Sign in with
Sign up | Sign in
Your question

IPC Performance Over Multiple CPU Generations

Last response: in Site Feedback
Share
a b à CPUs
April 12, 2011 5:14:29 PM

Hey Tom's editorial staff,

I have a somewhat ambitious idea for an article I would like you to consider.
It is my belief that many would appreciate an apples to apples performance comparison of as many CPU architectures as possible.
What would differentiate this article from your current reviews and charts is in how it would be performed.

Instead of comparing by price point or market segment, I envision this article matching as closely as possible all variables except the CPU architecture.
To that end I would propose that all CPUs are tested with only one core enabled, at an identical clock rate with all turbo modes disabled and with RAM Data Rate and Timings matched (when it is not possible to directly match RAM types).

Additionally, CPUs that support SMT could be tested again with SMT enabled under a threaded workload.
This would allow you to accurately show any improvements in implementations throughout different generations.

Excluding oddball platforms (Atom, Brazos), this testing could be done with a minimum of motherboard swaps and reinstalls.
A P45 or x48 based LGA775 platform would take you from a P4 through the 45nm Core 2 arch, an AM2+ platform could take you from an Athlon x64 to Phenom II and an additional LGA1366, LGA1156 and LGA1155 platform would round it off.

At the end of such an article you would be able to definitively quantify relative IPC performance between dissimilar architectures and different generations of similar architectures.
Additionally, it would be possible to create, and maintain upon the release of new architectures, a new chart showing the Performance Per Clock of each arch for simple reference.

I believe an article such as this would be extremely enlightning and quite true to Toms roots.
Thanks for reading and considering this proposal.

-outlw
April 13, 2011 2:19:13 PM

Cool suggestion! I'll pass it along. :) 
a b à CPUs
April 14, 2011 9:50:25 AM

Thanks :) 
Related resources
April 22, 2011 2:31:36 PM

This is a really neat idea, and something I've wanted for a long time.
a b à CPUs
July 26, 2011 10:02:49 AM

Hey, the article just Went Live!
Good read and looks to have been tons of work.

Thanks Toms team for making this idea come to light [:jaydeejohn:5]
July 29, 2011 3:43:02 AM

The issue is that for a decent part of interest for say any compariosn would say that each design be within a place or "equally" placed interest of use.

And of accordingly with each design for a "equally" placed use.

In most places of interest may seem of lack of thought of course but rather or not is is probably as placed as the interest would be of thought on anything of the idea.

To say at anytime though that something "specific" to say has ever taken a part of interest for anything of interest is probably as hard found as it is of what might be specific placed, if not in lack of better words. Use might work better.

Obviously though of all the say information of such ideas is placed within only knowing of rather any pretain of place of actually information. Given of course though probably 99% of information is this way. Least of the idea on idea there can be information of it, the idea.

Given though say, of thought only so much information of information can be of actually say of infomation given what could be found of information. But still of it is a reporting part of say the information, yes?

I would say of that for even Toms use of idea of applied is in alot of conflict of the ideas of present for issues of any sorts of ways of information. So, even of the idea is one of lack right now of actually gaining any support of the issue within non-lack of one.

But of all information, information, is information, all that is actually probably needed ins't to some form of it. But only specifically preferred I think would be a better place of say to say.

Of course, interest to say of even place of part of information for information might be something of information that is only that. I could probably type information over and over again, literally the word for itself only be able to get across the idea of information. Or Information in itself. Even then though to say rather that is still possible within doing so is anyones guess.

But still, of the idea, we must ask, is it one already in use?? Do we have to ask?? We are reading question yes, or anyone who does?? If not a question to say. Sometimes and idea isn't a question, but can bring from maybe what a question is.

Rather there is any relevence of the difference is hard placed though. Finding is probably always best, otherwise it just is, Yes?

Otherwise it is just information, relevence is usually illrelevent to say, for the fact of it. Yes? But , not always for the idea of though at least as well too. This might be specific though, yes?

To say information is or not is anyones guess. But of it though is information. So, to say its a bad idea, who knows... I would say say it would be alot of an idea to say maybe. And alot isn't the idea say for here at least at the site, rather in part or whole. Yes?

So, of working within anything of the idea would only probably be placed within how the part of idea has kinda already been in take for "a" idea.
a b à CPUs
July 29, 2011 7:13:00 AM

Sorry K-zon, but I can not understand a word of your post :??: 
!