Slashdot Mirror

Except early reviews shouldn't be like this. Reviews should be detailed and get into everything. It doesn't look like the ethernet bug was terribly difficult to reproduce or only occured under a rare and exotic set of conditions.

Charlie Demerjian is right in his latest rant. Too many reviewers are under the spell of PR dweebs.

http://www.theinquirer.net/?article=21648

Physics to your heart's content.

It doesn't matter, since Intel's dual core gaming performance will "blow dead goats". Games being mostly single-threaded and all, and Intel's dual cores running substantially slower than their single-core counterparts.

You'd be far better off buying an Athlon 64 FX with a nForce4 SLI board today. That's still the gaming king-of-the-hill. Torch your money responsibly.

Could help thinking of that article in my fave online hack-mag the Inquirer.

"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."

"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.theinquirer.net/?article=22318

Meanwhile FPGAs have displaced DSPs, FFTs and are overtaking CPUs for embedded applications. There are even rumblesof FPGAs seriously impacting the HPC market. Times are a changin so I'm not surprised to see traditional CPU-based CS research being downsized in response to this paradigm shift. Perhaps we need to take VIVA seriously just as Cray, SGI, Starbridge Systems, SRC, Nallatech and others are doing.

Meanwhile, a man swims across the Atlantic ocean at 80km/day, and a woman rows through the Pacific at 110km/day.

And remember the fly-eating robot which crawls 5m/day. I bet I could do better.

I won't welcome our new UAV masters until one of them completes the International Aerial Robotics Competition.

At least they called him by his name, not just "The iTunes back door guy."

I'm pretty sure his nickname is "dvd jon".
Remember that whole DeCSS thing?
--
Fairfax Underground: Where Fairfax County comes out to play

The Inquirer is reporting that Intel will counter the AMD Turion 64 Mobile Processor with a Pentium M Extreme Edition. It is an alphabet soup of potential Intel Pentium M releases and you'll probably have to read it through twice or thrice to understand it all, but an interesting and inciteful read nonetheless.

There's another interesting article about the future of 64-bit as it relates to Intel here.

And of course, we can't forget our beloved Celeron.

Don't believe all of Steve Job's hype about 2x-10x as fast as a PC. All your mac games are belong to x86.
http://www.theinquirer.net/?article=21988

"There isn't quite the anticipation that there once was."

Well, that's conjecture really. Your two points are based on your own opinion, not necessarily the reality of the marketplace. The video cards for instance...

Read this story about video card sales (Nvidia specifically). Nvidia had it's biggest (fiscal) year ever, even though it lost market leadership to ATI.

So, if the former number one company had its biggest year ever...and the former number two company has an even BIGGER year- then obviously the market is GROWING. This assumes that the video card market is currently a two-horse race, which it is.

Er - that isn't the Register saying that. It's the Register reporting what someone from the Federation of Small Businesses is saying - and he's hardly an independant party.

With anything new that costs money (technological or not) there's an initial resistance to it. This statement is one side of an ongoing discussion, rather than a "fact".

That's not to say that respected journos don't have issues with chip and pin, though:
http://www.theinquirer.net/?article=17247
(lots of links from the article, BTW)

http://www.theinquirer.net/?article=21949

It says that Yahoo may NOT support firefox. Oh well, it would have been really nice!

http://www.jewelrymall.com/

Though in theory the Niagra design is another CMT implementation, its the implementation that is the crux here. CMT theory, has been worked around in academia since 6-8 years I think.

Here is a very informative article on the Niagara design.

For the lazy some main points from the article.
- The Pentium 4 is a single core dual threaded CMT implementation. The Niagara has 8 cores and each core is capable of executing 4 threads.
- Depending on the model of the application that is executing, a programmer can choose to either utilize it as a single process with multiple threads each mapped on to a hardware thread or as multiple processes mapped to hardware threads. Apart from this, individual cores can also be assigned to an individual process, adding one more level of flexibility.
- Sharing data between threads on the same core is an L1 read and is extremely fast. Sharing data among threads on separate cores is an L2 read (since L2 is shared among cores)
- The new chip provides a lot of flexibility in terms of how the programmer wants to allocates hardware threads across software processes or threads. But it looks like programming on it will be difficult unless the operating system provides very good support for it.

To a lesser extent, the JFTC objected to the Intel Inside co-marketing fund, which provides money to manufacturers bearing Intel's logo. One of the 'requests' from Intel was that AMD logos and machines were moved to pages buried deeper within their websites.

with Microsoft, you get the ridiculous situation of OEMs hiding their Linux offerings as well and also having "XXX recommend Microsoft XP Pro" messages on the same pages...

