Sign in with
Sign up | Sign in
Your question
Closed

AMD "Zembezi

Last response: in CPUs
Share
February 12, 2011 5:50:08 PM

Hey im looking towards the future and I'm eyeing the AMD 8 core bulldozer CPU'S coming down the line. I'v seen some source say there going to use a AM3+ Socket and im wondering if that means youll be able to toss one in a current AM3+ compatible board?
Will my current http://www.newegg.com/Product/Product.aspx?Item=N82E168... msi 870A Fuzion work i noticed just now that its a AM3 not a AM3+ I'm guessing that means ill need a new mother board cause the sockets are comparable?

More about : amd zembezi

a c 886 à CPUs
a c 352 À AMD
February 12, 2011 5:59:27 PM

You are correct on the assumption that you will need a new board!
Score
0
February 12, 2011 8:47:16 PM

Odd are you are going to need a new board.
Score
0
Related resources
a c 127 à CPUs
a b À AMD
February 12, 2011 10:14:04 PM

If you get a AM3+ mobo then you can us a Phenom II for now and get Zambezi but you cannot put Zambezi into a AM3 mobo.
Score
0
February 13, 2011 6:13:01 AM

Okay any idea when we will start seeing AM3+ boards im really chomping at the bit to try out a this new archt and 8 core set up.
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 6:18:20 AM

yes well people forgot one of the first octocore cpu was a xeon octocore, a while back, but was very expensive, so for the mass public, will have to wait for the mainstream 0ctoc0res its unfortunate but heck thats life,
Score
0
February 13, 2011 12:37:28 PM

if amd were loyal to their announcements am3+ cpus and mobos should already be on shelves...
there is no way of knowing for sure when those are going to come out...
but i dont think am3+ mobos are going to be available before any am3+ cpus are ready for consumers...
if you happen to find a am3+ mobo be ready for the bulldozer as it will probably come shortly after
Score
0
a c 127 à CPUs
a b À AMD
February 13, 2011 8:00:48 PM

illfindu said:
Okay any idea when we will start seeing AM3+ boards im really chomping at the bit to try out a this new archt and 8 core set up.


No real 100% solid info has been laid out.

Plus don't forget its not 8 cores. Its 8 modules. Not the same.

Now Intel will have a 8 core CPU out later this year based on Sandy bridge.
Score
0
a b à CPUs
February 13, 2011 8:03:12 PM

Yes, but I can't imagine that an 8 core SB would be affordable considering how well the 4 core is doing.
Score
0
a c 127 à CPUs
a b À AMD
February 13, 2011 8:06:34 PM

It all depends really. It will probably come out high to start but then lower end models will hit that will be friendlier in price.

Of course thats the way it always is.

I just wonder what AMD will do if the modular design of BD fails them. Will they go back to the core based or keep trying.
Score
0
a c 131 à CPUs
a b À AMD
February 13, 2011 8:27:06 PM

jimmysmitty said:
No real 100% solid info has been laid out.

Plus don't forget its not 8 cores. Its 8 modules. Not the same.

Wrong. It is the same. Obviously you haven't been keeping up with the news.

All they did is have the pairs of cores (module) share a few more resources. They are still cores. However, each core takes up less space than before.
Score
0
a b à CPUs
February 13, 2011 8:28:00 PM

The 6 core i7s never came down in price (though it would be awesome if 8 core SBs were semi-affordable).
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 8:28:54 PM

well if they put more cores, and reduce power consumption even more that would be swell
Score
0
a c 127 à CPUs
a b À AMD
February 13, 2011 8:48:01 PM

enzo matrix said:
Wrong. It is the same. Obviously you haven't been keeping up with the news.

All they did is have the pairs of cores (module) share a few more resources. They are still cores. However, each core takes up less space than before.


If you compare a 8 core SB chip with a 8 "core" BD chip its not the same. Each SB core has its own resources while each core in BD shares resources. Thats the reason why AMD is calling the modules instead of ccores because they are not each a full core.

It is AMDs version of SMT (called CMT) on a higher level. It means that their version should produce better results than SMT which normally can push 20% better threaded performance, this should be much higher.

