“This article is concerned with the technical differences between [x86 and PowerPC] not the market differences,” writes Nicholas Blachford for OS News.
“The x86 family of CPUs began life in 1978 as the 8086, an extension to the 8 bit 8080 CPU. It was a 16bit CISC (Complex instruction Set Computing) processor. In the following year the 8088 was introduced which was used in the original IBM PC. It is this computer which lead to todays PCs which are still compatible with the 8086 instruction set from 1978,” Blachford begins. “The PowerPC family began life with the PowerPC 601 in 1993, the result of a collaboration started in 1991 between Apple, IBM and Motorola. The family was designed to be a low cost RISC (Reduced Instruction Set Computing) CPU, it was based on the existing IBM POWER CPU used in the RS/6000 workstations so it would have an existing software base.”
“x86 has the advantage of a massive market place and the domination of Microsoft. There is plenty of low cost hardware and tons of software to run on it, the same cannot be said for any other CPU architecture. RISC may be technically better but it is held in a niche by market forces which prefer the lower cost and plentiful software for x86. Market forces do not work on technical grounds and rarely chose the best solution. Could that be about to change? There are changes afoot and these could have an unpredictable effect on the market,” Blachford explains.
“Computers are now so fast it’s getting difficult to tell the difference between CPUs even if their clock speeds are a GHz apart. What’s the point of upgrading your computer if you’re not going to notice any difference? How many people really need a computer that’s even over 1GHz? If your computer feels slow at that speed it’s because the OS has not been optimised for responsiveness, it’s not the fault of the CPU – just ask anyone using BeOS or MorphOS. There have of course always been people who can use as much power as they can get their hands on but their numbers are small and getting smaller. Notably Apple’s software division has invested in exactly these sorts of applications,” writes Blachford.
Blachford concludes, “What is going to be a hurdle for x86 systems is heat. x86 CPUs already get hot and require considerable cooling but this is getting worse and eventually it will hit a wall. A report by the publishers of Microprocessor Report indicated that Intel is expected to start hitting the heat wall in 2004. x86 CPUs generate a great deal of heat because they are pushed to give maximum performance but because of their inefficient instruction set this takes a lot of energy. In order to compete with one another AMD and Intel will need to keep upping their clock rates and running their chips at the limit, their chips are going to get hotter and hotter.”
“You may not think heat is important but once you put a number of computers together heat becomes a real problem as does the cost of electricity. The x86’s cost advantage becomes irrelevant when the cooling system costs many times the cost of the computers,” writes Blachford. “RISC CPUs like the 970 are at a distinct advantage here as they give competitive performance at significantly lower power consumption, they don’t need to be pushed to their limit to perform. Once they get a die shrink into the next process generation power consumption for the existing performance will go down. This strategy looks set to continue in the next generation POWER5.”
“The POWER5 (of which there will be a “consumer version” [read: G6]) will include Simultaneous Multi-Threading which effectively doubles the performance of the processor unlike Intel’s Hyper Threading which only boosted the performance by 20% (although this looks set to improve). IBM are also adding hardware acceleration of common functions such as communications and virtual memory acceleration onto the CPU. Despite these the number of transistors is not expected to grow by any significant measure so both manufacturing cost and heat dissipation will go down,” writes Blachford.
There is significant depth and much more to read in the full article here.
Wintel zealots:
Insert your bogus retorts here:
Mac fanboys:
Explain MASSIVE heatsinks on G5.
Which is all very encouraging, and I can’t wait to get my hands on a G5. However, let me tell you a story…
I got into work today an done of my colleagues was trying to get photos from her digital camera onto her Win2K PC and having all sorts of driver problems. She asked for my help so I suggested she try plugging it into the sole Mac in our office, an ageing 233MHz G3 iMac running OSX. Guess what? Yup, the memory card appeared immediately on the desktop and we copied the photos from there. Problem solved, everyone’s happy.
It’s not how fast the hardware or software is, it’s what it enables you to do.
Massive heatsinks? Try again. They are not “massive” in the Power Mac G5. All you need to do is compare a P4 with a G4 or G5 to see the power comsumption differences. x86 is old tech now hitting the wall. Apple Mac is positioned perfectly (no thanks to Motorola) now and will lead “Wintel” for the foreseeable future. In fact, “Wintel” will continue to fall behind.
Edd, that is true. However, Windows 2K was never meant to be a multimedia OS. It’s a workstation OS. XP is better for that, and yes it does recognize my memory card readers and cams.
And speed does matter. The macs at work do what I want it to do, but they are SLOW.
Fred are you blind?!? You have got to be kidding me, those are MASSIVE!!! and explain why the hell it needs 9 fans!?!?
Quit dreamin buddy!
