here's a little bit more info, no word on T1000's involvement.

However, I wouldn't be surprised to hear that owners of this new "metal liquid cooling" at a LAN party ending quite horribly.
I can see it start with a few leaks, the liquid metal all joins together... T1000 lives again...

Well, I'm not a lawyer, but those sound like pretty specifically defined activities, why not just pass laws against them?

You could try, but the companies would argue that they were genuine patents, until proven otherwise in a court of law. Since the possible profits if they win can go into billions of dollars, there is a good incentive for doing so.

A good example is the Rambus vs. Infineon, Hynix and Micron patent dispute which dragged on for five years, and was eventually settled at least with one company.

AMDZone.com Tech Report Sudhian Hexus Hot Hardware Anandtech xbit xbit PCWorld Trusted Reviews

Found it: http://www.xbitlabs.com/articles/video/display/ati -powercons.html. Unfortunately they only looked at ATI chips. Looks like they haven't published part 2 yet.

Xbitlabs found that Venice uses slightly more power than Winchester (the older 0.09u core) around a month ago. They tested cores at the same speed unlike Lostcircuits, and while LC is a good site, xbit is generally better. Not to mention the guy at LC blew up a few MBs before "finding out" how to do his measurements. Aslo Xbit is the only site I know that has an accurate video card power consumption database. http://www.xbitlabs.com/articles/cpu/print/athlon6 4-venice.html

I'm sure this has some use at the low end but the PCs that most of us use are requiring more power not less. This article said an AGP slot is limited to 41.8 Watts. http://www.xbitlabs.com/articles/video/display/ati -powercons.html Even my older ATI 9800 pro needs additional power connector since it needs 45+ watts. Maybe they could make higher gauge netwrok cables? Maybe bring back Coax?

I wouldn't say "rebranded" (because they are not exactly the same), but "Intel" motherboards are/were definately manufactured by Asus, Foxconn, Wistron and other Taiwanese companies. For example, see:

http://www.xbitlabs.com/news/mainboards/display/20 040702071453.html

And btw, AMD *does* make their own chipsets, for use on server (Opteron and Athlon MP) boards:

AMD-8000(TM) Series Chipset
AMD-760(TM) MPX Chipset

I think more people will want a single-G4 iBook that uses the single-core version of Freescale's next-generation, fast bus (up to 667MHz) G4 chip. Yes, a pin-for-pin compatible single-core version has also been announced. If these products ever get released, I think they will make nice low-power alternatives to the Pentium-M/Celeron-M platform.

Here's a nice, short article on about Freescale's next generation G4s: Freescale Discloses Dual-Core PowerPC's Details

From the article:

The MPC8641D device is designed to offer all this performance within a power range that is expected to be 15-25 Watts (typical), according to the company's estimations.

...To minimize chip-level bottlenecks, the MPC8641D processor offers low-latency access to its dual e600 cores through a high-bandwidth integrated MPX bus that is designed to scale to 667MHz.

...In addition to unveiling the MPC8641D processor, Freescale is disclosing development of two additional processors based on the e600 PowerPC core: the highly integrated MPC8641 processor, a pin-for-pin compatible single core implementation of the dual core device...

Thank humanity for big blue!

Here is a better overview of the changes and feature additions

Forgot to mention a great on the new core and its new features and benchmarks from Xbit Labs

I read this article, LCD Guide, that goes into great detail on the different types of LCD monitor (apparently there are three different types of underlying LCD technology). The article makes the point that each type of LCD technology has differing strengths and weaknesses (eg. response time vs. color fidelity vs. viewing angle, etc) and that there is no best technology.

However, I've never really seen this information anywhere else in other LCD reviews. So I'm not clear if the points that the X-bit labs article makes are really important or whether the writer is just a specialist making a mountain out of a molehill.

Anyone know?

"Arrgh... practically every point in the above post is misleading or wrong, and it get's modded to +5"

Ok, the two dies on one chip was true, or believed to be true when they first demoed:

Source: http://www.xbitlabs.com/news/cpu/display/200409151 34740.html

I'll concede that point to you - that Intel is now putting 2 cores on a die... however they were never engineered to work that way initially. They only have an 800 MHZ FSB, not 1066 like the newer P4's, so they have even less bandwidth to share. Want a source?? Here:

Source: http://www.anandtech.com/printarticle.aspx?i=2252

As far as my other points go, let's go over them, shall we???

"the new dual core P4s won't be compatible with a majority of Intel boards on the market"

Source: http://www.theinquirer.net/?article=21793

"The two cores use hyper transport to communicate with various system devices"

Source: http://www.amd.com/us-en/0,,3715_11787,00.html

It actually uses a cross-bar to handle the switching as well.

"Now for the best part - anybody with an existing Socket 939 AMD based motherboard will be able to use one. Worst case, you'll have to download a bios update to enable it, but it will work."

