The Official Pentium M vs. Turion Thread.

[Shenkoa]

This is not an AMD vs. Intel thread, this is a thread that fairly compares the 2 specific processors. Please no flaming.

Post your benchmarks. I would like us to compare models with similar frequency. Also I would like the compare the 2 based on price.

Please show proof of your benchmarks by taking a picture of CPU-Z running with the benchmarking app and results.

 

[WobbleWobble]

Pentium 4-M or just Pentium M? They're two very different CPUs.

 

[Shenkoa]

Updated. Thank you!

 

[n19htmare]

DO they have to be my Benchmarks or can i Post a link to someone elses'?

http://www.gamepc.com/labs/view_content.asp?id=turion64&page=4
I'll post it anyways.

 

[Brunnis]

Originally posted by: n19htmare
DO they have to be my Benchmarks or can i Post a link to someone elses'?

http://www.gamepc.com/labs/view_content.asp?id=turion64&page=4
I'll post it anyways.

That test is hillarious! I've always wondered how they managed to make the Pentium-M utterly the destroy similarly clocked A64s and Turions in that test. It doesn't match other tests of these CPUs and when you calculate what frequencies the A64 would need to compete, you realise just how stupid those results are.

I'll see if I can run some tests on my Pentium-M 1.7GHz later. Anything in particular that you're interested in?

 

[openwheelformula1]

gamepc's reviews are very good as always. Turions don't perform better clock for clock, but it has more features and priced cheaper.

 

[Brunnis]

Originally posted by: openwheelformula1
gamepc's reviews are very good as always. Turions don't perform better clock for clock, but it has more features and priced cheaper.

Well, their results seem to disagree with most other reviews of the Pentium-M, but I guess it's all the others that are wrong.

Also, I wouldn't say that GamePC is a serious review site. The Turion article was about "efficient computing", yet they failed miserably in the power consumption tests. They actually ran the Turion MT at 1.35V instead of 1.2V and despite them knowing about this serious flaw, they refuse to take down the charts, remake them or even put in a note about it.

Also, a Pentium-M is NOT 20-30% faster clock-for-clock, as those gaming tests show.

 

[n19htmare]

Can you post some links where I can see, what you may call "legit" tests and charts?
What is this flaw you speak of? The turions utalized the PowerNow! feature which automatically adjusts voltages and speed depending on load. Are you saying the PowerNow! feature is flawed?
Stop being so fanboyish and post some results or benchies that you feel are legit.

plus, its been said over and over that Pentium M does very well in games.

 

[Brunnis]

Originally posted by: n19htmare
Can you post some links where I can see, what you may call "legit" tests and charts?

I don't really care to dig up all the tests I've seen. A Google search probably brings up a bunch.

Originally posted by: n19htmareWhat is this flaw you speak of? The turions utalized the PowerNow! feature which automatically adjusts voltages and speed depending on load. Are you saying the PowerNow! feature is flawed?

Excuse me? Did you even read my last post? I quote myself:

"They actually ran the Turion MT at 1.35V instead of 1.2V"

Originally posted by: n19htmareStop being so fanboyish and post some results or benchies that you feel are legit.

So, now I'm a fanboy of Turion, even though I own and love a Pentium-M Dothan. Come on!

Originally posted by: n19htmareplus, its been said over and over that Pentium M does very well in games.

Yeah, I know it's good in games. Just not that good. Example:

The tests indicate that it would take an A64/Turion @ 2.5GHz to match a Pentium-M @ 1.6GHz in Halo. Or a 2.55GHz A64/Turion to match a 2.13GHz Pentium-M in FarCry.

The Halo result is obviously botched and that puts the other results in question as well, since there may have been something wrong with the AMD system.

 

[dexvx]

Obviously you don't know the power of the Pentium-M in gaming. Its large, extremely fast L2 cache makes it a big winner. The results are exemplified when you overclock the Pentium-M. Putting these things on a desktop environment usually means that they are top performers.

The Yonah at 2.5 - 3.0Ghz can easily best overclocked X2's in most scenarios.

