I am late to the game but allow me to weigh in here.

I agree that the Number Crunching forum is a good place to discuss CPUs, and what's new on the market and how it performs reletive to other CPUs.

I also agree that Who?'s post was a bit over the line. That line being the "no namecalling, no attacks to other users... etc" line. On the other hand, I realize that English is not his primary language and so I felt it was reasonable to give the benefit of the doubt and assume he did not intend the word choice to come across as harshly as it may have to some.

Since that post the discussion seems to have degraded into more subjective and opinionated discussion. Some of which I would have promptly deleted had I seen it before it was responded to etc. At this point, the discussion is disrupted if I start deleting things. And I don't feel anything here is so terrible that I must delete it.

...but let's keep our shirts on here and stick to discussing CPUs, and supporting our assertions.

Suggestions for threads that should be locked, moved, hidden or otherwise moderated should be directed to the Moderator's Contact thread in the Cafe. Posting such suggestions in the thread in question is "off-topic".

---

Rosetta Moderator: Mod.Sense

I am late to the game but allow me to weigh in here.

I agree that the Number Crunching forum is a good place to discuss CPUs, and what's new on the market and how it performs reletive to other CPUs.

I also agree that Who?'s post was a bit over the line. That line being the "no namecalling, no attacks to other users... etc" line. On the other hand, I realize that English is not his primary language and so I felt it was reasonable to give the benefit of the doubt and assume he did not intend the word choice to come across as harshly as it may have to some.

Since that post the discussion seems to have degraded into more subjective and opinionated discussion. Some of which I would have promptly deleted had I seen it before it was responded to etc. At this point, the discussion is disrupted if I start deleting things. And I don't feel anything here is so terrible that I must delete it.

...but let's keep our shirts on here and stick to discussing CPUs, and supporting our assertions.

Suggestions for threads that should be locked, moved, hidden or otherwise moderated should be directed to the Moderator's Contact thread in the Cafe. Posting such suggestions in the thread in question is "off-topic".

so, it is ok to post about intel having a "feature" that will collapse the universe ... but it is not ok to post about AMD lack of delivery ... I see !

who?

ok, so, i appologize if you felt that i was flaming somebody, in the mean time, take a look at my posting history, you ll find systematically the bad pengin posting something that has nothing to do with my posting subject.

in this case, the subject was Barcelona not delivering it promess, and he replied with a intel "bug"

if you look into my history of posting, this happen 6 times.

just got tired of it.

who?

i never took offense to any comments or observations. in fact, when the op received his first -1, i gave op a +1 to bring him back to 0.

Rosie is fortunate to have some members who possess significant industry experience.

i look forward to those postings.

but as we would say in law school, when the topic of "broken processes" is brought into the conversation by advocates of one position, it is fair to have a counter-position presented.

my apologies if you felt i was thread-jacking.

ok, so now that everyone has had their say, lets get back to what this thread was about. A new type of cpu being released.

---

OK, no offense to you either...but Who? offers some evidence for his opinions. Where are your counter-arguments?

Well im sorry, but in my eyes saying "naive quad core" added with some wannabe facts and no profs aint evidence, and im sorry, i cant counter-argument on something that simply aint an argument...

Or open your own thread as you often like to suggest to others.

I doubt i ever suggested this to anyone...u must mix me with someone.

Also I dont quite get why so many jumped into, while i cleary was addressing the thread starter?

anyway, thx to mod.sense for clearing the situation, enough of this, and nobody shall say, i cant start an argumentetive discussion, so here i go (watch it who, you might learn something, how to get some facts provided and express then on a neutral and non offending way)


I was wondering about the following: We all know, the market is devided something like 70% intel and 25% AMD +/- some percentage, dont nail me there, im pretty close tho. So we also have +/- this CPU situation over here at the rosetta stats.
Then im wondering about this :

https://boinc.bakerlab.org/rosetta/top_hosts.php?sort_by=total_credit

Top 12, 10 CPUs from AMD

Seems like AMD CPUs are much more stable and able to run over a much longer time then Intel CPUs, no? Sure, atm a Intel Quad core might pull more RAC - but for how long? :)

