Core Multiplexing technology???

Quote:

---

Originally Posted by Ailleur

I dont think anyone ever doubted (not that ive seen anyway) that code could be paralelized by hardware. What was doubted (and rightly so) is that one instruction could be split to execute on 2 cores.

---

David Kanter of RWT didn't believe so:

http://www.realworldtech.com/forums/...9280&roomid=11

Some bought it out of the shoot, others (like myself) were simply not convinced choosing to be more skeptical. It took me a few hours over two weekends to dig up enough literature and educate myself on the principle.

Actually, some of the enthusiast HW sites are exclaiming that AMD with RHT will meld 2 cores to mimic 1 virtual core, the Inq. claims it will take two 3 IPC (issue) cores and make one 6 IPC (issue ) core. This is not quite true, in fact the peformance speed up is governed by Amdahl's Law for the most part and how effectively the thread can segment and execute correctly. A 2x gain is quite not possible in a normal single threaded application. David Kanter does a good job above rationalizing the two different architectural states of each core.

if this is true the cpu will be fast as hell

So would this actually require a driver to be installed into the actual OS as well as a BIOS option?

Quote:

---

Originally Posted by Haltech

So would this actually require a driver to be installed into the actual OS as well as a BIOS option?

---

Preferably just a Bios update. kind of how early dual core AMD samples needed a bios update for the computer to detect the second core...

Quote:

---

Originally Posted by lndeo

802.11g
802.11g is a proposed standard, describing a wireless networking method for a WLAN that operates in the 2.4 GHz radio band (ISM--Industrial Scientific Medical frequency band). By using OFDM (Orthogonal Frequency Division Multiplexing) technology, 802.11g-based WLANs will be able to achieve a maximum speed of 54 Mbps. 802.11g-compliant equipment, such as wireless Access Points, will be able to provide simultaneous WLAN connectivity for both 802.11g and 802.11b equipment.

---

further -

Quote:

---

Originally Posted by lndeo

OFDM is nothing new — its core multiplexing principles have been applied to everything from satellite broadcast to ADSL. Over the last decade, the technology has played a critical role in wireless, forming the basis of the IEEE 802.11a standard and, most recently, the critical multiplexing scheme for the WiMAX Forum's next generation of wireless broadband specifications.

---

http://forums.overclockers.ru/viewto...dcecf98e79ad8c

if bad axe has 802.11 integrated, bios item core multiplexing can just control 802.11 -:))))))))))))

though phrase "core multiplexing principles" can be explained also as "fundamental multiplexing principles" - if so, I am sorry

This thread made it to TweakTown ;)

http://www.tweaktown.com/index.html#news_5891

lol it looks like core multiplexing was removed from the most most recent bios.

I don't have a Badaxe so I don't know, but didn't it just say they moved it from the main page... so the option could be on a different one? (I have no clue, just stabbing around in the dark so to say).

do you still beleive in intel virtual core?
unknown bios menu item is not a proof of its existance
one more myth

Quote:

---

Originally Posted by Burdman

I don't have a Badaxe so I don't know, but didn't it just say they moved it from the main page... so the option could be on a different one? (I have no clue, just stabbing around in the dark so to say).

---

They hid the BIOS option. It is still there but hidden. Open the Bios with ITK to see.

somebody, send me this bios image
i will disassemble it and look at it's internals
just interesting

Wow, rumourmill is churning out a lot of pointless stuff from the gutter.. Homemade pictures and people believe in it.. Yes, "added for effect" sure made the wanted effect.

Quote:

---

This is what Intel spokesman said when asked about it:

Quote:

---

“We will support the disabling of one core in BIOS in a future BIOS rev.,” said Daniel Snyder, a spokesman for Intel Corp., when asked about the background of the technology. This means that once one core is disabled, the whole 2MB or 4MB cache reservoir on microprocessors that have shared level-two (L2) cache will be usable by one processing engine, which should boost performance in applications that cannot take advantage of two executing cores.

It is highly-likely that the feature will only work on the upcoming Core 2 processors code-named Conroe, which have shared L2 cache between its cores. It is also likely that the capability will allow quad-core chips to act like two dual-core processors in situations when four processing engines cannot be used efficiently.

---

---

Quote:

---

Originally Posted by Scyphe

Wow, rumourmill is churning out a lot of pointless stuff from the gutter.. Homemade pictures and people believe in it.. Yes, "added for effect" sure made the wanted effect.

---

This is totaly different BIOS option (more related to power saving) and been known for a while now

Yes.. and it's probably what all this misdirected hullaballo is all about. But what do I know (or anyone else for that matter).

Quote:

---

Originally Posted by freecableguy

yes we do ;)

EDIT: pictures added for effect. :)

Conroe: 2 -> 1 core possible

http://www.xtremesystems.org/forums/...1&d=1151105210

Kentsfield: 4 -> 2 cores possible

http://www.xtremesystems.org/forums/...1&d=1151105299

-FCG

---

Congratulations, these diagrams are on all the enthusiast sites.

Quote:

---

these diagrams are on all the enthusiast sites

---

but it doesn't work and scarcely will work

Quote:

---

Originally Posted by LOE

did you guys even read what Intel said? They said core multiplex disables one core so app can take full advantage of the shared cache...

---

where did u read that ? link please ?

i||uSi0n^

Quote:

---

Originally Posted by LOE

did you guys even read what Intel said? They said core multiplex disables one core so app can take full advantage of the shared cache...

---

Thats not Core Multiplexing, thats the SW Single Core option in the BIOS.

No, as far as I know with SW Single Core "enabled" in BIOS, one core is always disabled.

CMT lets to use the whole cache to one core when single thread app is running, but both cores are "active".

They are different things.

Quote me

Quote:

---

SW single CPU does indeed cause the PC to boot and use only 1 core. SW single core gave a slightly faster Pi time tho that may be an anomaly.

---

Quote Cooper in next post down

Quote:

---

Don`t think it`s a anomaly. L2 is shared, so you have all 2MB just for one core -> better result.

---

Given that explaination it looks like SW core disable does shove all the cache over to 1 core, and multiplexing is somethign else, probably as FCG described

I don't think it's the same explanation. With SW single core enabled in BIOS, one core is *ever disabled*, so you have only one core, and yes, because shared cache, the only core enabled uses all cache.

