Pentium 4 6XX Sequence and New EE P4s Launched

Mojo-Dog writes "Today Intel took the wraps off their new Pentium 4 Processors with EM64T extensions for 64-bit computing. The Pentium 4 6XX Sequence and Pentium 4 3.73GHz are based on Prescott 2M cores with a full 2MB of on-chip L2 cache as well. HotHardware.com has a full review with benchmarks posted of these new P4s, many of which also offer Intel's SpeedStep technology for power savings and improved thermals, which has been available in Pentium Mobile CPUs for some time now."

Comments

'lagging a bit'

[Eatmorecake]

"It's no secret that Intel has occassionally been playing a bit of catchup this year in the desktop and workstation processor arena"

No kidding. Nintendo had a 64 bit processor back in like, '96.

Re:'lagging a bit'

[Anonymous Coward]

YOU ARE DENSE

Re:'lagging a bit'

[lord_rob the only on]

> No kidding. Nintendo had a 64 bit processor back in like, '96. Do you mean the Nintendo 64 ? So the PS2 had a 128 bits processor. NO all those consoles had only a 32 bits processor, but a 128 bits bus, because in consoles, there are many processors dedicated to a special task. So the bus could transport datas to the various processors ...

Re:'lagging a bit'

[bestadvocate]

Some feel that the N64 actually wasn't really 64 bits though http://www.emulator-zone.com/doc.php/n64/ for instance and they were not even the first to make the claim as Atari had claimed that for the Jaguar http://en.wikipedia.org/wiki/Atari_Jaguar

Re:'lagging a bit'

[Grounded0]

MIPS R4000 and Alpha 21064 were 64 bit processors back in 1992.

Re:'lagging a bit'

[Anonymous Coward]

You are so dumb. Please do us a favor by hanging yourself from the nearest rafter.

Yes, the N64 was a 64-bit processor. Does that make your penis feel small now?

Re:'lagging a bit'

[jizmonkey]

You don't know what you are talking about. The Jaguar used funny math to get the "64-bit" number. Everybody knows that a 64-bit blitter does not a 64-bit system make, and so the only people to bring it up (like you) do so to build strawmen. The CPU of the Jaguar was a Motorola 68000.

The page you link to, by making this analogy, shows that its author doesn't know jack about shit, either.

The Nintendo 64 had an R4300i CPU. It was fully 64-bit. It addressed 64 bits (40 physical), the same as high-end SGI workstations. It had 64-bit integer registers and 64-bit floating point registers. The system had a 500MB/sec bus to the Rambus memory. There is only one "32-bit" part about the R4300i, and that was the system interface. But the memory connected to the RCP, not the CPU (and the RCP, obviously, had heavy bandwidth requirements of its own to do the graphics rendering and sound), and so it would have been wasteful to run the same wide bus between the CPU and RCP.

The RCP was another 64-bit processor, also a customized MIPS chip.

It is true that the R4300i had a 32-bit compatibility mode which was often used in games, but that is irrelevant. Most people run 32-bit software on their Athlon 64, too.

Re:'lagging a bit'

[CelticLo]

Ian Mapleson of the SGI Depot has a subsite on this... http://www.future tech.blinken lights.nl/n64.html Although a lot of her external links are now dead, he does keep the info upto date.

Re:'lagging a bit'

[The Tyrant]

The bitness of the Jaguar has been contended for a long time, and as with many of the attacks directed against it, the words get repeated endlessly almost by rote, without thought or research. I will thusly correct your mistakes.

The Jaguar consists of 5 main units: 3 processors, a blitter, and the object processor (an advanced sprite engine in effect). They all share a common 64 bit wide data bus. The "CPU" is a 68k yes, which has 32 bit instructions and registers and a 16 bit bus, but it is the CPU in name only, as its so slow most games use the risc chips exclusively. They are the GPU and DSP, each of which is primarily a 32 bit chip with 32 bit registers and instructions, but can perform 64 bit load/store operations.

The blitter and object processor are both entirely 64 bit engines, but they are not turing complete processors.

Because the main bus is 64 bit wide, and because some of the processing units are 64 bits wide, it is generally considered that the system as a whole is 64 bit, in so much as the bit-ness of systems matters. It was mostly a marketing thing back "in the day" as to how many bits a system has, much in the way that the number of polygons a system can push around now is touted as a comparison between systems that really means very little.

If you really want to bash the Jaguar, for whatever personal reasons you may have, please, do so about some of its real failings, like the way the two risc processors are limited to running from their internal cache because they will crash on a jump or branch instruction into or out of main memory, or some of the bizare behaviours of the A1 clipping flag of the blitter, and stop dragging up the old flawed arguments.

We're going widely off topic here but as a jaguar homebrew coder I feel the need to set the facts right.

Re:'lagging a bit'

[drinkypoo]

The Jaguar DOES have some 64 bit instructions and 64 bit data types. It handles some 64 bit data natively. It's not 64 bit all the time, though.

It's not surprising that the R4300i has a 32 bit mode, as you say; Other MIPS processors like the R4400 and R5000 share this particular feature so they can run legacy MIPS code.

Re:'lagging a bit'

[Anonymous Coward]

+4, Funny?! Only on slashdot.

Re:'lagging a bit'

[javiercero]

Actually the R4000 had problems with its early revs that could not execute the whole 64bit instruction set. So the R4000s were not used in 64bit mode much.

It came earlier than the alpha though, so for all intents and purposes the R4000 was the first commercial 64bit RISC micro.

Re:'lagging a bit'

[Anonymous Coward]

For the record.

RCP has a 128-bit SIMD unit.
N64's CPU is almost never used in 64-bit mode because 32-bit instructions are smaller and move around faster and generally good enough.

And real games never ever get 500 MB/sec out of those stupid Rambus chips.

Re:'lagging a bit'

[Anonymous Coward]

Nintendo never had a 64 bit processor. The N64 was acctually two 32 bit processors.

But yes Intel is lagging just a little

Re:'lagging a bit'

[evilviper]

The CPU of the Jaguar was a Motorola 68000.

Which is completely irrelivant, because it's primarily only used for controller input, and is NOT what the games run on.

From Wikipedia:

consensus exists with those who are familiar with the system hardware that because Jaguars main data bus, and some of the processors, are 64 bit, the entire system can consider itself 64 bit.

At least

[reassor]

"older" P4 will have a price drop,which will be good for People saving 50$ on a new System.

Re:At least

[Breakfast Pants]

Let me ask... does this pentium support DMA in 64 bit mode.. I've heard the xenon's don't.

Re:At least

[Anonymous Coward]

I've heard the xenon's don't.

I've heard that xenon's are best for illuminating scenes to be focused onto film or a CCD via a lens, illuminating a screen through developed film (thus projecting an image) or even illuminating the road ahead of your vehicle.

The gas becomes much more conductive if excited by very high voltages (around 6kV) and will emit a very high amount of light if a large current is allowed to pass through it while it is in this highly excited and conductive state. It will even emit some x-ray radiation under these circumstances.

It is an inert gas.

What does DMA stand for, with respect to xenon?

; )

Re:At least

[Breakfast Pants]

Ah, with respect to xenon.. Well to ask that question you must first ask this one: what does xenon have to do with Intel releasing 64 bit p4's? Well you see intel has a chipline, Xeon, that is one letter away from xenon the element. Using a bit of deductive reasoning you might infer that a mistake was made and the post actually referenced Xeon. So, with respect to xenon with respect to intel launching a 64 bit p4, DMA stands for Doctor of Musical Arts, but there is a decent argument to be made that it might actually be a reference to Direct Memory Access. Anyway, check here and look at comment #3.

Re:At least

[VAXGeek]

Maybe you should just buy an Athalon.

Re:At least

[EchoesEchoes]

lolz!! he teh bad spellaar and j00 madeth teh funnay!! lololZZZ!!!!!!!!!!!!!111one

Re:At least

[reassor]

Sorry,i am stuck with Intel.Maybe the Point,that all my Systems get used days and weeks without reboot.On Friday a friend brought his PC to my house.It served Music for our inhouse-Party since them.

Um

[Anonymous Coward]

And how much did intel pay for this story on slashdot . It reads like a marketing blurb

Re:Um

[Anonymous Coward]

And how much did intel pay for this story on slashdot . It reads like a marketing blurb

I think you misunderstand the way stories work on Slashdot. The first one is free. Intel has to pay for the duplicate story six hours from now.

