AMD and Intel Update CPU Roadmaps

vincecate writes "Recently AMD updated their processor roadmap. It shows their move to 90 nm and has a range of new processors over the next 1.5 years, including dual-core chips. An unofficial AMD roadmap shows speeds and performance increasing. Intel also recently updated their roadmap. Intel does not show anything faster than the current 3.6 Ghz in the next 11 months, including the recently delayed 4 Ghz chip, except to say '3.6 Ghz or greater.' Strangely, some of the recent SPEC benchmark results show the 3.6 Ghz chip to be slower than the 3.4 Ghz chip. One possible explanation for this is that the 3.6 Ghz chips will slow down due to 'thermal throttling' if you are not very careful to keep them cool. So it seems like heat may be the reason Intel's roadmap does now show much improvement."

Comments

Water cooling?

[Cyberax]

Well, why not just make water cooling mandatory for new CPUs, just like Apple did?

Re:Water cooling?

[NoodleSlayer]

This still does not address the massive power consumption problem seen in the P4s, especially the "Prescott" version of the P4s. While heat is a problem, when you're already using +1 lb heatsinks more active cooling is just a temporary fix. Not to mention that Intel, while it can give recomendations it can't ensure that every OEM to produce machines to their specs. I've opened up a number of Dell boxes only to find below-spec power supplies and such.

Prescott in general has had more then its fair share of problems. Prescott is a massive CPU with a 31 stage pipeline, compared to the older P4's 20 and the Athlon XP's 12. I'm not sure off the top of my head how many stages the Athlon 64 has.

All this extra complexity is supposed to make it easier to clock up the processor, and was the same trick Intel used to gain clock speed from the PIII to the P4, so the marketing folks said "Do it again."

Of course the biggest reason why Intel doesn't show many (or any) speed increases is they've scrapped all their future P4/Prescott based designs, even projects that were closed to or already completed because of the problems they have had with Prescott. Intel's plan is to rework their Centrino/Pentium-M core into a desktop chip, but that will take several years.

Re:Water cooling?

[Wytter]

Actually, during a review session with the 3.6GHz LGA775, we experienced so high heat production that we had to use water cooling to ensure that the thermal throttling was not enabled. When using regular air cooling the processor would reach temperatures > 70 degrees during load, and from the results at this load we saw that at some times the processor had to use thermal throttling.

Another disadvantage with this high heat production is that other core components in the computer (such as the mainboard) will be exposed to more heat as well, hence the durability of these components will be lower.

If Intel and AMD continues to approach Itaniums heat production, water-cooling or similiar technologies will become mandatory for high end processors.

Re:Water cooling?

[Rich0]

FYI - I have an Athlon 64 and heat hasn't been a problem at all. I just have the retail processor with the el-cheapo heatsink that it comes with (nothing fancy - just thermal compound and a reasonably-sized sink). I haven't seen it exceed 55C under heavy load. Granted, my case is fairly well-ventilated, but nothing excessive (well, the case was excessive, but I unplugged about half the fans). Oh, did I mention that I overclocked it by about 8% or so?

AMD used to have a high-heat reputation and used to be known for difficult-to-overclock processors. Honestly, I don't think that is nearly as much the case with their newer processors. The Athlon64 seems to run fairly cool, plus it supports frequency scaling when it isn't busy (note - the 55C figure I gave was under heavy load for considerable time - no scaling in effect). Right now, I'm typing on the machine and the CPU is reading 37C - only 1.5C higher than case temperature.

I think AMD is actually passing Intel in this respect. Intel had better watch out if they expect year-long delays - eventually AMD will be releasing 3-4GHz Athlon 64's and they'll be FAR faster than anything Intel currently has...

Re:Water cooling?

[multipart]

Prescott in general has had more then its fair share of problems. Prescott is a massive CPU with a 31 stage pipeline, compared to the older P4's 20 and the Athlon XP's 12. I'm not sure off the top of my head how many stages the Athlon 64 has. All this extra complexity is supposed to make it easier to clock up the processor, and was the same trick Intel used to gain clock speed from the PIII to the P4, so the marketing folks said "Do it again."

That's the problem Intel has right now, really. Marketing seems to say, "Make it sound faster", only looking for good warrior CPUs in the Mega Hertz Wars. IBM/Apple and AMD have not been trying to go for faster clock speeds but instead for faster CPUs.