This goes along with a stress test made by a popular german page, tomshardware.
The put 2 dual core CPUs under 100% usage over 18 days, what happened can be viewed in this video : http://unterhaltung.thgweb.de/vorschaltung.html?thg_video_17_stresstest_wmv.zip

I dont want to spoil, but the AMD System ran without any reboots or hardware failures, while the intel... well watch the video :)

Some benchmarks can be found here http://unterhaltung.thgweb.de/2005/06/03/update_fazit_stresstest_amd_vs_intel/page29.html also the entire test - in german tho, im sry.

But as we are talking about BOINC and the comming quadcores from AMD, i got something very intereting for everybody who looks for a new crunching maching and wants some serioues RAC :

However, AMD has always had an advantage when it comes to memory efficiency, because each Athlon 64 processor has its own integrated, high-speed, low-latency memory controller. The first Athlon 64 processors supported DDR400 (Socket 754) or dual channel DDR400 memory (Socket 939). The current generation of Athlon 64 and Athlon 64 X2 processors on Socket AM2 runs dual channel DDR2-800 memory. A CPU core can fetch requested data directly, without the detour through a memory controller that is part of the motherboard core logic.

Windows Vista Ultimate Edition will be able to tell processors or nodes apart from simple processing cores. This allows the operating system to assign threads in a more resource-efficient manner: one large task can be executed exclusively on CPU A, while another huge workload runs autonomously on CPU B. Inter-processor task switching is eliminated due to the enhanced hardware awareness of Vista Ultimate, and performance will scale much better with increased core count per processor.

Now, let's go back to the beginning: why is this so important? Remember that an Athlon 64 processor has its own memory controller, and thus a higher memory bandwidth per processing core. As soon as intelligence is added to the multi-threading/multi-tasking game, AMD's Quad FX platform will be able to show some serious muscle that it cannot in today's operating environments. Again, though, you have to bear in mind that we're talking about serious workloads that exceed what you and I typically do with our PCs.

directly taken from : tomshardware.com http://www.tomshardware.com/2006/11/30/brute_force_quad_cores/page2.html

Conclusion : The K10 archtecture/memory control offers serious advantages over Intel when it comes to Running multiple, heavily multi-threaded, processor-intensive applications simultaneously - like BOINC !

Now i would like Who to get on this argumentation, please guys, let him do his work, id really really would love to see the next post done by him (also covered with some real evidence for us to look at)

thx for takeing the time to read :)

Then im wondering about this :

https://boinc.bakerlab.org/rosetta/top_hosts.php?sort_by=total_credit

Top 12, 10 CPUs from AMD

Seems like AMD CPUs are much more stable and able to run over a much longer time then Intel CPUs, no? Sure, atm a Intel Quad core might pull more RAC - but for how long? :)

Seriously? You picked the "total credit" sort? Wow...pretty weak, if arguing current technology strength.

---

Reno, NV
Team: SETI.USA

Then im wondering about this :

https://boinc.bakerlab.org/rosetta/top_hosts.php?sort_by=total_credit

Top 12, 10 CPUs from AMD

Seems like AMD CPUs are much more stable and able to run over a much longer time then Intel CPUs, no? Sure, atm a Intel Quad core might pull more RAC - but for how long? :)

Seriously? You picked the "total credit" sort? Wow...pretty weak, if arguing current technology strength.

hmm. some ppl always seem to miss the point, no?
Im refering to realiablity of CPUs, and provided 2 evidence
- A direct 2 CPUs stress test
- The practical overview of 100.000 CPUs tested "live"
Both test are won by AMD, obviously.
Which source on Rosetta would you pick, to show which CPU runs stable on long terms then the total credit then..?

Im still waiting for Who, who calls the AMD 4 core CPU naive - pretty funny, when his own company does not even have a real quad core... isnt that beeing... naive ? ))))

Anyone who reads these forums knows that Who and Penguin throw zingers at each other. It's so easy to be offended by something, but it is really our choice to be offended by something, is it not? Who or Penguin do not choose our emotions, we do.

