AMD Phenom II X4 965 vs. Intel core i5-750

[dantoshi]

Which of these processors is the best one?

 

[sighQ2]

Does anybody actually have hard numbers for the ICC market share (and market share of all major compilers preferably)? I've seen numbers ranging from <2% to 80% so my guess is that most people actually don't have a clue and are making up percentages based on other people posting things like "Intel has the majority" or "Intel's compiler is only used for HPC."

I would love to see reliable info on this too.

I reject most comments on it. It went on for a long time. Per cent would be most useful over last few years; but the compiler talk is not news - only the recent full blown exposure of it.

 

[Chad Boga]

Turbo will be OFF in oclocked mode. It is useless there. It's a mere trick to lie the bentmarx.

You once again misinterpreted what was being said. I was talking about Turbo boost working in a system that has not been manually overclocked by the user.

In an ultimate sense, all I have is my personal experience - if I lack that, I am not here, or not alive, or don't exist. CB seems to deny his own experience - or at least we hear nothing of him.

Exactly what do you mean by "experience" or "deny his own experience"?

It's his system and he has observed problems.

You want he should link you to his system?

That would be a security breach. 😀

It looks like he is talking about CnQ on an AMD system, so it is hardly comparable to Turbo on a Lynnfield or Nehalem processor.

 

[Chad Boga]

I myself can not accept a mechanism that creates sporadic and unpredictable behavior in a system. Since the Turbo-Marketing feature can not be guaranteed and there is no way of knowing whether it will produce the same results from one day to the next I find the entire mechanism to be lacking and unacceptable.

You haven't stated that you believe Turbo is going to actually produce data errors(although I think you would be happy for people to believe this is likely), so your whole argument about not producing the same results is pretty lame considering the small window of possible variance.

That fact combined with the fact that it doesn't really provide a huge performance boost in real world situations makes it completely worthless. In other words the price paid for getting that small boost is not worth it.

No, your other words is just biased FUD not based in the real world at all.

The Anandtech review of the i7-870 showed that with Dawn of War II(9%), Sacred 2(14.9%) and WoW(16.7%), Turbo boost delivered a nice little boost.

Sure it produces enough of a faux performance increase in benchmarks to fool some people; but if the performance boost is not 100% guaranteed then it is not acceptable. In addition it is not acceptable to mislead people into believing they can count on it.

The explanation of how Turbo boost works is simple enough for most folk to understand fully, I don't know why you are having such troubles.

On a similar note some people accept a certain amount of errors when overclocking to be acceptable. I personally would not find that situation to be any more acceptable than the unpredictable behavior allowed by this useless mechanism you seem to revere.

:lol: :lol: :lol: Yet again another one of your ridiculous flawed analogies. Turbo boost is guaranteed by Intel to deliver the same lack of errors as any processor they release that doesn't have Turbo boost.

And you seem to think I revere Turbo boost because I respond to your baseless attacks against it, another strange perspective on your part.

 

[Chad Boga]

I read that thread of Scientia's over @ AMD zone. There is the only way I can describe it and AMD zone in general....

My sig describes them perfectly. 😀

 

[Chad Boga]

I just can't wait to see the mountain of bullshit you are going to speak when AMD implements a similar scheme.

<YAWN> I'll be saying the same thing I'm saying now and I'll be disabling such a feature in the BIOS.

But then there are absolutely no rumors of such a feature being added to any future AMD chips. The only rumors that might exist were started by Intel fanboys on forums attempting to make failed arguments.

Hey Keith, I just spotted an Intel fanboy confirming that Bulldozer will have Turbo Boost, this Intel fanboy goes by the name of "JF-AMD", have you ever heard of him? :lol:

http://www.xtremesystems.org/forums/showpost.php?p=4187237&postcount=94


Now with all the practice you have had with being wrong, I'm sure you will get over this little hiccup just fine.