Reviews of Pentium-M's:

http://www.x86-secret.com/articles/divers/ct479/ct479-4.htm
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2382&p=12

Yonah Overclocking:

T2600 @ 2.7Ghz @ 1.3V (1.25V default)
http://www.xtremesystems.org/forums/showpost.php?p=1355976&postcount=485

 

[thescreensavers]

AMD Cheaper intel more expensive done. AMD has 64 bit support and intel does not.....

Benshe

Unless battery life while performing CPU-intensive tasks is paramount, choosing a Turion-based laptop over a Dothan-based laptop is recommended.

the battery on the intel lasted lees then 10 min more and some times amd won

 

[Brunnis]

Originally posted by: dexvx
Obviously you don't know the power of the Pentium-M in gaming.

Well, I just didn't realise that the Pentium-M went from "equal to slightly faster than an equally clocked A64" to "20-30% faster than equally clocked A64" (or even faster). The tests you linked don't really show this either.

I was just reflecting over GamePC's unusually inflated results for the P-M, but since no one else seem to find them peculiar, I was probably wrong in critisizing them.

 

[Duvie]

Originally posted by: dexvx
Obviously you don't know the power of the Pentium-M in gaming. Its large, extremely fast L2 cache makes it a big winner. The results are exemplified when you overclock the Pentium-M. Putting these things on a desktop environment usually means that they are top performers.

The Yonah at 2.5 - 3.0Ghz can easily best overclocked X2's in most scenarios.

Reviews of Pentium-M's:

http://www.x86-secret.com/articles/divers/ct479/ct479-4.htm
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2382&p=12

Yonah Overclocking:

T2600 @ 2.7Ghz @ 1.3V (1.25V default)
http://www.xtremesystems.org/forums/showpost.php?p=1355976&postcount=485

Leave it to you to misrepresent the truth...

Even AT's own article shows yonah is clock for clock about equal to AMD x2 at same speed...being a 3800+ is on par with the 2.0ghz yonah.....AMD has edge on games and for the most part AT and their suspect reviewing of late runs high res on gpu limited games like fear...Why even bother us with that test in a cpu review then...As faster gpus arrive those number and differences between the platforms could become more apparent as the gpu bottleneck is released...Just questionable review practices in my opinion...

Back on topic...If clock for clock yonah is equal to X2 (and the one with half the cache) how do you figure 2.5-3.0ghz can "easily best" and X2??? I see opterons 170's doing 2.8ghz to 3.0ghz and they are pretty much same price as 419.00 dollar yonah at newegg....So the way I see it you will have to get to 2.8 to 3.0ghz to stay equal...

But ofcourse in your world commonsense makes no sense....

Quit your FUD, your lieing, your downright sickening fanboyism....

 

[dexvx]

Originally posted by: Duvie
Back on topic...If clock for clock yonah is equal to X2 (and the one with half the cache) how do you figure 2.5-3.0ghz can "easily best" and X2??? I see opterons 170's doing 2.8ghz to 3.0ghz and they are pretty much same price as 419.00 dollar yonah at newegg....So the way I see it you will have to get to 2.8 to 3.0ghz to stay equal...

Yea... the AT review has it on stock.

Guess what? When you overclock, you do a commonly done practice known as raising the FSB. Yonah has basically 2 Dothan cores sharing a pathetic 667FSB. When you raise the FSB to over the 1000Mhz range, they can easily do full damage.

Moreover, not all X2's overclock to 3Ghz. Not all Yonahs will overclock to 2.7Ghz at stock voltage. Given the range of X2's/Opterons at 2.5-3Ghz, Yonahs at a similar frequency will match or exceed them, as early previews with the Aopen 975X board has shown.

Originally posted by: Duvie
But ofcourse in your world commonsense makes no sense....

Quit your FUD, your lieing, your downright sickening fanboyism....

You can start by shutting up on your TDP myth.

 

[Duvie]

Originally posted by: dexvx

Originally posted by: Duvie
Back on topic...If clock for clock yonah is equal to X2 (and the one with half the cache) how do you figure 2.5-3.0ghz can "easily best" and X2??? I see opterons 170's doing 2.8ghz to 3.0ghz and they are pretty much same price as 419.00 dollar yonah at newegg....So the way I see it you will have to get to 2.8 to 3.0ghz to stay equal...

