Slashdot Mirror
News on Pentium IV
MotaK writes "Ace's Hardware and ARS-Technica has reported on PC Worlds article on the Willamette Processor, dubbed the P4. This proc. will apparently be only a 200Mhz frontside bus, and launch sometime in 2000. "
← Back to Stories (view on slashdot.org)
Come on Intel, isn't it time to retire the Pentium name? As if Pentium II and III weren't bad enough, now we have to deal with the Pentium IV. Even Williamette would be a better name.
If it wasn't for the Itanium, they'd probably still be calling their chips Pentiums 10 years from now...
AMD has had a 200 MHz FSB since they released the Athlon. Intel is only now getting around to it. I also heard recently that in AMD's Dresden fabrication plant that they are turning out 1.2 GHz chips while Intel is only /talking/ about getting over a GHz (w/o cooling). I think that Intel's star is falling and that the Athlon's superior performance over the P3 was no fluke. (Also that is one mighty unoriginal name)
If the money had been put into decent development, we might be seeing high-speed, 64-bit, dynamically configurable processors -today-.
(As it is, we'll have to wait another 3 or 4 weeks for Transmeta to release theirs.)
Alternatively, we could have seen, for the same cost as developing a new processor, Intel, or one of the other premier chip companies, experiment with preparing silicon or gallium-arsonide in microgravity. A slow-cooled batch, under those conditions, would be near flawless, and allow for some serious clock-speeds. And people -would- buy! I'm sure of it!
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
Wow, news about news about news! Keep flying around the web like this, and it starts to resemble a sick game of Operator!
"Tom's said that Ars' said that ZDNet said that Wired said that PCWorld said that Jane's said that... Corel is buying Amiga? Woo-hoo!"
Seriously-- should Intel be concerned about the Japan market and their 4-aversion? Are they going to call it the Pentium III+?
Yeah, who needs faster CPU's? I use a 4Mhz Z80, and it only takes a week to compile a new Kernel! Why would i want to do anything faster?
Syllable : It's an Operating System
From Intel, analysts expect 800-MHz PIII chips during the second quarter, and the Pentium IV chip, code-named Willamette, by the end of the year. Willamette is expected to handle more simultaneous instructions than the PIII, and to break the 1-GHz barrier. The accompanying chip set will likely support a 200-MHz system bus, like the Athlon's.
I couldn't disagree more with what they write:
"Itanium won't be relevant for PCs until 2003 at the earliest, more likely 2005,"
Especially because their main argument is:
"Software has yet to be written or recompiled to accommodate a 64-bit processor. "
So, they really think that Microsoft will be able to hold back computer progress once again? Last time, there were no alternatives. You would run 16-bit dos, like it or not, but now we have choice and freedom.
If Microsoft doesn't move fast on this one, they'll be losing market shares on the server end of things in no time, and increasingly rapidly on the desktop too.
If they move fast, however, they will have to abandon their huge installed base and start at the same level as anyone else. It would be dangerous position for a company that has never excelled at quality and innovation.
I think 64-bit architectures may very well turn into Bill Gates' Waterloo; and it will all be over before we know it.
I'm always in a bit of shock after I talk with people that are relative newbies (ie, less knowledgable than us folk :) about computers. They'll tell me something like "I got the 12.2 gig RAMs with a 15" drive and 256 of cache. Of course, it's a Pentium III. They're the fastest, you know."
Explaining that the speed increase between a P2 and a P3 is negligible doesn't seem to help any. They just know that they've got to have that "III," they have to have that "MMX" on there.
I wonder how much longer it will continue like this? Remember the rabid VCR market in the late 80s and early 90s? Maybe it was just my young geek mind, but it seemed to me that there was always some new feature, some great reason to upgrade to the next great generation of VCRs.
Where has that gone? In part, DVDs have increased the upgrade crazy, to be certain. But, if we go back a couple of years, you'll notice a laid-back attitude about these simple devices. "Does it record? Good enough." Again, this might just be my perception.
This same pattern has been repeated with radios, telephones, TVs (to some extent), coffeemakers, refrigerators, and just about any other overpriced gadget that you can think of. They become a commodity.
Is the processor industry going to drive itself into commodity status? I assume so. No doub t that you and I will keep right on upgrading and getting the biggest backside cache and fastest motherboard speed that we can. But as computers are reduced to appliance status, consumers won't care about whether it's a P3 or a P4. They'll just want to know if it's "on the e-mail."