Re:Um

[Anonymous Coward]

I think you misunderstand the way stories work on Slashdot. The first one is free. Intel has to pay for the duplicate story six hours from now.

You forgot the bit about Roland collecting the revenue.

2MB Cache?

[daskalou]

Today's technology never ceases to amaze me...

Re:2MB Cache?

[Grounded0]

MIPS R12000 system that's sitting on my desk has 8MB of L2 cache. And yes, it's circa 2000.

Re:2MB Cache?

[Anonymous Coward]

It's how much you can fit in the cache that matters, not the sheer size of it. Your 64 bit CPU will need larger cache to have same amount of information. (Assuming associativity and other specs are the same).

Re:2MB Cache?

[CelticLo]

well my R10000 with its 2mb L2 cache I reckon is sitting in the same circa 2000 machine as his R12000 with its 8MB of L2 cache. I for one welcome our 8Mb L2 cache overlords.

Re:2MB Cache?

[photon317]

RISC processors always have more cache than CISC processors, it's part of the design tradeoff. RISC takes less silicon to implement the core than CISC, which leaves more room to dedicate to the cache. Also the same complex operation requires more instructions on a RISC than a CISC, thus you need more L2 to keep the same amount of functional code in cache.

Re:2MB Cache?

[Anonymous Coward]

One of the biggest factors is that RISCs usually have fixed-length opcodes, where as CISCs tend to have variable-length opcodes. That means groups of simple instructions on CISCs take up much less memory/cache than on RISCs (which, in such cases, waste most of the opcode space). On the other hand, fixed-length opcodes make decoding much easier, so it's all down to memory/cache speed/size.

Re:2MB Cache?

[Salamander]

MIPS R12000 system that's sitting on my desk has 8MB of L2 cache.

...and you need it, because the cache/memory speed disparity is much greater on that system. Don't repeat Intel's "bigger numbers are better" mistake; 2MB plus faster memory is a better design tradeoff today than 8MB plus slower memory.

Re:2MB Cache?

[akuma(x86)]

Where do I begin?

The 8MB of cache on the R12000 is OFF-DIE. It is connected to the CPU using a bus that is in fact SLOWER than the bus to DRAM on modern PCs (MIPS L2 cache BW is ~2GB/sec). So great, you have an 8MB cache but it's 2x slower than the 512MB of DDR DRAM that you can find in a PC! I could say that my PC has 512MB of cache...

Secondly, the 2MB of cache on the P4 is ON-DIE. Let's do some math...that's one 128-bit load per clock at 3.73GHz which is a shitload of bandwidth (59.68 Gbytes/sec). This is of course, no accident - you better design a memory system capable of feeding a 3.73GHz execution core otherwise it will starve.

Re:2MB Cache?

[bani]

too bad the r12k performs like shit.

Windows XP 64-bit

[AnimeEd]

and just in time for Windows XP 64-bit!
how lucky!

Re:Windows XP 64-bit

[Anonymous Coward]

Actually, 64 bit windows won't be ready but Microsoft will release it anyway.

Re:Windows XP 64-bit

[CastrTroy]

But that version will cost you twice as much. Since 64 bits is like 2 32 bit processors, you'll have to get a 2 processor license.

Re:Windows XP 64-bit

[MPHellwig]

luckily enough xp is in a 2 processor license

Re:Windows XP 64-bit

[Anonymous Coward]

I've used the beta/RC versions of 64-bit Windows XP on my Athlon 64, and the OS itself seemed 'ready' ages ago (at least as 'ready' as the released 64-bit Linux/BSD OSes I've tried). The only problem is the lack of 64-bit drivers for some of my hardware (Linux and BSD are even worse there, of course). Hopefully that will be rectified before XP 64-bit officially ships. I'd still like a good Linux/BSD OS too, but it looks like it will be a long, long time before the driver support gets there.

Re:Windows XP 64-bit

[bob beta]

No. It's like 2^32 32 bit processors, so you'll have to buy 4,294,987,000 licenses.

Re:Windows XP 64-bit

[Anonymous Coward]

are you retarded?

I've never had driver problems with Linux built in 64 bit mode. I have a production server running with it and still going.

amd64 root # uptime
22:08:59 up 170 days, 10:13, 1 user, load average: 0.00, 0.00, 0.00

amd64 root # uname -m
x86_64

Re:Windows XP 64-bit

[drinkypoo]

Yep, the question is, why are intel and microsoft still in bed? Microsoft is in complete control of the Microsoft-intel relationship, or at least it should be. If intel vanished tomorrow, the PC world would continue with AMD processors and it would hardly notice, except that prices would begin rising until VIA figured out how to make fast CPUs. (Maybe they'd do dual-processor quad-core machines; the power consumption would probably still be less than a P4.) If Microsoft vanished tomorrow, intel would apparently lose its best friend. 64 Bit XP has been working right for some time now...

Re:Windows XP 64-bit

[Anonymous Coward]

are you retarded?

Oh dear, I certainly hope not.

I've never had driver problems with Linux built in 64 bit mode. I have a production server running with it and still going. amd64 root # uptime 22:08:59 up 170 days, 10:13, 1 user, load average: 0.00, 0.00, 0.00 amd64 root # uname -m x86_64

Servers are irrelevant; Windows XP is an OS for desktops and laptops, not servers. To me, an operating system is ready when it runs on a broad range of hardware systems in the target category, taking full advantage of their features. On the various laptop and desktop systems I've used, Windows XP 64-bit (RC version) has mediocre hardware support, but Linux and BSD are even worse. For small servers, any of Windows (Server 2003, not XP), Linux or BSD is fine, but BSD doesn't scale to larger systems, leaving only Windows and Linux (ideally 2.6, since 2.4 can't keep up with Windows in terms of scalability).

In the laptop market, I wouldn't even consider Linux/x86 to be 'ready'. Its laptop hardware support is very poor compared to Windows XP, especially in terms of power management. Very often, even though it can use the hardware in some fashion, it can't make use of all its capabilities. For most desktop systems Linux is fine.

If running a kernel on the chip were all that mattered, Windows (or, more precisely, the NT kernel) would have been 'ready' since before the AMD64 shipped, since Microsoft had it running on prototypes from AMD, and Microsoft's main kernel developer had been working with AMD on the chip design for years.

Re:Windows XP 64-bit

[Anonymous Coward]

I hope to god you're trying to be funny.

Re:Windows XP 64-bit

[Anonymous Coward]

The sad thing is, a lot of AMD computers have the "designed for windows 95" or etc. stickers on them.
The actual AMD chip has the windows logo engraved on it too. In my Fujitsu Point 510 tablet, the windows logo is actually engraved on the chip. Now, this is an old computer, so I don't know if current AMD chips have a similar enraving/sticker.

Re:Windows XP 64-bit

[Mortlath]

No, they don't. I installed a AMD a couple months ago, and I saw no window stickers or engravings.

Re:Windows XP 64-bit

[Bri3D]

Yep...Read any little XP CDKey label up to the very latest XP with SP2 ones which don't say it. "Windows XP Professionial 1-2CPU." It's been this way since Windows NT 4.0.

Re:Windows XP 64-bit

[drinkypoo]

That's just in (IIRC) the K5 and/or K6s. You're not going to see a made for windows logo on any kind of Athlon chip. Some of 'em have an AMD logo etched into the metal though.

Non-dupe certification

[Anonymous Coward]

I certify that I, anonymous coward, have reviewed this article in comparison to other recent articles and have found it to NOT be a dupe.

This certification provided 'as is', all guarantees and warrantees are disclaimed.

This has been a public service posting.

Re:Non-dupe certification

[Anonymous Coward]

Wait a few hours.

Erm Wait . . .

[OverlordQ]

Shouldn't they of released their space heaters at the *beginning* of Winter?

Re:Erm Wait . . .

[lachlan76]

Before Intel was founded, this time of year was still winter!

Re:Erm Wait . . .

[DrSkwid]

there are *two* hemispheres, you insensitive clod!

Re:Erm Wait . . .

[mattjb0010]

Shouldn't they of released their space heaters at the *beginning* of Winter?

I come from a land down under,
Where Intel's glow, and Winter begins in June.

Re:Erm Wait . . .

