Tom's Hardware End of Year CPU Roundup

Wister285 writes "Tom's Hardware has just posted one of their now famous CPU comparisons. Aside from looking at all of the nice graphs, they also compare the speeds of overclocked processors with their factory rated counterparts. It looks like the AMD chips just don't overclock as well as the Intel ones do, but when run at their specified level AMD almost always has the best price/performance ratio. Hopefully the upcoming year will be as promising in the processor sector as 2003 was!"

Comments

where's the G5 comparisons?

[The Lynxpro]

Sure, a Mac is a Mac but there should be a G5 performance comparison with there. After all, not too many Tom's Hardware readers have Itaniums in their home PCs. And with the PowerPC970 (G5) climbing to 3Ghz by March 2004, it should really be included in the article.

If at the very least, they could do speed comparisons on the AMD64, the P4, and the G5 all running various Linux distributions to make it fair. (I'm heavily assuming the Yellow Dog distribution supports the G5)...

Overclocking reviews

[CTho9305]

Overclockability reviews are pointless for a couple of reasons. The first, of course, is that there are never any guarantees - not every one of the famed 300MHz celerons would run at 450MHz, and just because the few samples a reviewer tests overclock well (or poorly) does not mean that all chips will be similar.

The other major problem is that review parts are often hand-picked, nullifying their value as indicators of overclockability completely.

Overclocking

[Anonymous Coward]

I have figured out the hidden jumper on the G5 motherboard to allow me to overclock the G%. Here is a snapshot of my cpuinfo from Linux running on it.

james@g5linux -> uname -s -r -m -p
Linux 2.6.0-65 PPC G5

james@g5linux:~> cat /proc/cpuinfo
processor : 0
vendor_id : IBM
cpu family : 6
model : 6
model name : PPC 970 (G5)
stepping : 2
cpu MHz : 2315.13
cache size : 2048 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 1
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 mmx fxsr sse syscall mmxext 3dnowext 3dnow altivec
bogomips : 12473.98

That's one way of thinking of it

[TubeSteak]

But don't forget that you pay a premium for the pleasure of using Intel procs. $220 for an AMD64 3000+ w/512k of L2 vs $270 for a P4 3GHz 800MHz FSB w/HT (both oem from newegg). I realize that isn't quite apples to apples, but you get the idea. If Intel uprated their lower end CPUs, they could offer lower price w/out compromising performance. Wait a second... isn't that AMD's game?

I think maybe they're keeping things as is to maintain a foothold in the enthusiast market.
After all, who doesn't like somethin' for nothin?

Re:you fail it dikky

[Hoser McMoose]

The "thermal problems" with the AMD Athlons is a PERFECT example of why you should NOT read Tom's Hardware Guide! At the very least do not take the articles read at face value without verifying the facts first!

1.) Their P4 was shown to run at a constant 29C. Thermal throttling on the P4 doesn't even start until ~65 or 70C. If the chips were running at 29C, they wouldn't be throttling at all.

2.) The P4 can throttle down to an absolute minimum of 1/8th of it's clock speed, though it's set to 30-50% by default (factory setting) according to Intel's thermal design guidelines. At 30% of it's clock speed, a P4 will still consume easily 20-30W of power, which is WAY more than you can disapate with no heatsink. Yanking the heatsink off a P4 WILL cause it to crash in a very short period of time.

3.) The comment that was made that AMD's thermal sensor could only react to 1C/sec temperature changes was absolutely ridiculous and CLEARLY showed that the author was completely clueless! Such terrible performance couldn't be accomplished by incompetance along, you would really have to TRY and make it that bad!

The whole deal about the instabililties of the PIII 1.13GHz wasn't so much technically incorrect for the simple reason that there was next to no technical info provided, it was almost all just self-congradulation.

I DO judge the articles by themselves, and the articles on Tom's site generally leave a LOT to be desired. The article linked from this story seems to be mostly fluff with a few benchmarks requiring the standard (ie very large) grain of salt.

the fastest solution RIGHT NOW?