But calling the each real cores is a lie because in fact they are not each true cores.

It would be like calling each core in Atom a real CPU core when in fact they are just parts of the CPU core.
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 8:57:17 PM

could u explain me the difference, because i was shur amds new cores, where actually physical cores, im interested thanks
Score
0
a b à CPUs
February 13, 2011 9:54:16 PM

jimmysmitty said:
If you compare a 8 core SB chip with a 8 "core" BD chip its not the same. Each SB core has its own resources while each core in BD shares resources. Thats the reason why AMD is calling the modules instead of ccores because they are not each a full core.

It is AMDs version of SMT (called CMT) on a higher level. It means that their version should produce better results than SMT which normally can push 20% better threaded performance, this should be much higher.

But calling the each real cores is a lie because in fact they are not each true cores.

It would be like calling each core in Atom a real CPU core when in fact they are just parts of the CPU core.



Hey Jimmy :) 

any news on what sort of speed we expect...

sounds like it wont be too impressive... i mean the 6 core was a bit of a flop... i dont know anyone whos got one.
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 9:56:37 PM

6 cores is useful, for example u use 4 coreds for 1 task, encoding hd video, and use the 2 other cores, to game, and windows , so it works out quite well, it just most people dont do more than 1 thing at a time honestly that require alot of cpu power
Score
0
a c 127 à CPUs
a b À AMD
February 13, 2011 9:58:47 PM

Its hard to fully explain but thi picture does a decent job:



Each core has its own pipeline, L1 DCache and Int scheduler but they share the Fetch, Decode, FP Scheduler, 2 128bit FMACs and the L2 cache. The L3 cache is shared among all the cores.

This may look like a dual core but its not. A Sandy Bridge core has all of that per core, minus the FMAC units, Intel ahsn't implemented FMAC yet and will not till Haswell but are still using a single 256bit unit per core.


Here is a Phenom II (Deneb core) for comparison:



As you can see the Core is just a core, has its own everything including L1/L2 cache and then shares L3 and IMC.

The only thing shared by Sandy Bridge CPUs is the L3 cache and IMC but the IMC in BD is also shared as its part of the CPU as a whole.

Without knowing performance, I cannot guess as to what it would take in order to get 8 real cores worth of performance. If each module gives 1.5 cores worth of performance then it would take more than 10 modules to give the same performance as a real 8 core.

Of course its all speculation which is why I will wait till BD hits to see its performance but it will be hard to say if the 8 "module" BD CPU should go up against a 8 core Sandy Bridge CPU.

Hellboy said:
Hey Jimmy :) 

any news on what sort of speed we expect...

sounds like it wont be too impressive... i mean the 6 core was a bit of a flop... i dont know anyone whos got one.


For BD, AMD has nothing in expectations of clock speed but people have been "theorizing" that because it is AMDs first step into 32nm and HK/MG that it might not be as impressive as SB is.

I can't say but I would at least expect it to be near stock clocks of Phenom II when it hit, but as for overclocking, I don't see it passing SB. Hell some people patched the BIOS for P67 and were hitting 5.5GHz on air on i7 2600Ks. Of course they are using very nice air coolers but still, 61% stable OC on air is insane.

http://www.xbitlabs.com/news/cpu/display/20101123230924...

Thats a rumor of 3.5GHz but I wont hold my breath. First gen process normally doesn't blow away previous generation mature process in stock clock speed or overclocking. Hell Gulftown wasn't better than nehalem but SB is blosing everything previous out of the water.
Score
0
a b à CPUs
February 13, 2011 10:08:32 PM

jimmysmitty said:
Its hard to fully explain but thi picture does a decent job:

http://images.anandtech.com/reviews/cpu/amd/hotchips2010/bulldozermodule.jpg

Each core has its own pipeline, L1 DCache and Int scheduler but they share the Fetch, Decode, FP Scheduler, 2 128bit FMACs and the L2 cache. The L3 cache is shared among all the cores.