[ciroknight]

Hey, it's a joke, but at least Intel took a really good step: Including SpeedStep by default on their DESKTOP processors. This was a move I predicted would happen in 1999-2001, back when the Pentium 3's were running into thermo problems as well, and then the Pentium 4's were just getting out of the gate. Even though it can be argued AMD doesn't need to take this extra step, such a step would be great if not for power savings alone, but also a possible boost in durability of the processor.

My negative statement: Intel should have used SpeedStep2, and had an adjustable multiplier down to 8x or 10x. If they could drop the temp down to around 35dC, and around 1.5GHz, and people won't really notice a huge performance hit. I really love the way the Pentium M and Pentium 4 are working together for Intel.

Re:Erm Wait . . .

[Anonymous Coward]

Shouldn't they of released ...

Do you people who write "of" instead of "have" simply not understand the meaning of what you're writing, or don't you know what you're trying to say in the first place?
Exactly what do you think "shouldn't they of [past tense verb]" means?

I have NEVER seen any of us who are not native English speakers make that totally nonsensical mistake. Is it because we actually have to THINK while typing?

Re:Erm Wait . . .

[Anonymous Coward]

Shouldn't they of released

Wow, what inner-city school are you going to?

Shouldn't they have released

I hope the "funny" mod is because people are laughing at you...

Re:Erm Wait . . .

[Darren Winsper]

AMD have been shipping Cool'n'Quiet-enabled processors for getting on for a year now.

Re:Erm Wait . . .

[bradleyland]

"Hey, it's a joke, but at least Intel took a really good step: Including SpeedStep by default on their DESKTOP processors."

Do they really have much choice? I mean, the 660 runs at 73C under load.

Re:Erm Wait . . .

[reassor]

We had fresh snow since yesterday,so its winter.

Maybe I'll get one...

[Eatmorecake]

Will it help my '1st' comment on slashdot show up '1st'???

I know I'm dense, but I'm competitive, too.

An additional reference

[Anonymous Coward]

The Tech Report also has an excellent writeup 4 -600/index.x?pg=1>

Re:An additional reference

[Anonymous Coward]

Turn on HTML formatting next time, brother.

http://techreport.com/reviews/2005q1/pentium4-600/ index.x?pg=1

Re:An additional reference

[Anonymous Coward]

TR is good as usual. Here is another good one:

http://www.hardcoreware.net/reviews/review-263-1.h tm

Compatibility with AMD64

[chefren]

"EM64T is nearly completely compatible with AMD64 technology"

Wow, nicely said. Is this close enough to make binaries interchangable or are they two separate platforms? Either way I am 100% sure that things are exactly as they are.

Re:Compatibility with AMD64

[Anonymous Coward]

Binaries are interchangeable. The only differences are certain platform features which have always been different between AMD and Intel.

In other word, you could say it's 100% compatible. Or 100% ripoff. :-)

Re:Compatibility with AMD64

[frakir]

... and few instructions separate enough to make icc (intel C compiler) produce code which won't run on AMD64...

Re:Compatibility with AMD64

[cnettel]

Possibly, depending on the settings. On the other hand, I've seen several benchmarks (at least on x86, not looked at AMD64) where icc gave better performance on K7/K8 CPUs than GCC and the Microsoft compiler.

Intel wants you to use their compiler for all your needs and if you can afford it (and possibly take the time for extra annotation and library usage) you get great performance on all implementations.

Re:Compatibility with AMD64

[DarkEdgeX]

Wow, nicely said. Is this close enough to make binaries interchangable or are they two separate platforms? Either way I am 100% sure that things are exactly as they are.

On Windows (I haven't looked into the issues, if any, on *nix), yes. 64-bit executables on Windows utilize the PE32+ format which can be flagged with a machine type. Up until AMD64/EM64T the most common machine type was IMAGE_FILE_MACHINE_IA64 (for Intel's Itanium architecture). But AMD64/EM64T compilers emit images with the machine type set to IMAGE_FILE_MACHINE_AMD64. In other words, they're pretty much one and the same.

That having been said, there's still a few minor differences, but AFAIK most compiled code shouldn't run into them. For example, Intel's 64-bit extensions offer a CMPXCHG16B instruction where AMD's doesn't (though recent updates to AMD's technical docs for AMD64 seem to indicate that they're supporting this extension as well as SSE3 in future AMD64 processors).

And you can expect future extensions ala MMX/SSE/SSE2/SSE3/3DNow! to come down the pipe on just Intel or AMD's processors-- it'll be up to software to detect the processor capabilities when/if these become an issue.

Re:Compatibility with AMD64

[Ectospheno]

I don't know why the parent is marked troll when he is just stating the truth. I didn't know we had so many Intel fans here at Slashdot.

I don't see much of an improvement.

[Celestial Avenger]

Especially in encoding. Is it really worth the extra several hundred to shave 6-10 seconds off of rendering a model or enconding an MP3?

Re:I don't see much of an improvement.

[agent dero]

or enconding an MP3?

Why do you want to know?

Sincereley,
Your Friendly Neighborhood RIAA Agent

Re:I don't see much of an improvement.

[Tim C]

That really depends on how much of it you do, doesn't it?

If you spend a significant amount of time waiting for that sort of thing to complete then it could well be worth it, especially if you're rendering more complex models.

If you're just ripping the occasional CD to mp3/ogg for your media player, then what do you think?

Re:I don't see much of an improvement.

[Celestial Avenger]

"If you spend a significant amount of time waiting for that sort of thing to complete then it could well be worth it, especially if you're rendering more complex models." If I did that, I'd be better off with an Intel Xeon processor or two, not this.

Re:I don't see much of an improvement.

[Anonymous Coward]

or enconding an MP3?

Meh. What I'd be interested is decoding MP3s. So far, MP3 decoding is limited to realtime. Also, when are we going to be able to decode multiple MP3s at once?

still

[Foo2rama]

Runs hot, still going to be a cooling nightmare... And we all knew intel was putting a 2mb on die cache to speed up the proc. The only mysteries are why the 64 but extensions which look to prove pretty worthless in the long run, have been added (lic from AMD). And what took Intell so long to put the speed step tech on the desktop p4's? I mean come on it is a great way to cool those p4 heat pigs, people have been screaming for it for about a year, kinda a no brainer.. gg Intel still catchup. Not being a fan boy or anything but I will still save my money and get the AMD chips, and deal with slower excel benchmarks, since that extra 4 seconds I waste every few hours will really add up.

Re:still

[Anonymous Coward]

Maybe you should read a few other reviews before jumping to conclusions (perhaps some reviewers who actually tested temperature and power consumption levels?)

Re:still

[Foo2rama]

your right.. since an idle temp of

The new Pentium 4 Extreme Edition at 3.73GHz, again with out SpeedStep capability, idles at around 56oC with stock cooling in our open-air testbed. When loaded up with our Folding client, we see similar high-end temps at 73oC.

Your right idleing at 56 is not indicative of a heat pig since most amd 64's idle at 34 and max at 48 under load.

The new Pentium 4 6XX Sequence and Pentium 4 Extreme Edition 3.37GHz CPUs offered a bit more performance in gaming scenarios but not enough to catch AMD's fastest Athlon 64 chips at what they do best. And again, when it comes to media encoding or conversion, 3D rendering and modeling, and most new standard business applications,

Does this not state that amd's are still in the lead, except for some business benchmarks

On the 32 and 63 bit gameing bechmarks the cost per fps is still in AMD's favor, as well as showing the p4's have incomplete 64 bit execution.

So yes I did read the tests thank you come again...

Re:still

[Henk Poley]

Ehm, though not exactly "SpeedStep(TM)" all Pentium4s can be throttled by software. My MythTV system -running a Celeron 2.4GHz- drops to 300MHz when idle. Support for this has been in the Linux kernel for some time now, though not that long. It is called "Intel Pentium 4 clock modulation".

Basicly you set an upper bound to the hardware throttling built into the Pentium 4.

Re:still

[bani]

there's little advantage to speedstep/clock modulation though, at least on desktops. it doesn't really save you any power.

why? because if you use linux or similar OS which halt the processor in idle, you're already placing the CPU in the lowest power state it can possibly be in -- totally halted in most cases.

and when you're using the processor, you're going to want to run it 100% speed anyway -- there's no point in running it 50% speed because it will take 50% longer and thus the same (or more) power to compute the same task.

for desktops you'll generally find that running cpufreq or whatnot will simply result in a slower desktop, and virtually no power savings.

for laptops you're better off using a cpu which is power efficient to begin with, eg the pentium-m or mobile amd64.

