Slashdot Mirror
Intel Reveals Next-Gen CPUs
EconolineCrush writes "Intel has revealed its next generation CPU architecture at the Intel Developer Forum. The new architecture will be shared by 'Conroe' desktop, 'Merom' mobile, and 'Woodcrest' server processors, all of which were demoed by Intel CEO Paul Otellini. Rather than chasing clock speeds, Intel is focusing on lowering power consumption with its new architecture. Otellini claimed that Conroe will offer five times the performance per watt of the company's current desktop chips. He also ran the entire keynote presentation on a Merom laptop, and demoed Conroe on a system running Linux."
Rather than chasing clock speeds, Intel is focusing on lowering power consumption with its new architecture.
Exactly what we've all been waiting for. Is Intel Good(tm) now?
The Digital Couture Collection
Ok, Conroe appears to be a lake in Texas, Merom is a bluff near the Wabash river in Indiana...where/what was the inspiration for Woodcrest?
So instead of clock speed how about execution speed of standard benchmarks on a reference machine? Or would that show how much they suck per dollar next to AMD?
Does anybody know what instruction set these three new processors implement? The article states that these are 64-bit CPUs, but doesn't say whether they feature the AMD64 or the Itanium instruction set.
John Sauter (J_Sauter@Empire.Net)
So its the revamped P3 once again. I'm glad they optimized it for power instead of marketing, but will it scale to higher clockspeeds? Will it be able to reach 3 Ghz in the next 2 years?
Fundamentally, most markets of any age undergo specialization, niches form, and those most fitted to the niches, do best. But having a unified architecture between server / laptop / desktop flies in the face of that; it either claims there is no niche market anywhere, or that there is a "killer chip" which fits all niches better than anything else.
Now, I can guess what Intel would choose of those options, but is there something about the chip industry that makes it immune to this specialization idea? What am I missing?
In Soviet Russia, us are belong to all your base.
That's been a common thread in mobile technology for a long time. It's a lot more difficult to optimise the same chemicals to store more energy in a smaller container than it has been to build smaller and smaller computing components.
As a matter of fact - reading around a little bit will show that basically mobile device design is driven around the battery. We could go much smaller, much faster, and generally far niftier with our devices if we didn't have to strap a car battery to it.
I feel good about the choice that Steve made but I don't think he capitalized on the announcement.
Here's hoping that the new architecture is not just a M$, Linux thing.
I'd really like to have a low-power multi-core 64 bit chip blazing away in my next iMac.
MSBPodcast.com The opinions expressed here are my own. If you don't like 'em... Think up your own stuff.
The screenshots make it look like Intel isn't including HT with this next gen core. Is that because it's likely the pipeline is shorter? I thought it would be uber-cool to have a dual-core CPU with HT for some awesome synthetic 4-core action. But, I guess the real question is: Should I care about HT anymore?
Incidentally, I did RTFA...
Sometimes the thought process goes well beyond what's in black in white.
"Simplify, simplify, simplify!" Thoreau
Yes, but you with the size of games today, you won't have enough time to actually load Level 3 before your battery runs out.
I bet hard disks and Cd-roms are sucking down a lot of power today compared to teh CPU. The new solid-state storage ideas look cool in helping with that.
The problem is that the physics for how to increase the number of transistors on a chunk of silicon is very well understood and the physics of how to make better batteries is not.
To double the number of transistors on a processor is primarily a matter of lithography, that is etchich smaller and smaller lines into an existing wafer. Same materials, more or less, and same technique, more or less. With batteries, it's far more hit and miss.
The technology and fabrication process to make a lead-acid battery is vastly different than NiCd. NiMh is somewhat similar to NiCd, but then Lithium Ion is rather different and requires a lot more technology to make it work. Then you've got fuel cells as a possibility, and that's vastly different from anything I just described.
There's a lot of effort being put into battery research because everybody understands what a fundamental limitiation it is to everybody's dreams of pervasive wireless. It's rather ironic to describe these internet coffee shops as having "wireless" when you still have to have A/C power to do anything. The problem is that it does not have the clear and obvious path that CPU's have had.
I expect that fuel cells will eventually be the way to go. Still there's a certain inconvenience in them. If I want to charge my laptop batteries, i just plug in my laptop. If I've got a fuel cell, do I have to buy numerous cells? Do I have to fill them up with methanol, etc? It doesn't seem like there's a panacea for portable power (and other p words) anytime soon.
This sig has been temporarily disconnected or is no longer in service
'Conroe', 'Merom', and 'Woodcrest'. Hmmfph!
Enough with the name game, where's my Moore's Law mandated doubling of CPU speed every 18 months!
And flying cars, dammit they're due too. I want my flying car running on my 12Ghz "Zoomy" processor.
I have to wonder if Intel basically ditching the last 5 years of CPU development in favor of their Israeli skunkworks ranks at or above the famous Microsoft IE U-turn?
I mean, Intel sold millions and spent billions on Netbu(r|)st, and hit the wall far before the 5+ghz figures bandied about back in the day. This is basically ctrl-alt-del on a large part of their roadmap, though I'm sure they'll still be selling 'traditional' P4s for awhile.