With CMT both cores are *ever enabled* but when a single thread app is running, CMT lets that the core where it runs uses the whole cache too.

I extract this possible explanation of what CMT is, from here http://www.xbitlabs.com/news/cpu/dis...627095448.html

Maybe here we have answer?
http://www.anandtech.com/tradeshows/...spx?i=2507&p=7

so how is single core different from this core multiplex technology?? they are different right?? CMT turn multi thread into 1 core or 2 core (kentsfield) right??

Quote:

---

Originally Posted by theteamaqua

so how is single core different from this core multiplex technology?? they are different right?? CMT turn multi thread into 1 core or 2 core (kentsfield) right??

---

If its the same as what is shown in the Anandtech article then Core Multiplexing would allow an idle core to do speculative threading work instead of sitting doing nothing. If you have multi-threaded code then it goes to work on the other thread instead automatically.
Single core mode turns off the second core completely, no operations carried out whether you have multi-threaded code or not.

Quote:

---

Originally Posted by yoti

Maybe here we have answer?
http://www.anandtech.com/tradeshows/...spx?i=2507&p=7

---

No, Mitosis, at this moment, is only a paper project, far to be implemented...

Quote:

---

Originally Posted by PetNorth

No, Mitosis, at this moment, is only a paper project, far to be implemented...

---

HAHAHA! But RH/T is real and proven right?

dunno about him, but they are both BS in my book

its too early to say anything until both AMD and Intel give out some info.

i||uSi0n^

Quote:

---

Originally Posted by i||uSi0n^

its too early to say anything until both AMD and Intel give out some info.

i||uSi0n^

---

QFT!

As for Core2 Duo,there is no clustered mulithreading in it.Just simple no.Mitosis is a 5 year project with possible introduction in Nehalem core(which is not so distant time).

And as for AMD's clust. multithreading ...Well ,Rahul Sood just confirmed it on his blogspot(in comments section on his latest blog entry).

So expect to see it introduced on the dawn of Conroe's release.
Performance were not mentioned,but Rahul said that it "Sure helps" in the fight against Core2 Duo.We will see how much ;)

Quote:

---

Originally Posted by Donnie27

HAHAHA! But RH/T is real and proven right?

---

I thought this thread was about CMT. Did I miss something?

Quote:

---

Originally Posted by PetNorth

I thought this thread was about CMT. Did I miss something?

---

Its about Intels new tweak yes, but we are bound to have talk of AMD's responce also as in reality they are the same thing.

It makes me wonder if you guys don't want more speed reading this thread, some of you seem unwilling to embrace new tech...

Its just a shame I haven't dug any further info as of yet...

No Tony, the question is that some of us are unwilling to embrace simple rumors, speculations, inventions or whatever, without any near or remote fact.

Quote:

---

Originally Posted by Tony

Its about Intels new tweak yes, but we are bound to have talk of AMD's responce also as in reality they are the same thing.

---

Amd's responce to what???:confused: To disabling one core/using all the L2 cache?Amd use exclusive caches for their multicore...

For 1000th time,there is no clustered multithreading in Core2 Duo.Amd doesn't have to respond to anything since it is not there.

Quote:

---

Originally Posted by PetNorth

I thought this thread was about CMT. Did I miss something?

---

Explain that to the others link on post #133 LOL!

Quote:

---

Originally Posted by informal

Amd's responce to what???:confused: To disabling one core/using all the L2 cache?Amd use exclusive caches for their multicore...

For 1000th time,there is no clustered multithreading in Core2 Duo.Amd doesn't have to respond to anything since it is not there.

---

Here, try out this response?

Quote:

---

Originally Posted by Hans de Vries

Originally Posted by back in April
Name: Hans de Vries (hansdevries@chip-architect.com) 4/6/06

ten9 (jhdjksa@huhu.com) on 4/6/06 wrote:
---------------------------
>Hello Hans,
>
>Do you think there is a fourth decoder like Gipsel argues
>here:
>
>http://www.aceshardware.com/forums/...60237&forumid=1
>

These are the micro-code ep(roms) for complex cisc
instructions. They operate as one single memory since
they all get the same address from the micro-sequencer
which handles the complex instructions. Going from 3 to
4 therefor doesn't say anything at all, it's just more
memory, or the same amount of memory with larger cells.
The rest of the architecture is visibly 3-way. The re-
order buffer, the integer schedulers, the integer ALU's.


>And what do you think about the floating point units?
>

It's virtualy identical to existing K8's. There are also 3 HT
units and not 4 as claimed by somebody at aces. It's not a K8L.

>Regards,
>
>Ten9
>

It seems to be an earlier prototype in which they were still
experimenting with the new much denser L2 cache. The fact
that they left open such a wide area with the size of the
old cache means they were not sure enough about it at that
time. Showing the cache now would imply that it must be OK.

More cache would be the most important thing for AMD to
counter Conroe's integer IPC.

Regards, Hans

---

So much for the other BS!

Now it reamins to be seen what and how Core Multiplexing will work but at least let's wait and see!

Quote:

---

Originally Posted by PetNorth

No, Mitosis, at this moment, is only a paper project, far to be implemented...

---

If you are interested in more technical details of Mitosis, here are a few Intel authored paper:

http://www-cse.ucsd.edu/users/tullsen/pldi2005.pdf published in June or 2005
http://www.ece.lsu.edu/tca/papers/collins-01.pdf another 2001 I believe.
http://www.cs.ucsd.edu/~jbrown/papers/sp-cmp.pdf
http://www.iccd-conference.org/proce...4/22310360.pdf

Just a handful, but Intel has been working on this for quite some time evidently, I have found papers (PDF files not electroncially available) dating back to 1996.

Quote:

---

Originally Posted by JumpingJack

Just a handful, but Intel has been working on this for quite some time evidently, I have found papers (PDF files not electroncially available) dating back to 1996.

---

:eek: thats quite a long time ago lol

I wonder that Anandtech said 5 years (in 2005)... that would mean at least 14 years of research. Seems very long. Lets hope that CMT [exists and] is an implentation of Mitosis.

Interesting how for years we try to go multicore and what have you and the moment we get it we all try to get it to act like a single core again.

Obviously an extreme oversimplification but yeah. I really think we're all better off getting devs writing multithread happy code and hoping that the os's and the drivers and the hardware starts communicating together better.