[x102output]

so what exactly then is the fastest solution? they dont exactly specify that at the end of the review. i've got some x-mas money to spend, and I'm not sure weather I should buy a AMD 64-bit chip (to prepare for the onslaught of 64-bit software) or to buy the latest p4 chip? I'm looking for the fastest solution and a solution that will carry me the longest time (at least a year and a half)

Re:the fastest solution RIGHT NOW?

[Loki_1929]

" so what exactly then is the fastest solution?"

If you have infinite money to spend? Go with an AthlonFX-51. It's the single fastest solution available, but it's at a premium price. The boards are around $200, and 1GB of memory will cost you around $350 because you have to buy Registered ECC memory. The upside of all this is that you're buying components rated for server operation, so you're looking at very high stability. I just built a $4300 computer system for a customer based on the FX-51. I was expecting some problems here and there because it's all such brand new technology, but was pleasantly surprised at the unbelievable stability. Word to the wise: if you're going high end on everything else, go with a high end power supply. A True Power 380 or 430 from Antec is a smart choice. For reference, I went with an Asus SK8N for the mainboard in this case. Also, make sure you get the recommended memory from Asus (listed at the bottom of their website's page for the board). It'll cost you more money, but it's worth it to not have to worry about stability.

If you don't want to spend quite that much, an Athlon64 3200+ is also a good value. Intel has confirmed, accidentally, that it's got a 64-bit desktop CPU in the works in case the AMD64 platform takes off, so you can bet your bottom dollar that we'll probably see a bunch of 64-bit applications available in the next year and a half.

Dollar per megahertz (overclocked)

[SharpFang]

What I would like to see - "If I'm going to overclock, which one pays better"?

First they give overclocking capablities and then non-overclocked price/performance ratio.
We know Intel CPUs are overclockable better but more expensive than AMD.
So, say, I can buy a 2GHZ AMD and overclock it by 300MHZ, getting 2.3GHZ. For the same money I can get a slower Intel and overclock it more. Now, if it was that I can get i.e. 1.7GHZ Inter and overclock it by 600MHZ, it would mean the CPUs are pretty much equivalent for me. Means - about the same price per megahertz overclocked. But if I can buy P4 1.6G overclockable by 500MHZ, giving total 2.1GHZ, it just pays better to buy the AMD.

Re:Overclocking a Z80

[carndearg]

Has anybody overclocked a Z-80?

In a word: yes!
When I was a young and foolish electronic engineering student I and my friends did just that and partially ruined an otherwise perfectly sound rubber keyboard Sinclair Spectrum. I can not remember the exact details but it was not a succesful project. IIRC we tried feeding the system clock line from a squarewave of our own making and tried to run some timer code in an EPROM to flash an LED on an i/o port. My guess is that the Sinclair support chips (and possibly even the NEC Z80 chip our spectrum used) were like AMD processors: just about able to work at their rated frequency, not higher.

I've not looked at a z80 since then but a quick Google search finds that the instruction set has not faded away, here are just two offerings claimed to be Z80 compatable.
http://www.rabbitsemiconductor.com/products/Microp rocessors/
http://www.ab-semicon.com/datasheets/181e-20.pdf

I've not tried tandooring a haggis yet, you've given me ideas.

Re:Stability?

[Loki_1929]

I would tend to look elsewhere for the stability issues you're seeing. While no product is ever 100% perfect by any stretch of the imagination, the AMD chips, in my experience, don't have any more problems than Intel chips since the Athlons. If you could tell me which configurations you've had problems with, then perhaps I could shed some light on where things are going awry.