If the current laptops could run for 20+ hours on the current batteries, this will be a non-issue. It will be even less of a non-issue when laptops can run off solar power.
OTOH, should batteries change, you have a whole lot of electrical/chemical issues that come with high amperage, including temperatures high enough to fry your lap. Of course theres a huge demand for high power batteries in the industry. But batteries have changed little and will change little (NiCD was invented in 1899), while moore's law is still working making chips more powerful (or smaller for the same power) much faster than batteries can change, so the focus remains on the silicon.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
As an aside, there is an argument that, for reasons of safety, you only want to go so far with power density. A fully charged Li-Ion battery already packs a pretty large amount of chemical energy in a small space -- laptops catching fire is fortunately a rare occurence, but not a pleasant one. Go too far with chemical energy density, and essentially everybody is carrying potential bombs around.
In other news this morning, I heard that Intel has just inked a licencing deal with RIM to use their powersaving technology in exchange for RIM getting some technology from Intel.
So, could it be RIM technology instead of Transmeta technology that they use in these new processors?
Maybe I'm missing something, but I don't understand how performance per watt is useful as *the* statistic for comparing processors. Granted, clockspeeds aren't the law of the land, but at least they gave you some idea of how processors stack up against each other. The lines have become fuzzier recently, but I can know with a resonable amount of certaintly that a 3ghz P4 will kick the living daylight out of a 1mhz CPU.
Performance per watt tells a different story. While performance return per unit power consumed may tell how efficient a processor is, it doesn't tell me how good a processor is at doing what I want it to -- crunch numbers, really fast.
Performance per watt is a ratio, so the rating can increase when performance increases or power consumption decreases. Therefore, a solar calculator with a 5mhz processor and (I'm making this up) 0.1 watt power consumption would have a 50 mhz/watt rating, and a 3ghz CPU with a 100 watt consumption would have a rating of 30 mhz/watt. So, now Intel sells both these processors and advertises their performance/watt ratings. When someone goes to buy a new computer, they're surprised to find that the 50 mhz/watt computer is actually slower/worse/crappier than the 30 mhz/watt one.
A rock has infinite performance per power usage. It performs one instruction using no power.
~The log of the limit is equal to the limit of the log.
Most laptops only use ~30W of power, hopefully less as time goes on... This makes portable solar cells an option.
I'm not really sure about wind power... but an interesting idea would be to make a "3-in-one" alternative laptop powerer.
You could have a 30W solar pack, and two small windmill things (maybe with detachable fins for easy carrying). The fans could double as hydro generators if you stick them in a river.
You know... for all those times you're next to a river with your laptop (and there is no wind).
I suppose another idea might be to incorporate solar cells into the case of laptop.
Alternative energy is no solution to the battery problem, but I still think it's a cool idea. With even just solar cells you could easily work outside all day without needing to change batteries.
I don't know how useful this would be indoors, but I could see even indoor lighting generating some power (hey it works for calculators)...
I'd definitely carry around a solar pack even if it only increased my run time by 2 hours, any less and I don't think it'd be worh it. But I'd be pretty stoked about it if I could sit outside (think BEACH) all day with a laptop. How sweet would that be?
Laptop users, as well as people running server farms. If they told some enterprise that they could save a few million bucks on power (which is getting more expensive all the time and wil l never stop), they'd net themselves a big fat sale.
For home users, it's more of a reliability/creature comfort thing. More power means more heat, and 1) nobody likes loud computer fans, or wants to buy a liquid cooling system and 2) heat makes chips fry.
Moore's observation is that the number of transistors per m^2 doubles about every 18 months. This is still happening. What has stopped at least temporarily is the use of this increase in transistor count as a means of increasing CPU throughput. A variety of factors including the fact that RAM access can't keep up, power consumption increases as the cube of clock speed and that increasing pipeline depth to enable higher clock speeds has been taken as far as is practical means that CPU execution speed is currently not increasing as fast as in the past.
Until a means to get around these problems is found by a future Noble Prize winner CPU designers have resorted to putting multiple CPUs on a die. This is great for processes that can be made to run in a parallel fashion (and for programmer employment since this requires more software development), but not so good for linear single threaded applications.
So much for that nonsense about increasing CPU performance
:)
First the OB-peeve: Moore's Law has nothing to do with clock speed or relative performance, only that the number of transistors per unit of area will double every X months (where X lies between 12 and 18, depending on which "version" of his law you use).
Okay, that taken care of...
AMD and Intel hit a barrier "harder" than the mere doubling of transistors... They reached a point where running a PC noticeably increases the electric bill (a typical single-core P4 costs around $1.50 per month to run 24/7 in the Northeastern US, just for the CPU, not counting the graphics card, monitor, hair dryer, or whatever other power-sucking toys you might have attached); and relatedly, that high density of power consumption requires getting rid of a proportional amount of heat.
