AMD's X2 A Failure Over At Tom's

[Pabster]

Originally posted by: porkster
The topic we are discussing is AMD?s X2 failure to multitask.
.

Good luck, the AMD zealots here will turn the topic to everything BUT the thread title.

 

[porkster]

It's amazing how much AMD fans will overlook the faults or base their purchases on generalisations.

* AMD X2 4800+ is not cheaper than Intel 840EE
* The AMD X2 is to be sold as a multitasking CPU, so yes it is expected to multitask properly, which it is not doing!
* It is unfair to expect the competing CPU to have features disabled. You can?t say disable Hyper Threading so as to stop Intel being shown as the better CPU.
* Both systems started with the same settings and the AMD failed the multitasking expectation in the test. Even if the test had a stability theme, the test still was to place a multitasking load on the systems.

.

 

[Pr0d1gy]

Originally posted by: The Pentium Guy
I'm trying to be as unbiased as possible here (not a fanboy on either side, despite my name):
Just wondering... who the hell RARs and plays music and encodes DivX while playing a game? Unless you're an INSANE multitasker, I think it's kind of useless to do all that at once.

-Intel still wins in video encoding. Point for intel
-AMD wins in gaming. Point for AMD.
-Intel wins in price. However before I get flamed: X2 prices WILL come down. Point for Intel.
-Intel's using 2x540 (Prescott) processors. Being a prescott owner, I realize how hard these are to cool. TWO of them? Point for AMD.

I still think that it's the same as before(Multitasking/Encoding->Intel, Gaming/Performance->AMD), except this time Intel's got the price advantage.

Guys, correct me if I'm wrong - I'm an open minded guy. Please don't flame or anything.

-The Pentium Guy

Props to The Pentium Guy for not being a total fanboy. If you want to play games, get the AMD. If you want to do video editing, while encoding video & surfing the web, then get the Intel. Price shouldn't be a factor between these two, so just choose the one that's right for you. Of course in the lower end of duals the Intel is cheaper, but you'll need a new mobo & stuff (which means it's a good choice if you're building a whole new PC).

 

[Pabster]

Originally posted by: Chode Messiah
THG is an intel fanboi website. The X2 will run circle around any pentium dual-core. Anand's reviews show that the X2 is awesome at multitasking. What I really like is how in one article, a 3500+ beat a pentium D in almost every test. This thread is littered with troll fesces. X2=Domination.

LOL. I always get a good laugh when the AMD zealots accuse THG of being an Intel "fanboy" site. Didn't you same idiots accuse Anand of exactly the same not all that long ago (pre Athlon-64 days) when all those Intel ads ran on this site? Get a grip.

Now, that said, I find this DiVX encoding "test" to be quite ridiculous.

 

[porkster]

Originally posted by: PabsterGood luck, the AMD zealots here will turn the topic to everything BUT the thread title.

Yeah it wasn't my choice to for the thread to be placed into the shark's den.

The AMD community is mainly made up of teenagers, so it is very difficult to explain facts without challenging their stereo-types and generalisations.

.

 

[SVT Cobra]

Originally posted by: SynthDude2001

Originally posted by: DaveSimmons
Nice troll thread.

Exactly.

lmao Tom's website is the biggest amount of BS ive ever seen...its always biased and this is just another stunt so they cna get more hits...

EDIT:: can we have a filter for all these trolls that keep registering just to bring BS into these forums and trying to disprove something that is not true just to get attention/give a reason for fanboyism.....look how he keeps posting incoherently just to back himself...got something to prove g00ber?


anyways I read it and Tom's hardly makes any conclusion to why X2 is "taking a beating"...once again 3 out of 4 tests is winning...plus what it lost at is not new news...and if you read anand's article is cares to differ on what tom said...but of course we all know who has been right in the past.....

not tom

 

[Lonyo]

Originally posted by: porkster
It's amazing how much AMD fans will overlook the faults or base their purchased on generalisations.

* AMD X2 4800+ is not cheaper than Intel 840EE
* The AMD X2 is to be sold as a multitasking CPU, so yes it is expected to multitask properly, which it is not doing.
* It is unfair to expect the competing CPU to have features disabled. You can?t say disable Hyper Threading so as to stop Intel being shown as the better CPU.
* Both systems started with the same settings and the AMD failed the multitasking expectation in the test. Even if the test had a stability theme, the test still was to place a multitasking load on the systems.

.

The OPERATING SYSTEM handles what the CPU does, not the CPU.
If the OS doesn't send the encoding thread to the CPU, there is NOTHING the CPU can do about it.
The OS could have diverted time from the RAR archive to encoding, or from the game test, or the CD rip, and increased the amount of encoding done, but it didn't.
This is not the fault of the CPU, it is the fault of the system scheduler.
The CPU multitasks properly, the test does not, and the OS does not.
You would not rip the same CD over and over, you would not RAR and archive over and over, you would probably change focus to give the encoder higher priority.