Re:still

[Cthefuture]

I can't understand why Intel doesn't do more with the Pentium-M. I mean, if they would crank up the clock and add 64-bit support, they would be very close or better than the Athlon64/Opteron line in terms of heat and performance.

The Prescott core sucks. It always has. They need to dump that thing and move on.

Re:still

[Dashing Leech]

"Does this not state that amd's are still in the lead, except for some business benchmarks"

No, you didn't finish the quotation:

"And again, when it comes to media encoding or conversion, 3D rendering and modeling, and most new standard business applications, the Pentium 4 extends it lead today with these new additions to the Intel lineup. Especially in common multitasking workloads and usage models, with an OS that supports Hyper-Threading, the Pentium 4 obviously is at its best."

What the report says is that the AMD 64 still wins in 3D gaming where it is best, but for median encoding/conversion, 3D rendering & modeling, business apps, and multitasking, the new Pentium 4 6XX wins. This is exactly what the plots show too. So it's only gaming that the AMD 64 wins.

Of course the binary decision of win/lose shouldn't really be the metric. Winning by 1% at a 300% increase in cost and 80% more heat doesn't cut it for me. (No, these aren't the real numbers, I'm giving an example.) I'd rather see some ratios of performance to cost and/or heat produced along with the absolute performance specs. I can do this on my own, except they didn't report the cost point of the AMD FX-55 or 4000+. I guess I'll have to look them up.

Re:still

[Anonymous Coward]

Actually, most computing activity isn't CPU bound. I've got a mobile Athlon 64, for example, and with obvious exceptions like games or media encoding, the CPU usually runs in the slowest mode, with low utilisation. On the other hand, with all the stuff I run (ssh sessions, email client, web browsers, media players) it's relatively rare for the CPU to be doing nothing at all.

Among other things, running the CPU in the slowest mode saves power because it reduces cooling pressure, so the fans and whatnot can run at lower speeds. This is on a laptop, but my desktop has ACPI-managed fans too.

Re:still

[drinkypoo]

No one knows if Intel will do more with the Pentium-M or not. Just because they have new P4s out doesn't mean the P-M core is dead. With its vastly shorter pipeline and decreased die area it's still a more efficient chip. There will be serious cooling problems with multi-core P4s, but a multi-core P-M might not be too bad.

Re:still

[HuguesT]

I'm throwing away my mod points to respond to this.

What you are saying is simply false, you haven't done the experiment yourself.

My desktop AMD64 system runs at 35C when throttled with cool'n quiet at 1GHz (equiv speedstep) and at 54C when unthrottled at 2GHz, even when idle. The cpuspeed daemon under Linux does what you describe, as soon as the load goes up it sets the CPU at full speed, so there is *no* downside.

These techs are *very* useful. You can set cpuspeed to only allow the CPU to run at the lowest speed no matter the load, and then you can stop the CPU fan *completely*. The CPU stays cool around 40-45C with passive cooling only under the heaviest load. Complete silence.

The way Pentium-M and mobile amd-64 achieve their efficiency is through the speedstep/C'nQ technologies. So much so that if it is not enabled on your laptop for some reason (e.g. lack of support in the kernel) the autonomy of your wonderful P-M machine drops from 4h to just 90 minutes.

I know this because I used to have such a laptop in my very hands.

In other words you should check your facts, with all due respects.

Re:still

[bani]

i should have been more clear.

it does nothing for desktop p4's.

i have one. it has clock modulation. the clock modulation works.

however there is zero difference on idle between lowest speed and highest speed. it does nothing for temperatures. zero. nada. zilch. this is in fact what several review sites found and reported, much to their suprise.

because when the p4 is HLT'd, you can't go any slower than that -- the cpu is stopped utterly and completely.

as for being useful by allowing the cpu to run at the lowest speed no matter what the load? well. you can always underclock most any cpu, you don't need cool'n quiet to do that. what's the big deal then?

Re:still

[HuguesT]

OK I stand corrected for desktop P-IVs, however I have a hard time believing you for P-M.

With clock modulation on, laptop endurance is much longer. This is only obvious since max speed is limited and so are consumption and temperature.

Clock modulation is still useful for desktop because hardware underclocking usually requires at least rebooting, if not twidling with jumpers. With software throttling you can completely and safely stop the fan if what you want is watch TV or listen to music, which would be most of the time, but if once in a while you decide that you need to do some fast movie encoding, you still can. Kick the fan into play and unthrottle the processor, nothing else is involved.

Note that while decoding a DVD or music the processor is not idle, but that the throttled speed of the processor is high enough to get the job done without overheating.

Re:still

[bani]

if the processor in your laptop is able to overheat under any circumstances, then imo the laptop is flawed and defective.

Re: here in India...

[Anonymous Coward]

I am Habib from India. This is old news since Intel jobs tens of thousand Indians. So we had advance unit. I just build new system with P4 so I can online kiss woman. :~)

The most intriguing part...

[Anonymous Coward]

... of this new CPU is how little power it uses compared to older Prescotts:

http://www.hardcoreware.net/reviews/review-263-11. htm

http://www.techreport.com/reviews/2005q1/pentium4- 600/index.x?pg=16

Load temperatures are the same levels as idle temps on the old prescotts!

Re:The most intriguing part...

[DrMrLordX]

Erm . . . if load temps on these processors turned out to be as low as the old Northwoods, I'd be impressed. The fact that they still suffer the same temps as the old Prescotts is not impressive.

Re:The most intriguing part...

[Anonymous Coward]

The 6xx Prescotts have a load temp that is around the same as the IDLE temp of the 5xx Prescotts. ;)

Not sure where the Northwood fits in anymore though...

EM64T Extensions - 64-bit computing?

[bestadvocate]

What do these things do? Emulate?

Re: EM64T Extensions - 64-bit computing?

[Grounded0]

Basically they're just IA-32 architecture without it's most worst design errors.

1. 8 registers increased to 16 (it still sucks compared to SPARC's 128).

2. Larger addressing width (eg. can allocate more than 4GB of memory limited by 32-bit architectures). Alpha and MIPS had this capability in 1992.

3. NX bit (can prevent buffer overflows). Has been available for ages on good CPU architectures.

Re: EM64T Extensions - 64-bit computing?

[Anonymous Coward]

1. 8 registers increased to 16 (it still sucks compared to SPARC's 128).

Intels have many more internal registers and use register renaming. Basically that means you don't optimize by using a bunch of registers but instead try to keep the processor pipeline full enough so the out or order loads and stores from memory, which is hopefully in cache, have zero cost. But you do that naturally when you program, don't you?

Re: EM64T Extensions - 64-bit computing?

[Anonymous Coward]

Item 2 isn't a "design error", it's a trade-off at any moment in time whether you support 64-bit addressing, doing so means a lot more transistors, and if (as with Intel) most of your customers are buying mid-range desktop machines that's a bad trade in 1992, in fact it was still a bad trade as recently as 5 years ago.

Item 3 is an improvement, but you mis-described NX, it doesn't "prevent buffer overflows" at all. It's a _marginal_ defense again deliberate stack smash attacks in which executable code is written during a buffer overflow. Buffer overflows have been used by Black Hats quite happily on Alpha, MIPS etc all these years despite non-executable stacks. It remains to be seen whether the development cost for this feature pays for itself in terms of raising the bar for black hats.

Item 1 is a trade-off again, but one that Intel should have made years ago, perhaps when they designed the 386. 128 registers means a lot more silicon, yet many inner loops will never use more than a dozen or so registers, meaning you either make price/performance worse, or you sacrifice something else (maybe vector instructions) to keep costs down. Every designer makes their own decisions here, and they're validated in the market. Eight wasn't enough, Sixteen is definitely closer to the sweet spot.

AMD made good trade offs with x86-64, they were rewarded in the marketplace and Intel are jumping on the same bandwagon now with EM64T.

Re: EM64T Extensions - 64-bit computing?

[gloth]

3. NX bit (can prevent buffer overflows).

It does not prevent buffer overflows, it just makes it harder to exploit them, because things that one might manage to write past the allocated buffer will not be readily executable.

Re: EM64T Extensions - 64-bit computing?