Chomper, the 9 fans are for optimized zoned cooling. They are not the 9 full-size full-power fans that are required to cool a typical 2.5GHz and up PC. I know, the PC I have at work is LOUD and it’s loud all the time. The Mac fans aren’t as loud and they aren’t needed at all times.
chomper’s an a$$
Overall a very good report.
It is interesting to note the author does not give Motorola’s 88000 chip set as part of what was used as a basis for the PowerPC. The reason the PowerPC was capable of adding more functional units (such as AltiVec) was because the internal bus of the PowerPC was based upon the internal bus of the 88000 which was explicitly designed to include a bus which would allow the easy addition of more specific functional units. (Motorola was thinking about adding in a graphics processing unit, among other things, into the CPU in those days.)
I also disagree with the author’s premise that CISC is inherently more power hungry and produces more heat than RISC. The original POWER chip sets came in 5 chip and 7 chip sets. Yes, the CPU was not on one chip. This was primarily due to huge power and heat of the original POWER chip sets. Sure, the POWER chip sets stomped anything from Intel, Sun, Mips, Motorola, HP, or anyone else, but they paid the price in power requirements and heat output.
It took IBM over two additional years to figure out how to make a single chip version. It took another couple of years to figure out how to get the POWER functionality (combined with the 88000 features) into a desktop single chip CPU.
However, my overall impression of the article is that it is fairly accurate and well balanced.
I think it’s going a little far to say that Chomper is an A$$. Now, if you were to say he was a DUMBA$$, then I could go along with that.
I must say, though, I wouldn’t laugh nearly as much were his comments not included. Ignorance is bliss – and very funny!
Chomper:
Until people have got their hands of the merchandise, this is all clearly speculation. However, it would seem to me that the size of the heatsinks is principally to increase the dissipative surface area and hence allow for a reduction in airflow. This would tie in with the use of 9 small, low rev. fans (rather than a couple of whizzing whoppas). The overarching purpose of all this seems to be noise reduction (yay) – which, if the G5 does indeed run at just 35 dbA (normal r.t.), seems to have been achieved.
Cheers.
Brother Mugga
PS: I’m not saying the 970s don’t run hot (they clearly do), but rather that the size of the heatsinks is not commensurate to the temperature of the chips and should not be taken as a direct indication of power dissipation.
Chomper, it uses 9 fans, it doesn’t need them except to keep it quiet… which is the same problem on most x86 computers… of course, you have all sorts of extra crap in a wintel box that isn’t designed to do anything but get in your way when you mistakenly pry open the case.
That said, the heat sinks in the G5 aren’t that big, they are well placed and should be QUIET (which is, honestly, necessary, not an aesthetic issue) while the heatsinks on the new HP P4 desktops that we have here in my office are using 3 fans, all of which are LOUD, and heatsinks that are at least three, and quite possibly four times the size of those in the G5. So who has the real issue here? You, I would presume, since even though those computers are at my company, I have a relatively quiet MDD DP G4 and a PowerBook… ah, the life…
heat is an issue, as anyone with a 12″ PB will tell you, but I know I read somewhere about the heat of the 970 (G5) being less than the high end G4s because of a design correction… now if I could find that link, I’d be really happy…
Does chomper have a job, a life, or anything else? It seems like he/she has too much time on his/her hands.
PC’s are just as guilty of cooling fans. Some PC’s must have a fan attached to the CPU or they will not work not to mention the video card. And I know many PC’s with VERY loud fans. You tell me when a group of PC people banded together like the Mac Fanboys as one seems to call them to complain about something. And they fix it. You just dont get that sense of community from the PC world. It’s too big that it seems cold just like the very people that use them.
why is it mac fanboys always have to attack people if they disagree? I use a Mac at work and favor macs, no problem there. I just hate seeing propaganda.
I agree with some points and glad that some people are willing to have an intelligent convo. Of course there are others who aren’t as bright.
Grow up…
It’s not necessary to speculate on the reason for the fans. Apple has specifically stated that they are meant to keep the computer as quiet as possible, which is why the interior is divided into four compartments and the fans are individually and variably speed-controlled by the system software so no fan spins faster than it has to.
It’s not the number of fans that make the noise, it’s the speed at which they spin.
MJG: “…seems cold, just like the very people that use them.”
Hmmmmmmm – nice and inflamatory (rather ironically, given the topic under discussion).
Well, I’m a PC user (been waiting (about 18 months) for the 970/G5 to appear before switching), and one of the (many) reasons I want to switch is – as you say – to become part of a community, rather than a target consumer group.
Which makes comments like yours (unless tongue in cheek) all the more disappointing.
And *everso* slightly moronic.
Now – in the true spirit of universal geekish brotherhood – why don’t we all just skip off together and render some pictures of rainbows and puppies…
Brother Mugga
Intel Inside – we cost less to run, and keep your house cooler too!
Has it really come to this?
LMAO.
