• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Bulldozer Finally!

i don't know if this has been posted but a review of an engineering sample has been posted: http://www.donanimhaber.com/islemci...-Bulldozer-FX-islemcisi-ve-test-sonuclari.htm

shows the 8 core faster than the i7 2600k in x264 encoding which isn't suprising as intel's is only 4 cores. So it looks to be a lot slow if intel and amd had the same number of cores but if intel price the 8 core well then that is irrelevant.
 
It's always seemed pretty meaningless to me, performance could be vastly different on SuperPi between CPUs when in the real world they are quite close.
LOL, that CPU is rubbish it's nowhere near the performance of <insert other CPU>!!!!!! *sigh*
Aside from it failing to complete the run in high overclock scenarios, showing instability (does this even happen anymore?) I just don't know what it proves.

Haven't ran it since my 754 Athlon setup...
 
Martini1991 said:
That only makes BD look crap lol.


Single core benchmark, BD, unlike Phenom II has the same instruction sets as Intel CPU's, why shouldn't it be viable?
Click to expand...

Because there is NOTHING out there that mimic's superpi, keep in mind Intel actively make the die size bigger to enable hyperthreading, and it improves performance in most situations.

Now ask yourself why, because MOST software can not use a full 4 issue core as Super pi can, most code is simply much much more complex. If Superpi was "standard" in terms of software and usage, hyperthreading would rarely if ever boost performance, the fact that it does, and Intel know it does, pretty much proves Superpi is all be irrelevant.

Anyway, even Fud now is linking to stuff saying Bulldozer beats a 2600k, anything from a little to quite a lot.... Fud, well to be fair he's mostly pro Nvidia than anti AMD(and its really Ati) but its still a fairly big thing that he's going with that kind of info.

Superpi is, well, theres several other apps that do exactly the same work, ridiculously faster than Superpi, it was viable when we only had single cores, even then being fast or slow in Superpi had no real bearing in anything else. In the age of multicore, Superpi doesn't relate to anything.

Case in point Bulldozer apparently gets smashed in Superpi, yet beats the 2600k in x264 encoding, by 36% no less, in 3dmark, in Cinebench, in all kinds of things. So it gets smashed in Superpi, but is faster than the 2600k in anything you'd actually use......... I know which I'd go with.


Before you say it, of course there is single threaded software, and people who rely on (mostly older) software thats single threaded, for work, or anything else, and theres no reason not go to with the fastest cpu for you, in specific cases. But this cases really are few and far between, the average user simply won't face those issues, and even when/if they do, would you get a 2600K because its faster in one application you use once a month, when a Bulldozer for the same cost is faster in everything else you use every day?
 
Emlyn_Dewar said:
It's always seemed pretty meaningless to me, performance could be vastly different on SuperPi between CPUs when in the real world they are quite close.
LOL, that CPU is rubbish it's nowhere near the performance of <insert other CPU>!!!!!! *sigh*
Aside from it failing to complete the run in high overclock scenarios, showing instability (does this even happen anymore?) I just don't know what it proves.

Haven't ran it since my 754 Athlon setup...
Click to expand...

I would say I like to run it, seems to show up any memory instability almost instantly when I overclock. IE memtest takes ages, haven't run that in years, windows can stay stable for ages and crash at the end of a long gaming session but Superpi + unstable memory settings and it will rarely finish.

For measuring performance of real world software, of 99% of real world software, its meaningless.
 
drunkenmaster said:
Because there is NOTHING out there that mimic's superpi, keep in mind Intel actively make the die size bigger to enable hyperthreading, and it improves performance in most situations.

Now ask yourself why, because MOST software can not use a full 4 issue core as Super pi can, most code is simply much much more complex. If Superpi was "standard" in terms of software and usage, hyperthreading would rarely if ever boost performance, the fact that it does, and Intel know it does, pretty much proves Superpi is all be irrelevant.

Anyway, even Fud now is linking to stuff saying Bulldozer beats a 2600k, anything from a little to quite a lot.... Fud, well to be fair he's mostly pro Nvidia than anti AMD(and its really Ati) but its still a fairly big thing that he's going with that kind of info.

Superpi is, well, theres several other apps that do exactly the same work, ridiculously faster than Superpi, it was viable when we only had single cores, even then being fast or slow in Superpi had no real bearing in anything else. In the age of multicore, Superpi doesn't relate to anything.

Case in point Bulldozer apparently gets smashed in Superpi, yet beats the 2600k in x264 encoding, by 36% no less, in 3dmark, in Cinebench, in all kinds of things. So it gets smashed in Superpi, but is faster than the 2600k in anything you'd actually use......... I know which I'd go with.


Before you say it, of course there is single threaded software, and people who rely on (mostly older) software thats single threaded, for work, or anything else, and theres no reason not go to with the fastest cpu for you, in specific cases. But this cases really are few and far between, the average user simply won't face those issues, and even when/if they do, would you get a 2600K because its faster in one application you use once a month, when a Bulldozer for the same cost is faster in everything else you use every day?
Click to expand...

I have literally no idea what you've just said.
But the Fritz benchmark there isn't impressive.

I don't care for 8 cores, 8 cores aren't going to be utilised much, and by the time they are, newer and faster CPU's will be out.
 
It just looked strange to be so good in other benches while having a SuperPi score like this.

It just prooves that BD are highly optimised for all the multi-tasking/multi-threaded applications. Personally, I love it, and if AMD keeps making this line of products better and better, soon they might gain the upper-hand in this market.
 
Martini1991 said:
I have literally no idea what you've just said.
But the Fritz benchmark there isn't impressive.

I don't care for 8 cores, 8 cores aren't going to be utilised much, and by the time they are, newer and faster CPU's will be out.
Click to expand...

If you have no idea what he said, why are you trying to analyse the performance? It would seem you're not too equipped to do so. Unless of course you were just being assinine because you had no counter-argument.

I can think of one piece of software which 100% of PCs use 99.9% of the time .... it loves more cores. The OS ... whether it's Windows, Linux, OSX, BSD etc.
 
pmc25 said:
If you have no idea what he said, why are you trying to analyse the performance? It would seem you're not too equipped to do so. Unless of course you were just being assinine because you had no counter-argument.

I can think of one piece of software which 100% of PCs use 99.9% of the time .... it loves more cores. The OS ... whether it's Windows, Linux, OSX, BSD etc.
Click to expand...

Two different things?
What he said is a wall of text, what I was analysing were actual results.. And it's basically a little faster clock for clock than Deneb, 8 cored and 32nm.
And on the O/S front? That's funny, I was running an old Athlon x2 6000+ on my SSD, and noticed zero difference with my 4.8GHZ 2500k or 4.3GHZ Phenom II 1055.

The way to see which is the best architecture, is a face off with the 4 core BD CPU and the 2500k, put them at the same clock, then overclock both to the maximum.
 
Last edited:
You must log in or register to reply here.
Back
Top Bottom