Anyways, to the point of "planned obsolescence"... I disagree. I once sat down with an Intel engineer who said in 2000 that they had the next 10-15 years of designs already made and that they simply wait for the "right market" to release everything sequentially. A rumor...

Yeah, something better will always be around the corner and a vast majority of informed PC buyers (and a decent number of the uninformed) realize this. Its important for these discussions to take place (especially reviews & side-by-sides), because most people plan their purchases. Speculation about the future is important, especially when people are plunking down hard-earned money for a dedicated crunching machine (essentially a donation to science).


...I have to doubt that AMD will have a solid cruncher until their CPUs have 2MB cache per core (which R@H makes good use of).

---

I agree, AMD's let themselves down with only having small cache sizes, having said this, they make a fair use of what they've got! The best way to compare the performance of AMD v Intel in an app like Rosetta, is to look at two similiar rated processors (like an Athlon 3000+ and a 3.00GHz P4) which both have their target CPU time set at the same (1 hour is 3600 seconds so any multiples of this will will show the set time in hours or thereabouts) and see who gets the most cred per CPU. I know someone who reads this is thinking that P4 hyperthreading will make it perform worse in this regard, but you get the general idea. I agree with sailorboy that to make any comments about a CPU you need some proven numbers, since that's what they deal in.

---

AMD Barcelona performance promises revealed

So, what will Barcelona deliver?

For starters, SPECint_rate2006 and SPECfp_rate2006 speak the voice of doom for the 366 MHz faster clocked Xeon - and these are the reasons why Intel was downplaying performance of FP and praising the INT.

These figures were from a few months ago, so things may well have changed since then. But in the Integer test, a Barcelona 2.3GHz yields 21% higher score than Clovertown 2.66 GHz, but Floating Point test leaves a staggering 50% performance deficit for Clovertown, and this is not something 45 nanometre Penryn can solve overnight. Unless, of course the clock deficit for AMD is such that Intel speeds past.

When it comes to comparing Barcelona to Santa Rosa, a 3.0GHz clocked Opteron 2222, Barcelona is in general, around 65-70% faster than the highest-clocked dual-core Opteron. SPECweb99 yields a hefty 67% performance increase, SPECweb99_SSL offers 66%, while SAP-SD offers 70% performance increase.

The highest gain, of over 100% can be seen in SPECweb2005/Ecom benchmark, while smallest gain was in TPC-C SQL2000, where only 42% gain was marked. This was all based on 2P (dual-socket) systems, of course.

In the four-socket arena, Opteron 8222 versus 8356 offers an average of over 60% performance boost, which is not a small thing - given that clock difference is 700MHz. SPECweb99 and SPECweb99_SSL give 68% performance increase, SPECweb2005/Ecom yields another scaling dream (91%), while most modest increase is again, TPC-C SQL2000. Nevertheless, TPC-C Oracle test will yield 75% performance increase while Terminal Services will offer 71%.

Overall, these are very impressive score increase promises. All of the performance increases happened with a processor that has 30% smaller TDP. Opteron x222 is a 120W Max.TDP, while this Barcelona 2356 stays in the 95W range.

The only real question that now remains is whther AMD can execute. Sadly, the company's recent track record does not bode well, with constant delays of products and events. And we'll also wait to see real tests of the Barcelonas rather than paper promises.

AMD Barcelona performance promises revealed

So, what will Barcelona deliver?

For starters, SPECint_rate2006 and SPECfp_rate2006 speak the voice of doom for the 366 MHz faster clocked Xeon - and these are the reasons why Intel was downplaying performance of FP and praising the INT.

These figures were from a few months ago, so things may well have changed since then. But in the Integer test, a Barcelona 2.3GHz yields 21% higher score than Clovertown 2.66 GHz, but Floating Point test leaves a staggering 50% performance deficit for Clovertown, and this is not something 45 nanometre Penryn can solve overnight. Unless, of course the clock deficit for AMD is such that Intel speeds past.