[owlstead]

Yeah, it is still IA-32, so this means:
- it's compatible
- it's fast
- it supports more (important) instructions
- larger address space
- additional security feature
- it's relatively inexpensive

So in my view there is little wrong with it. Too many processors claimed to be better, but were slower and more expensive instead - and that's what counts. The compilers will compile for it without too big a fuss, so what's your point?

If it can keep up with AMD on performance, power/heat requirements and compatibility is another matter, my vote still goes to AMD, especially since I suspect foul play by Microsoft on 64 bit support. Windows 64 bit will be released as soon as enough chips are available from Intel.

Re: EM64T Extensions - 64-bit computing?

[trezor]

• 8 registers increased to 16 (it still sucks compared to SPARC's 128).

Wow. I guess the IA-32 platform really does suck. Even my Amiga 500 with an old Motorola 68k CPU way back in the nineties had this.

Not being a troll or anything, but back in the days, any Motorola-based computer with a similar speed of an Intel-based machine beat the crap out of the Intel-based machine since most of the instructions was actually processing data and not loading and unloading registers. If the compiler supports the additional registers, this does way more for performance than adding a few 100 MHz every now and then. I just can't believe Intel still haven't made anything better than this.

Re: EM64T Extensions - 64-bit computing?

[Anonymous Coward]

Basically they're just IA-32 architecture without it's most worst design errors.

IA-32 worst design errors were not those, IMO. x86 ABI is a "register-memory" type of CPU, I wish AMD would have designed a pure register-register CPU like RISC processors did a few years ago. Instead, AMD just added 8 registers more (crappy, VAX had 16 too, PPC has 32 like most of RISC processors, if AMD were adding more registers why not add upt to 32 at least) and made the registers 64-byte wide. They haven't fixed anything, the instruction set is the SAME with the same semantics except for 2 new instructions. In fact, they have condemned us to live with the x86 ABI (except for the 64 bits) for another 20 years.

I wish AMD had failed with x86-64. Intel at least did have a clue and redesigned the whole CPU with the itanium. Itanium may not be great either but at least they designed it from the ground. AMD has just patched a crappy architecture, which makes x86-64 be...a crappy architecture.

Re: EM64T Extensions - 64-bit computing?

[ciroknight]

The fact is, AMD and Intel have BOTH been better than this for years (I believe they started Out-of-order operations and register renaming with the original Pentium, but don't quote me on that), but to maintain compatibility, Intel really didn't want to budge on this original spec. In fact, Intel really didn't want to budge on ANY of the spec, so the ISA got really old, really fast. Of course, through multiple layers of obsfuscation, AMD and Intel have gotten around most all of the lagging bits. The last problem that really couldn't be snuck around was the memory address space, which AMD fixed with their spec, and Intel stole.

Re: EM64T Extensions - 64-bit computing?

[Anonymous Coward]

If it can keep up with AMD on performance, power/heat requirements and compatibility is another matter, my vote still goes to AMD, especially since I suspect foul play by Microsoft on 64 bit support. Windows 64 bit will be released as soon as enough chips are available from Intel.

I doubt there's any anti-AMD foul play by Microsoft, considering Dave Cutler* worked with AMD on the design of the chip, ported the NT kernel to it and allowed AMD to publish his strongly pro-AMD comments on their website. (Note that Cutler's comments are pretty old, pre-dating the release of Windows Server 2003.) The AMD site also contains supportive comments from Brian Valentine, Senior Vice President of the Windows Division for Microsoft.

I've been using the pre-release versions of XP 64-bit for a while, and the only weakness is a lack of 64-bit drivers from hardware companies that don't provide source code to Microsoft (all the hardware with driver support in Windows works fine on the 32- and 64-bit versions). I'm just guessing, but my suspicion is that Microsoft are waiting for drivers before releasing the OS. I mean, if I had bought a final version (rather than getting a free RC version), I'd be an unhappy customer, since there's no driver for my 802.11g hardware.

* Dave Cutler is the most senior software developer at Microsoft, and headed the design of the NT kernel.

Re: EM64T Extensions - 64-bit computing?

[maraist]

Wow. I guess the IA-32 platform really does suck.

IA-32 sucks like the c-language sucks. It sucks like SOAP over HTTP sucks. In other words, it is just an intermediate platform. A communication protocol between the compiler and the hardware. If the protocol changed too often say the Motorol 6800 -> Motorola 68k -> IBM/Motorola PowerPC as Apple has done, then you loose a LOT of 3'rd party support. It is expensive to develop high-performance general-purpose software for an architecture that keeps changing. The biggest issue is that you can't attract new support if you don't have a large established base. It's just economics.. Risk is a cost. Uncertainty equates to risk. Firms choose the lowest overall cost.

So anyway IA-32 hardware has translated IA-32 instructions into completely different representations for over a decade now.. No CPU has actually run IA-32 instructions in all that time. NexGen was the first company to do 100% translation of IA-32 into internal RISC instructions (with Registers that didn't map exactly to the 8 GRPs). AMD and Cyrix quickly followed suite. And finally Intel dumped their direct instruction translation with their Pentium Pro line.

The main negatives of instruction translation is the extra work that has to be done. But this hurts pipeline misses more than anything else. If you just have a sequence of instructions then you'd never notice the added delay, and an IA-32 compatible CPU could dance with the best of them.

While it's true that Motorola 68K CPU's tended to be faster for each generation, they also tended to run on more demanding hardware and software, so the overall system was slower than a comparable PC. First MAC's verses DOS (no competition in performance). Later the AMD / Intel wars brought about faster CPUs' for a short time. Then when the faster PowerPC came out, the video graphics wars had started and it was an embarrasement to the MAC how few video cards you could put into it thereby restricting yourself to several months behind the video-wars and thereby the performance curve.

Most of this was circumstantial history. But so is the development of HTTP as a base-line transport for so many client-server applications today. It's there, it has a proven track-record. Firewalls support it. Proxies support it. 3'rd party integration is there. Build XML-RPC, build SOAP, build java-script/server integration to emulate a client-side application. It's archaic, but the cost is so low, and the developer expertise is so high, that alternatives are simply not considered.

The Intel Itanium was an excellent processor. It is one of the fastest CPU's out there for scientific computing. But's also one of the most primative. There is no instruction translation (of course because it's a 1'st generation CPU), so it can't adapt to bad compiled code. It's also an example of throwing money and resources at a design problem. But the Itanium has not been touted for it's mild nich superiority, but instead lambasted for lack of practical backward compatibiilty. IA-32 was designed into the Itanium instruction set, yet the impeedence mismatch between IA-32 and IA-64 pushes the performance envelop back into the stone ages. Not even Linux with it's hardware egnostic mantra could not save Itanium. The risks/costs were simple too great.

Re: EM64T Extensions - 64-bit computing?

[Anonymous Coward]

Holy crap, someone talking sense on /. Hold the presses.

Re: EM64T Extensions - 64-bit computing?

[bani]

actually what happened with itanium is intel made a number of huge gambles on technology.

in order for itanium to be successful, every single one of them had to pan out.

what happened is virtually none of them panned out.

intel blew their load on a high risk gamble, and lost.

hahahaha

[Anonymous Coward]

Thank you for allowing me to mod you down twice in less than 10 minutes. I usually don't care for mod points, preffering to act out with offtopic yet relevent posts like my "Stallman Feeds Self Whole Chicken" work. Still, your persistance has allowed me the enjoy my mod points for once. Now I've jost got to find somewhere for my last 2 modpoints... Time to look for Free Ipod Sigs.

Re:hahahaha

[ekuns]

I'm not certain who you modded down, but assuming it was your parent post, I hope you understand that by posting about it in this discussion, you just undid all of your mod points in this discussion! Still, your post was funny. Good luck finding those Free IPod sigs.

Re:hahahaha

[Anonymous Coward]

He replied as AC. His mods stand. Good luck with those snarky corrections ;)

Re:hahahaha

[ekuns]

He replied as AC. His mods stand.

Is this true? If so, that seems like a hole in the system. The FAQ talks about not being allowed to post and mod the same discussion, and it doesn't say "unless you post anonymously." Have I read into the FAQ a rule that isn't there?

Good luck with those snarky corrections ;)

Well, I tried! But I'm always willing to listen to factual corrections.

Still catching up to Athlon wrt games

[aendeuryu]

Quick summary for gamers:

This P4 still lags behind the Athlon FX-55 and 64 4000+ for Doom3, HL2, UT2004, and the general 3dMark benchmark. Pricewatch has the FX-55 at 900$ US and the 64 4000 at 620$, which is cheaper than the best chip of the bunch at 999$. Granted, video cards are probably the biggest system decision for gamers, but if CPUs figure into your decision, you might want to consider the comparisons.