Source: http://hardware.gamespot.com/Story-ST-x-1583-x-x-x

"AMD designed the K8 core to be dual ready out of the box, so this whole thing about them having an extra year isn't exactly true - they've had much longer than that."

Source: http://www.theinquirer.net/?article=13344

Still think almost my whole post was wrong? About what you said:

"Re: sharing I/O bandwidth. Intel has to do this because they don't have a built-in MCH. It has *nothing* to do with "selling chips with 2 normal P4 dies on them"."

It has EVERYTHING to do with having 2 P4 cores in a single package - look at that anand article I posted above, here is a quote from it:

"The major issue with Intel's approach to dual core designs is that the dual cores must contest with one another for bandwidth across Intel's 64-bit NetBurst FSB. To make matters worse, the x-series line of dual core CPUs are currently only slated for use with an 800MHz FSB, instead of Intel's soon to be announced 1066MHz FSB. The reduction in bandwidth will hurt performance scalability and we continue to wonder why Intel is reluctant to transition more of their CPUs to the 1066MHz FSB, especially the dual core chips that definitely need it.

With only a 64-bit FSB running at 800MHz, a single x40 processor will only have 6.4GB/s of bandwidth to the rest of the system. Now that 6.4GB/s is fine for a single CPU, but an x40 with two cores the bandwidth requirements go up significantly."

http://www.xbitlabs.com/news/storage/display/20031 014160044.html http://www.seagate.com/cda/newsinfo/newsroom/relea ses/article/0%2C1121%2C1555%2C00.html

I don't know - is this a useful technique or just another trick? When the salesman tells you that laptop runs 6 hrs. on system battery, but only if you don't touch it - how useful is this for you?
Reminds me of other fallacies: the gigahertz myth, the LCD display reaction-time. myth

IMHO, the area in which AMD has really distinguished itself is in the power consumption of its desktop processors. Generally speaking, non-Intel x86 CPUs (from AMD and Cyrix) historically had a reputation for running extremely hot. The situation has been reversed in recent years, with Intel pushing the upper limits of power consumption with its Pentium 4 (especially with Prescott) while AMD was doing the exact opposite with its Athlon 64. This has resulted in a huge difference in power consumption between the two competitors. Consider the following CPUs which are basically direct competitors (roughly the same price):

Power consumption at idle
Athlon 64 3500+ (Winchester): 13.4W
Pentium IV 640 (Prescott 2M): 35.4W

Power consumption at full utilisation
Athlon 64 3500+ (Winchester): 47.5W
Pentium IV 640 (Prescott 2M): 129.4W

Source: 90nm Processors from AMD and Intel Pentium 4 6XX.

The often trivial differences in performance look rather insignificant in comparison. Also consider that these results come after Intel's best attempts at reducing the P4's power consumption (enhanced idle states in P4 5XX and SpeedStep in the 6XX) and you can see how inefficient the architecture is in this regard.

This of course applies to desktop CPUs. Intel redeems itself somewhat with its Pentium M in the notebook market.

IMHO, the area in which AMD has really distinguished itself is in the power consumption of its desktop processors. Generally speaking, non-Intel x86 CPUs (from AMD and Cyrix) historically had a reputation for running extremely hot. The situation has been reversed in recent years, with Intel pushing the upper limits of power consumption with its Pentium 4 (especially with Prescott) while AMD was doing the exact opposite with its Athlon 64. This has resulted in a huge difference in power consumption between the two competitors. Consider the following CPUs which are basically direct competitors (roughly the same price):

Power consumption at idle
Athlon 64 3500+ (Winchester): 13.4W
Pentium IV 640 (Prescott 2M): 35.4W

Power consumption at full utilisation
Athlon 64 3500+ (Winchester): 47.5W
Pentium IV 640 (Prescott 2M): 129.4W

Source: 90nm Processors from AMD and Intel Pentium 4 6XX.

The often trivial differences in performance look rather insignificant in comparison. Also consider that these results come after Intel's best attempts at reducing the P4's power consumption (enhanced idle states in P4 5XX and SpeedStep in the 6XX) and you can see how inefficient the architecture is in this regard.

This of course applies to desktop CPUs. Intel redeems itself somewhat with its Pentium M in the notebook market.

Over at X-bit labs, they have a more comprehensive review of these chips' Thermal characteristics and power consumption. You will still need a big PSU and a good HSF if you are going to multitask or play games on these puppies.

We are really very happy with this server solution, because it does show very high stability, reliability and performance. I believe that you can notice it yourselves by the short time it takes to load X-bit's pages today... We have had good experience with this server and see it working reliably and fast...

Eight Caviars in one year? Are you joking or do you work for Seagate?

WD got elected the best HDD maker of 2004 on http://wwww.xbitlabs.com/.