This may look like a dual core but its not. A Sandy Bridge core has all of that per core, minus the FMAC units, Intel ahsn't implemented FMAC yet and will not till Haswell but are still using a single 256bit unit per core.


Here is a Phenom II (Deneb core) for comparison:

http://media.bestofmicro.com/AMD-Phenom-II-X4,L-0-174420-13.jpg

As you can see the Core is just a core, has its own everything including L1/L2 cache and then shares L3 and IMC.

The only thing shared by Sandy Bridge CPUs is the L3 cache and IMC but the IMC in BD is also shared as its part of the CPU as a whole.

Without knowing performance, I cannot guess as to what it would take in order to get 8 real cores worth of performance. If each module gives 1.5 cores worth of performance then it would take more than 10 modules to give the same performance as a real 8 core.

Of course its all speculation which is why I will wait till BD hits to see its performance but it will be hard to say if the 8 "module" BD CPU should go up against a 8 core Sandy Bridge CPU.



For BD, AMD has nothing in expectations of clock speed but people have been "theorizing" that because it is AMDs first step into 32nm and HK/MG that it might not be as impressive as SB is.

I can't say but I would at least expect it to be near stock clocks of Phenom II when it hit, but as for overclocking, I don't see it passing SB. Hell some people patched the BIOS for P67 and were hitting 5.5GHz on air on i7 2600Ks. Of course they are using very nice air coolers but still, 61% stable OC on air is insane.



Just as i thought... thats a no then :( 

Would be nice if AMD got something to have a chance with - oh well, looking towards Windows 8 when it comes out i guess..

Why dont Apple just release their os on pcs too.. Dual boot pc and apple os legally as its been done illegally for ages. I used a Mac mini the other day with Windows on it natively and you know what its quite quick running xp.. for a size of a large burger box.
Score
0
a b à CPUs
February 13, 2011 10:09:56 PM

i thought JFAMD? stated that if the first core was being used at 100 percent that the second core could run at 90 percent or both at 95. if that is the case then i think they might have a winner.
Score
0
a c 127 à CPUs
a b À AMD
February 13, 2011 10:13:17 PM

Hellboy said:
Just as i thought... thats a no then :( 

Would be nice if AMD got something to have a chance with - oh well, looking towards Windows 8 when it comes out i guess..

Why dont Apple just release their os on pcs too.. Dual boot pc and apple os legally as its been done illegally for ages. I used a Mac mini the other day with Windows on it natively and you know what its quite quick running xp.. for a size of a large burger box.


I am not saying BD is going to suck. Just that its hard to say with no real basic info beyond the arch itself.

It may be amazing or it could suck.

cbrunnem said:
i thought JFAMD? stated that if the first core was being used at 100 percent that the second core could run at 90 percent or both at 95. if that is the case then i think they might have a winner.


I think it depends on the actual job thats being done. In servers this may be true. But on consumer desktops it may be different. AMD tends to focus on server design more than consumer design due to the larger profits to be made in that market.

I say wait and see. I think the idea is interesting but I don't think it will achieve 90-95% or a real core since it has to share a lot of the CPUs parts.
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 10:39:00 PM

i find it not intelligent, or productive to have cpu cores or modules that arent running at 100% capacity, maybe when in idle, but besides that, i dont see the point,
Score
0
a b à CPUs
February 13, 2011 11:09:59 PM

Well, while AMD may not have the resources of Intel, they still have intelligent people (directly in the company and in the other companies working with them). They chose this design for a reason: a balance of performance, power, and cost (die size). While I doubt it blow SB out of the water (in desktops at least) I'm hoping it will provide a solid alternative.