When it comes to comparing Barcelona to Santa Rosa, a 3.0GHz clocked Opteron 2222, Barcelona is in general, around 65-70% faster than the highest-clocked dual-core Opteron. SPECweb99 yields a hefty 67% performance increase, SPECweb99_SSL offers 66%, while SAP-SD offers 70% performance increase.

The highest gain, of over 100% can be seen in SPECweb2005/Ecom benchmark, while smallest gain was in TPC-C SQL2000, where only 42% gain was marked. This was all based on 2P (dual-socket) systems, of course.

In the four-socket arena, Opteron 8222 versus 8356 offers an average of over 60% performance boost, which is not a small thing - given that clock difference is 700MHz. SPECweb99 and SPECweb99_SSL give 68% performance increase, SPECweb2005/Ecom yields another scaling dream (91%), while most modest increase is again, TPC-C SQL2000. Nevertheless, TPC-C Oracle test will yield 75% performance increase while Terminal Services will offer 71%.

Overall, these are very impressive score increase promises. All of the performance increases happened with a processor that has 30% smaller TDP. Opteron x222 is a 120W Max.TDP, while this Barcelona 2356 stays in the 95W range.

The only real question that now remains is whther AMD can execute. Sadly, the company's recent track record does not bode well, with constant delays of products and events. And we'll also wait to see real tests of the Barcelonas rather than paper promises.

SPEC_FP_RATE is 1 out of 8 benchmarksssss of the SPEC_CPU suite. you should ask AMD about the 7 other scores ... :) because they lose all of them, from SPEC_INT, SPEC_FP, Peak, even SPEC_INT_RATE. 7 out of 8 of the suite ...

Strange they forget to speak about those ...

and you forgot the speak about the great performance on Povray and Cinebench.

On the IQR, Theo just repeat what he was told by AMD, he actually did not run any of the benchmark. remember, the ATI card was suppose to wipe nVidia ... did not!



who?

cant u read ? :S

SPECint_rate2006 - 21% AMD there is ure INT btw
SPECfp_rate2006 - 50% AMD
SPECweb99 - 67% AMD
SPECweb99_SSL - 66% AMD
SPECweb2005/Ecom - 100% AMD
SAP-SD - 70% AMD
TPC-C SQL2000 42% AMD

stop blowing hot air, when numbers are already called.

When you feel you have some numbers to add, then do so, and dont write "Strange they forget to speak about those ..." cuz this tells nothing at all...

PS: funny that u didnt comment on my facts about realibility - truth hurts ? :)

Next month i might put an AMD x2 6000+ up, in benches it beats the C2D 6600 and its listed with 139 € - can anyone beat that atm ? :o
DC wont be the main use of that system, but ill see what RAC I can pull :)

---

http://www.MIAteam.eu

sailor said:
Conclusion : The K10 archtecture/memory control offers serious advantages over Intel when it comes to Running multiple, heavily multi-threaded, processor-intensive applications simultaneously - like BOINC !

Let's see how K10 does on benchmarks that people were able to check:

On Povray: (perfectly threaded) 1st Benchmark choosen by AMD, probably one of their best case!!!!

obviously faster ...


A serious advantage, sure ...

nothing better than a little video on yourtube

on cinebench:: (perfectly threaded)
very very fast

but not enough it seams.

on heavily multithreaded application, K10 gets smoked! see data in the articles :)

and it is already 1 millions of them out there!

those are the only available benchmarks publically up to TODAY! the rest is AMD powerpoint presentation and their "projection in lalala land", face it!

Sailor, that's enough solid data for you?

who?

cant u read ? :S

SPECint_rate2006 - 21% AMD there is ure INT btw
SPECfp_rate2006 - 50% AMD
SPECweb99 - 67% AMD
SPECweb99_SSL - 66% AMD
SPECweb2005/Ecom - 100% AMD
SAP-SD - 70% AMD
TPC-C SQL2000 42% AMD

stop blowing hot air, when numbers are already called.