By dropping the energy requirements by a fifth, you can consequently have five times as many cores for the same heat-dissipating capacity. If each of those pushes a mere half the numerical performance of the single power-hungry core, you still get a net gain of 1.5 units of processing per unit of area.
oh bullshit, if this is flamebait then the original parent poster should also be labelled flamebait.
but there is some mod hellbent on making it seem like transmeta was some cpu long powered god (just look at the flamebaits that are marked in this thread alone) when in fact it's performance was below that of cyrix.
i would post with my name, but seeing as some certain mod is a transmeta fanboy, i don't want points modded away.
I don't see the Pentium M's as hitting any performance wall at all. In fact, if anything, I see them hitting a Watt wall, and being told by the senior execs that they won't release a Pentium M chip that puts out more than 30 Watts, period. Something tells me this is even the reason we haven't seen them in desktops.
As for performance per watt, the Pentium M is more superior than you want to claim. 27 Watts is hard for anything in the desktop world to compare to; the AMD64's are all up in the 50W range (max-out though, average out might be comparable to the Pentium M's max out), Intel's Prescotts max output's over the hundreds.
AMD put a shot across the bow for a dual-core race, and Intel declined it. It'd be funny to see Intel shoot a clock/watt race across AMD's bow, and wait for their decline. We know who's best in what realm, now we're waiting for a head to head race, Pentium 3 verses Athlon style.
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
These new processors are the reason Apple is switching to x86. They're coming out in the 2nd half of 2006, just when Apple said its first x86 machines would be released and they offer improved "performance per watt", i.e. the exact same terms Jobs used when he announced the switch. My guess is that Apple will also be wanting the .5W handtop cpus for its Video iPod and that there will be some video enabled version of Airport Express to go along with it.
the APwC - accumulated performance-per-watt cost.
(performance/watt) / cost
I think that's more relevant.
The best processor would be one that offers the highest performance-per-watt at the lowest price. I have a feeling that the AMD-64s currently hold that crown.
Since dual cores are the quite common these days, we need a measure that can scale even based on the number of processors used to achieve the performance numbers.
So whether it takes 50 transmeta processors or 2 AMD 64s or x Intel processors, at the end of the day, what matters is how much was spent to achieve the same performance. Therefore, we need to take this into account as well.
Find a job you like and you will never work a day in your life.
Quite. Getting Apple on board might be big news in the Apple world, but the rest of the universe doesn't even know what 'Intel Inside' means or why they should care. Now Apple too has been assimilated, all we need is for AMD to go bankrupt and chip development will grind to a halt completely. You can't beat a good, old fashioned, American monopoly!
That was classic intercourse!
ATP isn't an energy storage molecule - it's more like an energy transfer one. Fats are the main long term energy store.
e mical/
IIRC fats do almost as well as Gasoline, which is very good indeed, 30x better than Lithium ion batteries.
http://www.tinaja.com/glib/energfun.pdf
http://hypertextbook.com/physics/matter/energy-ch
My back of the envelope calculation says that we should get 25x the energy density in fat based power source. Which is pretty impressive. Mind you, getting all the energy out of burning fat would be tricky. Plus, it's a nasty idea.
Personally, I like the idea of running laptops on butane or propane - you could buy lighter fuel like pressurised containers from a shop, and burn the contents in some suitable engine - maybe a gas turbine or a Stirling engine connected to a dynamo.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
An FSB exists in all processors. On an AMD64, the FSB is the DDR memory bus directly, not an intermediate bus from processor to memory controller.
i ndex.x?pg=2
LOCK is an outdated instruction. It is used for indivisible memory accesses. This idea went out in 1990. Processors use MESI (or MERSI or MOESI) protocol now, because bus locking is not efficient (nor always even possible) in multi-processor systems.
See link:
http://techreport.com/reviews/2005q2/opteron-x75/
MERSI works by having the two processors watch each other's memory accesses so they can keep their caches coherent, instead of locking.
Also note that the only CPU dedicated memory (outside of the register file) in a multi-processor system is the caches for each processor. So each AMD processor does have a dedicated link to its own caches, the bandwidth to that cache is reserved for that processor. But caches are relatively small, and switching tasks on a single core will flush out the cache about as much as moving to the other core anyway.
So I said processors don't talk to each other. I did oversimplify, but here's the gist of my comments. What good is 20GB/sec between processors? You don't need it to send a MERSI flag to other processors for each 32 bytes line accessed. You would need it to copy vast amounts of data between the processors, if you did that. Like I said, there is no instruction to copy data between processors, you must use memory to get between them.
Intel's effeciency is lower when accessing some areas that are highly contested between processors. But most areas of memory are "Shared", not Modified or Reserved by one processor.
AMD's system is better, but it's really easy to overstate the value of it.
We'll see if Intel goes to a system that allows cache line state signalling faster than the FSB. I would imagine their new chips (which can even use the L1 and L2 caches for one processor when the other is shut down) do this, at least when on the same die.
Putting the GPU on the HT bus would be interesting. It would have the negative side effect of causing the GPU to go through the CPU when it needs to access memory. That is because the memory controller is in the CPU on AMD systems. But it would seem that when accessing VRAM, the HT bus speed could be useful.
http://lkml.org/lkml/2005/8/20/95