I seem to remember reading ssomething from intel about how they're actually moving toward a somewhat cell like approach with lots of "special purpose" mini cpus that are much better at doing what they do best and having a single general purpose unit that can allocate the workload off to the other more specialized units but without such a penalty as Cell seems to have with it's non optimised code where it just falls over.

Oh happy first post to me. Been lurking for awhile but figured i'd better start somewhere :D

Quote:

---

Originally Posted by Tranzmit

Interesting how for years we try to go multicore and what have you and the moment we get it we all try to get it to act like a single core again.

---

Happy 1st post! Singlethread performance is a bit interesting for me right now, next year i probably couldnt care less. But maybe i care again when/if i get a Kentsfield? Lets say a coming game is optimized for dualcore and cant utilize the 4 cylinders of Kentsfield, then this sounds like a great way to make Kentsfield a monster Twin.

Quote:

---

Originally Posted by Donnie27

Explain that to the others link on post #133 LOL!

---

You know, I'm only responsible for my posts ;)

Quote:

---

Originally Posted by ted3

Happy 1st post! Singlethread performance is a bit interesting for me right now, next year i probably couldnt care less. But maybe i care again when/if i get a Kentsfield? Lets say a coming game is optimized for dualcore and cant utilize the 4 cylinders of Kentsfield, then this sounds like a great way to make Kentsfield a monster Twin.

---

I am sure they don't make it dualcore optimized but multithreaded...;)

Quote:

---

Originally Posted by Vassili

I am sure they don't make it dualcore optimized but multithreaded...;)

---

Wish i could be as sure about that as you are... Parts of a games code can be executed in separate threads but it demands a very solid code to hand off everything to threading. Most games could prove to complex to do that, its very likely that the main logic has to execute in one thread, what remains is not enough work to utilize 3 cores (or even one core in some cases), those threads could too often just sit there and wait for the main thread with a Kentsfield.

Anandtech interviewed Tim Sweeney about this once, the future looks bright but you could also get the impression that multicores mainly give the developers the chance to add lots more bells and whistles. Good for realism, lets hope thats not all.. Just got to wait and see, i hope you are correct Vasilli, but i have my doubts for now :)

Quote:

---

Originally Posted by PetNorth

You know, I'm only responsible for my posts ;)

---

Yes you are, my bad.

Quote:

---

Originally Posted by ted3

Wish i could be as sure about that as you are... Parts of a games code can be executed in separate threads but it demands a very solid code to hand off everything to threading. Most games could prove to complex to do that, its very likely that the main logic has to execute in one thread, what remains is not enough work to utilize 3 cores (or even one core in some cases), those threads could too often just sit there and wait for the main thread with a Kentsfield.

Anandtech interviewed Tim Sweeney about this once, the future looks bright but you could also get the impression that multicores mainly give the developers the chance to add lots more bells and whistles. Good for realism, lets hope thats not all.. Just got to wait and see, i hope you are correct Vasilli, but i have my doubts for now :)

---

What if that second core could help the GPU, NIC and Sound cards? Folks are selling P-GPUs now.

Isn't this what multiplexing is really About?

http://www.intel.com/pressroom/archi...0040218net.htm


Intel Unveils Platform Strategy For Ultra-Wideband Wireless Technology ...
... complete specification for a multi-band orthogonal frequency division multiplexing (OFDM) technology-based ... For more information on IDF and Intel technology, visit http://developer.intel.com



I believe we will see Mitosis with the Nehalem core If AMD has RH/T now as many claim . We may see Mitosis on Penryn

I am sorry for being late for this very interesting discussion.

Quote:

---

Originally Posted by Pomme

That seems like a very innovative and impacting development for the future. That would make life of programmers a lot easier, causing low cost software to benifit from multiple cores.. Right ?

---

Wrong!

That seems like a completely unneeded and uncalled for thing to waste expensive silicon estate on. Like someone would actually blame CPU manufacturers because their latest multi-core CPUs are slow at single-threaded apps?!? Come on people :slapass:, we all know that software is light years behind the current hardware.

This technology instead of helping us to close the gap between hardware and software it will just make it worse. It will slow down software development because there would be no need to optimize for multi-core, to change algorithms, logic, and go parallel. Software prices would stay high because nobody would see the need to invest R & D money in speed improvements in order to gain advantage over the competition when they will be getting improvements for free -- improvements they do not deserve!

In many cases it will simply not work. Think of this, you insert CD and select the drive in Total Commander and it blocks waiting for the drive to become ready.So even if you throw two cores at it via Reverse-HT or CMT it won't unblock. Same goes for Windows Explorer.

So while Total Commander or Windows Explorer or (________ insert your favorite app here) is stalled spinning on one core of your dual-core CPU you still have another core free. With CMT and Rev-HT what will you have? One busy core unresponsive for other tasks. No hardware can sort that programmer's mess out.

God how I hate programmers who wish their lives to be easier!!! Then don't be a programmer! Yes, it is that easy -- just go load some coal instead.

So if you haven't figured it out yet, I am all against wasting time and silicon on those two technologies and I call both AMD and Intel to action -- spank some programmer's asses instead!

Link

Quote:

---

Originally Posted by audiofreak

God how I hate programmers who wish their lives to be easier!!! Then don't be a programmer!Link

---

I fail to see how this is a bad thing. Making their lives easier with this technology means they can push out code easier and more efficiently and not have to worry about making programs which are multithreaded and optimized for dual core. This way, all programs become dual core ready. It also means that those programs that are written for dual core will run that much faster.

BTW, I'm not a programmer, and I don't write code. This is logic, pure and simple. It's not hard to understand. In this day and age, making a process easier usually helps those who are involved in the given process.

so wait, if i get conroe and not doing anything to bios. this thing is enabled just like that?? cuz i heard someone said ints on the cpu side ...

just so long as you realise that "this thing" in Conroe has nothing to to with speculative threading and that all the discussion in this thread is in no way related to what is in Conroe...