However I can't wait to hear how you will be turning off Turbo boost in Bulldozer and rallying against that feature. :lol: :lol: :lol:

 

[roofus]

holy crap what a lot of bickering over Turbo Mode of all things lol. turbo mode or some renamed variant of it will end up in everything from both sides at some point. like it or hate it, call it "cheating" if that is your view but understand what it was designed to do instead of crying about it. Turbo more was not aimed and benchmarks or aiding overclocking for the enthusiast. It is there for mom, dad, the person who just wants to turn the thing on and not have to fuss with it. It does precisely what it is intended to do. No more, no less. My 955 of course doesnt have it but if it did, I could really care less. That feature wouldnt sway me one way or another but could be meaningful to average Joe who will never attempt overclocking. Nothing wrong with that is there? Are you put off by the fact your graphics card throttles down when you are running desktop apps? Do you feel cheated it isnt scorching the inside of your case to work in Excel?

 

[logainofhades]

The thing that bugs me is that if AMD would have been the one to implement Turbo Mode and not Intel, these AMD fangirlz would have thought it was the best thing ever.

 

[Chad Boga]

The thing that bugs me is that if AMD would have been the one to implement Turbo Mode and not Intel, these AMD fangirlz would have thought it was the best thing ever.

And a sign of how AMD is the great innovator.

Too bad they will be copying Turbo Boost from Intel. 😀

 

[roofus]

well i wouldn't call it copying. we are ok with throttling up and down other components in our pc. this just makes sense. take the thought process and learning curve out of it for those who dont want to mess with anything but using their computer

 

[keithlm]

Hey Keith, I just spotted an Intel fanboy confirming that Bulldozer will have Turbo Boost, this Intel fanboy goes by the name of "JF-AMD", have you ever heard of him? :lol:

http://www.xtremesystems.org/forums/showpost.php?p=4187237&postcount=94


Now with all the practice you have had with being wrong, I'm sure you will get over this little hiccup just fine.

However I can't wait to hear how you will be turning off Turbo boost in Bulldozer and rallying against that feature. :lol: :lol: :lol:

What was the timestamp on that post you just linked? And what was the timestamp on my post? Looks like you are working very hard to create things to attempt to actually combat the fact that Turbo-Mode is only a marketing tool. Too bad you failed. Yet again.

It is too bad that AMD might actually start using the same kind of failed marketing mechanism. Luckily there is always "disable". I don't need the marketing gimmicks. I prefer predictable and repeatable performance results. Too bad you can't seem to comprehend the concept because you and many other Intel fanboys are too busy trying to insist that everybody accept your fanboy opinions or automatically be wrong.

Without your glorified benchmarking gimmick the CPU which you are infatuated with just doesn't compete as well in benchmarks. I guess that irritates many Intel fanboys. It's a harsh and cruel world when people can't use faux results to be condescending on forums.

BTW: how many of those benchmark reviews that you guys link actually had a firewall, virus scanner, etc. and a few other applications running while the benchmarks were performed? (While being in an average case that a normal user would be using?) Can you even find ONE benchmark review that actually tests your marketing toy in real world conditions? If you can it is probably one that Intel fanboys generally ignore because of what the real world results actually show. Every attempt would be made to discredit such a review since it wouldn't be good to allow people to actually see that Turbo-Boost is merely a marketing gimmick.

 

[Chad Boga]

What was the timestamp on that post you just linked? And what was the timestamp on my post? Looks like you are working very hard to create things to attempt to actually combat the fact that Turbo-Mode is only a marketing tool. Too bad you failed. Yet again.

It is too bad that AMD might actually start using the same kind of failed marketing mechanism. Luckily there is always "disable". I don't need the marketing gimmicks. I prefer predictable and repeatable performance results. Too bad you can't seem to comprehend the concept because you and many other Intel fanboys are too busy trying to insist that everybody accept your fanboy opinions or automatically be wrong.

Without your glorified benchmarking gimmick the CPU which you are infatuated with just doesn't compete as well in benchmarks. I guess that irritates many Intel fanboys. It's a harsh and cruel world when people can't use faux results to be condescending on forums.