You know, i think the same. I had high hopes for the S3 DeltaChrome GPU line, which is DX9+ capable and has some very interesting features, like being able to process video in realtime using GPU horsepower and HDTV support. All of this at a very friendly price and using relatively simple cooling solutions, as S3 focuses on bundled / onboard solutions.

Yet, the reviews for it basically conclude it's a promising technology with poor drivers, which on GPU-land can make or kill a product. I still have hopes for them to release OSS drivers for it; over time, i think it could gain a good deal of acceptance among Linux/BSD users. Matrox did it, and sold a lot of cards to OSS users, but the 3D performance of their hardware was a bit lacking.

For some reason, i always liked S3 (even while bitching about those damn ViRGEs). Please, if someone at S3 is reading, we love you. Do it, and we'll root for the underdog!

This another attempt of hijacking PC memory business is going to fail. GDDR4 is supposed to come out this year, after all. Rambust may have gain a few round in Playstation 2/3, and busted a few DRAM manufacturers along the way, but the fact that RDRAM has never caught on shows XDR is NEVER going to be a mainstream.

>Why are you so sure that Nvidia are using their own hardware tech?

Because they say so, where have been for last few months? :). For example here is an interview of David Roman from NVidia:

"Anna (X-bit labs): From the technology stand point what will the new GPU developed for Playstation 3 resemble if we compare it to the desktop chips by NVIDIA?

David Roman: This is the next generation GPU, so after the GeForce 6 series this is going to be the next generation. So, this will be everything we have in GeForce 6 + whatever else we bring out. Obviously it will support DirectX 9, shader models 3, it will be the most feature-rich, the most powerful GPU that weve ever created actually, when it comes out."

Yes, NVidia will be designing the hardware for the PS3.

Try this article for a good overview of the different types of LCD panels (TN, MVA, PVA & IPS):

X-bit's Guide: Contemporary LCD Monitor Parameters and Characteristics

It weighs in at 27 pages, but if you really want to know what you're talking about when discussing LCDs, it's required reading.

Although most /. readers probably won't care, dual core CPU's are already on the market in the form of the UltraSPARC IV CPU from Sun Microsystems. Sun also happen to be sporting the most ambitious multi-core project going in the form of Niagara, which although initially an 8-core system has apparently been seen running Solaris 9 with 32 independent CPU cores.

In addition to this, the POWER 5 CPU is also available with multiple cores, fully supporting Linux.

Also of note is that the Opteron dual-core CPU's from AMD are apparently going to be pin-compatible with the current Opteron processors (by current,I mean, the latest socket 939 (I think) systems, not the original Opteron 2xx or whatever).

This is really of most use for the data center right now, but as more applications wrap their heads around paralelizing themselves, multi-core CPU's on the desktop will become more popular.

That said, developers really have no excuses for not having blazing fast "dual-core aware" apps... a multi-processor system purchased today provides about as much performance as a dual core system... so it's not like a wild new technology where application developers have to wait for SDK's or test hardware. Multiple cores, HyperThreading CPU's or multiple physical processors are all just additional CPU's from the operating systems perspective, and are developed for using the same tried and true thread libraries (pthreads, etc).

Multi-thread those apps people! There are so many instances, especially when writing GUI apps, where an extra thread or two thrown in the right direction can really improve the user experience.

Of course, a big problem is just how developers learn to program. Everyone learns their "Hello World!", then goes from there... but this is all very linear in approach. Finding good programmers who can think of an application in terms of what many parallel threads should (or shouldn't) be doing isn't easy... but I digress.

InfoWorld had a nice story about the Power5 multi-core CPU (You'll have to download the report) coming out this year. It may outperform the coming dual core AMD chip, both in raw performance and in lower power consumption.

AMD has a write up on their upcoming dual core processor and what it means to performance. Somewhere I believe there are some published numbers for how an AMD dual core CPU running 5 steps below it's single core counterpart can still outperform dual single core processors. (i.e., a 1.4 GHz dual core CPU will outperform a 2.4GHz dual processor machine)

Meanwhile, Intel's dual core demo was doubted doubted when presented at the same time as the above referenced AMD demo. Also, Intel's dual core will not perform significantly better than a dual processor system, or so the analysis of the two processors stated. (I really need to bookmark these things when I read them! Hopefully someone else will provide that reference.)

The ATI requires nearly the same. The reason for the second molex connector is stability. Under most conditions you can get away without it, however the AGP power is not always completely clean and if the molex is putting out a smaller amount, there can still be issues.

X-bit Labs did tests to show this. These tests show there is not a difference that is significant in power consumption throughout, although the new XT cards are improving with their heat loss and power consumption.

It's marginal when compared to the latest AMD offerings, whose power consumption varies between 35W and 70W. The 90nm versions even tops at 50W! And this is the desktop versions, the mobile versions use even less power and have the option to throttle back the clock automatically when idle, just like the P-M.

