Clarify this for me, please

[Xtrmi]

That was a pretty good review. I hear all this talk about the GPU being so powerful yet some games still get a big boost from the CPU. Its too bad I don't have any of those games installed to see how my CPU performance affects the FPS. I only have rainbow six vegas 2 installed now and I don't notice a whole lot between 2.4 and 3.6. I will look into WIC to see what differences I can dig up. It would also be interesting to look at CPU utilization during game play.

[cegras]

I moved to a E7200 from a s939 AMD 3800 X2 @ 2.7 ghz.

Seriously, except for faster OS and game load times .. I feel no difference at all except in benchmarks.

I should've realized that all the benchmarks people use to test processors with are things I'd never use, like those test suites .. and .. decoding .. and .. winrar ...

[stocius]

I moved to a E7200 from a s939 AMD 3800 X2 @ 2.7 ghz.

Seriously, except for faster OS and game load times .. I feel no difference at all except in benchmarks.

I should've realized that all the benchmarks people use to test processors with are things I'd never use, like those test suites .. and .. decoding .. and .. winrar ...

I've known that since 2000 and boy was it an eye opener for me. Benchmarks are good, do not tell the whole story regarding a person's computer experience.

[Devil's Prophet]

I've known that since 2000 and boy was it an eye opener for me. Benchmarks are good, do not tell the whole story regarding a person's computer experience.

But then again, when at some time someone really needs brutal computing power for doing an encode or archive job, it sure comes in handy.

[Jowy Atreides]

All i can say is that during first c2d hype i also bought conroe e6600 and it sure felt fast in the beginning and some benches during test phase, but once all sw installations were done and lots off background apps were there and running the system started to slow down allot, even my wife started to complain about the speed .... and she questioned why i updated the main rig. old Rig was by that time am2 x2 5600 btw, for the rest same os, mem, psu, gpu etc only board+cpu was shifted

can't say that games are smoother, since i play only older games, but indeed you hear a lot of reviewers talking about this smoothness.

hmm, weird

I have corel painter running with a crazy amount of cell textures (at least 5 GB of files)
my tv app in the background, firefox3, opera9.5, openoffice 3, my mail, limewire, utorrent,
reaper (with about 300mb of audio takes) and steamchat

all programs are open and actually being used and my pc feels as responsive as if nothing was running,
even though my cpu-usage is at 80% steady and has been for a long time

corel painter alone uses crazy resources

check that pc out :/

[gallag]

so when all evidence & reviews say that the phenom is slower than core, people come up with a unprovable victory for amd.

The funny thing is that when Intel wins a bench mark by 10-20% people say that they would not notice it in the real world and it is only a couple of seconds or a few fps but yet these same people can pick up on the milliseconds advantage the imc brings. lol, just lol.

Its the same old sh1t, just a different day.

[Pla123]

That was a pretty good review. I hear all this talk about the GPU being so powerful yet some games still get a big boost from the CPU. Its too bad I don't have any of those games installed to see how my CPU performance affects the FPS. I only have rainbow six vegas 2 installed now and I don't notice a whole lot between 2.4 and 3.6. I will look into WIC to see what differences I can dig up. It would also be interesting to look at CPU utilization during game play.

Some of the newer games use only 2 cores (load was 200-230%: 76% + 32% + 44% + 62%).
Try http://www.webtemp.org/ for logs while playing, but don't install speedfan as it recommends.

[keithlm]

so when all evidence & reviews say that the phenom is slower than core, people come up with a unprovable victory for amd.

The funny thing is that when Intel wins a bench mark by 10-20% people say that they would not notice it in the real world and it is only a couple of seconds or a few fps but yet these same people can pick up on the milliseconds advantage the imc brings. lol, just lol.

Its the same old sh1t, just a different day.