BrownTown you waste your time repeating that,i said it 10 x at least and no effect what so ever.The important thing is that ppl are spreading FCG's pictures on the net and kids are talking about CMT not knowing wtf are they talking about:rolleyes:

Quote:

---

Originally Posted by Turtle 1

Isn't this what multiplexing is really About?

http://www.intel.com/pressroom/archi...0040218net.htm


Intel Unveils Platform Strategy For Ultra-Wideband Wireless Technology ...
... complete specification for a multi-band orthogonal frequency division multiplexing (OFDM) technology-based ... For more information on IDF and Intel technology, visit http://developer.intel.com



I believe we will see Mitosis with the Nehalem core If AMD has RH/T now as many claim . We may see Mitosis on Penryn

---

Multiplexing is simply a term applied to many different situations, it is simply consisting or maintaining multiple parts or interleaving multiple parts to share singlular resources. It is applicable in radio technologies where signals will be multiplexed over similar bands or it is a logical application of term to the contcept of spreading a single thread over several cores.

Your assement above is a good one. I would tend to agree.

so whats with the bios 1181 on boarrd 975xbx?? i mean why did they enable it?? and took it out couple days later on a newer bios.

Quote:

---

Originally Posted by theteamaqua

so whats with the bios 1181 on boarrd 975xbx?? i mean why did they enable it?? and took it out couple days later on a newer bios.

---

:) Look at what it has done to the rampant rumors and speculation --- either it is what we think it is, but not ready for prime-time.... or it was imply a goof and means something else altogether.

I guess we'll have to wait till they "enable" it, which may well be after AMD does

Quote:

---

Originally Posted by freecableguy

4 cores -> multiplexed to 2 cores....imagine that.

Kentsfield at 3.6GHz could easily look like a Conroe @ 6GHz+

;)

---

and that mean - 4 sec in super pi :D

Quote:

---

Originally Posted by cupra

and that mean - 4 sec in super pi :D

---

takes the spliff from Cupras and inhales deeply too :p:

mmm thats some good :banana::banana::banana::banana: you smokin there

Quote:

---

Originally Posted by audiofreak

God how I hate programmers who wish their lives to be easier!!! Then don't be a programmer! Yes, it is that easy -- just go load some coal instead.

---

Wow, I do take offesne to such comment. If you happen to be a programmer, please only use machine language from now on in name of optimization. Your program will run twice faster if not more on many instances. And also, for loop instructions, optimize it per each cpu that it will be used since that will be most time consuming of processor utilization.
:stick:
I hate those people who think programmers programming should be an artist. It could be but in all practical senses, it has become art of production not art itself...
I get the feeling someone is still living under rock.

***warning... following can be very long and extremely boring***
Here is an example of why such technology can benefit.
Typical business setting. Business application that handles multiple things at same time. It can use optimization greatly to maybe improve performance by 60%. Software is used by 100 employees that actively uses it 4 hours a day. Let's say realized improvement is 20%. Realized revenue increase from improvement is 10% (this is very high number for those of you who have worked in IT... 5% is considered incredible).
Avg salary 50k is assumption here. Programmer salary avg let's say 100k (counting in the people who actually can do this multicore optimization... this is considered pretty high end).
Also, this application gets renewed every year in many facet in functionality, etc
Now let's boil down hard numbers: With optimization say we see 60% improvement in software.

Optimization cost for current application at least usually is 200k or so in such type of codes. Benefit from such code optimization first year. about (half a day) 10% of total employee salary of 100is 250k. So total gain first year is 50k.
Subsequent maintenance improvement based on schedule probably will cost 100k more than otherwise thanks to complexity of changing such optimized code. Subsequential gain of such endeavour is 150k each year. Life of such program usually is 5 years until some high lvl changes and wants brand new system that works with "the new goal of company"
so during life span of such program, benefit is 650k. Not a small number.

Now, without optimization but with optimized software let's say we see 40% improvement in software. Realized gain 13%. Revenue improvement 6.67%
Cost is none up front. First year gain in proportion would be 6.7% of total salary. 167k per year. benefit over 5 year span... 667k.

changing the number around a little to larger company of 200. We will have bit better return. 1850k for optimization, 1670k for non optimization...

Now, this didn't taken into account of downtime for entire company, etc for upgrading suite of software that goes with such major endeavour (basically H/W and software upgarde need to be closely matched etc which usually do add time to upgrade). Most of companies of non financial nature does expect 1-2 days delay of no system in such scenario (financial ones tend to do more qa and through line up of what should happen and backup procedure planning which adds huge amount of money on developmental/deployment cost).

So.... for all the trouble, how much gain is there? Really, how much gain? Programmers don't get paid to make art. They get paid to do the job that will benefit company...

I think I went a bit far off.. not saying optimization is futile, it isn't. For new applications, etc... it probably is more than worth it to invest time & money in. But disregarding technology that immediate benefit possible and cost saving to most companies especially small to medium sized ones... is... bit careless to say the least.

see now, someone went and p***ed off the programming gods

isn't it just good enough to say this technology would benefit single-threaded applications, and because of that, it is good...?

hardware is coming so fast in this days...software could not folow...programers fault?Not. my opinion.........

Ok,this is what intel rep. told to overclcokers.ru when asked about CMT:

Quote:

---

CPU Multiplexing Technology Is A basic input-output system Feature That Turns Off One Of The Processor Cores For Integrator Testing Purposes. This May be available in a future BASIC INPUT-OUTPUT SYSTEM revision.

---

Everyone sorry for a bit of offtopic but I believe this is important.

Quote:

---

Originally Posted by Mad Pistol

I fail to see how this is a bad thing. Making their lives easier with this technology means they can push out code easier and more efficiently

---

True that they could push out code easier and more efficiently, but that code won't be any better than it is now (which is very bad). Another part of the equation will be reduction in salaries because there will be less work to do. Moreover, if the trend that leads to (over)simplification of programming continues, it will end up with a bunch of monkeys bashing at keyboard for a handfull of peanuts.

Quote:

---

Originally Posted by Mad Pistol

and not have to worry about making programs which are multithreaded and optimized for dual core.

---

Even the most simple programs have at least two threads, one for processing user interaction and another one doing the work in background. Multi-threading properly done for dual-core now will scale up and get boost automagically on quad-core, octa-core, etc. IMO it is better to worry about that now because it is future proof rather than to do nothing with already broken code and expect hardware to fix bad programming practices.

Quote:

---

Originally Posted by Mad Pistol

This way, all programs become dual core ready. It also means that those programs that are written for dual core will run that much faster.

---

And how will those old unoptimized programs cooperate with properly multi-threaded ones?

Quote:

---

Originally Posted by Mad Pistol

BTW, I'm not a programmer, and I don't write code. This is logic, pure and simple. It's not hard to understand. In this day and age, making a process easier usually helps those who are involved in the given process.