What about the Dragon CPU? You know, the homebrew one which will keep China free from IP shackles in the Santa Clara?

I read a better article about the AGEIA 's PPU. They claim their card will be available by year's end and will be able to compute interactions of 100x more rigid bodies than a current generation CPU. They also claim that they're delaying release until most of the fifteen games being developed based on this card are ready for shipment.

Also, some nay-sayers posting in this thread have claimed that such a card will make all games alike or that it will force reality where reality isn't desired. That's simply not the case. This is just network in, network out. You could use it for anything that requires a dynamic mesh computation. Games will be free to define their networks/meshes as they please, and they're of course free to ignore the "normal" laws of physics altogether.

The main benefit here is that these games will be able to compute movements of individual hairs or blades of grass in a complex scene. What you do with that ability is up to the developer.

p.s. Personally I expect to see people using this card to accelerate stuff like encryption and (de)compression within a few months of its release.

The Inquirer had a big article on this yesterday. But then again they are always good at getting info out early :)

Something like this for example? That will be the worst show EVER, I'm eagerly waiting not to see it!

Does this means more pics like these:
Runtime error
Bluescreen

They are apparently including the opensource hsql database engine. I imagine that's the backend if you need it - otherwise, as this screenshot indicates, you can connect to an existing database server and use that. In that case, this becomes a pretty front end.

google's still not evil

The inquirer reports that SEO Blog and others think they are evil because of their new AutoLink toolbar feature: http://www.theinquirer.net/?article=21470

I don't thinks so. Google seems to have no desire to implement this feature in a firefox plugin, In fact, note that google recommends and links to the open-source Googlebar extension for firefox on the google toolbar download page. http://toolbar.google.com/googlebar.html

Google knows that if people are ready to click on well-placed ads when browsing using IE, then it is their duty as a company to place well these ads. I don't hear google complaining about the adblock extension for firefox that can be used to block all ads, even those tasteful text ads by gooooogle.

No, google is not evil, nor will they become evil. They are making money by gaining the trust of millions of users, and investing that money - and more importantly that trust - to continue to make products that people want.

Real SMP has two CPU's, two instances that can really work at the same time: do calculations at the same time. The scheduling is different.

I'm not an expert, but you can read about it in the following articles:

• Hyperthreading Technology (Intel)
• Operating Systems that Include Optimizations for Hyper-Threading Technology (Intel)
• Windows 2000 and the hyperthreading nightmare (The Inquirer)

It seems that the new version of the Google toolbar is evil, featuring "Autolink", basically the same as M$'s uproar-causing page-modifying "Smart Tags" that thankfully got dropped.

(Although I still see fit to put <meta name="MSSmartTagsPreventParsing" content="true" /> in the head of every site I build, thanks to that nasty scheme, just in case they ever change their minds.)

Anyway, if true, this is a real bitch to website owners. I really hope Google haven't turned to the dark side, but I have noticed that it's taking longer and longer to get new website content properly indexed these days, so in a way, I'm wishing for something to come along and put a bit of competition back into the search engine world, because Google ain't what it used to be.

How long before the Google toolbar is considered spyware? Last I checked, modifying page content was a tactic that well and truly belonged to spyware... and Microsoft.

Yeah, I'm sure MS will try again after what happened last time. . .
http://www.gamerah.com/ver_imagen.php?id=226
http://www.theinquirer.net/?article=20547

Meanwhile, people may try this trick to hack expiry date on ink cartridges, which might have been proven to work.

Do these cartridges have expiry date printed on them?

I'm sure many people know about this, but please read the following before applying the settings mentioned in the parent article. There are other things to consider. The following is an excerpt

The dearly beloved "run the turbines at Military Power 'til they blow up" Scribner on your staff who suggests sticking their foot through the floorboards by tweaking Firefox & setting "network.http.pipelining.maxrequests" to "30" connections (This means it will make 30 requests at once.)
Said Scribner, who is obviously a gamer & overclocker freak, _FORGOT_ to read the comments section at th4e bottom of the posting http://forevergeek.com/open_source/make_firefox_fa ster.php#comments
"#13 Great little tips, but only one problem, and that's that you're breaking servers by doing this. 3-5 requests is fine, but trying to do 30 requests at once puts some strain on the server. If two people try to access the same page at once with this set, that's 60 connections. Most httpd's are set to cut off after there are 100 connections made. So, 4 people with this set could not access the same site. I urge you to think things through before setting something like this and killing the websites you browse."