Re:Still catching up to Athlon wrt games

[ciroknight]

Games like Doom3, and HL2 were practically DESIGNED around the Opteron, so Intel's lagging behind because of optimization at this point.

But, gamers, if you really want to save some money, please buy the AMD. At this point, I'd wait for the next release of the 6XX line before buying one.

Re:Still catching up to Athlon wrt games

[Anonymous Coward]

Thanks, but who cares about the >$200 models?

I think "gamers" in this case should be prefixed with "fanatical" and postfixed with "who have more money than sense, or make money on their hobby".

"Normal" gamers (we who play for fun, but still want the best bang for our buck when it comes to hardware) are probably interested in how things compare to the non-FX Athlon64s.

Correction

[Compact Dick]

That's Shouldn't they have, not " Shouldn't they of".

Cheers,
CD

Re:Correction

[Anonymous Coward]

...and the contraction that sounds like "of" is written 've, as in "should've". Although I fear that by the year 2100, "of" is widely accepted as a verb. It'll be interesting to see what kind of conjugation the verb will have...

Re:Correction

[hunterx11]

You oves scared me greatly with your prediction.

Re: here in India...

[DrMrLordX]

Mahir has already kissed the online woman many, many times. You are late, my friend!

Nothing really about 64 bit performance

[GreatDrok]

I have been trying to find out what the performance of the AMD and Intel chips is really like with 64 bit apps on a 64 bit OS and have yet to find anything that covers it. This article as usual goes on about 32 bit apps on a 64 bit OS which really doesn't help. I want to know if the Intel implementation is as efficient as AMDs and this would be easy enough with Linux but none of these reviews ever consider running on Linux. Just saying that 64 bit support isn't an issue at the moment doesn't cut it, I want to know now!

Re:Nothing really about 64 bit performance

[Anonymous Coward]

Gentoo has some nice benchmarks on this. You can find it in the AMD 64 FAQ found here . Where also they link to another forum post containing some very interesting performance differences, found here.

Re:Nothing really about 64 bit performance

[kryptkpr]

Eeeek..wrong! Someone doesn't know how hardware works at all..

The 64-bit registers are twice the size of their 32-bit brothers, or equvillently, there are twice as many 32-bit registers in a 64-bit CPU.

Software will need to be recompiled, yes, but almost everything will likely benifit from having more registers, if from nothing else.

Re:Nothing really about 64 bit performance

[swillden]

Where also they link to another forum post containing some very interesting performance differences, found here.

Those are some very interesting results, particularly since they appear to indicate, overall, that 64-bit code on a 64-bit OS is faster than 32-bit code on a 32-bit OS. The exceptions, where the 32-bit code was faster, were all programs that are specifically optimized for x86 performance, including hand-tuned assembler. It's reasonable to assume that when those are hand optimized for AMD64, they'll be faster as well. Actually, all of them seem like applications that will really benefit from the 64-bit registers, so they'll probably be *much* faster.

I actually expected the 64-bit code to be slightly slower, because it tends to be a little larger. Larger code is less likely to fit in the various levels of cache which requires more frequent fetches from slower memory. It appears that the larger number of available registers the compiler can use more than offsets the performance cost of larger code size (and probably helps to reduce the expansion as well). Those additional registers obviously provide zero benefit to assembler code that doesn't know they're there and therefore doesn't use them.

Re:Nothing really about 64 bit performance

[Anonymous Coward]

Eeeek..wrong! Someone doesn't know how hardware works at all..

Number of registers have nothing to do with the width of the datapath of a CPU.

Re:Nothing really about 64 bit performance

[drinkypoo]

One would expect the 64 bit performance of Opteron to be better than P4, given the four-times-larger L1 cache.

Re:Nothing really about 64 bit performance

[Anonymous Coward]

AMD64 has (by design) twice as many registers as x86.

Re:Nothing really about 64 bit performance

[DarkEdgeX]

Right, and the other thing to keep in mind is that these 64-bit extensions also double the number of general purpose registers (GPRs) available to user code. Depending upon the ABI of your system (*nix vs. Win64) you could have as many as 4-6 additional scratch registers for use (either for the 64-bit compiler to utilize or for you to utilize in 64-bit assembly code).

Under 32-bit processors you get these registers (all 32-bit of course):

EAX, EBX, ECX, EDX, ESI, EDI, ESP, EBP (8 total)

Under 64-bit processors you get these registers (all 64-bit of course):

RAX, RBX, RCX, RDX, RSI, RDI, RSP, RBP, R8 - R15 (16 total)

What's more, you can now address the low byte of all the registers (previously you could only address the low byte of the 4 basic registers-- AL, BL, CL, DL). E.G. - SIL, DIL, BPL, SPL, R8B - R15B. The new registers (R8 - R15) are also word (R8W - R15W) and doubleword (R8D - R15D) addressable.

So.. yeah. Good stuff, plenty of opportunities for optimization by compilers and low level programmers.

Re:Nothing really about 64 bit performance

[xgamer04]

Exactly, it's stupid. The Windows 64-bit binaries take up more RAM, and the 32-bit apps they use don't take advantage of any of the new instructions, so it's basically a waste of time.

Re:Nothing really about 64 bit performance

[Anonymous Coward]

It Is

Oy!

[ggvaidya]

Get out and get a LIFE, man! Slashdot isn't so important! Sheesh, with the number of posting I see by you, it's obvious you haven't left your computer in years.

Re:Oy!

[nuclear305]

"Get out and get a LIFE, man! Slashdot isn't so important! Sheesh, with the number of posting I see by you, it's obvious you haven't left your computer in years."

I'm sure you see the irony here...

Re:Oy!

[ggvaidya]

*sheepish grin*

Intel fanboys? Biased Journalism?

[inflex]

Normally I don't pay much attention to these reviews, but damn this review smacked of Intel fanboyism and anti-AMD'ism. In summary, the comments fell into two catagories:

1. If Intel beat the AMD in a test
"Once again it's game over for AMD"

2. If AMD beats Intel in a test
"AMD struggles to keep ahead of Intel in this test"

I thought at first it was just a one off comment - but the almost all of the evaluations were like that.

Obviously we each tend to have a preference for one brand over another but please can we have consistent commenting.

Paul.

Re:Emulated 64 bit processing

[Anonymous Coward]

The inner workings of most CPUs bare little or no resemblence to their functionality. Look up 'microcode'.

Intel the leader in 64 bit extensions?

[diegocgteleline.es]

Sure, AMD invented those extensions, but Intel has 80% of the desktop processor market (amd only stole them a 2% in the last 6 months). This should mean that soon most of the desktop processors with 64 bit extensions will the ones from intel, not the ones from amd.

Re:Intel the leader in 64 bit extensions?

[bani]

in the meantime, ia64 continues to be a black hole for billions of intel revenue.

intel has been beating this dead horse for over a decade and it hasn't lived up to a single one of its design goals, and has never been profitable.

HotHardware.com

[ralinx]

wow... the name really does reflect the stuff they cover

Re:HotHardware.com

[VoidWraith]

And you can tell by the URL they're favoring the P4 ;).

Clarification ?

[ultranova]

From the article:

"Certain viruses that compromise a system can create buffer overflows by swamping a system processor with code."

Does this refer to a standard buffer overflow attack of giving longer input that the program expected, or does it describe another type of attack ? I really can't tell :(...

Re:Clarification ?

[Anonymous Coward]

It's okay because viruses are usually written for intel procs and so they dont run on amd procs

I've been waiting for this for some time now...

[karlandtanya]

Been planning a new system for a while. Got a dual PIII from 1998 right now, and waiting for the prices to drop.
Just needed the next "trendy new marketing development that really adds nothing" from Intel or AMD to push down the price of the chips I really want.

Re:I've been waiting for this for some time now...

[Graemee]

...and waiting for the prices to drop.

Sh*t or get off the pot.
If you've really been waiting for the prices to drop, you'll be the one obsolete by the time you get a new model. Buy what you can afford now and worry about the next great model later when you think it's time to get a new one.

Re:I've been waiting for this for some time now...

[Anonymous Coward]

This is why you probably have a house/apartment full of useless toys and he probably has a descent savings account.