Oh, and BTW, I don’t care how many fans, how big the fans are, or how big the heatsinks are – they’re tucked nicely inside of the best-looking personal computer ever made – my opinion only, but if your arguments are really based on this garbage, then you really have lost the battle…
MacMan: The Intel x86 parts run way hotter than the PPC G5. Not the other way around. x86 is less efficient and requires more power consumption than the PPC G3/G4/G5.
Thermal 101
Large heatsinks have a higher thermal mass meaning they can pull more heat out of the processor and they have a larger surface area which means they can more easily dissipate that heat to the air. If the heatsink has low enough thermal resistance and can run the processor without a fan like the previous generation of iMacs. Even if you still need a fan, you can get away with less airflow which means less noise.
With Apple’s recent experience with the Dual Optical Drive G4 aka “Wind Tunnel” G4, can you blame them for going the extra mile to correct this with the G5? Would you expect anything less of them?
So a large heatsink doesn’t always indicate high power dissipation, however, if it requires a fan from a real wind tunnel it probably does.
So it’s true then… we really ARE all Mac FANboys!
Intel has hit the x86 wall and this will surelly affect the direction Microsoft takes with the next generation of processors. The Mac’s move to a Unix OS is a move that could be copied by Windows should it come to that with the performance of x86’s CISC compaired to the PPC’s RISC CPUs.
[part 1]
Gosh, I’m a big fan of Rashomon — 5(?) views of the same event that only coincide in the tiniest way — but this article catalogs a wild range of fractional truths that add up to some conclusions that seem irrelevant to the audience (at least those who’ve responded here & there). Watch the movie, or better yet, read Pale Fire.
IBM, Intel, AMD, Moto, Transmeta & others are collectively staffed by thousands of incredibly bright, experienced and motivated engineers. They have access to billions of dollars for the incredibly sophisticated facilities to make chips (or hire out to a firm that does). They spend years on their designs. So when they make a tradeoff — deeper pipeline to get a higher clock speed, maybe — those decisions are expert, based on the likely base of clients for the chips, etc. Especially with 64-bit designs springing up, you see different groups in the same company (even, in the same product line!) make different choices and tradeoffs. One group ought to have been fired instead? … and by people with who can’t write 50 words or 5 pages without gross simplifications and errors? Don’t look for 3rd-grade answers to major business decisions. If it were that simple, why would there be such differences?
So what are the drivers of these differences?
Intel gets its $$$ by selling Windows boxes. It’s pushed the high clock speed aggressively, and has had great benchmark numbers for the past 5 years to show for it. To keep going this route will require even more microscopic transistors — and who better than somebody who makes gazillions of high-complexity chips already? In addition to the engineering feats that will require, they are also moving towards more oomph per clock-tick with their Hyper-threading and 64-bit approaches, among others. Windows users who want fast games, responsive databases, etc., have little to fear from the future.
[part 2]
IBM has had a different strategy — servers. Mainframes, ferhevvinsake. Their POWER series was totally unsuitable for the desktop because they made tradeoffs to favor their core needs. Server boxes need to slosh data around, more than calculation speed. And they need ultra-high reliability. So IBM made parts bigger (and therefore, slower & hotter) than a desktop user would care about. (Who cares if they have to re-boot every 10 days? An online vendor who will lose hundreds of customers a month, that’s who!) IBM also has a good business in the embedded space, thanks to the low-power, lower-speed PPC. When you dial down the clock speed, you devote a smaller fraction of the cycle to the transition between on and off, so you lose less energy in heat, and increase efficiency. That’s a big part of why watts per unit of work done rises with clock speed. Part of why I can use a G4 in a laptop with only a faint fan hum.
IBM has had a different strategy — servers. Mainframes, ferhevvinsake. Their POWER series was totally unsuitable for the desktop because they made tradeoffs to favor their core needs. Server boxes need to slosh data around, more than calculation speed. And they need ultra-high reliability. (Who cares if they have to re-boot every 10 days? An online vendor who will P.O. and thereby lose hundreds of customers a month, that’s who!) Part of the reliability equation is that IBM made parts bigger for less random noise (and therefore, slower & hotter).
IBM also has a good business in the embedded space, thanks to the low-power, lower-speed PPC. When you dial down the clock speed, you devote a smaller fraction of the cycle to the transition between on and off, so you lose less energy in heat, and increase efficiency. That’s a big part of why watts per unit of work done rises with clock speed. Part of why I can use a G4 in a laptop with only a faint fan hum. But NOT one of the Seven Virtues; rather, simple engineering.
Desktop users want a windowed interface that they can point’n’click. Software developers (and the relatively few hardware engineers at the PC companies) need mass market tools that work for dozens of different projects. Thanks to modern programming tools, programmers care much more about the quirks of the OS resources (what happens if you close a window while it’s trying to refresh?) than how many registers, etc.