Whoops, I accidentally posted only half a post. Her's the second half:

B) What about all the non-Windows boxes hooked to the network? And I'm not talking about Macs, I'm talking about all the little doo-hickeys that get hooked to the net like my printer, people's TIVO's, etc.

Well, there's no reason your OLD printer and stuff can't still work on an internal network. They just wouldn't be able to talk to the outside internet.

As for new stuff, there's a big push to start dumping Trust chips into pretty much everything that will be networked. Your 5 year old printer and webcam won't be supported by your ISP, but your New and Improved Network Secure printer and webcam will probably work fine.

If Dell said they were doing it it might be something to take seriously.

YES, I AGREE.

Only a few Dell models are currently Trusted Compliant, but as I said, not a single PC manufacturer will be selling non-compliant systems once Longhorn rolls out. Do you seriously think Dell is going to sell computers that can't fully run the new version of Windows? Computers that can only run the new Windows in crippled mode with a downgraded graphics interface? And you KNOW Windows will occationally pop up "error" messages complaining that it can't do X Y and Z becuase your hardware is incompatible.

-

With Lokitorrents getting taken down today, and left with a rather tasteless warning, I wonder if the MPAA will start looking to litigate the source of illegal content, like MythTV?

Do you (slashdot readers) think it's a possibility?

To tag along this topic, the boys at the Inq reported much the same (I was just beaten to the punch). Linky

http://www.tbreak.com/reviews/article.php?id=335
Athlon FX-55 - 2.6GHz.
I would say thats faster than a G5. AMD and IBM have been sharing alot of processor technology lately, its not suprising that there processors run about the same speed. more info

No duh pre-installing Windows on computers is a huge advantage, but it's not like the vendors don't have a choice.

This article says otherwise.

Some history.

Windows server: Sure, some folks buy it, but plenty don't. So far, Microsoft only has about one third of this space, and Linux is nipping at its heels. They knifed Windows for Itanium, to the disappointment of both Itanium users.

Server appications: IIS has lost market share to Apache in recent years, and Exchange isn't ubiquitous yet either. SQL server enjoys showing the web its limits.

Windows CE/Mobile/Tablet/whatever: Still no monopoly, and since sales of PDAs are shrinking and tablet PC's haven't really caught on, even if MS did take over this market...

Game Consoles: XBox did just have its first profitable quarter. Ever. But it doesn't seem to sell so well overseas, and Nintendo and Sony haven't been persuaded to go away yet.

Media: Media Center PC's aren't selling so well, and in a world with iTuneszilla stomping around, Windows Media suddenly seems less likely to rule the universe than it did a few years ago, even with "PlaysForSure."

Internet Services: Even with its added features, MSN Messenger doesn't seem to be destroying AIM or Yahoo Messenger. MSN doesn't seem to be destroying anybody in general, even if Verizon throws it in free with DSL, and even if MSN is the homepage for Internet Explorer. Now Microsoft wants to go after Google, too.

It's pretty interesting to consider that Windows Client and Office are so frickin' profitable that Microsoft can afford to throw gobs of money at their unprofitable products and divisions (which are pretty much everything but Windows Client and Office) and still have huge heaps of cash left over.

(Oh, and I left off Apple, because if 95% of the world abruptly switched to Apple, Microsoft is second only to Apple itself in Mac software development, and would still be one of the most profitable companies out there, on sales of Office for Mac, VirtualPC, etc. Also, because as long as Apple is out there, and isn't owned by Microsoft, Microsoft can point at it and say "look, there are other choices, we're not that much of a monopoly!" :)

if Intel steps up and builds TCPA support into the CPU itself

From the Inquirer:
Improved architecture for Prescott [CPU] includes better pre-fetcher branch prediction, advanced power management, improvements to hyperthreading technology, the PNI above, La Grande support, better imul latency and additional WC buffers. La Grande is the security feature Intel told us about at the last IDF, and includes protection in the CPU, at the platform level, and with software.

And this story:
Addressing growing security concerns in the PC market, Intel last week also gave a glimpse of La Grande, an on-die technology that will interface with Microsoft's Palladium and other upcoming security software. "We're going to take hardware security up a notch and work with future software developers" to implement the new system, Otellini said. "La Grande is not a Pentium 4 product. It will be a next-generation architecture."

And if you'd like a look at the Trust Chip embedded inside the existing Prescott CPU itself, look to the Micrograph at the bottom of this page. The Trust system eats up about 20% of the CPU die with an entire second CPU and Trust architecture to watch the main CPU.

AMD, Transmeta, and the other CPU makers all have projects to embed the Trust system inside the CPU itself. Oh, and as the recent Slashdot story on the uber-powerful Cell Processor pointed out, it too will have on-chip DRM system. That "DRM system" is doubtless none other than Trusted Computing.