Oddly, no mention of the Alpha, which I expect will end up owning the 64 bit arena for the foreseeable future. Why wait 'til 2003 for 64 bit performance when you can get it today? And the alpha today will probably be faster than Intel's deliveries years from now.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
What can the average person expect to see out of this? Not much, that's for sure. Maybe their MP3s will compress a little faster... I've got nothing against speed (a lot of places still need much more of it) but it's something that the Desktop PC market just doesn't have any use for any more of.
What we need now is innovation. Speed could only take us so far, now we need a brilliant flash of insight into making computing different... Better. What's the next step?
Use that speed. Better voice recognition. Artificial Intelligence systems that can figure out the difference between what the user says, and what the user wants. A machine that understands subtleties... a 3D desktop environment. Wireless T1-level access across the nation. WHY ARE WE STILL COMPUTING LIKE WE DID A DECADE AGO?
-----------
"You can't shake the Devil's hand and say you're only kidding."
I think the author of the PCWorld article has Windoze on the brain. When the Merced chips hit the streets you can BET that there will be a Redhat distro for it the same month (if not the same day).
It may be true that you won't be able to get Win200X (Specially built for Pentium IV! Upgrade today!) for quite some time, but the folks that just need to recompile like Linux, or BSD, will be there instantly. Slashdot itself has run the articles on Linux booting off a Merced simulator, and GCC being ported to run as well.
With Transmeta, 1.2 GHz Athalons, and Merceds coming out, next year should be very interesting.
Maybe they're just holding out...
It is going to get really interesting soon even for the people who understand computers better, as we will find that are choices are opening up. How are we, the folks in the "know" going to convey to those not so technically minded what all of this really means? The human mind tends to grasp 5 plus or minus 2 strange things before it starts to overload. There was once a time (1992 or thereabouts) when I could fit advice in the form of:
1) High MHz
2) Intel-based CPU
3) not Packard-Bell
4) high RAM
5) more hard-drive space is good
6) get CD-Rom
7) latest version of DOS/Windows
Now there are so many factors to take into account that I almost have to walk my computer-illiterate friends through the process of buying a computer. It doesn't look like this is getting any easier either. In the "old days", the person usually got at least 4 of the above criteria right, and was OK. *Sigh*
As we continue along this path, it is great for optimizing our tools, but we leave the general populace farther and farther behind. If only there WERE an unbiased metric that people could use to diagnose their needs compared to the products offerings... Maybe there is and I am simply not aware of it.
B. Elgin
B. Elgin
"Read at your own risk; feel free to ignore."
Well, gosh guys, no wonder intel chips are slower than AMD chips. They run Roman Numerals for crying out loud. It probably takes a few more clock cycles to add XX, IV, M and then divide by V than to use that pesky binary stuff.
Personally, I am waiting for the Pentium XXVII, which should be a real screamer.
I think perhaps the Pentium V will be called the Pentipentium.
I can't wait for the Dodecipentium. The chip will be fast!
-m@
"...this addition to the PIII design is responsible for supercharging Microsoft Office apps."
For some reason, I had trouble taking the rest of the article seriously after I read this line.
Weblogging Considered Harmful:
>>I think we should start asking computer salesmen to see the SPEC95 ratings of the chips and see what they do. : )
Most likely they'll tell you no. It's the manufacturers job to put out specs and benchmark results, not the salesperson's.
(Yes, I sell and fix computers for a living)
LK
"Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
Same with the segfault.org box...that's less important though, clearly, since the only reason to ever read segfault was for the weirdass trolls in the comments.
--
"HORSE."
"HORSE."
-Flaming Carrot
For immediate release:
The Inhell Pentagram processor, 666 Mhz. Sure it runs hot, but there is no need for cooling (cold day in hell? Ever seen one?)
You have never seen daemons dance so fast.
(Holy water user protection not included.)
Try to hack my 31337 firewall!
The magazine is about Personal computing. Thats why they aren't talking about the Alpha 21364. The G5 has nothing to do with personal computing, and the G4 is already out.
Two banks of memory operating in tandem so that each bank is operating at only 100MHz. Will only give you the performance in burst mode access, but as caches tend to work that way (AIUI), that's not such a bad thing.