BTW: how many of those benchmark reviews that you guys link actually had a firewall, virus scanner, etc. and a few other applications running while the benchmarks were performed? (While being in an average case that a normal user would be using?) Can you even find ONE benchmark review that actually tests your marketing toy in real world conditions? If you can it is probably one that Intel fanboys generally ignore because of what the real world results actually show. Every attempt would be made to discredit such a review since it wouldn't be good to allow people to actually see that Turbo-Boost is merely a marketing gimmick.

Keith, Keith, Keith,

You really must stop your projecting.

Just because you are obsessed with a CPU company doesn't mean that the people who call you on the bullshit you speak are similarly obsessed with a rival CPU company. That kind of dysfunctional psychological issue is your cross to bear.

CPU's have hit the thermal wall, thus successfully maximising the thermal envelope when less than all the cores are active, is going to become an area of ever greater importance in the next 10 years.

You are too blinded by your irrational hate for Intel to see the benefits of a technology that they have and AMD don't, but no doubt after AMD make it clear that there is no going back on this, you will find a way to eat humble pie.

Unless of course you know more than the designers at BOTH Intel and AMD. :lol:

 

[someguy7]

He and the rest of the AMD idiots will never stop.

Again turbo is NOT a gimmick. Just stop already with your stupid BS. When AMD has its version of turbo it will also NOT be a gimmick.

If you want to disabled the feature then go ahead and do it. I think your reason for doing is one of the dumbest things I ever heard from a AMD or Intel troll though. You want predictable and consistent results. What is consistent about the feature is that with it on it will always beform at least as well as it would if it where off and usually better. If you run the same tasks in the same environment on your machine with turbo on the results will be consistent.

Again this feature is NOT a gimmick. It is a great feature and we will become more important down the line. We shall start by going back in time a couple years. The entire dual core vs quad core debate. The choice was go for a higher clocked dual core that was faster in everything that did not use 4 cores or get the quad core if you where going to use applications that use 4 cores. The basic idea of turbo mode is to get past this.

In the future it is MORE important. AMD and Intel are both going in the direction of adding more cores. We have 6 core cpus out already and they will be entering the desktop market soon. Soon to follow is 8/12 core cpus. The more cores you add to a cpu the more power it is going to draw. The more power the lower the base clockspeed will be. So lets use the company you have a love affair for Keith. We are now in the near future. AMD bulldozer cpus are out on the desktop market. The cpu has 12 cores and runs 2ghz. Lets just that the bulldozer cpu ends up being 1ghz faster core for core clock for clock than the Denab core. This new 12 core cpu will then not be faster than a 3ghz phenom II in anything that doesn't scale past 4 cores/threads. Take the same 12core cpu and add a turbo like feature. Now lets say the workload thrown at the 12 core bulldozer only will load 4 or 6 cores. Bulldozer can then shut down half or 2/3rds of the cores and will all the power saved by shutting down those cores easly bump up the clockspeed to 3ghz or more.


That fact that you call said type of feature a gimmick is utterly foolish. If you want to disable it fine. If you have servers and do not want this feature running I can understand that as well. What I can not understand how anybody who is not just nothing but a pure Intel hater can say that what you're saying.

The goal of both companies is to make the best possible multi core cpu they can. One that excels in workloads that can take advantage of as many cores as you can though at and at the same time excel in tasks that do not like gaming right now. For you and others to think and say that turbo is just a gimmick to win benchmarks is just flat out stupid to be honest.

 

[keithlm]

Just because you are obsessed with a CPU company doesn't mean that the people who call you on the bullshit you speak are similarly obsessed with a rival CPU company. That kind of dysfunctional psychological issue is your cross to bear.

You are too blinded by your irrational hate for Intel to see the benefits of a technology that they have and AMD don't, but no doubt after AMD make it clear that there is no going back on this, you will find a way to eat humble pie.