Guess what kiddie, its the same computer weather you buy it for $3,999 now or $1,500 in a year.

Re:I've been waiting for this for some time now...

[cnettel]

Sorry, but AMD64/EM64T is really much more than just a fancy addition. To once again get into a situation where your virtual address space is totally superior to the amount you really need is positive. This is not without cost, though, as the memory bandwidth and space requirements increases.

8 more general purpose registers will do well to most code.

SSE3 in Prescott was an addition with very little real usage so far. The 64-bit x86-based ISA is a prime example of what you'll hate yourself for not having in a few years from now. So, now you have to wait some more time before you can get an affordable 64-bit CPU. If you're currently in love with the positive points of SMP, you will even have to wait for an affordable dual-core 64-bit chip. Good luck....

Re:I've been waiting for this for some time now...

[LokieLizzy]

I'm still trying to figure out how to create spaces between lines of text.

Hmm...

Re:I've been waiting for this for some time now...

[cthulhu11]

I'm increasingly confused by the variety of chips that are available. I figured out the Celeron scam, but I do wish Intel would start calling things P5's or P6's or something.

How to pronounce "EM64T"

[Anonymous Coward]

"AMD"

Signifcantly

[birder]

He also used the word 'signifcantly' a signifcant amount. I guess that was part of keeping things consistent.

64-bit GPUs

[G3ckoG33k]

If I'm not totally incorrect we may see 64-bit GPUs in the next few years (2007?). IIRC, there was some remark from some ATI/nVidia guy somehere. Perhaps it was relating to the upcoming Unreal 3 technology, I really don't remember. Or, was it 128-bit colours? Hrrrmmm...

Re:64-bit GPUs

[fgb]

IAPWATB (I am probably wrong about this but...) I thought most GPUs were 64-bit and even 128-bit processors.

Re:64-bit GPUs

[cnettel]

You're wrong. Or, rather, "bitness" is a very silly measure. In a general purpose chip, you can measure the maximum word size for single operations.

Then, you realize that the current SSE/3Dnow etc stuff will actually handle 128-bit data.

Then, you can think that you should measure the bandwidth of the memory bus. With dual channels, that's generally 128 bits now for CPUs, but for Intel, the memory bus is of course still a part of the chipset. Most GPUs top out at 256, with lower counts and basically the same architecture for the cheaper models. The front-side bus in Intel chips is 64-bit, but running on a higher frequency. Also, most accesses, IIRC, are aligned to be the size of one cache line - 64 bytes or 512 bits. Also, note that the 8088 was an 8-bit CPU and the 80386 sx a 16-bit CPU by this definition. Obviously not what we want.

Finally, we can measure it by the addressing model. This makes some sense and then we also get to the result that AMD64 was the first x86-like ISA to achieve 64-bit flat space addressing. The "flat space" requirement is important, as we want to consider the 8086 (/8088) 16-bit and not 20-bit (16-bit segment + 16-bit offset with locked segment spacing). In this area, many GPUs are tailored to their actual memory capacity. Why should we waste addressing bits and consequentially lines on stuff we can't use?

By this definition, a modern GPU isn't "even" 32-bit, but why the heck should we care. The number of bits as a performance metric is stupid unless one has to take extra measures to avoid the boundary. That was the case in 16-bit x86 code, and is currently the case in some heavy-iron 32-bit code. The number of bits "of" a GPU is not a relevant metric.

Re:64-bit GPUs

[G3ckoG33k]

IIRC, the bus widths are today 64, 128, or even 256-bits. But, the graphics still remain 32-bits.

Re:64-bit GPUs

[Anonymous Coward]

I believe when you say the graphics still remain 32-bits, you're referring to color depth? That's probably not a good way to state "bit-ness"

Re:64-bit GPUs

[Anonymous Coward]

So, after the GigaHertz myth, we now have a dekabit myth? What's next?

Re:64-bit GPUs

[ZephyrXero]

128bit colors would be a waste since the human eye can only see up to 36bit color ;)

..of course, I'm "color blind" so I only see the world in 16bit color :P

Thermal Characteristics & Power Consumption

[cyclocommuter]

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.

Warez check

[trezor]

• Windows 64 bit will be released as soon as enough chips are available from Intel.

According to some *ahem* backup-sites I've seen, Windows 64 is allready out on the internet and has SP1 embedded.

/FYI

Re:Warez check

[fruity_pebbles]

RC2 is out and available from Microsoft. It has roughly the equivalent of SP2 included (i.e. the SP2 firewall is there).

toms hardware

[bird603568]

i cant believe i cant find it there. unless there hiding it, they normally ahve all the new hardware news.

Intel President Paul Otellini said...

[Anonymous Coward]

Intel President Paul Otellini said on Jan 10th in his blog-

"While I hate losing share, the reality is that our competitor has a very strong product offering"

Further details on the story can be found here

After reading a few other articles about the 600s

[doormat]

Its quite easy to see how biased the HotHardware review is towards Intel. You wonder how much intel paid them for that review, or let them break NDA early or something. Its a shame /. is giving them traffic for that bullshit "review".

64 bit slower than 32 bit

[3770]

These tests show that 64 bit generally is slower than 32 bit, so I am anxiously awaiting 16 bit applications because that should be even faster.

(yes, yes, I am kidding)

Non-dupe certification

[Anonymous Coward]

I certify that I, anonymous coward, have reviewed this article in comparison to other recent articles and have found it to NOT be a dupe.

This certification provided 'as is', all guarantees and warrantees are disclaimed.

This has been a public service posting.

It figures

[angle_slam]

Literally 3 days after I ordered a processor, Intel comes out with a new one. I haven't even received the other one yet, and it is obsolete. ;-)

Mystery of the 64 bit extensions: Solved

[Anonymous Coward]

Ok, the extensions are not compatible, right? So why did intel put them in there?

Sell those chips now and gain market share. That is it, nothing more or less. Those extension don't do anything at this point. Its all about adoption in the market.

Its business people not technology.

RE: upgrades

[King_TJ]

It's one thing to endlessly chase the "latest thing", but this guy's saying he bought a dual CPU PIII system roughly *twice* as long ago as the average business would keep a system before depreciating it to $0 value - and he's *still* waiting for prices to drop on new machines??

Sorry, but I don't buy that excuse. It's fine to say "I don't see a need to upgrade my outdated PC yet." Maybe you only run 5+ year old apps on it and it's all you need? But I grow tired of the lame excuse of "I need a new computer, but I'm waiting for a better deal." Come on! This is the first time in the history of computers that anyone can grab a 2Ghz system with at least 512MB of RAM in it and 80GB or more of disk space for only $500 or so. (Heck, it's the first time in history you can buy an Apple *Mac* for that price range, brand new!)

Forests, not trees

[fm6]

As usual, somebody focuses on one data point and thinks that's the whole story. The MIPS 4300i in the Nintendo is not in the same class as the IA-32 processors in PCs, even if it does have a wider data path. If you'd been following the Intel-AMD processor wars, you'd know that the big issue is how we evolve beyond the IA-32. It's obvious that the successor will be 64-bit, but that's only one particular feature.

Intel and HP chose to work together on a development effort to produce a totally new processor that offers drastically improved performance, but doesn't execute IA-32 code very well. AMD chose to emphasize IA-32 support instead of overall performance. As in the past, backward compatibility won out over superior technology, and AMD has been winning market share from Intel.

Intel is doing a course correction for its 64-bit strategy -- not suddenly moving into the 64-bit world.

Re:Forests, not trees

[Ralph Wiggam]

Here's a little rule of thumb. If you think a post is stupid, look at the moderation. If it has been moderated "Funny", think to yourself "maybe this isn't a serious post and shouldn't rebut it on a factual basis".

-B

Re:Forests, not trees

[fm6]

Or it may be that a particularly lame post simply made a moderator laugh.

What you're really saying is this: you think you understand what the poster was thinking better than I do, and that the moderators back you up. My response: whatever. Get back to me when you finish that ESP course. I'm too lazy to assume that post says anything except what it says.

Re:Forests, not trees

[Anonymous Coward]

The problem is the Itanium didn't deliver better performance. In fact the Itanium 1 was horribly slow in comparison to contemporary x86 systems (running native code, not x86 code). It's basically a repeat of the i860, which theoretically offered great performance, but never lived up to its promise because generating machine code to take advantage of it proved incredibly difficult.

