Intels Conroe benchmarked!
- Thread starter boxleitnerb
- Start date
Wow, i'm happy for Intel, not because i'm a fan, but because now that the most pricey CPUs are also the best performance, i feel like there is balance in the universe.
And this also made me realise... I've never had an Intel CPU in my home PCs. Even my first PC had a Cyrix CPU... Bless them...
And this also made me realise... I've never had an Intel CPU in my home PCs. Even my first PC had a Cyrix CPU... Bless them...
Kombatant said:Quoting from the article:
Umm, so the others were tested with Intel demos? That should explain a whole lot
In their defence, the FEAR test showed the biggest gap between the AMD and Intel performance...
Accord1999
Newcomer
FEAR provided the largest margin of victory for Conroe.Kombatant said:Quoting from the article:
Umm, so the others were tested with Intel demos? That should explain a whole lot
Kombatant said:
Heh, you're right :smile: For all we know the Intel engineers could have accidentally not inserted one of the RAM banks in properly, so the AMD tests only had 512MB RAM... Kidding.
Personally i won't upgrade my system for a looong time, by then a Dual Core will be cheap, if i will ever need it. New consoles will more than satisfy my gaming needs for the next 5 or 6 years, so my A64-3200 will probably be enough for my PC needs for a loooong time...
I think macro-ops fusion can be seen as a way to "fix" some problems in the x86 ISA. Another example is "multiply and add." There is no fma instruction in x86, but a macro-ops fusion with "multiply and add" can make some x86 programs to enjoy the benefits of a fma unit without any changes.
Conroe was expected to have good performance. The main reason why it looks like they are stomping the Athlon is because they used slow memory on it. Put some PC4000 (250MHz DDR) memory on it or even faster and it'll gain something like 10% performance and cut the advantage the Conroe has by about 1/3.
The Conroe will be going up against Windsor with DDR2 memory which should give a nice performance boost (think 1GHz DDR) and if AMD manages to raise the clockfrequency to 3GHz it should be even with a 2.67GHz Conroe. The most interesting unknown part of Conroe would be how high it will clock, Anand guessed at 3GHz for the Extreme Edition which is probably a truckload of shit - look at how the current mobile versions have clocked and then back off abit to make sure it's stable and it'll probably land at 2.8GHz which should make it the clearly fastest x86 processor around. Intel fastest announced bin is the 2.67GHz, so the EE may well be launched later when they feel they need some good publicity.
The Conroe will be going up against Windsor with DDR2 memory which should give a nice performance boost (think 1GHz DDR) and if AMD manages to raise the clockfrequency to 3GHz it should be even with a 2.67GHz Conroe. The most interesting unknown part of Conroe would be how high it will clock, Anand guessed at 3GHz for the Extreme Edition which is probably a truckload of shit - look at how the current mobile versions have clocked and then back off abit to make sure it's stable and it'll probably land at 2.8GHz which should make it the clearly fastest x86 processor around. Intel fastest announced bin is the 2.67GHz, so the EE may well be launched later when they feel they need some good publicity.
Anova do you remember my comment?
I suggested AMD was going to tread water in the desktop market and Intel had a great opportunity to one up them. It seems that was correct. Of course we should wait until this stuff is actually out, and as was said I don't know why they did not use an NF4, but I am glad they overclocked it. Makes it a better comparison for me b/c conroe ain't out yet and by the time it is the fx-60 won't be top dog.
Here is what I said exactly
I suggested AMD was going to tread water in the desktop market and Intel had a great opportunity to one up them. It seems that was correct. Of course we should wait until this stuff is actually out, and as was said I don't know why they did not use an NF4, but I am glad they overclocked it. Makes it a better comparison for me b/c conroe ain't out yet and by the time it is the fx-60 won't be top dog.
Here is what I said exactly
Last edited by a moderator:
NocturnDragon
Regular
maaoouud said:
You should always try to compare apples to apples, why not put some DDR2 800 on the Conroe as well then?
maaoouud said:
I see 3.0 GHz as very plausible, I clocked my old Dothan 1600 (the old one with a 400MHz bus) to 2.500 with stock voltage and cooling. (and let me say that the stock cooler wasn't really a good one!). And that was a cpu from years ago!
I wonder how Intel's BTX startegy will be affected after the introduction of Core arcitechture. If I remember correctly the only reason Intel was trying to push BTX down into motherboard manufacturers' throat was to be able properly cool their Prescott processors. Now that their next CPU arcitechture is abviously less power hungry compared to anything the industry currently has how would this affect their BTX plans? Do you think they will still be insitting on the adoption of BTX standard?
I'm at a loss.....Joe DeFuria
Legend
Wow...it's actually starting to look like I may have a reason to finally upgrade my trusty ol' P4 (Northwood) 3.2 Ghz.
I still probably won't be upgrading until Vista ships though...
I still probably won't be upgrading until Vista ships though...
Intels chipset might not work with DDR2 800 yet. Or (more likely IMHO) they found out that lowlatency DDR2 667 memory is faster. PC4000 memory is old news for the Athlon 64, it even has a proper multiplier for it now so there is no reason to cry foul if they used it (it would only make the two systems more similar).
This benchmark was probably made public to get people a big "Hey look at us in half a year we will have better performance" show, and as such they used as fast a AMD processor that they could find (while crippling it as best as they could without seeming to do so in the eyes of the less informed), in order to turn the focus away from the bad news in their last financial quarter.
As for 3 GHz, I too hope that Conroe will be able to clock that high, but as I said, I don't think that they will release anything faster than 2.8GHz this year. Being able to run a few of the processors at a given frequency is not the same as being able to guarantee that they will perform perfectly at that frequency. Both Intel and AMD never launch a processor at the absolute maximum that the process can sustain (with the exception of the Pentium III), they need to be absolutely sure that it will work flawlessly.
This benchmark was probably made public to get people a big "Hey look at us in half a year we will have better performance" show, and as such they used as fast a AMD processor that they could find (while crippling it as best as they could without seeming to do so in the eyes of the less informed), in order to turn the focus away from the bad news in their last financial quarter.
As for 3 GHz, I too hope that Conroe will be able to clock that high, but as I said, I don't think that they will release anything faster than 2.8GHz this year. Being able to run a few of the processors at a given frequency is not the same as being able to guarantee that they will perform perfectly at that frequency. Both Intel and AMD never launch a processor at the absolute maximum that the process can sustain (with the exception of the Pentium III), they need to be absolutely sure that it will work flawlessly.
dunno seems to good to be true, but you never know 
The purpose of the test was to show relative performance comparisons between the two at stock settings, though the Conroe won't be out for another few months this is why they chose AMD's latest and greatest and even overclocked it. The Athlon 64 is designed to run with DDR400 ram and they even set it to run at optimal performance with 2-2-2-5 1T timings, you call that crippled? In contrast the Conroe is using relatively high latency DDR2 running at 1066 MHz, 4-4-4 because that is what it is designed for. Sure they could probably of used PC4000, but then they could have also overclocked the Conroe.maaoouud said:
It won't change. BTX allows for better cooling in general, not just for the cpu but for the whole system. As such, even if the cpu isn't a heater that just means a much quieter computer is a better possibility.
Hexus.net
Hexus.net also got to play with Intels two setups. More benchmarks:
http://www.hexus.net/content/item.php?item=4843&page=1
Hexus.net also got to play with Intels two setups. More benchmarks:
http://www.hexus.net/content/item.php?item=4843&page=1
Similar threads