I wouldn't be supprised if motherboard-based Trust chips are pretty much obsolete by the time Microsoft's Longhorn rolls out. (Longhorn a.k.a. Palladium)

-

1. "Trusted computing" would make it pervasive. "Treacherous computing" is a more appropriate name, because the plan is designed to make sure your computer will systematically disobey you. In fact, it is designed to stop your computer from functioning as a general-purpose computer. Every operation may require explicit permission.

Current Powerbook G4s are defficient because of their slow 167MHz FSB and battery life.

Freescale (formerly Motorola SPS) is releasing a new G4 core, the e600, with and integrated DDR momory controller. It will be available as single and DUAL CORES.
http://www.freescale.com/webapp/sps/site/overview. jsp?code=DRPPCDUALCORE

A dual core e600 with IMC would rock for performance and reduce the power sucking system controller in current machines.

Plus with Freescale's "SemiCustom Processor" program Apple could take some of that 6 billion that have in the bank and pay to have a HT link replace the 4 Gigabit controllers on the CPU.
http://www.freescale.com/webapp/sps/site/overview. jsp?nodeId=02VS0l72156067

They've already got the HyperTransport license!
http://www.theinquirer.net/?article=20920

Then they can start using any number of chipsets from ATI / Nvidia.

Dual Core G4 in '05!

Nvidia has a marketshare of 53% of DirectX9-capable cards. If you look at high-end directx9-capable cards Nvidias marketshare raise to 67%. http://www.theinquirer.net/?article=20994

The lines blur...

Take desktop search, for example.

It's been there since last century, as Jon Udell highlights in this screencast.

However, I do demand that I have the right to not face legal repercussions for something I type

Write a livejournal entry threatening the President. We'll see how your little illusions hold up then.

Proven:

1> There are SMP P4 computers:

(From just one of over 143,000 results):
"This time PC manufacturers are upset because Pentium 4 Xeons in a four way symmetric multiprocessing (SMP) configuration are thoroughly thrashed by a chip that Intel wants to consign to the microprocessor gulag."

P4 SMP has performance problems, but that's exactly why kernel support for scheduling partitions is important. Many of the results I posted are complaints about performance, but they all prove that P4 SMP exists.

2: Your doesn't know when you're beat.

The Inquirer is running an article headlined Battery life extender gives 18% boost about a similar product from BATTERYLIFE.

But do the maths using the figures in the article - the increase is less than 3.9%.

"The Pentium V is likely to fly along at between 5GHz to 7GHz, have 2MB plus of level two cache, be built on a 90 nanometer process, and have a stackable design." (Source, and another)

does anyone know what they mean by stackable design?
is this supposed to be taken literally? stacking one CPU on top of the other?
or just some buzzwords that mean nothing that this implies?

It could be worse.

> IMHO they need to standardize RAM like AGP or PCI-X.
> That way users feel more comfortable investing in it...
> you can upgrade and keep your RAM.

You may be interested in FB-DIMMs, if they ever come out. Basically a standard (buffered) interface to all RAM you might want to put on there. Just make a new buffer chip and you're set.

What are you holed up? Or do you just get your information from Slashdot which only reports on negative Microsoft stories and positive everything else.

But I'll give you some links to show there is more to life then reading 2-3 day old stories where the submitter spins reality to show their ignorance as is the case with this story:

Mac OS X holes

Linux Security Patches

Microsoft Patches

All recent patches/holes and all came out about the same time. So please don't tell me your shit don't stink every operating system has their flaws it's the nature of software development.

Especially now that Sony has decided to be a hardware company once again.

For comparison, the upcoming 2.8 or 3.0 GHz Intel dual core offering will be 130 W as mentioned in the Tom's Hardware news item. It's extremely likely that AMD's 2.2 GHz is even faster than Intel's 3.0 GHz, since a 2.2 GHz Athlon 64 is marked 3500+.

Future:

AMD's new Athlon 64 revision (to be released this month) will bring further power reductions thanks to the new strained silicon technology from IBM. It's conceivable that AMD can push the A64 well past 3.0 GHz with these optimizations, equivalent to 4500+ or more. And this is without breaking any new records in the power consumption arena.

The fact that a 2.2 GHz Athlon 64 can run at 35 watts full load (as shown by the Tom's Hardware chart) promises a good future for AMD.

Intel is dead in the water until they can swallow their pride and really start pushing P-M to the desktop.

My god, someone says this every time. It is not the National Enquirer you bozo, it's The Inquirer -- a legitimate source of tech news.