Core is no longer winning all "evidence & reviews" of the benchmarks. You seem to be stuck in LAST YEAR. The Phenom 9850 is actually beating the heck out of the Intel Q6600 and coming closer to the Q9300-Q9450 in performance. Welcome to reality! And that is at STOCK speeds. (Should I mention that people are hitting 3.0Ghz with older 9500 chips and 3.5Ghz with the new chips? Oh... perhaps I'll hold off... I don't want to completely blow your reality away.)

You are SO living in the past. But you are welcome to your biased viewpoint. Luckily we are not FORCED to buy inferior chips based on an old architecture that is already being replaced just because they come out ahead on a few non-relevant benchmarks.

Actually what you see happening is that people are noticing that their AMD machines are running better and they say: "Hey... how come the benchmarks don't show this.. it's obvious to anyone that pays attention." And then they look and try to explain why one company's chips benchmark better but do not actually perform as well as the other company's chips.

But if it makes you feel better you can go on believing that it is just people that prefer one brand exaggerating and making things up. (If it makes your bruised ego feel better... GO FOR IT.)

This is directly related to the fact that many people have ignorantly claimed that "what is good for servers is not always good for the desktop". I'm going to enjoy watching that myth get busted.

[Devil's Prophet]

This is directly related to the fact that many people have ignorantly claimed that "what is good for servers is not always good for the desktop". I'm going to enjoy watching that myth get busted.

You mean something like NCQ?


... OH WAIT

[DeepThought86]

I've known that since 2000 and boy was it an eye opener for me. Benchmarks are good, do not tell the whole story regarding a person's computer experience.

After I went from a Sempron to an X2 @ 2.6 GHz I found the main bottleneck was my hard drive. So I got 6 GB of mem and http://www.superspeed.com/desktop/supercache.php and dedicated about 3GB RAM to disk cache in XP x64 and voila, super responsiveness.

I also noticed with a dual core that sometimes I'd start the Winrar benchmark and forget, and only notice later when Speedfan's temp reading showed high in the taskbar, rather than notice a decrease in responsiveness.

[biohead]

so when all evidence & reviews say that the phenom is slower than core, people come up with a unprovable victory for amd.

The funny thing is that when Intel wins a bench mark by 10-20% people say that they would not notice it in the real world and it is only a couple of seconds or a few fps but yet these same people can pick up on the milliseconds advantage the imc brings. lol, just lol.

Its the same old sh1t, just a different day.

so do you own both platforms?

[Particle]

Ah yes, spinlocks. In my world, we call 'em SyncLocks. That is totally true. No matter how well you try to design a multithreaded system, if it isn't a benchmark then at the very least the work controller will need to synchronize the work unit tables. It's like I was trying to explain a distributed project I was working on one time: I can process this stuff very, very fast on five machines without any delays and minimal memory usage. However, good luck decoding the data into anything meaningful. Real life data has to be in a specific order to be useful. This can't be "promised" if your threads are just running chaotically without synchronization of the work being done. Synthetic benchmark data does not have this requirement. Because of this, gains in my distributed project weren't close to their theoretical potentials.

---

And I do have to agree--the quality of experience on my Phenom is much better than it was on my C2D despite the benchmark discrepencies. Call it BS if you want to, but until you've actually used both platforms enough to experience the difference first hand, your opinion is meaningless.

---

Games are almost always CPU limited. When is the last time you saw a game that couldn't max a single core no matter how high it was clocked? Or alternatively, when is the last time a game didn't manage to max 50% on a dual core or 25% on a quad? I know of no games that fall short of maximizing at least one thread. The bottom line is that games run as fast as they can, and more often than not the GPU is waiting on the CPU instead of the other way around. Better GPUs manage to do more work without the CPU's involvement, but it would take a major architecture overhaul of an entire system (not just the GPU) to completely eliminate the need for the CPU.

I can both tell and feel a large difference between my E6600 at 2.4GHz and 3.6GHz in all Source engine games. Other games are like that as well, but Source really shows off the difference in clock speed.

[accord99]

Core is no longer winning all "evidence & reviews" of the benchmarks. You seem to be stuck in LAST YEAR. The Phenom 9850 is actually beating the heck out of the Intel Q6600

It's not beating the heck out of the Q6600, it's barely competitive.

