Slashdot Mirror
New GHz Competitor In Processor Market Soon
pug23 writes: "CNET has an article about the Samuel 2, [a 1 Ghz-plus] processor which Via plans to begin production on in the first half of next year. More competition in this area can only be a good thing. Apparently they introduced the Samuel 1 (at speeds between 500 and 600 MHz) in June, but have been marketing it primarily in Russia, India, China and Eastern Europe."
You're talking about benchmarks for the current Cyrix III chip, which performs miserably. The reason it performs worse at over 500MHz on FPU intensive apps than a lowly K6 300 is that the Cyrix IIIs FPU is clocked at only half the core speed, so in that light the chip wouldn't do badly at all if the FPU were clocked at the same speed as the rest of the core--its performance is good considering this and the fact that is has no L2 cache whatsoever. If the whole core operated at 1GHz, and it had at least 128k of on-die L2, it would be a great budget chip. But that's not going to happen because of problems with the current FPU reaching high speeds, which is why they need a new design.
But the article makes a significant mistake--its author thinks that this will be a move by VIA/Cyrix into the high-end, making the classic mistake of equating clockspeed with performance. But VIA itself is quoted as saying "Samuel 2 will expand our market, moving into notebooks and information appliances"--not high-end markets. But as a mobile or appliance processor, even a 1GHz Samuel of the current design would do well, even with the FPU clocked only at half speed, considereing that 400-600MHz notebooks are still the lion's share of the notebook market, and the appliance market still uses 180MHz WinChip 2's through low end old Celerons. Not bad for those uses, at all, even a high performance choice for those markets--especially when you consider that laptops don't run at full clock speed unless plugged in or under heavy load, whereas the Cyrix chip can run relatively cool at rated speed. Weird calling a Cyrix chip 'cool', isn't it, considering that you used to be able to fry eggs on the old Cyrix MII.
As for that point made at the start of this thread about "who needs a GHz processor anyway"--considering that the wholesale price of 1 GHz Athlon Thunderbirds was just dropped, and will probably drop again within a month or 2, it'll only be a few months before a 1GHz Athlon can be bought for about $500 or less. Then, when we can afford them and get them, we'll realize how useful it is to have that kind of power to encode MPEG-2 video in real time with a cheap capture card at the same quality it usually costs to have special high-end hardware cards for, how nice it is to make MP3s quickly, and how great it is to playback MP3 files while doing heavy work without having the processor overtaxed enough to distort the playback. That much power may seem like too much to need for everyday stuff, but once you get that much power I bet your everyday habits might just change to accomodate your new abilities. I know mine changed when I moved from 100MHz 486 to a 400MHz K6-2, and I bet they'll change again when I get the cash to fly the Thunderbird. Even if all you'll ever use it for is turning on all the eye candy in Enlightenment or whatever you like to use, without a big performance hit, you can't complain that prices are dropping so steadily that a consumer will soon be able to afford a 1GHz machine--price cuts are good, period.
"The more corrupt the state, the more numerous the laws."--Tacitus, *The Annals*
The big architectural break was between the Pentium and the Pentium Pro, remember. That's when mass-market CPUs started looking like supercomputers inside, with serious superscalar architecture. The PII, PIII, and their low-end friends are all basically Pentium Pro derivatives. (The AMD chips are quite different.)
Designing one of those superscalar beasts is a big job. It took Intel upwards of 1000 people to get the Pentium Pro design to first silicon. But recycling some old design in a modern fab is easy. Maybe that's what Cyrix did. There's nothing fundamentally wrong with this; those superscalar engines are power hogs and take a big die, because there's a lot of stuff in there all going at once. It may turn out this is a reasonable way to make midrange CPUs. And it gets them that all-important "1GHz" label.