Remember, while it will not be able to 100% utilize all of the 8 x86 (integer) cores at once, it is doing it in less space than 8 full cores. So while total performance won't equal 8 true cores, hopefully the die size reductions will result in better performance per mm^2.
Score
0
a c 135 à CPUs
a b À AMD
February 13, 2011 11:14:58 PM

good point, but i still like to see it before i beleive it, honestly,
Score
0
a b à CPUs
February 13, 2011 11:25:23 PM

Definitely. I didn't mean to say it will be awesome (note the liberal use of 'hopefully'), all I meant to say was don't count it out yet. Processors, caches, pipelines, etc. are all such complex things that it is really impossible to look at pics or specs alone and say 'this one is faster'. Even the engineers who designed every part of these chips can't truly say until the first sample comes off. Remember how the ATI engineers were surprised of the performance of the 4xxx when they got the first real chips.
Score
0
a b à CPUs
February 13, 2011 11:43:09 PM

jimmysmitty said:
I am not saying BD is going to suck. Just that its hard to say with no real basic info beyond the arch itself.

It may be amazing or it could suck.



I think it depends on the actual job thats being done. In servers this may be true. But on consumer desktops it may be different. AMD tends to focus on server design more than consumer design due to the larger profits to be made in that market.

I say wait and see. I think the idea is interesting but I don't think it will achieve 90-95% or a real core since it has to share a lot of the CPUs parts.


Under heavy Floating Point loads, Bulldozer will act more like a 4 core product. Most heavy FP tasks are offloaded to the GPU these days (Games) but certain applications (HD Video Transcoding) does require a decent enough FP load of math.

I think it disingenuous to call it an 8 "Core" processor as it is not. Anyone stating otherwise is attempting to mislead others.

That being said... in a few die shrinks from now... the module approach could become quite lucrative (especially with the advent of OpenCL GPU offloading for FP loads).

EDIT: You can see why AMD is going this route. They own a Graphics company (ATi) and this marriage of sorts will lead to some great platforms (as we're seeing with the Ontario APU platform today).
Score
0
a c 131 à CPUs
a b À AMD
February 14, 2011 1:42:07 AM

There seems to be more misinterpretation of the information than there is actual misinformation though.

You guys might want to check out the blogs in their "server" products blog area. Note also that more information is revealed in the comments in the threads by the author of the articles than is revealed in the actual articles. Note also that it is specific to servers, though it is assumed the architecture itself will be the same in both server and client products.
Score
0
a c 127 à CPUs
a b À AMD
February 14, 2011 3:57:54 AM

enzo matrix said:
There seems to be more misinterpretation of the information than there is actual misinformation though.

You guys might want to check out the blogs in their "server" products blog area. Note also that more information is revealed in the comments in the threads by the author of the articles than is revealed in the actual articles. Note also that it is specific to servers, though it is assumed the architecture itself will be the same in both server and client products.


I don't think this is misinterpretation:



From what I can find thats what AMDs 8 core (Module) will be.

We have no idea what it will be able to do. There is no way to guess for sure.



That shows the way Intels SMT works and the way AMDs CMT will work. It looks to be much more powerful than SMT but does it mean a 4 module BD core will be able to keep up with a true quad core? No. It means it will be better than SMT. As to how much better is what we have to wait and see.
Score
0
a b à CPUs
February 14, 2011 4:23:10 AM

Here is to explain:

1 Bulldozer core can handle the basic 64 bit registry processing.

2 Bulldozer cores reside in a system called a 'module'. This 'module' enables 2 cores to work with each other to process data.

Now, Bulldozer will have 4 'modules':

2 x 4= 8 processing cores.

Now, the cores in each 'module' will share cached memory and communicate with other cores initially.
Score
0
a b à CPUs
February 14, 2011 8:12:47 AM

Didnt Intel do this sort of thing with the Core 2 Quad double cheese burger which so many amd fans bitched about...

Maybe it worked back then as software was dual core optimized but now programmers are learning how to multi core program - let the battle commence..
Score
0
February 14, 2011 11:50:31 AM

Hellboy said:
Didnt Intel do this sort of thing with the Core 2 Quad double cheese burger which so many amd fans bitched about...


No, the "double cheeseburger" thing was that Intel slapped two Core 2 Duo dies onto the same substrate. This really has absolutely nothing to do with bulldozer.
Score
0
a b à CPUs
February 14, 2011 4:37:08 PM

turboflame said:
No, the "double cheeseburger" thing was that Intel slapped two Core 2 Duo dies onto the same substrate. This really has absolutely nothing to do with bulldozer.



so its a double whopper side by side then :) 
Score
0
a c 131 à CPUs
a b À AMD
February 14, 2011 8:04:08 PM

turboflame said:
No, the "double cheeseburger" thing was that Intel slapped two Core 2 Duo dies onto the same substrate. This really has absolutely nothing to do with bulldozer.