Such long pipelines as the Prescott line may help achieving higher clock speeds, but 31 stages means that you'll see more pipeline stalls, so your CPU is happily running at higher clock rates, doing nothing. Of course, not all instructions actually have to go through all 31 stages, but still, it's impractical to have so many stages in an architecture when you know that every so-many-but-fewer-than-31 instructions you're going to hit a branch. Not to mention the additional complication for the on-die dependency tracking that you need in out-of-order cores like Prescott.

Of course in-order architectures with full predication ISAs would solve some of the problems with longer pipelines, but I guess we can't say that this other Intel architecture, ia64, is such a great success ;-)

Is the processor clock rate trend coming to an end

[Ckwop]

The clock rate of the CPU went up madly through the 90s but the wind appears to have gone out the sails a little. Is the actual speed of the CPU still climbing but they're doing this without adjusting the clock rate?

Don't really keep up on the hardware these days.. :P

Cheers,

Simon.

Whew

[Anonymous Coward]

An unofficial AMD roadmap shows speeds and performance increasing.

And here I was, afraid that they had decided to not increase speeds and performance. That was close.

Re:Whew

[Ari_Haviv]

unlike Intel...

So I'm screwed?

[reub2000]

I just got an MSI K8N Neo Platnium, which is a socket 754 motherboard. Looks like socket 754 is going no where.

Re:So I'm screwed?

[mondoterrifico]

It has been known for some time that amd was going to go with socket 939, until 2006. The socket 754 will simply move into the budget category, replacing the xp line.
Recent price drops of athlon 64 3000 make socket 754 solutions attractive price wise.

Re:So I'm screwed?

[Mesaeus]

And no worries about heat production either. I just assembled a quiet pc for a customer, containing the Athlon64 3000+. Boy what a cool chip. I used a 80mm 1800 rpm fan instead of the default and still it gets really cool. In fact on the motherboard I used, Asus K8V, there's a Q-Fan technology that lowers the speed of the cpufan according to the temp, and the fan regularly stops completely. And yes, this is by design. When not under load, the cpu temp actually goes UNDER the case temp if you disable Q-Fan and thus let the fan run at its full 1800 RPM (very quiet BTW). On top of that, it's real easy to undervolt the cpu, so you can run it at 2.0 gigahertz (3000+) and lower the voltage from 1.55V to 1.30V, this gives another big bonus in temps. The largest temp I saw while running under full load was 42 degrees celsius, the lowest 32. At the same time Intel has serious problems with heat, AMD seems to have made their coolest chip in years. Anyone else have positive experiences with this ?

Re:So I'm screwed?

[Mesaeus]

Actually, I've managed to stop the fan even under full load (when Cool 'n Quiet doesn't work). The important part is the temperature, and undervolting the cpu can drop the temp quite a bit. The important thing is that the Athlon64 can be made to run REALLY cool, while it is already a cool processor to begin with. So I don't have to use loud fans to cool it, that's why it's so fantastic for "quiet" pc's. I've lost count of the number of people who have asked me for recommendations to lower the noise of their jet-engine-screaming prescott towers.

Is it just me or are people stupid these days?

[Anonymous Coward]

The reason the 3.6GHz processor runs slower than the 3.4GHz processor is because they're different processors, not the same processor running at different clockspeeds. Just look at the die photos (www.chiparchitect.com) and you'll see what I mean. The idea is that the new processor will scale to higher clockspeeds which it, uh, already has. (Just look at the "OC records": nobody got an old Pentium 4 beyond 4GHz with standard HSF cooling - nobody. On the other hand, this is more or less straightforward with the new Pentium 4s.

What I don't understand is why more people aren't building Pentium M desktops.

Re:Is it just me or are people stupid these days?

[kinema]

"What I don't understand is why more people aren't building Pentium M desktops." It's simple. Intel's megaherts myth has finaly come around and bit them in the ass.

Re:Is it just me or are people stupid these days?

[Ianoo]

Being designed for laptops, arent Pentium M chips much more expensive than P4s?

I can't speak for American prices, but over here we can get a 1.7GHz Pentium M for about 190GBP, the same price as a Prescott 3.2GHz. So yes, there is a definite price premium, but no, the difference is not huge, especially since the Pentium M's are very overclockable, or so I've heard.

Also, can you get ATX mobos for them?

Yes

*sigh*

[SinaSa]

As I wait for the skin to grow back on my eyes from this horrible colour scheme, I can consider the information in the story summary.

We're obviously starting to see a convergence between the industrial processor market and the end-user one. I mean three years ago you would get a dual 3.2GHz (1.6 * 2) system to host a medium sized website, and that kind of horsepower is probably still adequate today. So what kind of apps (I mean, apart from Doom 3) do end users need this kind of grunt for? 3GHz? 3.6GHz? 4Ghz?! If Architects could use AutoCAD 2000 on a 950MHz cpu, without complaint, what has changed? Obviously a speed increase is nice, but three or four times that?

