Slashdot Mirror
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."
"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.
Don't you mean.. BIZZARO!
"older" P4 will have a price drop,which will be good for People saving 50$ on a new System.
and just in time for Windows XP 64-bit!
how lucky!
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.
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.
Shouldn't they of released their space heaters at the *beginning* of Winter?
Your hair look like poop, Bob! - Wanker.
The Tech Report also has an excellent writeup 4 -600/index.x?pg=1>
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.
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.
---In a time of Chimpanzees I was a Monkey.
... of this new CPU is how little power it uses compared to older Prescotts:
. htm
- 600/index.x?pg=16
http://www.hardcoreware.net/reviews/review-263-11
http://www.techreport.com/reviews/2005q1/pentium4
Load temperatures are the same levels as idle temps on the old prescotts!
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.
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.
That's Shouldn't they have, not " Shouldn't they of".
Cheers,
CD
Use ISO 8601 dates [YYYY-MM-DD]
or enconding an MP3?
Why do you want to know?
Sincereley,
Your Friendly Neighborhood RIAA Agent
Error 407 - No creative sig found
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?
It's official. Most of you are morons.
Mahir has already kissed the online woman many, many times. You are late, my friend!
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!
"I have the attention span of a strobe lit goldfish, please get to the point quickly!"
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.
MIPS R12000 system that's sitting on my desk has 8MB of L2 cache. And yes, it's circa 2000.
IRC: Grounded0 @ IRCnet. "I was lucky get into computers when it was very young & idealistic industry" -Steve Jobs
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.
IRC: Grounded0 @ IRCnet. "I was lucky get into computers when it was very young & idealistic industry" -Steve Jobs
"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.
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.
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.
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?
wow... the name really does reflect the stuff they cover
From the article:
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 :(...
Forget magic. Any technology distinguishable from divine power is insufficiently advanced.
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.
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.
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.
11*43+456^2
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.
"Reality is that which, when you stop believing in it, it doesn't go away." - Philip K. Dick
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.
He also used the word 'signifcantly' a signifcant amount. I guess that was part of keeping things consistent.
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...
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.
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.
Not Buzzword 2.0 compliant. Please speak english.
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.
According to some *ahem* backup-sites I've seen, Windows 64 is allready out on the internet and has SP1 embedded.
Not Buzzword 2.0 compliant. Please speak english.
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.
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
i cant believe i cant find it there. unless there hiding it, they normally ahve all the new hardware news.
Further details on the story can be found here
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".
The Doormat
If you're not outraged, then you're not paying attention.
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)
The Internet is full. Go Away!!!
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.
-Michael
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. ;-)
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.
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!)
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.
I wish we wouldn't call that "journalism".
...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.
Slashdot - News for Herds. Stuff that Splatters.
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.
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.
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.
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.
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?
"A truly wise man realizes he knows nothing."
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.
too bad the r12k performs like shit.
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.