The CPU is not at fault for OS issues.

 

[ProviaFan]

Originally posted by: porkster
The AMD community is mainly made up of teenagers, so it is very difficult to explain facts without challenging their stereo-types and generalisations.

You, sir, are an idiot. Not to mention that you speak from both sides of your mouth, in the same sentence. First, you stereotype AMD users as being teenagers, and then you blame them for stereotyping. Oh, the ironing! :roll:

Originally posted by: Lonyo
The OPERATING SYSTEM handles what the CPU does, not the CPU.
If the OS doesn't send the encoding thread to the CPU, there is NOTHING the CPU can do about it.
The OS could have diverted time from the RAR archive to encoding, or from the game test, or the CD rip, and increased the amount of encoding done, but it didn't.
This is not the fault of the CPU, it is the fault of the system scheduler.
The CPU multitasks properly, the test does not, and the OS does not.
You would not rip the same CD over and over, you would not RAR and archive over and over, you would probably change focus to give the encoder higher priority.

The CPU is not at fault for OS issues.

Maybe someone said it before, but regardless, this person speaks the truth! :thumbsup:

 

[ProviaFan]

By the way, what if I set up a benchmark with 5 threads on the P4. The same thing would happen that happens with the X2 now (the "problem" is a function of the OS, NOT the CPU), but this time I'd be blamed for "trying to make the P4 look bad." Again, oh, the ironing! :roll:

 

[UsandThem]

Originally posted by: ProviaFan
By the way, what if I set up a benchmark with 5 threads on the P4. The same thing would happen that happens with the X2 now (the "problem" is a function of the OS, NOT the CPU), but this time I'd be blamed for "trying to make the P4 look bad." Again, oh, the ironing! :roll:

I just want to point out that the Tom's review does not get very much respect from me.

I mean, come on, Michael "Wacko" Jackson's Dangerous? Who the hell still listens to that crap?

 

[vailr]

Maybe a better test would be:
A dual-CPU AND dual-core Opteron system
vs.
Dual-core AND dual-CPU Xeon? (Or, is a dual-core Xeon even available yet?)
Someone tell THG, that a newer (version 1.29) of CPU-z is now out.

 

[deveraux]

Originally posted by: Lonyo

Originally posted by: porkster
It's amazing how much AMD fans will overlook the faults or base their purchased on generalisations.

* AMD X2 4800+ is not cheaper than Intel 840EE
* The AMD X2 is to be sold as a multitasking CPU, so yes it is expected to multitask properly, which it is not doing.
* It is unfair to expect the competing CPU to have features disabled. You can?t say disable Hyper Threading so as to stop Intel being shown as the better CPU.
* Both systems started with the same settings and the AMD failed the multitasking expectation in the test. Even if the test had a stability theme, the test still was to place a multitasking load on the systems.

.

The OPERATING SYSTEM handles what the CPU does, not the CPU.
If the OS doesn't send the encoding thread to the CPU, there is NOTHING the CPU can do about it.
The OS could have diverted time from the RAR archive to encoding, or from the game test, or the CD rip, and increased the amount of encoding done, but it didn't.
This is not the fault of the CPU, it is the fault of the system scheduler.
The CPU multitasks properly, the test does not, and the OS does not.
You would not rip the same CD over and over, you would not RAR and archive over and over, you would probably change focus to give the encoder higher priority.

The CPU is not at fault for OS issues.

:thumbsup:

Probably the best explanation yet. It is THG's fault that they set the thread priority to Idle. That is NOT the proper way to benchmark two DC CPUs. The only thing it proves is that the OS sees 4 CPUs with the Intel chip and 2 CPUs with the X2. It doesn't say anything about the performance of the CPUs themselves. Now, if the X2 is performing slowly when all of the threads are set to Normal priority then you will have a point, but that is not the case.

Someone should close that site down just for being stupid and misleading people.

 

[SonicIce]

Our testing methods needs to be totally rethought.

 

[carlosd]

THG article is crap, it is plagued with major insconsistencies. How can yo read than kind of BS?

 

[MobiusPizza]

http://www.tomshardware.com/stresstest/charts.html

The benchmark page

 

[fatty4ksu]

Wow, the 840EE is whoopin ass.