---

Unfortunately your logic is broken. In this case, you have hardware vendors trying to accomodate hardware to the poorly written out of date software. It is ok up to a point but IMO this is way too much. Analogy in real life would be as if car makers would try to make cars for blind, instead of doctors giving them the ability to see and use regular cars.

For the record, I am a programmer and I believe that I know what I am talking about.

Quote:

---

Originally Posted by jinu117

Wow, I do take offense to such comment. If you happen to be a programmer, please only use machine language from now on in name of optimization. Your program will run twice faster if not more on many instances. And also, for loop instructions, optimize it per each cpu that it will be used since that will be most time consuming of processor utilization.

---

Wow, I sense a person who has once tried to optimize some code and gave up. Just you continue "producing" (or is it copy/pasting?) 100,000 of lines of code in Visual Basic a day, and don't worry, AMD and Intel will take care of your inefficiency. Give me a break!

Quote:

---

Originally Posted by jinu117

I hate those people who think programmers programming should be an artist. It could be but in all practical senses, it has become art of production not art itself...

---

Well I am one of those who consider programming to be a bit of an art and not a production line so I guess you hate me already. But let me tell you something -- if your work is all about quantity and nothing about quality then you have already lost. You lost yourself and when you are gone there will be nothing worthy left behind you as a proof that you ever existed. Same goes for all of you "code producers". :fact:

Quote:

---

Originally Posted by jinu117

I get the feeling someone is still living under rock.

---

Better that than working in a sweatshop.

Quote:

---

Originally Posted by jinu117

***warning... following can be very long and extremely boring***

---

It was boring and I believe your numbers are off just as your beliefs. I sense that you still don't understand that applications should be written with optimization in mind. Optimization should not be an afterhtought but rather part of a development cycle and when it is, it doesn't add that much to the cost.

For the cases where you already have unoptimized code, it is usually already hard enough to maintain it, so why not rewrite those most time consuming parts to finally gain some advantage from all those gigabytes of memory, MIPS-es and GFLOPS-es that are being wasted?

A friend of mine and I are optimizing medical imaging applications for a U.S. based company. We started from their code which has undergone some attempts of optimization by others. They even bothered to write SSE2 code for inner loop but we thrown that out because it was SCALAR. Since then we rewrote and rearranged parts of it in such a way that we got more thant 20x reduction in processing time from the initial optimized code for which everyone believed there is no way to make it any faster.

As a side effect of such code revamping, calculations got more precise resulting in clearer pictures. For their clients speed and clarity mean business advantage so the cost is heavily outweighted by the gain.

Right now when everyone believed that there is no more room for speedup, we made a version which runs on a GPU and it does so 4x faster than our heavily optimized CPU code. We had to change algorithms, we had to think of new ways of doing same things, to overcome limitations imposed by GPU architecture but we did it.

In my opinion there is no point in wasting silicon to make soon to be gone single-threaded applications run faster. Moreover, there is no point in wasting valuable time waiting for hardware manufacturers to fix things that we can and should fix.

I am sick and tired of having to upgrade every few months to be able to to continue to use new version of a same lousy bloated piece of software with only cosmetic improvements. Take Windows Vista as an example -- an operating system that needs 15GB of space and 2GB of RAM just for itself to run comfortably takes the top place in my book of software inefficiency. Now where is that code reuse everyone was talking about?!?

Quote:

---

Originally Posted by VulgarHandle

isn't it just good enough to say this technology would benefit single-threaded applications, and because of that, it is good...?

---

It may benefit and we have yet to see how much. On the other hand, bugging software vendors to fix their code and not letting them milk the same old cow anymore would do much more good to the end user.

So programming is an art? Are you an artist Audiofreak? :D
Im just a programmer, like any other job its hard sometimes and fun sometimes, sometimes very inspiring and sometimes just boring, cant see the big artistic aspect of it.

I have made a few multithreaded Win32 services for NT4 and W2K Server, and sometimes one thread would cause other threads getting queued up while it finished some of the harder stages (for example one case where working against a third party service), i would have welcomed higher single thread performance that time instead of one CPU doing all the work while all others are idle and waiting. Similar things happen all the time, lots of threads has to wait for a "main thread" before they can continue execution. Tech like this only opens up new possibilities, i cant see any scenario where it would make things worse, but then again, im just a code producer i guess...

One more thing Audiofreak, since you already mentioned bad programming practices, you are looking down on the skills of other programmers, and THATS what is really bad programming practice :nono:

Quote:

---

Originally Posted by grimREEFER

i dont like this concept, u get the best performance with kentsfield when there are 4 threads at once lol, how hard is it to do that !!!

---

Only very very, extremely insanely hard =)

Except of course for the few areas where paralellization is easy to do. easily predictable, non-chaotic code (which is "only" a lot of work to multithread well), but thats not a very big part of the software peopel normally use, and neither is it generalyl where we really NEED more computing power.

-Stigma

Quote:

---

Wow, I sense a person who has once tried to optimize some code and gave up. Just you continue "producing" (or is it copy/pasting?) 100,000 of lines of code in Visual Basic a day, and don't worry, AMD and Intel will take care of your inefficiency. Give me a break!

---

I am sorry to say these... but I probably do have much much more experience than you in many fields of programming through my carrier. I used to program in low level as low as device driver, machine recording for black box in boeing 777, naviational system sub system for few planes, all the way up to highlevel programming of SQL coding, etc, etc. Obviously optimization is daily part of my life now that I am more of DBA/Project manager than any other time. What would be your credentials... it seems like this is the exact opinion I had until I started working about 15 years ago in industry. (oh programming was in my blood for well over 25 years in total... I am one of those crowd that started with some peek and poke, assembly, C/D and saw technology improvement in PC area for entire life so far)

Quote:

---

Well I am one of those who consider programming to be a bit of an art and not a production line so I guess you hate me already. But let me tell you something -- if your work is all about quantity and nothing about quality then you have already lost. You lost yourself and when you are gone there will be nothing worthy left behind you as a proof that you ever existed. Same goes for all of you "code producers". :fact:

---

- Art of production. You just don't get it. Sweat shop and art of production are not same thing.

Quote:

---

It was boring and I believe your numbers are off just as your beliefs. I sense that you still don't understand that applications should be written with optimization in mind. Optimization should not be an afterhtought but rather part of a development cycle and when it is, it doesn't add that much to the cost.