Anyone know if it was two separate dies or the same die just side by side on the die?
Score
0
a b à CPUs
February 14, 2011 9:35:14 PM

It was two dies on the same substrate.
Score
0
a c 127 à CPUs
a b À AMD
February 16, 2011 12:46:51 AM

enzo matrix said:
Anyone know if it was two separate dies or the same die just side by side on the die?


Core 2 DUo was a true dual core. It was Core 2 Quad that they complained about which was two Core 2 Duos stiched together via the FSB.

And AMD already did the MCM approach with Magny-Cours so they already ate their words.

BD on the other hand is a module approach but it means they can cut "modules" when needed but two each time. Each chip will be monolithic but still ..... not sure.

But BD should not be MCM, at least for the 8 "core" version and lower.
Score
0
a b à CPUs
February 16, 2011 1:40:47 AM

jimmysmitty said:


And AMD already did the MCM approach with Magny-Cours so they already ate their words.



I do NOT know why they did that? maybe JF can answer that one.
Score
0
a b à CPUs
February 16, 2011 1:47:07 AM

To get the core count up ... and because it is not really that huge of a negative (if Intel didn't already prove that with C2Q vs Phenom I).
Score
0
February 16, 2011 1:57:42 AM

EXT64 said:
The 6 core i7s never came down in price (though it would be awesome if 8 core SBs were semi-affordable).



LAUGHTER ECHOES THROUGH THE DARK RECESSES OF YOUR MIND...
Score
0
February 16, 2011 2:01:01 AM

jimmysmitty said:
If you compare a 8 core SB chip with a 8 "core" BD chip its not the same. Each SB core has its own resources while each core in BD shares resources. Thats the reason why AMD is calling the modules instead of ccores because they are not each a full core.

It is AMDs version of SMT (called CMT) on a higher level. It means that their version should produce better results than SMT which normally can push 20% better threaded performance, this should be much higher.

But calling the each real cores is a lie because in fact they are not each true cores.

It would be like calling each core in Atom a real CPU core when in fact they are just parts of the CPU core.



Don't ask your friends. Don't ask JF. Don't ask me. Don't promote yourself to Distinguished Engineer.

ASK THE WINDOWS TASK MANAGER.
Score
0
a b à CPUs
February 16, 2011 2:12:38 AM

...or Ask Jeeves.
Score
0
a c 127 à CPUs
a b À AMD
February 16, 2011 2:26:12 AM

dogman_1234 said:
I do NOT know why they did that? maybe JF can answer that one.


Simple, as EXT64 said. To get more cores. As much as AMD mocked Intel for that approach, they knew it worked. It got Intel to a quad core first that worked great and was cheaper and easier to produce rather than a monolitich 65nm die,. Thats also why Phenom had a lot of heat issues, AMDs 65nm wasn't their best process. In fact their 90nm X2s were better than the 65nm X2s.

BaronMatrix said:
LAUGHTER ECHOES THROUGH THE DARK RECESSES OF YOUR MIND...


BaronMatrix said:
Don't ask your friends. Don't ask JF. Don't ask me. Don't promote yourself to Distinguished Engineer.

ASK THE WINDOWS TASK MANAGER.


See ya on the far side.
Score
0
a b à CPUs
February 16, 2011 8:18:18 PM

why oh why is any resonable discussion ruined by someone with a AMD processor planted in his anus and a void where their brain is...

how many threads have been locked by lunacy ramblings of people who no matter what will not take comic comments and their on sided views

if a product is a failure for what ever reason then its a failure

if its a success then its a success for what ever reason.

what ever intel do AMD fanbois come out from the drain holes and make mad comments about what their new oober processor is supposed to do..

dont get me wrong ive sold 20 amds to 1 intel so im not biased

i like amd, i like intel
Score
0
February 16, 2011 8:48:20 PM

Enter the "non-biased and neutral" anti-fanboy fanboy. They are the most pathetic fanboys on any forum because they have to put on blinders to actively ignore any valid point that might be said by somebody they are ridiculing.