 

[MobiusPizza]

hey calm down people, there's no X2 bashing at THG, to me AMD wins 3 out of 4 tests

 

[justly]

Its been a little more than 10 hours since my first post in this thread (where I made sure to list the DivX scores of each processor ). The timers for both system show that they have been online for longer than 11 hours yet in that time span the Intel system DivX score has only increased by 20. At this rate there is no way the current Intel score of 740 could have been accomplished while doing the other tasks. So either the Intel system was not multitasking at some point thus allowing it to only be working on DivX to gain this lead, the priorities where somehow set improperly or the score is totally bogus.
Meanwhile the AMD system has increased by 30 (as opposed to Intels 20), indicating that the AMD system is actually processing DivX faster than the Intel at this point.

The Intel system has had some where around 9 hours of down time, if that is taken into account (and the other scores are accurate, also questionable at this point) it would reduce the lead AMD has as far as performance vs actual time online but would still give AMD the lead (just not by as big a margin).

From an analytical point of view using the information I have witnessed I think it would be a leap of faith (more like wishfull desperation) to claim the Intel system is better at anything (at this point).

 

[fierydemise]

The Far Cry graph is also misleading, it shows the current FPS instead of the total number of runs, AMD has only 3FPS more but 425 more runs the graph shows the 3FPS more because showing the 425 more runs would make the 840EE look worse

 

[Lonyo]

Originally posted by: justly
Its been a little more than 10 hours since my first post in this thread (where I made sure to list the DivX scores of each processor ). The timers for both system show that they have been online for longer than 11 hours yet in that time span the Intel system DivX score has only increased by 20. At this rate there is no way the current Intel score of 740 could have been accomplished while doing the other tasks. So either the Intel system was not multitasking at some point thus allowing it to only be working on DivX to gain this lead, the priorities where somehow set improperly or the score is totally bogus.
Meanwhile the AMD system has increased by 30 (as opposed to Intels 20), indicating that the AMD system is actually processing DivX faster than the Intel at this point.

The Intel system has had some where around 9 hours of down time, if that is taken into account (and the other scores are accurate, also questionable at this point) it would reduce the lead AMD has as far as performance vs actual time online but would still give AMD the lead (just not by as big a margin).

From an analytical point of view using the information I have witnessed I think it would be a leap of faith (more like wishfull desperation) to claim the Intel system is better at anything (at this point).

There's a thread on this article in the CPU section, and yes, the Intel system had at least 1 session of doing nothing for 8 or so hours, so work whatsoever.
Basically the test is 100% useless for anything except showing system stability, because the Intel system has had long periods of sitting totally idle.

 

[V00D00]

Did anyone notice how the Intel System got DDRII 667mhz, while the AMD system got 400mhz.

Ok, Well there you go. I assume WinRAR is about 99% memory bandwidth dependant.

Right there the benchmarks are flawed. Why would those retards use such different memory????

 

[Lonyo]

Originally posted by: V00D00
Did anyone notice how the Intel System got DDRII 667mhz, while the AMD system got 400mhz.

Ok, Well there you go. I assume WinRAR is about 99% memory bandwidth dependant.

Right there the benchmarks are flawed. Why would those retards use such different memory????

Because one is DDRII and the other is DDR?
DDR400 is the highest official speed grade there is for DDR (JEDEC certified)
DDRII goes from 533 to 667 AFAIK (again, JEDEC official specs) and maybe 800MHz.
They are using all stock parts (stock heatsinks etc), so choosing an official standard for the RAM speed of both machines is a totally valid thing to do, it represents 2 standard, non overclocked systems.
The DDR2 also comes with higher latencies than DDR, which would decrease performance (slightly). Also, the AMD64 aren't quite so memory hungry as the P4's AFAIK. This may be different with X2's though.

When AMD come out with socket M2 and support DDR2 obviously tests will be able to use comparable RAM.

 

[DanDaMan315]

Whatever, won't stop me from buy one :laugh:

 

[Sean Maxwell]

AMD > Intel

(as of now that is)

 

[imported_BikeDude]

Originally posted by: deveraux
Probably the best explanation yet. It is THG's fault that they set the thread priority to Idle. That is NOT the proper way to benchmark two DC CPUs. The only thing it proves is that the OS sees 4 CPUs with the Intel chip and 2 CPUs with the X2. It doesn't say anything about the performance of the CPUs themselves. Now, if the X2 is performing slowly when all of the threads are set to Normal priority then you will have a point, but that is not the case.

I agree that this is THG's fault. If the user expects four threads to get equal attention from the CPU, then their priority level must be equal. But if the total/sum is what matters then it is not necessarily the way to go. It is quite easy to set thread priority using Task Manager, so this isn't exactly rocket science.

Another issue here is paging; How much memory do these four threads eat? It's not a good situation if switching context results in a page fault. (at that point you're benchmarking the hard drive, not the CPU) AFAICT Tom has these puppies set up with only 1GB worth of memory? (perhaps more than sufficient, I can't really tell from glancing at Tom's pages)