---

Maybe you were happily producing new code each day... but in reality, where money flow of codes are at (financial and normal business processing part of life), such can't just happen. In fact, on any decent sized application, the only part our team usually can touch is just portion of it. Believe me... such imaging technology or lab related programming is miniscule part progamming sector. Just look at how many people understand assembly really, not even machine language vs other type of coding languages? It is quite apparent.
In fact, I think something like your image enhancing can benefit greatly from such endeavour. Let me ask my friend who works at NASA on imaging to see if he got some comments about such :)

Quote:

---

It may benefit and we have yet to see how much. On the other hand, bugging software vendors to fix their code and not letting them milk the same old cow anymore would do much more good to the end user.

---

--> it cost those companies to revamp... they are out to make money... the cost goes straight back to customers... Bit surprised such simple concept can't be understood.

PS) Now... this has become more of discussion of impact of technology and beliefs of what would be advantage and not... which still isn't bad. I do kind of understand where you are coming from. Yes YOU ARE programming GOD who is better than your peers. You are IT. Maybe, get yourself involved in bit different sector of programming... whole new world where negotiation, project management, and specification writing in match with real world workflow adjustment, etc do take center stage than regular programming. Lot of project integrator in the site would agree :) Good day off to you and yes, you might be wonderful but that doesn't give you reason to put me down.

111111000011111
111110011001111
111100111100111
111110011001111
111111000011111
111111000111111
111100000000111
110001000010011
110001000010011
110001000010011
110001000010011
110001000010011
111111000011111
111110000001111
111110011001111
111110011001111
111110011001111
111110011001111
111000011000011

Programming art? :D

Quote:

---

I am sick and tired of having to upgrade every few months to be able to to continue to use new version of a same lousy bloated piece of software with only cosmetic improvements. Take Windows Vista as an example -- an operating system that needs 15GB of space and 2GB of RAM just for itself to run comfortably takes the top place in my book of software inefficiency. Now where is that code reuse everyone was talking about?!?

---

Yo Audio Freak!Still kicking ass all over the internet, i see :D.Good to have you here!:toast:
I think programers make instructions and also they receive instruction from their bosses :D.Somehow it seems that ,maybe,sometimes, some software are made of bad code for purpose.Buy more hardware,buy new hardware.:D

here's a little blulb from xbit labs conroe preview

"for instance the current discussion of Core Multiplexing Technology that indicates that Intel engineers are ready to offer their solution for dynamic disabling of the second processor core depending on the type of workload the CPU is experiencing"

Im not sure why you would want to disable the second core, other than power concerns, its not going to increase performance unless the cache can be linked

Quote:

---

Originally Posted by jbrukardt

Im not sure why you would want to disable the second core, other than power concerns, its not going to increase performance unless the cache can be linked

---

the l2 is shared, so 1 core can have 2/4mb if need be. (depends on the max cache the cpu was made with)

Quote:

---

Originally Posted by jinu117

Wow, I do take offesne to such comment. If you happen to be a programmer, please only use machine language from now on in name of optimization. Your program will run twice faster if not more on many instances. And also, for loop instructions, optimize it per each cpu that it will be used since that will be most time consuming of processor utilization.
:stick:
I hate those people who think programmers programming should be an artist. It could be but in all practical senses, it has become art of production not art itself...
I get the feeling someone is still living under rock.

***warning... following can be very long and extremely boring***
Here is an example of why such technology can benefit.
Typical business setting. Business application that handles multiple things at same time. It can use optimization greatly to maybe improve performance by 60%. Software is used by 100 employees that actively uses it 4 hours a day. Let's say realized improvement is 20%. Realized revenue increase from improvement is 10% (this is very high number for those of you who have worked in IT... 5% is considered incredible).
Avg salary 50k is assumption here. Programmer salary avg let's say 100k (counting in the people who actually can do this multicore optimization... this is considered pretty high end).
Also, this application gets renewed every year in many facet in functionality, etc
Now let's boil down hard numbers: With optimization say we see 60% improvement in software.

Optimization cost for current application at least usually is 200k or so in such type of codes. Benefit from such code optimization first year. about (half a day) 10% of total employee salary of 100is 250k. So total gain first year is 50k.
Subsequent maintenance improvement based on schedule probably will cost 100k more than otherwise thanks to complexity of changing such optimized code. Subsequential gain of such endeavour is 150k each year. Life of such program usually is 5 years until some high lvl changes and wants brand new system that works with "the new goal of company"
so during life span of such program, benefit is 650k. Not a small number.

Now, without optimization but with optimized software let's say we see 40% improvement in software. Realized gain 13%. Revenue improvement 6.67%
Cost is none up front. First year gain in proportion would be 6.7% of total salary. 167k per year. benefit over 5 year span... 667k.

changing the number around a little to larger company of 200. We will have bit better return. 1850k for optimization, 1670k for non optimization...

Now, this didn't taken into account of downtime for entire company, etc for upgrading suite of software that goes with such major endeavour (basically H/W and software upgarde need to be closely matched etc which usually do add time to upgrade). Most of companies of non financial nature does expect 1-2 days delay of no system in such scenario (financial ones tend to do more qa and through line up of what should happen and backup procedure planning which adds huge amount of money on developmental/deployment cost).

So.... for all the trouble, how much gain is there? Really, how much gain? Programmers don't get paid to make art. They get paid to do the job that will benefit company...

I think I went a bit far off.. not saying optimization is futile, it isn't. For new applications, etc... it probably is more than worth it to invest time & money in. But disregarding technology that immediate benefit possible and cost saving to most companies especially small to medium sized ones... is... bit careless to say the least.

---

Its a pretty gritty world out there. Kids becoming doctors that aren't fit to examine your pets. Kids becoming Lawyers that aren't capable of doing the paper work to lincess those pets. The doctors aren't qualified to diagnose.

Which brings us to programmers that take a month to right 1 line of code.
So basicily our higher education system is certifying people that aren't qualified. Its that simple.

Quote:

---

Originally Posted by Turtle 1

Its a pretty gritty world out there. Kids becoming doctors that aren't fit to examine your pets. Kids becoming Lawyers that aren't capable of doing the paper work to lincess those pets. The doctors aren't qualified to diagnose.