The P4 was always a power hungry processor. Again, for a modern desktop, there're comparable alternatives to the P-M for much less money.

It is being used to program games for the XBOX next, via dual G5 machines from Apple. I doubt the games are programmed on MacosX,plus, more than one source seems to agree...

The XGI Volare has two GPUs on one card already. It's been out for some time. It's performance is nothing special. Try this http://www.xbitlabs.com/articles/video/display/xgi -volari.html for a review.

Another Poll

-Dan

We're about to enter a really exciting time in computing. And you know what the Chinese said about that.

Besides SGI and HP, is there anyone really standing behind Itanium?

HP is already making some moves away from Itanium.

Others have speculated that this is the "thin end of the wedge".

Maybe Intel will start selling their own brand of servers.

"Advanced Micro Devices, one of the world's leading makers of central heating units, has patented a technology...."

My understanding is that the nForce-4 chipset/BIOS supports two PCI-E configurations: 8-8-1-1-1 or 16-1-1-1-1.

It's up to the motherboard maker to choose one. If you buy something that's labeled "nForce-4 SLI," that means you're getting the 8-8-1-1-1 layout. Also, I think some motherboards (maybe only the dual CPU ones) actually support some sort of switch that allows you to select either 16-1-1-1-1 or 8-8-1-1-1.

Here's an example of a board that's definitely 8-8-1-1-1 (although I don't see the x1 slots).

http://www.hothardware.com/viewarticle.cfm?article id=592&cid=1
http://techreport.com/reviews/2004q4/athlon64-fx55 /index.x?pg=1
http://www.bit-tech.net/review/364/
http://www.short-media.com/review.php?r=266
http://www.pcstats.com/articleview.cfm?articleID=1 666
http://www.tbreak.com/reviews/article.php?id=331
http://www.amdreview.com/reviews.php?rev=fx-55-400 0
http://www.techwarelabs.com/reviews/processors/amd 4000_fx55/
http://www.hardocp.com/article.html?art=Njc1
http://www.xbitlabs.com/articles/cpu/display/athlo n64-fx55.html
http://www.sudhian.com/showdocs.cfm?aid=614

How on earth anyone ever came to these conclusions (you're hardly the first person to say that), I'll never know.

Western Digital quotes nearly power consumption for their drives, when reading or idle, although that figure drops to about 1/20 if the drive is in sleep mode:

http://www.westerndigital.com/en/products/Products .asp?DriveID=59

AMD quotes a power consumption about 50% below peak, when idle, although again that drops to 1/20 when halted:

http://www.amd.com/us-en/assets/content_type/white _papers_and_tech_docs/30430.pdf

However, your GPU is likely to be the biggest problem, as I'm unaware of them having a sleep mode (although maybe they do, anyone know?), leaving their consumption at half peak:

http://www.xbitlabs.com/articles/video/display/ati -vs-nv-power_9.html

What this all means is that it's worth turning your computer off for any period of time longer than your start-up time, instead of letting it idle. If you put it to sleep, that figure becomes twenty times the startup time. For me, that's less than 20 minutes, not the 8+ hours I sleep for.

You?

As was already posted, AMD has Cool'n'Quiet on the desktop which runs chips at 1GHz using reduced voltage @ 22W.

Intel is planning something similar for the Prescott before eventually getting the P-M to the desktop now that Tejas has been canned.

http://www.xbitlabs.com/news/cpu/display/200406021 10858.html
"The new capabilities Intel plans to include are the so-called AAC technology that adjusts performance depending on load in order to maintain low heat dissipation and quiet operation of personal computers"

I looked at the specs; 15 watts of cooling power at 77 Kelvin. To me that means it can cool a 15 watt heat load to 77 Kelvin. A 3.2 GHz P4 has a maximum heat dissipation of 100W; a 3.6 GHz 115 W; and upcoming Prescott II P4s working at 4.0+GHz will dissipate about 150W of heat.So I'd think that had to be dissipating 200W of heat in the article (at 6 GHz), most likely more.

So yes, you're right. But Do you need to hold it at 77K in order to achieve an overclock to 6 GHz? Would 100K work? 200K? 200K is still -73 deg C/-99.67 deg F, which is mighty damn cold. I don't know how linear the whole heat dissipation thing is. That is, if it'll do 15W of cooling at 77K, would it do 30W at 154K (-119 C/-182.47 F)? 45W at 231K (-42.15 C/-43.87 F)? etc. So it may be possible to do it with four or five instead of 10+, depending on where the sweet spot is for temperature vs processor stability.

I'm curious about the logistics of calculating pi. Would a 4-way 5.6 GHz (he couldn't get 6 GHz to boot; read the article) system be able to calculate pi with any greater precision than has already been done? I don't know quite how they approach the problem of "computing" pi.