You can't stand the fact that somebody will not agree with you on the value of this marketing gimmick. It is making you apoplectic. So you pretend that this is all because I have an irrational hate for a brand in a veiled attempt to belittle my opinion. I've already told you the exact reason I find this marketing gimmick to be less than acceptable. I will be saying the same thing if or when AMD adds this garbage to their CPU. That is something that is really making your head crazy. Since I'm not basing my opinion on a brand your brain can't accept the fact that I could have another non-brand specific reason.

Some people might be willing to accept gimmicks that compromise the system. I do not find it acceptable and I will not lower my standards low enough to find it acceptable in any brand.

He and the rest of the AMD idiots will never stop.

Again turbo is NOT a gimmick. Just stop already with your stupid BS. When AMD has its version of turbo it will also NOT be a gimmick.

How many times did you say it was not a gimmick in your post? Perhaps you need to say it half a dozen more times like a mantra. Then you can pretend that your opinion is reality and there is no way anybody can have an opposing opinion.

It is my opinion Turbo-Boost is a benchmarketing gimmick. I am not the only person that has this opinion on this issue. For some reason you guys just can not accept the fact that people do not share your collective opinion and that this has nothing to do with brand and everything to do with functionality.

There is no doubt we will continue to get a bunch of rabid Intel fanboys joining together to defend their opinion at all costs. It must really bother you guys that you can't disprove the fact that it is a benchmarking gimmick. Instead of just accepting the fact that this "feature" is not acceptable to some people Intel fans often resort to personal attacks in failed attempts to defend their opinion against the godless people that do not agree with them.

Actually I find the fact that Intel fans can't accept that some people consider it a gimmick to be utterly pathetic.

So you Intel fans should just keep making incorrect assumptions and deny others the freedom to have their own opinion. The more defensive you get the more pathetic the arguments become.

EDIT: And BTW... it is a gimmick.

 

[Chad Boga]

You can't stand the fact that somebody will not agree with you on the value of this marketing gimmick.

:lol: Okay

So you pretend that this is all because I have an irrational hate for a brand in a veiled attempt to belittle my opinion.

Keith why would we need to pretend? Anyone familiar with your posting history knows you have an irrational hatred for Intel.

I've already told you the exact reason I find this marketing gimmick to be less than acceptable.

I know what you said, but I just can't believe you are genuine. I mean I know you and irrationality aren't strange bedfellows, but I just think you can't stand the idea of Intel having something of benefit that AMD doesn't have.

I will be saying the same thing if or when AMD adds this garbage to their CPU.

Don't you trust JF-AMD? Can't say I blame you, I think he comes across as slimey too.

That is something that is really making your head crazy. Since I'm not basing my opinion on a brand your brain can't accept the fact that I could have another non-brand specific reason.

Hey Keith, I can assure you that you are not so important to me to make my head crazy. :lol:

Some people might be willing to accept gimmicks that compromise the system. I do not find it acceptable and I will not lower my standards low enough to find it acceptable in any brand.

Good luck with VIA then. :lol:

It must really bother you guys that you can't disprove the fact that it is a benchmarking gimmick.

Yeah like it would really bother people who can't convince Fred Phelps to stop claiming every disaster is God's work because he is displeased with the USA being too gay friendly. :lol:

One knows the mental state of the types like Fred Phelps, before the conversation starts.

Actually I find the fact that Intel fans can't accept that some people consider it a gimmick to be utterly pathetic.

Yeah it is like you are from the Flat Earth Society and we are just normal folk telling you that your interpretations are nuts.

 

[notty22]

Drag racers in the 1980's called turbo's a "gimmick" to. Until the turbo cars broke all the speed records. Then they said, you can only run a 6 cylinder with a turbo against the 8's. They still lost. This troll sounds about as ignorant as someone denying the time slip with the lower number is not the faster car.
Cpu's are not engines but depending on the aggressiveness of the turbo the analogy is similar.
Its not that utilized in the i7920 cpu , but in the mobile cpus's its a 50% clock increase.
Its done at the hardware/bios level, its NOT done in software. Its nothing like a software overclock. Its very much the same as a cpu scaling down in power saving mode and instantly scaling up for performance. It never misses a beat.