Which brings us to programmers that take a month to right 1 line of code.
So basicily our higher education system is certifying people that aren't qualified. Its that simple.

---

you guys are so cool and know it all that you can explain what I had to explain in 30-40 lines in few line with no relation to topic. Awesome!!!

Quote:

---

Originally Posted by Turtle 1

Its a pretty gritty world out there

---

After reading your post severral times i am ready to take your word for it :confused: :confused:

Quote:

---

Originally Posted by Turtle 1

Its that simple.

---

Another very simple thing is to avoid quoting loooong posts your are not replying to :D

http://www.theinquirer.net/default.aspx?article=32790

AMD makes the first move it seems...i just downloaded and will start testing with FX62

Quote:

---

Originally Posted by jinu117

I am sorry to say these...

---

Wow, now you are the one "speaking from above". :)

As for your experience, I can match you when it comes to general programming, drivers, low level, peek'n'poke, but I must bow down when it comes to Boeing and SQL.

Although, I can say that Boeing engineers were presented with our reconstruction code and they almost passed out when they saw a reconstruction of a dataset which took less than 15 minutes on 3.0 GHz P4 because they used to have to wait 10 hours for that at home.

Quote:

---

Originally Posted by jinu117

- Art of production. You just don't get it. Sweat shop and art of production are not same thing.

---

They serve the same purpose - they feed this rotten consumer society with quantity instead of quality. But I don't expect you to admit that you are bored down to bits doing relational databases just as 14 year old boy in Indonesia is bored by sewing Nike size 10 left shoe for the 47th time today.

The only difference between you and that boy is that he is getting 1$ a day and you get much more, but don't worry. Once they teach them how to make RDB you will get the same offer too.

Quote:

---

Originally Posted by jinu117

In fact, on any decent sized application, the only part our team usually can touch is just portion of it.

---

With normal management you can always explain that some changes in other parts of application are needed to correct poor design or to gain speed, that is if you care of course.

Quote:

---

Originally Posted by jinu117

In fact, I think something like your image enhancing can benefit greatly from such endeavour. Let me ask my friend who works at NASA on imaging to see if he got some comments about such :)

---

Job offers are always welcome :)

Quote:

---

Originally Posted by jinu117

--> it cost those companies to revamp... they are out to make money... the cost goes straight back to customers... Bit surprised such simple concept can't be understood.

---

The cost goes to customers anyway, the question is how much will they get for their money.

What I am trying to say is that you get more from hardware than from software for the same amount of money. Not because hardware is cheap mind you, but because software is expensive and that expensiveness in 95% of cases is not justified.

Quote:

---

Originally Posted by jinu117

Yes YOU ARE programming GOD who is better than your peers. You are IT.

---

I never said that nor I intended to do so. I was just pissed off by all those wussies who keep whining how programming is hard. It was your choice to study it and get a programming job so have some dignity and take it like a man. It is also very interesting that I never hear any engineers working on a CPU complain how hard it is to design one.

Quote:

---

Originally Posted by Tony

http://www.theinquirer.net/default.aspx?article=32790

AMD makes the first move it seems...i just downloaded and will start testing with FX62

---

Well? How well does it work? :)

the dual core optimizer isnt RHT sadly

the dual core 'optimiser' (am i the only one who notices the misspelling?) really only fixes the few apps that messed up on dual core systems, it fixes that sync problem or whatever. not reverse hyperthreading in the least.

I thought AMD denied there was a problem with X2 when these timing problems was first pointed out a year ago? So why have they made this "optimiser"? THG reported strange results from their famous multitasking "stresstest" concerning X2 DVD encoding, the task had been more or less ignored, that problem could be related to this optimizer-thing. And now, the fact that ppl over in the XS AMD forum are reporting improvements when using this optimizer doesnt match well with AMDs denials. Too early to tell yet, but it could look like AMD has to bend over and take whats coming, the claims that Pentium D's was not real dualcores could strike back at them, at least Pentium D dont need any software patches...

Anyway, easy to forgive when considering the performance advantage of X2 over P-D, noone is perfect (they just like to think so), and people would still have bought X2 instead of P-D.

Quote:

---

Originally Posted by Tony

How about this.

Enable apps to control the CPU's on the fly..IE if the app is running in single thread mode all 2 or 4 cores are used..IE combined.

Then, as the app moved to multi thread the CPU's go back to hyperthread mode and you get the speed benifit both ways.

Could it be possible to do something like this?

---

you mean like sandra does ?

Quote:

---

It is also very interesting that I never hear any engineers working on a CPU complain how hard it is to design one.

---

who do you work with? ( what company? )

wtf? no answers lol

http://www.theinquirer.net/default.aspx?article=32885

Actually, this was all a rumor. At least for AMD, that is; they're not planning to release this anytime soon, if the inquirer can be trusted. :p:

Quote:

---

Originally Posted by i found nemo

wtf? no answers lol

---

It could take a while to get reply from that guy... However, someone mention Boeing to him and suddenly, "been there, they were sooooo impressed!". What a convenient coincidence... Now combine that with being experienced in programming but dont know anything about how the software business works in reality? His posts made me need another housing fan to remove the smell of con artist from my rig...

Quote:

---

Originally Posted by i found nemo

who do you work with? ( what company? )

---

Quote:

---

Originally Posted by i found nemo

wtf? no answers lol

---

I work for hire over the Internet. If you need more details, ask.

Quote:

---

Originally Posted by ted3

It could take a while to get reply from that guy...

---

You bet it could, but only because I have other things to do than hanging around here.

Quote:

---

Originally Posted by ted3

However, someone mention Boeing to him and suddenly, "been there, they were sooooo impressed!". What a convenient coincidence...

---

Read again, I never said that I have "been there", but they were impressed. Coincidence or not, it wasn't me who mentioned Boeing first in a chest-beating attempt.

I was criticizing the trend which is setting amongst the developers and that is to ask others (hardware vendors) for the easy way out, while other industry branches do not have that commodity. Does the word "slacking" ring any bells?

Quote:

---

Originally Posted by ted3

His posts made me need another housing fan to remove the smell of con artist from my rig...

---

Or you have just farted from too much brain exercise while trying to understand my post and you won't admit it? :hrhr:

Sorry, but you will need HEPA air-purifier for that, no housing (perhaps you meant case?) fan will do. :nono:

What a mature reply, i guess rear end humor is fun in your age? Just admit youre a student who thinks he knows everything. Reply in a few years when you reached the point where you understand that the more you learn the more you come to realize how little you know. You made it clear that you are not even close to that point yet, you obviously have no real world experience. Con artist, 100% sure now.