Are we going to see a point where the convergence turns to over taking, and end-user CPU's need to be faster than a lot of corporate stuff?

p.s: I'm aware of shit.slashdot.org, no karma whores please.

Re:*sigh*

[sholden]

As I wait for the skin to grow back on my eyes from this horrible colour scheme

Didn't that skin make it hard to see the colour scheme?

But back to the actual topic...

CPU speeds are just stupid for most people. I write code for a living (at the moment anyway) and the 400Mhz "Mobile PII" I'm using at the moment is adequate for that.

I understand that if your job involved compiling Mozilla or X11 a lot then more CPU (and more importantly more and faster RAM) would make you more productive.

I understand that if you are doing computer generated animation or physics modelling or whatever then more grunt would make you more productive.

But for most people, computers were fast enough a long time ago. This 400Mhz laptop is my fastest machine - both home computers are 300Mhz or so. One of them runs Windows XP Pro just fine, runs Office just fine, runs firefox and IE just fine, runs gimp just fine and even does all of those at the same time just fine.

Every time someone asks me for advice on buying a computer, I ask "do you want to play games?", and if the answer is no then my answer is "buy the slowest CPU model they sell and spend any extra money on RAM".

Re:*sigh*

[Okonomiyaki]

Are we going to see a point where the convergence turns to over taking, and end-user CPU's need to be faster than a lot of corporate stuff?

I think we will actually. If I understand your meaning correctly when you say "corporate stuff" I'm thinking web, file, email servers and so on. Like you said, 3 year old machines are fine for most of that stuff now and will continue to be for some time. On the other hand, the end user is going to be requiring more and more power and not just for games or pretty interface animations. Apple and Microsoft have both been talking about the idea of the PC as a digital hub (well, I don't think MS uses that term exactly because it may be a Steve-ism) for a while. As it becomes a hub for more and more devices it's going to need more power. Loading an iPod with songs is trivial. Manipulating digital photos is a bit tougher. Beyond that you get into editing video and burning DVDs. Encoding and Decoding video. Music creation software. Maybe it won't be long before we see easy to use, prosumer quality 3D animation software...

We've seen a lot of things that used to require very expensive, specialized equipment make their way into the consumer space in the past few years. It's not too hard to guess where that trend may go next. One thing is for sure, it will continue to require more and more powerful processors. Not everyone will need all that power every day but when you get back from that European vacation and you want to do something cool with all the video you shot, you'll be glad it's there.

Re:*sigh*

[Wetware]

Well... CPU speed is very important to me. One app I tend to spend a lot of time on is iMovie (run on an Apple machine of course, but IBM seems to be running into the same sort of troubles in its transition to 90nm processor manufacturing that Intel and AMD are experiencing) and I am always frustrated in waiting for each title, effect, transition, etc. to render. I don't think that iMovie is a particularly inefficient application. And home video editing is certainly no longer an obscure application. For those doing such work, every extra bit of speed will help.

Re:Is the processor clock rate trend coming to an

[opk]

I've noticed this. I got a 1GHz Athlon a few years back and it doesn't seem to be much behind the latest Athlons (especially when I count my athlon's overclocked speed). My previous machine was a 100MHz pentium and that seemed to go out of date really quickly.

Are the new processors really much faster?

Re:Is the processor clock rate trend coming to an

[no longer myself]

It's more along the lines that the clock speed was getting faster, but the performance wasn't proportional. Right now I've got a 2GHz Celeron laptop that is much slower at compile than my Athlon 1.47GHz. (Both have a modest 256MB RAM.) So obviously, clock speed isn't everything.

Don't get me wrong... I still love my Laptop! :-)

The important concept to keep in mind is that all these computers are powerful enough to do what I need them to do, so merely making CPU clocks tick at a higher rate isn't going to persuade me to run out and upgrade.

I'm starting to worry

[rokzy]

I have always thought AMD is better than Intel (price/performance, no annoying jingle, no annoying "... inside", no "MHz myth"), but now it seems Intel is getting its arse kicked so much I worry AMD might get too complacent.

Clock speeds seem to have stalled.

[arcade]

More people than me seem to have noticed that clock speeds seems to have stalled. I don't necessarily see this as a bad thing - as computers has grown fast enough for me lately. I'm still content with my 1.3Ghz Duron.

What I personally really, really want to see is cooler CPU's. CPU's that doesn't require a huge fucking fan. CPU's that are content with a heatsink would be nice.