 

[sighQ2]

holy crap what a lot of bickering over Turbo Mode of all things lol. turbo mode or some renamed variant of it will end up in everything from both sides at some point. like it or hate it, call it "cheating" if that is your view but understand what it was designed to do instead of crying about it. Turbo more was not aimed and benchmarks or aiding overclocking for the enthusiast. It is there for mom, dad, the person who just wants to turn the thing on and not have to fuss with it. It does precisely what it is intended to do. No more, no less. My 955 of course doesnt have it but if it did, I could really care less. That feature wouldnt sway me one way or another but could be meaningful to average Joe who will never attempt overclocking. Nothing wrong with that is there? Are you put off by the fact your graphics card throttles down when you are running desktop apps? Do you feel cheated it isnt scorching the inside of your case to work in Excel?

Good post roofus.

I esp. like the way you summed it up in 1 easy paragraph. If I had known I could have skipped 40 posts of useless contrariness by chad. Thx to chad and perhaps a few others, this forum tends to be a bs zoo - so much not worth reading.

The point about turbo being used to misrepresent benches, and determine who's best in whatever, still stands. That bs is not about turbo; but rather about marketing confusion to average public. I doubt chad can understand such concepts with his 8 yr old brain. I always like I am reading in slomo when (if) I read his drivel.

I am all for things being presented in an honest manner.

re JF - chad has no idea who JF is - the guy has more years server experience than chad has [days on the planet awake].
JF constantly declines comment on desktop hardware, and leaves that to the desktop people.

- not knowing the context of chad's flamelink, it is probably not even relevant.

But I found it interesting to read that BD will have a better implementation of a "turbo-like" function.

chad probably thinks p-states are measures of how desperately he feels the urge. I doubt he truly feels anything else. Note that some will turn p-states off too. chad perhaps wishes he could. O well, try pampers.

I have seen some good posts from you before roofus; usually when you are not in flamer mode - same for a lot of us, huh. 😛

Thx again. sorry to waste time commenting on waste of time.

sigh
.

 

[Chad Boga]

But I found it interesting to read that BD will have a better implementation of a "turbo-like" function.

Ahhhh the President of the Flat Earth Society has joined the discussion. 😀

It is good to see you are already on board for Turbo boost by AMD, but now you will be at loggerheads with Keith.

Oh no, how will this play out. :lol:

 

[roofus]

I try to be as objective as can be but sometimes I have to stir the pot a little hehe. I have no dog in this fight so to speak as I am happy with my 955 and couldn't complain about my 920 during it's short stay.
The benchmarks using turbo mode are fine by me. Intel having Turbo is fine by me. The ISSUE really lie in the presentation of the review itself. The value of Turbo is in apps that aren't quad optimized and not enough is being said about that. I think that should be in the conclusion of all of the articles since Turbo may be very useless if software ever catches up with hardware.

 

[sighQ2]

someguy said >>>> "we will become more important down the line. We shall start by going back in time a couple years".

This is almost like something I would say. 😀

 

[warmon6]

Ok end this.


First off, Turbo boost is not a gimmick. It something that works very well on single threaded app when need. It's a feature for those who dont like overclocking there cpus but would like to have a speed boost when not using the extra core(s).

Here we have the core i5 Stock speed, turbo, and overclocked to 4 GHz. As you can clearly see, core i5 in turbo boost shaves off almost 20 seconds of time compared to stock.

Now when you looks at the rest of that review here , Any multi threaded apps wont take the advantage of turbo boost as multi threaded app run faster on more cores than fast single/dual cores.

Also if it was just a gimmick, then why is AMD patenting a tech thats almost the same as intel turbo boost?

http://www.patentstorm.us/patents/7490254/fulltext.html (AMD patent for there version of turbo boost. )

 

[sighQ2]

The point about turbo being a benchmark scam is not about whether or not turbo is useful - obviously it is useful, in some, not all, circumstances.

One problem however is that it is used in test reports to test what is supposedly a 2.6 cpu. But it is always unknown what the real clox is for that cpu.