Yea... the AT review has it on stock.

Guess what? When you overclock, you do a commonly done practice known as raising the FSB. Yonah has basically 2 Dothan cores sharing a pathetic 667FSB. When you raise the FSB to over the 1000Mhz range, they can easily do full damage.

Moreover, not all X2's overclock to 3Ghz. Not all Yonahs will overclock to 2.7Ghz at stock voltage. Given the range of X2's/Opterons at 2.5-3Ghz, Yonahs at a similar frequency will match or exceed them, as early previews with the Aopen 975X board has shown.

Originally posted by: Duvie
But ofcourse in your world commonsense makes no sense....

Quit your FUD, your lieing, your downright sickening fanboyism....

You can start by shutting up on your TDP myth.

According to most who have read it I wa s right and you and your boyfriend Dmens didn't discount anything that was said...

I dont know maybe it is just the intel crew....viral marketing and all!!!!

I said they were not the same...I still stand by that ...i had quotes from Intels white papers they say just that...

The person who should shut up is the one who wasn't able to disprove anything I said....

I never said 75%...All I said is they are not figured the same....100% true and if you cannot see that then you are too dumb to have a further conversation with...


Let see AMD 3800+ X@ has 85watt TDP and 4800+ x2 has 85 watt....Doesn't that ring a bell in your head?? It should unless no one is home!!!



Go have fun with your buddy FUGGER (biggest fanboy I have ever talked to in PMs)

 

[dexvx]

Originally posted by: Duvie
According to most who have read it I wa s right and you and your boyfriend Dmens didn't discount anything that was said...

I said they were not the same...I still stand by that ...i had quotes from Intels white papers they say just that...

I never said 75%...All I said is they are not figured the same....100% true and if you cannot see that then you are too dumb to have a further conversation with...

Intel Thermal Documents intended for system integraters clearly stated it, not from the idiots who write the processor datasheets.

No, you didnt say 75%, but you did say something on the lines of lying about the TDP.

Originally posted by: Duvie
Go have fun with your buddy FUGGER (biggest fanboy I have ever talked to in PMs)

Not xtreme enough? Because you like being the big man here?

 

[Duvie]

Originally posted by: dexvx

Originally posted by: Duvie
According to most who have read it I wa s right and you and your boyfriend Dmens didn't discount anything that was said...

I said they were not the same...I still stand by that ...i had quotes from Intels white papers they say just that...

I never said 75%...All I said is they are not figured the same....100% true and if you cannot see that then you are too dumb to have a further conversation with...

Intel Thermal Documents intended for system integraters clearly stated it, not from the idiots who write the processor datasheets.

No, you didnt say 75%, but you did say something on the lines of lying about the TDP.

Originally posted by: Duvie
Go have fun with your buddy FUGGER (biggest fanboy I have ever talked to in PMs)

Not xtreme enough? Because you like being the big man here?

hardly....

I had a run in with some foul mouth guy on the boards there and FUGGER protected his own...i mean Intel users...He basically made comments to me in his PMs that was downright shocking.....I new that was not a place for me to hang out....I actually had Intel only system at the times....

I dont care to hear from ppl like that...

I think you fit well there...

 

[Shenkoa]

Lets get back on the topic please.

Any one else?

 

[Keysplayr]

Shenkoa, what benchmarks do we run?

Additionally, we can create a web page with a grid for similar frequency/system specs comparison. Its easier to view results that way rather than finding them in random posts.

So, list your benchies, people will list their specs (in detail) and post their scores. I can take the scores and put them on the grid.

Kudos.

P.S. If the benchmarks are run at anything but default settings, state so for consistency.

P.S.S. Guys, look at this poll. This should not be opinion based. Either the Turion is overall a better performer or the Pentium M is. Why both of these processors have votes is beyond me. Should be a landslide/shutout. One or the other.

PM 1.73 GHz
512DDR2 400
60GB 5400rpm
915 integrated graphics (shared memory)

Super Pi SSE2 patched 1M

 

[daclayman]

I bought an Athlon once...

My woman left me, my dog ran off, my truck died and my trailer burned down


Seriously, do you want Pentium Ms benchies from laptops or desktops? Can a Turdion run on a desktop board? What kinds of benchies? The game benchies favor memory bandwidth and GPU; if we could keep that the same, then the fanbois could stop hiding in their closets.