Generally speaking, I find that using a name-brand power supply, such as Antec, with a Gigabyte or Asus mainboard, and crucial memory solves virtually all stability issues. You can actually put together a pretty nice system for around $450 - $500 using high quality components. The problem with buying a system that's pre-built is that you have no idea who's making the parts. For the cheaper pre-built systems, it's often an ECS (aka PC Chips) board with generic RAM and a generic power supply. It may work well for a while, but you'll invariably run into problems. Personally, when it comes to servers, I want something that I can just build then sit in a customer's office for a few years without any necessary maintenance. I've had success with both AMD and Intel in this area, and I'm now leaning much more towards the AMDs now that the Athlon64s and Opterons are available.

I may actually have a customer who'll put out the money for a really nice dual Opteron system. I'm very much looking forward to building that, as it'll be sitting on a freshly-built gigabit network when it's completed.

Blahh

[LittleLebowskiUrbanA]

I just upgraded (MSI motherboard died) from an Athlon 1.33 to an Athlon XP 2600+ (1.92.ghz). Can't tell much of a difference. Seems kind of depressing but then I remind myself that w/ negligible difference between last year's and this year's processors, we can all afford to wait for the 5ghz 64bit processors of our dreams.

Re:Conclusion

[Monkelectric]

Toms hardware is pretty weird. Three or for years ago now they were looking for reviewers and I applied. They "offered" me a "job" reviewing hardware based on experience and a writing sample. They said I'd have hard deadlines, not much time and the "job" would require alot of dedication the odd thing was there was -- no pay, no freebies, (I still might have done it to get my name on a few articles), but the killer was I had to *pick up* the hardware, they wouldn't even ship it to me (their office was 200 miles one way from me).

That should give you some kind of idea what kind of crud their reviewers are willing to put up with for no good reason.

AMD x86-64 with non-Microsoft OSes?

[RallyDriver]

I'm surprised no-one else is bringing this up ....

The review takes pains to point out that AMD-64 binaries are as rare as hens teeth, and for the reviewer's primary audience who are gamers on Windows, and who have to run whatever P4-optimised or Athlon-optimised binaries the games vendors supply, that's pretty much true.

However, for many readers of this august forum, things are a bit more flexible - the only app I run at home that works the CPUs at all hard is digital video processing (transcode / mplayer / mpegenc on Linux), all the binaries for which are of course built from source, thus could potentially be 64-bit if one had AMD-64 hardware and suitable compilers.

Likewise, for the scientific community using Beowulf clusters, who generally run home grown code, this surely has a lot of potential.

Can someone post a summary of the state of the art in terms of AMD-64 binary output from gcc/egcs, and some info on how well it runs with CPU-intensive number crunching like this?

Professionally speaking, all our stuff at work is Java based, and we are looking for price/performance and space/performance ratios - our latest batch of servers (1U pizza boxes with desktop 2 CPU chipsets are the best price/perf compromise) have dual P4's because of the better memory bandwidth of the i7500 dual channel setup compared the dual Athlon chipsets which were stuck at single DDR-266 for the longest time, but if there was a byte compiler which targeted AMD-64 I could see potential for really nice price/performance with the Socket 940 systems, and even just using 32-bit code the higher memory bandwidth would help a lot with Java apps.

I used to overclock

[io333]

I used to overclock, but I don't anymore. It mattered when a medium speed CPU was barely affordable, and then I could ramp it up to being a fast CPU by OCing. And then when CPUs starting getting cheap it turned into a hobby, and I'd buy a new CPU not because I needed extra speed, but because I just wanted to see what I could pull off. I had MEGAHUGE fans all over the place and finally graduated to water cooling. I was even starting to think about cryo stuff. Then one day a year or two ago I bought an XP2000+ for $65 shipped. I even clocked it up for a few days, but it was so fast at stock speed I just couldn't tell a lick of difference. Stuff happened either instantly, or instantly. The only delays on my system, were non-CPU related. Now today, for practically no money at all, I can have a rediculously fast CPU, or a rediculously fast CPU, depending on whether or not I want to try to clock it. So I don't bother.