Furthermore, I would love it if Dual configuration became more widespread (and thus cheaper). Personally I would love a multi-CPU machine far more than single-CPU ones.

My personal wishlist:
- 64bit CPUs to become the norm (seems to be happening).
- Cooler CPUs, not requiring fans (seems to be happening, look at the VIA EDEN CPU's)
- Dual/Quad/Multi -CPU configurations becoming the norm in home computers.

I don't care much whether single CPU's grow much faster at the moment, as there doesn't seem to be applications requiering it for regular use. There are of course specialist tasks that require more horsepower, but those are .. specialist tasks.

Re:Clock speeds seem to have stalled.

[10Ghz]

My personal wishlist:
- 64bit CPUs to become the norm (seems to be happening).
- Cooler CPUs, not requiring fans (seems to be happening, look at the VIA EDEN CPU's)
- Dual/Quad/Multi -CPU configurations becoming the norm in home computers.

You can have those, just not at the same time. Via Eden runs fanless. But it's still 32bit! And it doesn't run in SMP-configurations (yet. there has been some info about SMP-solutions).

I think you could buy an Opteron 2xx-machine, underclock it to around 1GHz so it might run fanless. Then you would have your fanless 64bit SMP-machine,

Re:Clock speeds seem to have stalled.

[Tim C]

There are of course specialist tasks that require more horsepower, but those are .. specialist tasks.

Once upon a time, viewing images was a specialist task. Then, viewing them in full colour, then editnig them. Sound used to be a specialist task, then editing sound.

Now, things like video encoding/editing is a specialist task, requiring (relatively) serious amounts of horsepower.

Well, once that sort of horsepower becomes commonplace, the task stops being specialist, as more and more people do it simply because they can.

True, there will always be truly specialist tasks that never become mainstream (animation and rendering work, phsically simulation and similar number crunching), but there is stuff now that could most certainly benefit from more CPU power (whether it be from single- or multi-cored machines) that would become more mainstream when that power became affordable.

Apple's premiums can handle the extra cost...

[michaeldot]

...but maybe the cheaper PCs cannot?

Also, a liquid cooler is probably inherent harder for Intel to package with an OEM processor. Affixing a liquid cooler to a processor requires more case aware design than simply clipping a fan to a mainboard socket.

Opteron, Linux 2.6 and Java 5 benchmark

[gregluck]

Last week I benchmarked the 2.2Ghz Opteron on 64 bit Linux 2.6 and Java. I got almost three times the performance of a 3Ghz Xeon. For details see http://gregluck.com/blog/space/start/2004-07-29/1# AMD64,_JDK1.5.0_and_Linux_2.6_rock!/

Re:Forget CPU, enter the GPU

[pmjordan]

In addition to this, until we start seeing widespread use of PCIe, the downstream AGP bus is still a serious bottleneck as well. Uploading data to the GPU is really fast, downloading maxes out at ~133MB/s.

I haven't had the chance to play with a Pixel Shader 3.0 card yet, so I don't know how useful for generic computation they are. It usually helps if you're trying to process many sets of the same kind of data, rather than evolving one calculation through a long or iterative algorithm.

~phil

Where is the roadmap I want?

[MancDiceman]

Where is the roadmap for low-power consumption chips that can operate either fanless, or with low less cooling gear?

I survived just fine on a PII for several years until recently biting the bullet and getting myself a P4 box in a Shutttle Zen XPC case (relatively quiet). I seriously considered getting myself an EPIA box as my main machine, simply because it would be lower power (therefore cheaper to run), silent and enough umph to use mutt, firefox and ssh into the server kit where the real work is done. The only reason I ended up with a P4 is because a friend had a 3GHz one going very cheap.

I want less power, not more. The idea I should overclock, buy liquid cooling systems and should pay a ridiculous amount so I can play some games? I'm sorry, what planet are you all on?

Re:Is the processor clock rate trend coming to an

[wass]

Speed of light limit has been a known issue for a long time. At 4 GHz, a photon in vacuum will travel about 3 inches between clock cycles. Add in the actual index of refraction of the stripline leads, and it's probably more like 2 inches of travel.

I was talking to my friend about this the other day, and we think that eventually they cannot go that much faster (well, maybe have a SMALL core of the chip that can go faster), and they'll start stacking in parallel instead. Ie, massively hyperthreaded processor cores. So maybe in a few years we'll see 6 GHz chips with 8 or 16 hyperthreaded processors?

We're physicists, though, not engineers, maybe there are some other clever ways to keep pushing the envelope?