Quote:

---

Originally Posted by ted3

What a mature reply, i guess rear end humor is fun in your age? Just admit youre a student who thinks he knows everything. Reply in a few years when you reached the point where you understand that the more you learn the more you come to realize how little you know. You made it clear that you are not even close to that point yet, you obviously have no real world experience. Con artist, 100% sure now.

---

Tsk, tsk, tsk... you could have checked my age in my profile, that would spare both the others and me from having to read such rediculous claims.

Moreover, you can't actually say that your reply to my original posting was anything better to begin with.

I am quoting your post again for the record:

Quote:

---

Originally Posted by ted3

His posts made me need another housing fan to remove the smell of con artist from my rig...

---

Now let me break it down for you:

- You are not addressing me directly but instead you are gossiping behind my back
- You are talking about me in derogatory terms insinuating that I stink and that I am a liar with no proof to back it up
- There is no smiley face next to it

We hopefully all know how such posts (and posters) are classified.

Following are your claims about me based on my reply to your mouthwashing:

Quote:

---

Originally Posted by ted3

You made it clear that you are not even close to that point yet

---

Quote:

---

Originally Posted by ted3

you obviously have no real world experience.

---

Quote:

---

Originally Posted by ted3

Con artist, 100% sure now.

---

Thanks God that just you saying it doesn't make it true.

You haven't challenged any of my claims but instead you are hitting below the belt by disputing my credibility while you still haven't established your own.

It is such a mature way of discussion -- congratulations ted3 for mastering it so quickly.

Tnx, i know im the best. :toast: All other programmers are just whores for the money, they dont care about the art in it. See, i have no idea about teamwork, i spit on other programmers skills. Now does that sound like you or what?

I dont want to play "mention a big company and i made apps for them too" or any other game of yours, you can reply anyone with better credentials and greater achievements anyway, thats what con artists do best. In fact its the only thing they do, lol. Ofcourse i cant prove what a braggard con artist you are, but as long as im convinced that noone who been in the trade could say anything of what you said then it works for me.

Quote:

---

Yo Audio Freak!Still kicking ass all over the internet, i see

---

Obviously not the first time you state extreme controversial opinions on forums. Youre one of those who can get into an argument about how to correctly wind a wristwatch.

Sory for off topic, i think everyone except one agrees that core multiplexing would have been/will be of benefit to users.

Quote:

---

Originally Posted by ted3

Tnx, i know im the best. :toast: All other programmers are just whores for the money, they dont care about the art in it. See, i have no idea about teamwork, i spit on other programmers skills. Now does that sound like you or what?

---

Of course it doesn't. Yet again you are attacking and discrediting me personally while I have been commenting on a (IMO) negative trend in the industry.

Quote:

---

Originally Posted by ted3

I dont want to play "mention a big company and i made apps for them too" or any other game of yours, you can reply anyone with better credentials and greater achievements anyway, thats what con artists do best.

---

Are you intellectually challenged or what? Read what I said again, but do it slowly few times until it sinks in, I really hate when I must QFT myself and I apologize to everyone for the offtopic:

Quote:

---

Originally Posted by audiofreak

As for your experience, I can match you when it comes to general programming, drivers, low level, peek'n'poke, but I must bow down when it comes to Boeing and SQL.

---

Note how I said "I can match you", and not "I am better than you". Also note how I said "I must bow down when it comes to Boeing and SQL".

Hello?!? Do you get it? I am not a con artist, he knows SQL and I don't, he has worked for Boeing and I haven't. I just mentioned that a company I work for hire over the Internet had some contact with Boeing as an example how code optimization can be much better approach than CMT or RHT and that is all. I am not stealing anyone's 15 minutes of fame because I don't care.

Quote:

---

Originally Posted by ted3

In fact its the only thing they do, lol.

---

Then perhaps you could share your doing with us if you are so bold in accusing someone else of doing nothing?

Quote:

---

Originally Posted by ted3

Ofcourse i cant prove what a braggard con artist you are, but as long as im convinced that noone who been in the trade could say anything of what you said then it works for me.

---

Aside from not even being able to prove that you know proper English by using correct spelling in your posts I consider it normal that you can't prove something which is not true. If anyone could do that then the world would quickly come to a bitter end.

Btw, if you keep calling me names I will report your next post instead of wasting time to reply to such childish acts from a 36yr old.

Quote:

---

Originally Posted by ted3

Obviously not the first time you state extreme controversial opinions on forums. Youre one of those who can get into an argument about how to correctly wind a wristwatch.

---

The person who posted that comment is a friend of mine from another forum. And no I wouldn't because I do not even use wristwatches so get a life.

Quote:

---

Originally Posted by ted3

i think everyone except one agrees that core multiplexing would have been/will be of benefit to users.

---

That goes to show that you haven't even bothered to read the whole thread. In other words, you can think whatever you want but when the facts don't match your thinking you simply end up looking rediculous.

@audiofreak & ted3

I don't care who's right and who's wrong. But, knock it off.

-FCG

Quote:

---

Originally Posted by audiofreak

Of course it doesn't. Yet again you are attacking and discrediting me personally while I have been commenting on a (IMO) negative trend in the industry.

---

OMG... You came here to brag about how good a programmer you are and how terrible everyone else is, and you escalated your bragging till its impossible to believe you. Your post was nothing but offensive to programmers, a tribute to yourself and your allegded optimizing skills. Bottom line is, your post had nothing to do with CMP, you dont care about CMP or any other CPU tech, you care about talking :banana::banana::banana::banana: abt programmers.

Most stupid post ever:

Quote:

---

Originally Posted by audiofreak

It is also very interesting that I never hear any engineers working on a CPU complain how hard it is to design one.

---

But programmers complain all the time, except you ofcourse.

Quote:

---

Originally Posted by jinu117

Yes YOU ARE programming GOD who is better than your peers. You are IT.

---

I cant say it better, and i dont know why you denied saying it, but its a good way to end this, since it sums up what you said in your first post. Im knowcking it off now FCG. Sorry...

I take it this technology just disappeared off the face of the earth. Pity, it could've increased the effective performance by ~80%+ in singlethreaded apps.