Bill - aka taniwha
--
Leave others their otherness. -- Aratak
As a consumer, I just can't WAIT to get my hands on one, Intel. I'm just seething with anxiety over new features. Heaven forbid that they should f00f this one up.
Of course it's all simple mathematics, really. The more Intel rushes things, the more likely AMD will come out ahead.
:-)
Best regards,
SEAL
Intel reminds me of the american car companys during the 60's, They are increasing speed by bumping up the MHZ, kinda like bumping up desplacment, we need to see more efficient "import" processors.
The Pentium was developed because in 1993 we were in the depth of the worst recession since 1980 and engineers had two choices: work their asses off and get some major breakthroughs or join the thousands who were getting laid off. Since we don't have those pressures there's no need to develop anything new. Not until we have another crash like 1993 will there be anything phenomenal.
I believe that what you're referring to is the story that the Japanese words for 4 and 9 sound similar to the Japanese words for "sickness" and "death". Consequently, hospitals in Japan have no rooms with the numbers 4 or 9 in them. I don't know whether this is true, or just an urban legend, but that's the way I heard it.
Not anyone attribute does a good system make. However, the average joe consumer does not realise this. They are caught up in the malestrom of advertising and hoopla. Remember in the EARLY 80's when 300 baud modems were it, floppy disks were literal, and you were DAMN lucky to have color! Programer has very little to work with (looking back). They had to write tight efficient code or not at all. Now any fool can write a bit of code and processor speed makes it all even (on some levels). If MORE people who were writting usable code tighten it up, things would increase on their own. If people would take memory into consideration when writting, etc... I think the "I got a 12 gig HD for my PC" would also deminish. What we would be left with is an industry that would HAVE to make marked improvements. Instead of just jazzing up the existing material.
The wages of sin are unreported and back taxes are hell to pay.
Anything new? You mean new instructions that need more transistors that no one will use anyways? I hope not!
For a start I was a little un-impressed with the article. The news item had me expecting some specific information but the article had few specifics.
Several of the posts here I've read seem to imply that AMD is soon to get the upper hand and that Intel is playing catch up. This is unlikely to be true for the foreseable future, the lead Intel has will stay with us for a while yet regardless of the competition.Here are some of the biggest issues surrounding the market.
Intel Brandname: Many of you will remember that not that many years ago only the total techies like us actualy new who made the processor inside your computer, the brand was the manufacturer, how many of you today know who made the chips in your mobilefone? your pda? your wristwatch? your microwave oven? Intel changed all this with an extensive and heavy duty branding efort (The Intel Inside stickers, the TV adverts and all that). AMD has not got a brand name anything like as big as intel, the general public 'Knows' that Intel is the best even when it isn't.
AMD Will slash Athlon Prices: This is one of the biggest misconceptions about, for a long time AMD has been known for being the cheap option, not because they could design or makes the chips vastly cheaper than Intel but becuase they had to cut costs to compete. This all changed with the Athlon that for the first time put them ahead in the performance stakes, the Athlon price is now in the same bracket as the Intel chips and it can't cut the prices by mutch, the development costs have really cut into their revenue to the point that they have no choice but to compete on a level price playing field. That leaves AMD fighting only on the performance and branding front's and they only have edge in one of those areas.
AMD Has The Performance Advantage: True, but for how long. Many people have said that AMD has now proved they can make better processors and will continue to have the edge. This is not necisarily true, Intel is very large with vast resources. Basicly AMD have cought Intel napping, for far to long Intel has has a clear lead in the field and they have got more than a little complacement. The Intel Brandname will only cary them for so long, Intel knows they will have to fight to regain the performance edge, and Intel knows how to fight. I am reminded of the over quoted Admiral Yamamoto after pearl harbor "We have awakened a sleeping giant and have instilled in him a terrible resolve". And I'm sure you americans will be quick to point out that not eveyone caught napping is the inferior side.
Natalie Portman: Has nothing to do with this issue.
And what OS will run on this machine... You'd have to get rid of all your legacy software, pretty much revamp the linux kernel, etc...
Unless, you switch to either the BeOS or Mach kernel... and then run Linux on top of Mach.... of course as i often say, I am not a programmer so i may be completely wrong.
