• 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!

Martini1991 said:
On what basis? You've literally just pulled that out of no where.
Click to expand...

On the basis that AMD will definitely, 100% release an improved version of BD, ie. BD2. They will never ditch the new architecture which they have spent years developing, specifically to shine in multi-threaded performance.

And assuming that AMD do release the improved version (which based on the above, they will), the improved version will either be able to clock higher and/or offer a higher IPC. It is more likely the new CPU will be more clockable, as based on the past, the newer version of a particular CPU is always more clockable. EG: P4 (pre Northwood) vs P4 Northwood.

In the CPU world (in case you don't know this Martini), the easiest way to bring out new higher performing parts, is to release the same CPU, but clocked higher. This is usually achieved by refining the production process. Improving IPC is generally more difficult, but this has also been done in the past, so it is not unreasonable to expect AMD to improve IPC.

To suggest that BD2 won't be improved in some shape or form is ludicrous.
 
I know fine well Piledriver will be an improvement, but it clocking much higher? You pulled that out of no where.
Who the hell suggested Piledriver wouldn't be an improvement?

Piledriver is touted 20% faster than Zambezi, which is probably a mixture of clocks and IPC.
And IPC is still damn important, it inherently increases performance across the board.

But no way in hell can anyone at this point in time come out with a blanket statement of "IT'LL CLOCK MUCH HIGHER".

I'm not saying it won't clock better, it probably will clock higher, and Piledriver CPU's will come out higher clocked as standard, but they could top out around the same, or marginally higher than Zambezi is now.

Zambezi to Piledriver will be like Agena to Deneb, higher clocked as standard, much better IPC, higher clocking. That's exactly the way I see it. But don't forget that Ivy will also launch the same as that, although to a lower scale.


EDIT : Also, undeniable proof that AMD allowed lies http://www.xtremesystems.org/forums...nd-Bulldozer&p=4531177&viewfull=1#post4531177

JF-AMD is no small fish, he'd have damn well known how it would have performed.
 
Last edited:
1st gen BD is a disaster end of story it doesn't even match AMD's expectations much less the consumer's there is no getting away from that and no defending AMD on that score because nowhere is this debacle being more hotly discussed then inside AMD right now. Something that should have worked much differently is performing way below what is was supposed too and that is being worked on and all performance figures given out in the past are now null and void future releases performance increases cannot be judged on the cpu that is out now.

Whose fault is it take your pick engineers trying to improve something that was working well and having completely the opposite effect basically screwing the chip, glo fo who clearly have a terrible 32nm process that is in major need of sorting out and cannot produce what was asked of it. All we can do is give AMD time and hope they can sort this out and get out a cpu that is competitive. Personally i think they can and they will, only question is how long it will take them to sort out any design problems and how long glo fo will take to nail down the 32nm process.
 
don't think its fair to accuse JF-AMD of lying, at the end of the day he knows more about how Bulldozer has been designed, intentions, standards, expectations and what not more than anyone on this forum. keeping in mind his stance on this product, he never once faltered from his statements that Bulldozer 'should' (clearly something isn't going as its supposed to!) have higher IPC than the previous generation. keep in mind all of the stuff JF-AMD says appear to draw upon an obvious knowledge in the field rather than someone being purposely deceitful to sell a product.

even looking at the design of the processor and how the third ALU/AGU in Phenom II was pretty much redundant and spent most of its nothing helps explain why AMD axed them from the processor and intended to get an overall IPC boost using better pre-fetch and branch prediction to reduce the number of wasted cycles caused by dodgy prediction. this combined with the fact that the second integer core takes up almost no space (~10%) and was designed with clock speed scaling in mind suggests that something has went amiss with the actual production of chip rather than the architectural premise itself.

what is Bulldozer? it is an interesting balancing act between IPC and multi-threaded horsepower and on paper it is sound, and in the slides produced by AMD regarding the architecture, it is again a sound step in the right direction. so what has went wrong? either AMD spent many years, thousands upon thousands of man hours, billions of dollars making a giant failure or something is holding back the single-threaded performance of the processor and therefore the performance of the whole chip.

judging by the fact that AMD have lots of competent and trained engineers (who know more about processors than we do!) who've spent considerable time of their life designing this processor from the ground up, would be willing to put aside a little faith (not in any hurry for upgrade personally) and go with the second one, that something is fundamentally wrong inside the workings of the chip that goes against the architectural premise.

not trying to defend the rather terrible launch (cause it has been on so many levels!) but I just don't want Intel to monopolise the market, it is bad for everyone if they do, we need AMD to succeed to keep Intel honest. :)
 
Right well I may as well come right out and say it i am an AMD fanboy always have been since my first Athlon, I even bought a BD on Pre order!! lol but in an hours time when i get paid i will be ordering a 2700k OEM and a new board. and i will be saying cheerio to AMD not because i like Intel i am very much in favour of backing the underdog especially when they are doing a good job and it's costing me less money but the price to performance gap is now totally out the window. It's game over for AMD desktops if you are gaming or just generally looking for the best performance for your £££££'s bye bye AMD.

-1 customer
 
Last edited:
Gashman said:
I just don't want Intel to monopolise the market, it is bad for everyone if they do, we need AMD to succeed to keep Intel honest. :)
Click to expand...

Agreed.

However at the moment it's looking more and more like it will be ARM and not AMD who give Intel a run for their money; ARM already dominate the low power mobile device market and will soon into the desktop and server markets with the introduction of its first 64-bit architecture "ARMv8".
 
Okay! With Gareth's Benches, I agree the chip is not just bad, but very terrible. But still want to get into a fist fight with Martini for the suspension...:). Might lose but will take the chance. And No, This isn't a dup account. Sure, the mods can pick up on that!
 
You must log in or register to reply here.
Back
Top Bottom