My Super PI for my Celeron M is 40secs at 2.21ghz (check my FS for the screenshot), but it doesn't feel as fast at DVD encoding as my Northwood based P4-m did at 2.7ghz (225FSB) on the same mobo.

 

[dmens]

Originally posted by: Duvie
According to most who have read it I wa s right and you and your boyfriend Dmens didn't discount anything that was said...

I dont know maybe it is just the intel crew....viral marketing and all!!!!

I said they were not the same...I still stand by that ...i had quotes from Intels white papers they say just that...

The person who should shut up is the one who wasn't able to disprove anything I said....

...

Let see AMD 3800+ X@ has 85watt TDP and 4800+ x2 has 85 watt....Doesn't that ring a bell in your head?? It should unless no one is home!!!

Too bad I was taking a forced vacation when you posted this... typed up a response and got stopped cold... what a shame.

I really like how you refer to stuff "you said" when all you did was point to a silentpc article, copy/pasted a few sentences from white papers on a topic you barely understand (measurable current draw), then grandly assert that "most people" who read "your" stuff thinks you are "right", LOL.

If you actually read my critique on your sole contribution to the TDP argument (that being a link to an article that you did not write), you'd know I already addressed all the points you steadfastly cling to, including the one about the 3800 and 4800 having the same spec'ed TDP. Go read it, since it is obvious you have not done so.

By the way, I've already had my fun baiting you for responses, and I'm actually trying to teach you something here.

 

[openwheelformula1]

dmens stop with the flame bait already. You offered no "critique" on the TDP discussion except everything against Intel should be discredited because SPCR lacks the knowledge. You are the only one NOT reading anyone else's arguement due to your internet cockiness. You can't simply discredit everyone else by claiming yourself as an Intel employee. Perhaps you have trouble finding women (or men), but please flex your cyber muscle elsewhere cause it's getting annoying. If you can't face the fact that netburst is inefficient compared to AMD64, then there is NOTHING you can "teach" to any well knowledged forum members here. Go learn from those Intel senior engineers, they keep their mouth shut so they don't lose face for their employer.

 

[Keysplayr]

Originally posted by: openwheelformula1
dmens stop with the flame bait already. You offered no "critique" on the TDP discussion except everything against Intel should be discredited because SPCR lacks the knowledge. You are the only one NOT reading anyone else's arguement due to your internet cockiness. You can't simply discredit everyone else by claiming yourself as an Intel employee. Perhaps you have trouble finding women (or men), but please flex your cyber muscle elsewhere cause it's getting annoying. If you can't face the fact that netburst is inefficient compared to AMD64, then there is NOTHING you can "teach" to any well knowledged forum members here. Go learn from those Intel senior engineers, they keep their mouth shut so they don't lose face for their employer.

I don't subscribe to the baiting part, but what if a forum member really only "thinks" he/she is well knowledged? Then what?

 

[Viditor]

You guys missed a review...

http://techreport.com/reviews/2006q1/pentiumm-vs-turion64/index.x?pg=1

 

[Markfw]

Originally posted by: Viditor
You guys missed a review...

http://techreport.com/reviews/2006q1/pentiumm-vs-turion64/index.x?pg=1

Thy didn;t you post the conclusion:

The Tech Report

Conclusions
From a performance perspective, it's clear that the Turion 64 is the winner. By my count, the Pentium M was faster in only five of the tests, and one of those (the hardware OpenGL test in Cinebench) was probably due to graphics drivers. The rest were either a toss-up or a win for the Turion 64. The other thing that struck me about the results was that even in the tests the Pentium M did win, its margin of victory was fairly small. A number of the Turion 64 wins, however, were by an impressively large margin.

From a power consumption perspective, the Turion 64 surprised me. Yes, our Turion 64 test system consumed 19W more power than the Pentium M system at 100% CPU load, but unless you're using your laptop to crunch that Folding@Home work unit on the plane, maximum power consumption isn't usually all that important. For typical use, it seems likely the Turion 64 would be reasonably competitive with the Pentium M on the battery life front, as well.