Regarding more high-speed CPU production, the poster wrote, "More competition in this area can only be a good thing." Is it really? Yes, competition drives down prices, which I like. But sometimes I wonder... What would happen if CPU speed progressive much slower than it does today, and the speed increases had to be accomplished via more sophisticated programming? What if hardware change was slow enough, that developers had to finesse every last bit of performance from the machine? Consider the lowly video-game console. The first gen. of games on those things are interesting, and look decent. By the third or fourth gen. of games, you might think someone secretly upgraded your console. Instead, locked into an unchanging hardware profile, developers learned sweet-nothings to whisper into the console's ears, in order to coax out greater performance. And, without losing system stability (maybe even increasing it?) If nothing else, might we have more stable OS's and apps that crash less? The time I would save from a rock-solid system would probably be greater than that from tripling the system speed.
ShoutingMan.com
In and effort to instill proper family values amonth the computer-using community, the Christian Family Coalition, in an unprecedented foray into high-technology and inter-faith healing has announced a complete line of CPUs for the home user. Here's some features of the upcoming processors in the series:
* Moses: Has only 10 opcodes, burned directly into the silicon using patented "Finger of God" lasing technique.
* David: All web content appears as though run through www.askjesus.com.
* Maccabee: No irrational number mathematics permitted. No division by zero and no infinite loops. You must take all results on Faith.
* Joshua: Linux runs fine on this chip, but BSD will definitely NOT. Something about an inappropriate logo...
* Aaron: Any LONG pointers are immediately truncated. Pointers of unauthorized programs are set to null.
* Solomon: You can just FORGET running SATAN to scan your networks.
* Ruth: Children's games featuring the Telle-Tubbies crash inexplicably.
A new, 64-bit series of CPUs has also been announced. Features are unclear, but twelve distinct processors have been listed.
* Peter: Rock-solid performance. Water cooled.
* Thomas: The availability of this chip is somewhat doubtful.
* Judas: Special purpose hardware for network 'honeypot' machines. New, silver-based transistors.
* James I, James II, Matthew, Mark, Andrew and the rest are noted are general purpose and peripheral control processors at this time.
It's a consipiracy I tell you.
-- What you do today will cost you a day of your life.
This looks like the Cyrix Jalapeno (Which I thought was cancelled...)
Still, by the time this hits mass production it will be incredibly out of date. Standard for the recent Cyrix processors (Ironic really, because back in the 486 days they were bigger than AMD).
It seems obvious that VIA is going after the "low cost market", but it seems that they are doing it in an unusual market... Perhaps to appease Intel so they can keep compatiblites with their Motherboard chipsets?
In any case, if it works out, it could create a brand loalty in those areas, after all, with the amount that Intel chips are overpriced, a "discount" chip like this could really bring computers in a ubiquidous fashion to all these areas. VIA sure seems to think so. They look to be going for volume in a new market. I hope that they can pull it off.
I would say that the odds are good though, with a weak FPU I cannot see the chip gaining any popularity in Western Europe, Taiwan or North America.
Still, never mind anything else, competition is a good thing!
Try to hack my 31337 firewall!
While these new CPU's may not have the horsepower to compete head to head against AMD or Intel's best in a pure CPU comparison, they could certainly take advantage of the fact that Via is probably the premier mobo chipset manufacturer right now.
You could get some amazingly small form factor, power machines if they smash their mobo chipset, the CPU, and say a graphics chip into one big "Slot-1"-sized unit.
Maybe they could out make the guts of a machine to out-"cube" Apple, if it's really as low power as the article makes it sound.
The US government maintains export controls on any processor with a performance of greater than 2 gigaflops, making it slightly difficult for some high tech companies and government agencies in India, China, and Russia to purchase high end Intel chips. By being a Taiwanese company, Via can potentially grab a huge, rapidly growing market from Intel and AMD, which may have legal difficulties selling chips from even their non-US chip fabs to these countries.
Arun
We can't be blinded by the fact that these are GHz chips. Who knows how good of a processor they are? When the WinChips came along, they tried to say that they would be able to create a cheap, competitive chip by just reving upthe speed and not adding any of the 'fancy' aspects of the other, high-end, processors from AMD and Intel (they offered a barebones processor, we're not talking about just no MMX or 3D-Now! or whatever).
How good are these processors, and are they just trying to win us over with large numbers?
And just as a side note: I couldn't help but read about where they've released their chips already and be reminded about the '16 processor hardware solution' for seti@home that appeared on /. earlier. . .