I'd see no advantage of switching from one fast processor to two slower processors... To two fast processors, yeah it's worth it if my apps care about the second cpu. What do i care about the heatsink on top of the chip? I usually keep the case closed, so it doesn't really matter all that much to me.
Enough with the oxymoronic names already! "Pentium IV"? Please. You'd think that Intel could make it's chip names correspond a little better to chip differences, too. The only significant difference between a PII and a PIII is the (little used) SSE support, whereas you have to shop carefully between PIII releases to make sure you get one of the uber-cache "Coppermine" (disclaimer: no copper included) models that actually can compete with an Athlon.
It's a shame that Pentium IIIs, while invariably poor consumer buys, are still doing well because of marketing. Want a cheap computer? Get a Celeron. Want a fast computer? Get an Athlon, which will outrun any PIII of the same price.
A neighbor of mine got their first computer last Christmas. Maybe my advice got there too late, because their overpriced, unstable Compaq PII system was coupled with a lousy ATI video card and a winmodem. I had the pleasure last month of trying to figure out driver problems with someone's dual PIII, 128MB (or was it 256?) RAM, Voodoo 3 3500, behemoth system... that was having conflicts with his ISA network card.
Granted, there are a lot of CPU-intensive things (Quake 3 - intense!) out there I'd love to have an 800Mhz Athlon for, but those are the exception (Quake 3 - exceptional!) rather than the rule. (Quake 3 rules!)
And even in 3D games, we're getting to the point where the processor won't be the limiting factor anymore. I mean, once you're getting 60fps at 1024x768, do you shoot for 90fps? No, you crank up your resolution, detail, or color depth. And once you do that you're worrying about your video card's fill rate, texture memory, or texture RAM bandwidth, not about your CPU. Hell, with T&L going on new video cards, we're going to be at the point where the AGP bus and human perception are the limiting factors on visual quality, not the CPU. Maybe games like Halo will have ultra-impressive physics and AI to use all those CPU cycles, but I'd like to see it.
Granted, there are always going to be applications (if only Beowulf clusters) where CPU value increases linearly with CPU speed.. but these are niche things compared to the huge consumer market being sold to today.
What I want to see isn't faster CPUs, it's broadband access! I have a K6II on a 10baseT college dorm connection this year, and if I have to trade it for a quad 1.2Ghz Athlon on a 56K modem when I graduate, it's not going to be a good trade. Whoever thought up Intel's "our CPU makes the internet faster!" campaign should be flogged.
AMD Will slash Athlon Prices: This is one of the biggest misconceptions about
The Athlon 600 is retailing for as little as $379 now, about half of what they were at four months ago. Granted, it wasn't in one dramatic price slash, but it's a hell of a drop. AMD has kept the Athlons cheaper and faster than same-Mhz PIIIs forever, and I don't see that changing soon. Maybe Intel will get ahead in the Mhz war, but that won't change the market situation for people not buying the absolute fastest chip.
The marketting division is serious diluting the brand name "Pentium"
Let's look:
"Pentium" -- a decent 5th gen proc.
"Pentium with MMX" -- Should've been Pentium+, it contained important L1 cache enchancements (P166 w/ MMX outperforms plain P200, etc).
"Pentium Pro" -- Why not a new name, like P2? This is a 6th generation code.
"Pentium ][" -- Finally, a proper increase in number. Pretty much the same core, but with cache slower.
"Pentium ]I[" -- Well, there are two kinds of P3. Ones which have KNI, and no other changes. And the P3 which does have KNI, but which also has faster/less L2 cache, and other important tweaks. They rushed the Pentium 3 "name" out the door to get people buying what is essentially the same chip, which not as much as a performance grab as the Pentium w/MMX over the original Pentium. Not to mention serial numbers (oy vey).
Now they have the "Pentium IV".. Does anyone else think it's just wrong to have 5 separate chips based on the same cores when, in the same span in the 1980s, Intel was actually inovating and took us through the 80186 (used on controller boards), the 80286, and the 80386 (with the prototype 486 chips just out the door 10 years ago). It seems that rather than reacting with the inovation they had of the 1980s, they are reacting with the Marketting Dodos who brought us "I was born to web!".
If you'll let me indulge in a little metaphor, Intel is currently roping a nice little noose around its neck, with the word "Marketting" written on it. AMD is currently moving in to kick the chair out from under Intel. Anyone wanna buy some Intel stock?