The Itanium 2 is much better performance-wise, but the last systems I used (in 2004) still couldn't keep up with the best AMD64s in native mode, not to mention when running x86 legacy code.

All in all, the Itanium simply isn't superior technology to the AMD64, at least in the 1-4 processor realm. When you get up to 16, 32 or 64 CPUs, it may be a different story, but that's a different market, and has traditionally been dominated by RISCs, not x86.

Re:Forests, not trees

[Mornelithe]

So you're too lazy to develop a sense of humor, but you're not too lazy to write a two paragraph, relevantly linked diatribe in response to a one line jibe?

Re:Forests, not trees

[fm6]

I have a sense of humor for things that are meant to be funny.

Re:Forests, not trees

[evilviper]

Your own post is pretty misleading.

The Itanium didn't offer drastically improved performance for the price, and AMD processors don't sacrifice much performance for x86 compatibility.

<blockquote>As in the past, backward compatibility won out over superior technology, and AMD has been winning market share from Intel.</blockquote>
Not true at all. Price/Performance won out. In this case, the better performer for the price, just happens to have better backwards compatibility as well.

Re:Intel fanboys? Biased Journalism?

[MerlinTheWizard]

I wish we wouldn't call that "journalism".

A crappy processor with a new crappy lease on life

[Anonymous Coward]

(yawwwwn) A crappy processor with a new crappy lease on life. The Intel lemmings should flock to this one.

So far I haven't heard any decent basis for the new p4 being faster than G5's or Opterons.

I'm glad Intel is on a severe decline. They've had their time in the sun but now it's time for others to take the spotlight.

Itanium not excellent!!!!!!!!

[Anonymous Coward]

The itanium is like a science experiment gone wrong. Had HP continued development of Alpha it would be kicking its ass all over the place, much like IBM is doing today with the Power5. Which coincidentally is so much faster than the Itanium it is embarrassing. No there is no real IA-32 compatibility in IA-64. Intel screwed up bad this was there chance to finally give x86 the boot and now we are stuck with 64-bit extensions. No matter what you do it is inevitable as processors get faster that decode into micro-ops will look more and more expensive.

Oh yeah and no IA-32 sucks way more than those other things you mentioned, at least they were considered good at one point. IA-32 was a joke of a design when they made it, that is why IBM picked it for the PC.

As for apple they made the right move, do you realize how easily they transitioned, do you realize how much less money the PowerPC processors cost comparatively. Not per unit mind you but total design and build cost for a given number of processors. If intel were sane processors would be cheaper, better, cooler, and more flexible but they are not. Rather Intel is the biggest bunch of dumb asses on the planet who can get beaten by a smaller company with fewer resources.

Balanced Smoothness? wtf

[Anonymous Coward]

From the article...

"This is a very interesting test because it shows you the balanced smoothness of Intel's Hyper-Threading technology in action."

What the heck are these crakeheads talking about.

Re:Balanced Smoothness? wtf

[Anonymous Coward]

Uhh... Anon Coward, err Crack Dealer, whatever...

Have you actually TRIED doing any serious multitasking with an Athlon 64 or even a Pentium mobile chip that doesn't support Hyperthreading?

Like try converting an MP3 or ripping an audio CD, while you spin a model, surf the web, stream a video, whatever... just run a couple of CPU intensive apps simultaneously.

Hyperthreading works very well and is similar to having a multi-CPU SMP setup, in terms of general feel and system responsiveness in multitasking.

I think that's what they were referring to. The only Athlon rig that can compete with a P4 in terms of multitasking performance, is a multi-chip config.

THAT'S what the test in the article was showing, if you bothered to read.

Re:A crappy processor with a new crappy lease on l

[psydragn]

I think 'severe decline' is somewhat strong wording for Intel's current state. They still owned over 82% of the X86 market in the last quarter.

Don't forget that Intel does a lot more than X86 CPUs too. They just retook the NOR flash sales title (admittedly after losing it, through another stupid business decision), and Hector Ruiz may now be mulling the sale of Spansion because of the intense competition. On one hand they are up against the wall WRT being forced to use band-aid solutions for the current P4 CPUs as a result of their bull-headed run for MHz, as well as the limited acceptance of Itanium. On the other hand, however, they are dominating the mobile sector with P-M and are expanding that platform; they also have their hands in things like WiMax and other emerging technologies; and don't forget they have enough money in the bank to probably buy AMD.

With Otellini now being fairly frank about the competitive landscape, I think it's possible that the company has reached a turning point.

MOD DOWN - NO IT'S NOT

[Anonymous Coward]

MOD DOWN - NO IT'S NOT

No it isn't

[Spuffin]

Meh. What I'd be interested is decoding MP3s. So far, MP3 decoding is limited to realtime. Also, when are we going to be able to decode multiple MP3s at once?

MP3 decoding is not limited to realtime. Have you ever used the diskwriter output option in winamp? It will decode your mp3 into a wav file much faster than realtime. And as for decoding multiple MP3s at once, why? Using the same diskwriter option you can set up a batch conversion by having winamp run through your playlist to convert all the MP3s. Decoding multiple MP3s at once seems inefficient and pointless but perhaps I am missing something.

Note: You can also use other programs such as CDex to convert MP3s to WAVs faster than real-time; I was merely using winamp as an example.

Re:No it isn't

[Anonymous Coward]

That was a joke. Do you really listen to songs at 6x or listen to 10 songs at the same time? Of course it's pointless to decode at high speed or to decode multiple streams of songs for the purpose of listening music.

LOL WHAT

[Anonymous Coward]

Whoosh! Whoosh! Whoosh! Lookie up there, y'all! There flies a joke! He spelled it "Athalon" and U didn't even flinch. Yee-e-e-es, laugh now. That self-deprecating laugh. Hau hau hau. Endut! Hoch hech.

LOL WHAT

[Anonymous Coward]

What U say? :-((( Lookie lookie how sad I am...

LOL WHAT

[Anonymous Coward]

I clicky U're link but it don't load. What gives? I'd liek to reed that referance. Plzzz??????

Worthless Review

[ZephyrXero]

Is it just me, or do you feel like you wasted your time reading (even skimming) that article? How can you compare Intel's new 64bit chips to an Athlon64 on a non 64bit OS. These "hot-hardware" guys obviously don't know much about computers to be testing 64bit chips in Windows. 64bit Windows XP will probably come out AFTER Longhorn....they are a long way away from figuring it out. Linux (and maybe BSD?) is the only way to really get an accurate test of these chips....sure running "legacy" 32bit apps is worth a look, but not the whole damn article. When will people learn that computers are about constant change and quit trying to be little fanboys of just one thing?

LOL WHAT

[Anonymous Coward]

Hes right U're wrong. Its "shouldnt they of released" my teecher told me so!!!!! I think U're a dipshut.

news flash, pentium 4 and intel "64bit" sucks ass

[Anonymous Coward]

compare it to an amd64 cpu and it sucks ass on the same 64bit code. much longer latencies and fixups on various operations.

Hello - This is 10 years ago calling!

[Anonymous Coward]

The RISC vs CISC debate is over. Modern x86 CPU's are RISC with a frontend that translates any CISC. In addition, the percentage of the transistor budget needed to implement the old CISC stuff is negligible nowadays, so your "CISC uses more transistors so RISC can have more cache" argument is so obsolete its dangerous.

Worthless Review? NOT!

[Anonymous Coward]

ZephyrXero,

You need to learn to READ an article before you pass judgment. HELLO?? In the article it specifically shows Windows XP Pro x64 Edition was used for testing in the 64-bit benchmarks, listed in BOTH the test setup specs page AND right before the 64-bit test section, with a screen shot of the Control Panel General Properties tab. I love how folks like you make assumptions and draw conclusions without checking your facts.

Of course there are very few 64-bit APPLICATIONS that are avaialable right now, for testing 64-bit performance. One of those benchmarks is a very quick testing program that they used, called SiSoft Sandra, which they did run. I thought the review was actually very balanced, devoid of "fanboyism" (love when folks throw that stupid word around) and comprehensive.

WTF?

[Anonymous Coward]

"By Design"? Gee I thought it was by accident.

And... "as x86"?!? x86 WHAT? you mean 8086? 80286? 20386? 486? 586? What version? They all have differing numbers of registers!!!!!

Next time let daddy proof your comments for you, you are clearly too young and ignorant to be posting anything here.