And then they look and try to explain why one company's chips benchmark better but do not actually perform as well as the other company's chips.

Except where are these applications which the C2D benchmarks better yet the Phenom performs better? If it does and is noticeable, it should be easy enough to measure.

[Devil's Prophet]

Except where are these applications which the C2D benchmarks better yet the Phenom performs better? If it does and is noticeable, it should be easy enough to measure.

Do you accept the fact that not every experience that a user will undergo when using a certain setup is reproducable? Because that is what a lot of users are mentioning here.

Sure, Intel wins in a lot of benchmarks. But those benchmarks only show an incomplete performancechart. A lot of experience depends on things like responsiveness et al, but those things are far less perfectly reproducable, thus rendered useless for benchmarking. A competitor can perform lousy at the typical suite of benchmark, but surprise the common user in the gray area of performance, which is what is discussed here.

So when throwing with the typical benchmarks where Intel supposedly wins, you should know that the betterness of AMD which users are experiencing isn't covered by that typical testsuite of benchmarks, but rather is in that grey zone of performance where objective measurement is more complex and difficult.

This isn't just an excuse to suck at typical benchmarks though, but if several users confirm this theory, I'd like to believe them. Not everyone speaks out of fanboyism. Although there is a social theory that states that a person likes the item he bought more than the item he didn't buy, just because he bought it. But that argument is null and void since most users here have an Intel and an AMD setup. Total objectiveness can never be achieved, but we can presume we're getting close. Or maybe not?

[accord99]

Do you accept the fact that not every experience that a user will undergo when using a certain setup is reproducable? Because that is what a lot of users are mentioning here.

No I don't. Human perception is so unreliable as to be meaningless.

So when throwing with the typical benchmarks where Intel supposedly wins, you should know that the betterness of AMD which users are experiencing isn't covered by that typical testsuite of benchmarks, but rather is in that grey zone of performance where objective measurement is more complex and difficult.

That sounds like alot like the argument of a tube amplifier lovers or expensive speaker cables.

[Devil's Prophet]

No I don't. Human perception is so unreliable as to be meaningless.

Agreed.

But then again: the suite of benchmarks used to put a number on the performance of a processor is in (not only) my opinion not fit to give a complete image of the performance of this processor in its every aspect it can be used. Don't you agree with that?

That sounds like alot like the argument of a tube amplifier lovers or expensive speaker cables.

Also true, but my guess is that speed (although in relative more complex situations) as in repsonsiveness and latencies actually CAN be measured, as opposed to the "quality" of sound or even a certain signature that is added to the sound by tube amps and/or oxygen-free cables and the lot.

Anyway, I'd like to see an evolution in computerbenchmarking that will uncover the not so explored corners of cpu performance in every day use as a workstation. Bench suites like spec perf are nice for servers of which the tasks are preset and limited and where a quasi constant workload is assured, but for workstations where the overal performance depends on a lot more than just the performance in several benchmarks when the computer is doing nothing else than being benchmarked, it is less meaningfull to giving an overall image of its potence. Also this also depends on how the user uses his workstation, which makes such a fitting image very complex to get to. I know, maybe it's all not worth the trouble.

Also I'm aware I'm just stating the obvious. But to me it seems that some people don't want to hear this story and go all the way on the limited set of today's benchmarks when justifying some brand over the other.

[biohead]

No I don't. Human perception is so unreliable as to be meaningless.

not when you're talking about personal experiences. if you were to throw human experience out of the equation, you'd be denying your own species. like letting a computer with a checklist tell you whether or not you've got ADD.

[keithlm]

It's not beating the heck out of the Q6600, it's barely competitive.

Please define what you mean by "barely competitive". If you mean that it still loses a couple of benchmarks against a Q6600 then you are correct.

Of course when the Phenom was winning about 30% of the benchmarks against the Q6600 it was deemed "an utter disaster". So I guess the Q6600 is a complete and utter loss now.