When you feel you have some numbers to add, then do so, and dont write "Strange they forget to speak about those ..." cuz this tells nothing at all...

PS: funny that u didnt comment on my facts about realibility - truth hurts ? :)

Next month i might put an AMD x2 6000+ up, in benches it beats the C2D 6600 and its listed with 139 € - can anyone beat that atm ? :o
DC wont be the main use of that system, but ill see what RAC I can pull :)

those are projection numbers, they actually did not file them in SPEC database. no more comments!
with your 6000+, with good luck, you could get in the top 1000 ... wow!

who?

cant u read ? :S

SPECint_rate2006 - 21% AMD there is ure INT btw
SPECfp_rate2006 - 50% AMD
SPECweb99 - 67% AMD
SPECweb99_SSL - 66% AMD
SPECweb2005/Ecom - 100% AMD
SAP-SD - 70% AMD
TPC-C SQL2000 42% AMD
"lalala land projection, nobody did measure this, not even AMD, it is PROJECTED ;-) , do you know anybody who will project losing????"
stop blowing hot air, when numbers are already called.

When you feel you have some numbers to add, then do so, and dont write "Strange they forget to speak about those ..." cuz this tells nothing at all...

PS: funny that u didnt comment on my facts about realibility - truth hurts ? :)

Next month i might put an AMD x2 6000+ up, in benches it beats the C2D 6600 and its listed with 139 € - can anyone beat that atm ? :o
DC wont be the main use of that system, but ill see what RAC I can pull :)

those are projection numbers, they actually did not file them in SPEC database. no more comments!

who?

You may beat a 6600, but you will not beat any of the X6800 or Q6600 for sure, thanks for admitting this. I don t even speak about Penryn ... no chance to even get close here! yes, it is already played

smile

who?

How about an independent match between the two, done on cnet.com, and not using the processors to just crunch numbers, but do a number of tasks that everyday users would do.
Dual-core desktop CPU bout: AMD vs. Intel

Based on the results, I know what my next processor will be, and it will not be Intel.

---

Ok finaly some links, will read them later when i find some time to studdy them, thx for that :)

As I said, im not buying & building my PCs as dedicated crunchers, my main goal is to run games fast & reliable, which we in our team do accomplish nearly perfect. Ive yet to see any of my teammates crash during a match in the last 12 months, while our opponents tend to get 1 or even 2 players down in most matches. The last crash i recall during a match was due to a northbridge overheat on a socket 939 board using nforce 3 chipset. Changing heatsink compound fixed that issues - all our team members are using AMD powered rigs expect 1.

So basicly i will never reach the RAC which my CPU really could offer, simly cuz im not running BOINC 24/7 - also I dont really care where i stand in the stats - im giving what i got like everyone, every participant is equally important to the project imo.

And yes sir, my 6000+ wont beat the 2xduo core Q6600, but when i look at the price: im getting my 6000+ for 139 € + 66 € for mainbaord, while the Q6600 would cost me 359 € + another 110 € (?) for a mainboard.
So 205 € compared to 470 € is not really the same class, you cant compare apples to bananes, no ? :)
On the otherhand, the E6600 goes by 209 € without board, so thats already more expensive then the 6000+ - who are nearly equal in CPU power, so i think thats where to look at, to get the best price&performance.

Ofc Intel got a good architecture, pretty much needed after the P IV performance, but like we also use to say : "there is always someone better then you out there"

---

http://www.MIAteam.eu

And here is a counterpoint,
Where is AMD’s Intel-killer Barcelona?
but then, I don't run servers, so I don't care if AMD is behind in this market. I will still choose AMD for my home computer.

---

How about an independent match between the two, done on cnet.com, and not using the processors to just crunch numbers, but do a number of tasks that everyday users would do.
Dual-core desktop CPU bout: AMD vs. Intel

Based on the results, I know what my next processor will be, and it will not be Intel.

Hahahahah , this test does not have ANY Core 2 based system, it is 2 years old!

who?