---
--
Internet Explorer (n): Another bug -- that is, a feature that can't be turned off -- in Windows.
Microsoft has a lot more difficulty, because: (1) They are committed to binary backwards compatibility, and (2) there are a bunch of types that are specified as being 32 bits.
--
Man is most nearly himself when he achieves the seriousness of a child at play.
****Gfx Scrollbar Special case hit!!*****
Let's take a look for a second at Intel's chip names...
8086 -- Intel's first big 16-bit processor
80286 -- Intel's next 16-bit processor - name is known also as 8x286, shortened to the 286 (easier to call it the 286 rather than the 80286)
Pentium -- Intel finally feels that a name's better than a number. Many laugh at the name, but soon the term 586 becomes associated only with AMD.
Pentium Pro -- Again, another attempt to use words to describe power
Pentium II -- A legitimate upgrade to the Pentium in chip architecture (586 to 686) and in the name.
Up to that point, Intel's had a good strategy for naming things. But look at the Pentium III! Ther'es no big change in architecture except for a few instruction extensions, but they upgrade it from II to III! Why? Promotion. No other reason. It's really pathetic.
Pent- means five. It was named for the 586. That was back five years ago, and the name is just too old in technology years. It needs to be changed to something other than the "Pentium IV," but with their last name change from Merced to Itanium, I'm worried what they might come up with!
I'm not convinced that this is likely; Digital has long had some pretty good products, but have lately had an inability to sell their way out of a wet paper bag.
The recently announced Compaq/Samsung venture to put effort back into Alpha may be helpful, if they actually provide powerful product for decent value. It's not clear that they're likely to out-market Intel, which is a critical issue.
This connects doubly to AMD:
I suspect their choice needs to be between third-sourcing Alphas or creating an "IA-64 clone."
The former merely makes them a "me too" vendor; the latter runs the risk of running afoul of Intel patents and/or other "design license" restrictions.
I am at a loss to decide which outcome is more likely.
The common thing is the memory access protocol, which implies very little about there being any other interoperability between Athlon and Alpha.
If you're not part of the solution, you're part of the precipitate.
The AMD 200MHz FSB used on the Athlon is a point-to-point bus. The Intel 133MHz FSB used on the Pentium III is a shared bus. They each have their own advantages and disadvantages. Point-to-point busses are inherently faster, while shared busses enable easy SMP. It's easy to say that "Intel is only now getting around to it [a 200MHz FSB]" but in truth, AMD's bus is not as amenable to a quick SMP solution - where are the multi-processor Athlons? If this supposed 200MHz FSB for the Willamette is a 4-stub shared bus it will be quite an achievement since these are quite tricky to design.
However, as a side benefit of requiring banks to get the bus width, it was possible to use slower (thus cheaper) memory and still get similar performance so long as the memory was accessed sequentially. Other tricks like row pre-select were also used to increase the effective bandwidth of the memory. It was clever tricks that kept the 60-70ns memory useful for so long.
Bill - aka taniwha
--
Leave others their otherness. -- Aratak
If there is a 64 bit AMD CPU, called the K8, why isn't it listed on the AMD website as a product that they sell?
Reality is that There is no such product. "K8" has not been announced. Do a search at the AMD website and you will not find it.
AMD has announced something codenamed "Sledgehammer" but that was announced as a FUTURE PRODUCT.
And as far as the Athlon/Alpha motherboard interoperability, I'll believe it when I see it.
If you're not part of the solution, you're part of the precipitate.
Ah but you forget one thing about dual processing, each of the 800mhz chips are sharing the same bus and clock. Four 800mhz chips are still running at 800mhz they just have four times the Int and FP power than just a single 800mhz chip. Forking over more money for a 1ghz processor would be prudent in many aspects because it's likely the 1ghz processor will have much increased Int and FP capabilities than the older 800mhz. When you have to share the same bus you lose a good deal of speed between the processor and the rest of the system. The actual speed difference between a 450 PII and a 500 PIII is only 50mhz but in actual processing power the PIII is almost twice as powerful.
I'm a loner Dottie, a Rebel.
If SGI is still relying on Intel processors in 2005 I will cry my little eyes out. LONG LIVE MIPS!
I'm a loner Dottie, a Rebel.