AMD 32 nm CPU Conquest to Begin in 2010

[Flibolito]

agreed they have their work cut out for them
but the race is definitely not over and in the best interest of the consumer (us)
you want the race to be pretty close
I for one am not bias on CPU's
I love both Intel and AMD.

 

[DaedalusHelios]

lol, took you Intel monkeys (no pun intended, there are AMD monkeys too) that long to figure out? AMD expects 32nm by 3Q 2010.
Also with 32nm you can expect to see 20-24 core Processors from AMD since AMD designs their CPUs to be VERY small.

But it will have some strange errata again I'm sure. Like DDR3 catching on fire during BSODs and they will fix it in the next stepping. j/k

 

[eidairaman1]

TBH i think what needs to happen for AMD is to keep hohum on their next CPU lineup, and only reason Intel managed to stay ahead is because they keep on bribing JDEC to approve Crappy Ram (Cough DDR3). If DDR was still around and just had a Die Shrink nothing else, to say 45nm or even 30 it would probably whoop the DDR3 easily thx to tighter timings and not require a High Clock speed, and with the process shrink means less voltage is needed.

 

[Flyordie]

DDR2 is good... I can run my DDR2 @ 3-3-3-10-14-1T @ DDR2-840.

 

[Noggrin]

"AMD 32 nm CPU Conquest to Begin in 2010"

Conquest you say?

more like "amd will start give us lolz again in 2010" ..

 

[btarunr]

"AMD 32 nm CPU Conquest to Begin in 2010"

Conquest you say?

Conquest you read

 

[KBD]

DDR2 is good... I can run my DDR2 @ 3-3-3-10-14-1T @ DDR2-840.

yep, DDR2 is still good, DDR3 was rushed to the market for really no good reason. Socket 775 platforms dont benefit that much from it.

 

[Assimilator]

AMD have just barely transitioned to 45nm and now they're talking as if 32nm is going to be a magic bullet to fix all their woes? Their problem is not the fab process, but the fact that the K10/Phenom architecture is simply not competitive with Core i7. I'd rather see a 65nm AMD CPU that can compete with Intel's best as opposed to a 32nm model that can't, thanks very much.

TBH i think what needs to happen for AMD is to keep hohum on their next CPU lineup, and only reason Intel managed to stay ahead is because they keep on bribing JDEC to approve Crappy Ram (Cough DDR3). If DDR was still around and just had a Die Shrink nothing else, to say 45nm or even 30 it would probably whoop the DDR3 easily thx to tighter timings and not require a High Clock speed, and with the process shrink means less voltage is needed.

The amount of factual inaccuracies and bias in this statement is so laughable I'm not even going to bother to dissect them, except to recommend that you check Wikipedia to educate yourself.

yep, DDR2 is still good, DDR3 was rushed to the market for really no good reason. Socket 775 platforms dont benefit that much from it.

DDR3 provides more bandwidth than DDR2, which is one of the reasons why Core i7 is designed around DDR3: that architecture needs massive memory bandwidth to perform well. On the other hand, DDR3 on a S775 platform is a waste because the memory controller simply can't take advantage of the extra bandwidth.

 

[DaedalusHelios]

TBH i think what needs to happen for AMD is to keep hohum on their next CPU lineup, and only reason Intel managed to stay ahead is because they keep on bribing JDEC to approve Crappy Ram (Cough DDR3). If DDR was still around and just had a Die Shrink nothing else, to say 45nm or even 30 it would probably whoop the DDR3 easily thx to tighter timings and not require a High Clock speed, and with the process shrink means less voltage is needed.

Incorrect. I want to know who told you that because thats kind of sad...

Is that just something you made up because anyone in the computer field knows that is wrong.. I am not trying to be mean but tight timings only mean so much..

 

[eidairaman1]

well explain why even DDR at 600 MHZ clobbers DDR2? It takes alot more bandwidth to overcome performance issues that DDR2/3 has vs DDR1 at lower clocks. Im pretty sure if DDR1 was shrunk down it would probably be able to maintain tight timings and then also require less voltage, but able to ramp the clocks higher without having to loosen the timings to what DDR2/3 requires. Also on the Intel Bit, AMD didnt move really when DDR2 came about but it seems eachtime they move Intel moves on to the next Memory standard, so it sounds like they are actually bribing JDEC to approve standards that are slower, and TBH QPI/HTT dont need all the Bandwidth in the World to get work done as they are a low latency solution.

 

[Steevo]

ok so more cores is not always the best way at all.
more cores = more complex software to actually take advantage.
and AMD has not lost any race at all.
Transistors@(X)GHz/price is the real race
for example 2 chips 1 has 500million @3GHz, the other 1billion@3GHz
if chip 1 is $200 and chip 2 is $65 then chip 2 wins even though chip 1 is faster
you have to understand most people are not enthusiast and dont know the difference very well but like the $65 much more than $200 especially since they never even tap into that power the chip 1 has.
so there are 2 races 1, the race for transistors/power/fabrication. race two is same as race 1 but the mighty $ factored in.

More doesn't equal better if you can't keep them busy.