Signal 11 is an error.
This is a WinChip made by the Centaur design team. All Cyrix employees have left VIA. Cyrix III is __NOT__ a Cyrix design, but a Winchip. The original Cyrix III was to be Joshua but the yields were too low, so instead VIA substitued the WindChip design, which sucks worse than Joshua did. The head of the Centaur team said that he'd have a 1.2 GHz chip by using an 18 stage pipe. Unless he has extremely good branch prediction, an 18 stage pipe is mainly idle on an x86 since in x86 there's a jump every 3-4 instructions, which causes a pipe flush if mispredicted. I expect this CPU will suck big-time, perhaps even to the extent people will realize that MHz is not performance (although the PR rating Cyrix used wasn't either at the end of its life).
Jobs' presentation provided a Photoshop (TM) shootout between a dual-processor 500 MHz Power Mac G4 and a single processor 1 GHz Pentium. As expected, the PowerPC finished the test in about half the time it took the PC.
That's because the test was, as expected, rigged. That is, it only used a certain set of filters which happen to run faster on PPC than on x86. It would be quite easy to pick a different set of filters and "show" that the PIII is faster than the G4 clock-for-clock on Photoshop. (Not to mention the fact that Photoshop is perhaps the only mainstream program better optimized for the Mac than the PC.)
A fairer Photoshop benchmark (and using Photoshop as your sole benchmark is pretty shortsighted, to say the least) is PSBench, which runs not 3 specially selected filters like Steve did, but a full 21. The results? A 500 MHz G4 is a bit slower than an 800 MHz P3. A dual 500 MHz G4 is probably not much faster than a 1 GHz P3, and certainly no faster than a (cheaper) dual 800 MHz P3.
For a rather exhaustive look at G4 vs. x86 benchmarks, try here. The upshot? A G4 500 is maybe as fast in raw integer and FPU speed as...a PIII 400. That is to say, the G3 was about equal with the PII clock-for-clock; however, the Coppermine PIII's have since added some stuff which the G3/G4 can't match--namely, a much faster L2 cache and 133 MHz FSB.
Where the G4 really shines, of course, is in those programs which can take advantage of AltiVec--and indeed, those are about the only benchmarks you'll find on that page. (You won't, however, find any gaming benchmarks, because the Mac would of course be "unfairly" limited by its lack of good graphics cards.) In raw SIMD-plus-FPU, a 500 MHz G4 performs about as well as...well, it depends, but a fair guesstimate would be a PIII 750 or an Athlon 650. If you look at the page, you'll find that the Mac wins quite a few benchmarks, and that one or both of the x86 chips wins most of them, and that the margins of victory vary widely.
Suffice it to say, though, that even if you do run Photoshop all day, the performance of Apple's hardware is not a good reason to buy a Mac. With the exception of Seti@Home and RC5 (but not OGR!), there is a significantly cheaper PC which will run any program faster. This isn't to say there aren't other good reasons to buy Macs. But when one platform's top chips double in speed in a year, and the other's only go up by 50 MHz, you can bet that the first platform is going to be faster.
Jobs' presentation provided a Photoshop (TM) shootout between a dual-processor 500 MHz Power Mac G4 and a single processor 1 GHz Pentium. As expected, the PowerPC finished the test in about half the time it took the PC. I haven't had an Apple since //e. With Power Mac's current performance and the 'coolness' of OS X, I really might get a new toy soon. However, I recently browsed a Goodwill ComputerWorks store for the heck of it and found it to mainly be a graveyard of Apples (original Macs $3).
The site of the eventual fate of most Macs was scary, but I just don't see a dual-processor 500 MHz Power Mac G4 being out-dated any time soon (?).
even if they manage to release an 1 GHz chip, it's probably gonna be PR-1000 aka "equivalent to a 1 Ghz Pentium III" Of course, benchmarks will show it to be a bit little slower than a PIII in integer performance and more like a 500 mhz celeron in float point perf.
Zetetic
Seeking; proceeding by inquiry.
Elench
A specious but fallacious argument; a sophism.