It is also known that spintel misleads (for years) in reporting it tdp specs. They have a convenient core and uncore and it seems likely that the uncore does not make it into tdp.

Add to that an unknown clox, and the tdp is fully unknown. And power consumption is also suffering as the clox is elevated. As is temperature.

Turbo responds only if temperature allows - or they call it thermal limits. This is the argument for it being useless in oclox conditions; since the clox, power consump, and temps, are already elevated.

Add to this picture another note of concern, or doubt, or lack of confidence - that it is well known, that the stock cooler is inadequate - constantly people talk of replacing the stock cooler - and they refer to oclox intentions mainly. But this further adds to cost of expensive cpu, to stabilize temps, which are thrown to the brink by turbo, if it is engaging, or is it not (??). So you have potential for instability in some users' usage conditions due to deliberate cpu stressing.

There is an awful lot of trust in a lying monopoly busted for antitrust, compilers, bribery, etc etc more to come....

If you trust spintel, then you could support them and their technology. But the basis for all the antitrust kinda undermines any trust. The main reason for all the bribery, rebates, etc. was to prevent oem's from succumbing to consumer demand for AMD products, which, at the peak of the antitrust tactics, was the true performance leader.

I doubt that, if you follow this, I need to say a lot more - so I won't.

The thing is you need to trust a crook re unknown circumstances of performance - and using this trickery, they once again claim to be performance leader. Yet they also deny or ignore all the tonnage of evidence that is stacked against them in the antitrust cases. And this, after they have already been found in violation in 3 other countries on the global scale.

Trust that if you want. More will be revealed.

Turbo is not great tek, nor really anything so amazing; it's a convenience if everything else is as marketed. But the marketing of the king of antitrust has a very dirty track record. It's your choice; and you can choose what you think is best for you.

 

[keithlm]

Yeah it is like you are from the Flat Earth Society and we are just normal folk telling you that your interpretations are nuts.

I see you have started resorting to personal attacks since you can't force your opinion down my throat. Getting desperate?

You claim it is your opinion that I am irrational. What is really bothering you is the fact that I'm not. But claiming that is the only thing you can come up with since I won't drink your Kool-Aid.

I think that should be in the conclusion of all of the articles since Turbo may be very useless if software ever catches up with hardware.

Not only is it a worthless marketing gimmick... it has planned obsolescence and any possible benefit currently gained will disappear. Well except in benchmarks. People will still run useless benchmarks and claim they mean something; just like is often done today.

 

[sighQ2]

Ok end this.


First off, Turbo boost is not a gimmick. It something that works very well on single threaded app when need. It's a feature for those who dont like overclocking there cpus but would like to have a speed boost when not using the extra core(s).

http://media.bestofmicro.com/X/U/234498/original/iTunes.png

Here we have the core i5 Stock speed, turbo, and overclocked to 4 GHz. As you can clearly see, core i5 in turbo boost shaves off almost 20 seconds of time compared to stock.

Now when you looks at the rest of that review here , Any multi threaded apps wont take the advantage of turbo boost as multi threaded app run faster on more cores than fast single/dual cores.

Also if it was just a gimmick, then why is AMD patenting a tech thats almost the same as intel turbo boost?

http://www.patentstorm.us/patents/7490254/fulltext.html (AMD patent for there version of turbo boost. )

understand what you are saying.

what is "STOCK"

Is that turbo on or off?

And how can they show on and off if we don't know if stock is on or off?

that is not very clear to this AMD kinda guy. Is that why you need to end this?

Please describe what "STOCK" means - is that some ES engineering sample? - never mind that - just tell me what stock means.

 

[greenlines]

Hummmmm... turbo is not a gimmick.
Hrummmmm... turbo is not a gimmick.
Hrrruuummm... turbo is not a gimmick.

This is fun, I like chanting mantra.

 

[roofus]

sighQ2- my definition of stock would be Turbo on. i think it just needs to be understood this isn't benefiting programs optimized for multi-core CPU's.