That particular action requires more bias than anything that can be posted by somebody that fully admits to having a brand preference. (And it puts these clowns on the top of the fanboy hierarchy.)

EDIT: Not to mention that anti-fanboy fanboys are also usually well known fanboys of a particular brand that are now pretending to be neutral for some unexplained reason.
Score
0
February 16, 2011 8:53:07 PM

jimmysmitty said:
Core 2 DUo was a true dual core. It was Core 2 Quad that they complained about which was two Core 2 Duos stiched together via the FSB.

And AMD already did the MCM approach with Magny-Cours so they already ate their words.

BD on the other hand is a module approach but it means they can cut "modules" when needed but two each time. Each chip will be monolithic but still ..... not sure.

But BD should not be MCM, at least for the 8 "core" version and lower.




There is a WORLD of difference between Amds and Intels MCM. Intel's MCM was just a common package with two routes to the FSB.

AMDs MCM is two chips with a single route to main memory through the HT links.

JF can correct me if I missed something...

Like I said no wonder I banned myself...
Score
0
a b à CPUs
February 16, 2011 10:08:24 PM

keithlm said:
Enter the "non-biased and neutral" anti-fanboy fanboy. They are the most pathetic fanboys on any forum because they have to put on blinders to actively ignore any valid point that might be said by somebody they are ridiculing.

That particular action requires more bias than anything that can be posted by somebody that fully admits to having a brand preference. (And it puts these clowns on the top of the fanboy hierarchy.)

EDIT: Not to mention that anti-fanboy fanboys are also usually well known fanboys of a particular brand that are now pretending to be neutral for some unexplained reason.

And here enters Rush Limbaugh...

Yes... fanbois are oppressed. You poor things have had to endure logic, reason and rationality (as well as reality) thrown into your face anytime you make a ridiculous claim.

Lets all pitty the fanbois.

There is no such thing as an anti-fanboy fanboi. That's like claiming that an Atheist is religious. :heink:  Some of us just don't like BS and don't like it when people blatantly try (and succeed) at misleading others.

We all know that you're upset and hurt over the years of pwnage at the hands of people such as myself. Maybe if you were actually a respectable individual who didn't try to lie/mislead people I'd let you be... but no. You post your misinformation in thread after thread after thread.

When someone wants to purchase a new system... how about just giving them the facts and letting them make the choice. Try to remain objective for once.f
Score
0
February 16, 2011 10:13:18 PM

EXT64 said:
The 6 core i7s never came down in price (though it would be awesome if 8 core SBs were semi-affordable).

Quote:
Beside rolling out the 990X, Intel also adjusted the price tags of two of its LGA1366 CPUs, the 3.2 GHz i7-960 and i7-970.

The 960, which is a 45nm part with four cores (8 threads) and 8MB of L3 cache, has went down from $562 to $294, matching the new Core i7-2600, while the 970, with its six cores and 12MB L3 cache, has dropped from $885 to $583.

Source
Score
0
a b à CPUs
February 16, 2011 10:23:40 PM

Note the date of my post - 1 day before that announcement.
Score
0
February 16, 2011 10:25:27 PM

EXT64 said:
Note the date of my post - 1 day before that announcement.

I am well aware, that's why I didn't make any comments or anything. ;) 

My post merely shows that Intel does put their processors on sale, the 950 came down in price previously too.

Intel just hasn't been forced to put their stuff on sale due to its competition.

If BD does prove to be a worthy performer, Intel will have to price their processors accordingly, which will be good news for people waiting for Ivy Bridge. ;
Score
0
a b à CPUs
February 16, 2011 10:29:41 PM

Gotcha, and this is one case I am glad to be wrong.
Score
0
    • 1 / 10
    • 2
    • 3
    • 4
    • 5
    • More pages
    • Next
    • Newest
!