I'm sorry that people can no longer play the "Even the best can't beat the worst" card anymore... but they need to move on. Why don't you tell us about how the 9850 can't compete against the Q9450. <yawn> Wonder how the 9950 is going to compare against the Q9450 since they will both clock at 2.66Ghz. (Perhaps that's why AMD decided to clock it at 2.66?)

(EDIT: Mistyped 9440 instead of 9450.)

[accord99]

not when you're talking about personal experiences. if you were to throw human experience out of the equation, you'd be denying your own species. like letting a computer with a checklist tell you whether or not you've got ADD.

No, it'll be like those people who spend thousands on expensive speaker cables and claim it enhances the audio quality even though in a double-blind test they fail to tell the difference between those cables and 12 gauge Home Depot wire.

[accord99]

Please define what you mean by "barely competitive". If you mean that it still loses a couple of benchmarks against a Q6600 then you are correct.

I mean that the Q6600 wins a significant majority of benchmarks against the 9850 in virtually every review. From Anandtechs, to Hardware.fr, Matbe, Hexus.net, Xbitlabs, etc.

[Devil's Prophet]

No, it'll be like those people who spend thousands on expensive speaker cables and claim it enhances the audio quality even though in a double-blind test they fail to tell the difference between those cables and 12 gauge Home Depot wire.

HAH, couldn't come up with your own example? :p

In any case, this is different from those audiophile nuts. Computer experience is all about quantity (of time), not quality like audio. Quantity is measured far easier than quality. Therefore this so called fluency that has been used as a argument pro AMD actually can be measured, although indeed in not as simple ways we typically benchmark computers/processors. That makes your analogy erroneous.

[keithlm]

I mean that the Q6600 wins a significant majority of benchmarks against the 9850 in virtually every review. From Anandtechs, to Hardware.fr, Matbe, Hexus.net, Xbitlabs, etc.

Most of the reviews show the 9850 having no problem winning a majority of the benchmarks against the Q6600. It was scoring about the same against the Q9300 as the Phenom 9600 scored against the Q6600.

[accord99]

HAH, couldn't come up with your own example? :p

To be fair, I did mention expensive speaker cables first.

In any case, this is different from those audiophile nuts. Computer experience is all about quantity (of time), not quality like audio. Quantity is measured far easier than quality. Therefore this so called fluency that has been used as a argument pro AMD actually can be measured, although indeed in not as simple ways we typically benchmark computers/processors. That makes your analogy erroneous.

On the other hand, both rely on human perception. The typical human ear is usually not able to determine the difference between pretty good hardware and highend hardware. Similar to the old adage of how a new system has to be 50&#37; faster than the old one before a person can perceive it to be faster. If a Phenom is better that it is noticeable by a person, then it should be measurable.

[accord99]

Most of the reviews show the 9850 having no problem winning a majority of the benchmarks against the Q6600. It was scoring about the same against the Q9300 as the Phenom 9600 scored against the Q6600.

Did you even read the reviews? Anandtech review has the Q6600 winning or tying every benchmark with a 9850 except for one video encoding test, Xbitlabs has the Q6600 winning every one while Matbe has the Q6600 comparable to a overclocked 2.9GHz Phenom.

[stocius]

But then again, when at some time someone really needs brutal computing power for doing an encode or archive job, it sure comes in handy.

Yes, it does. Encoding and crunching are both faster on my Q6600 as well as rendering, but only with the OC at 3.4 to 3.6. I haven't had any of the newer Intel quads so I can't talk about them.

I'm merely stating I like the feel of my Phenom better. It is very difficult to reproduce exact setups as not all Phenoms clock the same even among the same stepping and there is variation on the Intel side too from chip to chip, stepping to stepping. There may be variation of other components like RAM OCs and GPU OC too. Then you take into account the various skill levels of OCers.

I've said my piece, you can accept what I say or not. Neither AMD or Intel pays me a dime so I could care less.