AMD embraces AVX making a new superset with SSE5(256bit support)

[Smartidiot89]

Because AMDs engineerers are stupid and have no clue what so ever what they are doing

[generics_user]

great news, hopefullythey'll make it to the market on time

@shintai: please stop your pointless holy crusade against amd and make some useful posts, it's really annoying to have that much space on my screen wasted due to useless destructive posts...

[Glow9]

So does this mean they will finally be able to be faster than high end Intel Quad core 775's?

[Helmore]

Not necessarily, although it would be shameful if they weren't by then.

[Anemone]

Well AMD going out on their own and saying "we're 10% of the market but we're going to do our own instruction set" is just as ridiculous now as it was years ago with 3Dnow. 64 bit was a whole different ballgame and it wasn't till Intel joined that party that you really began to see mainstream 64 bit software. Even now, years later, the move forward is slow on the software side, and 3Dnow is forgotten tech, while SSE is everyday stuff.

It's ok to venture out and do it all by yourself. Just do it in a place that is truly market changing, not on these crazy little spats about extended instructions.

[Glow9]

Another question are these going to be AM3's or new socket?

[ILikeCosmosS]

i heard magny four cores was on the g34 socket and it should be a new socket

[roofsniper]

the new socket. who knows what else will be on am3. maybe the desktop version of instanbul but besides that most of amd's new designs are on the new socket.

[Shadowmage]

So does this mean they will finally be able to be faster than high end Intel Quad core 775's?

According to an AMD engineer that I know, AMD doesn't have a chance to compete with Intel in absolute performance until Bulldozer.

[AKM]

According to an AMD engineer that I know, AMD doesn't have a chance to compete with Intel in absolute performance until Bulldozer.

I don't think you need an AMD engineer to tell you that lol

[gOJDO]

LOL, AMD fans never lose hope...

Do you guys have any clue how these new SSE7, AVY or whatever will improve performance of current and future software?

[roofsniper]

According to an AMD engineer that I know, AMD doesn't have a chance to compete with Intel in absolute performance until Bulldozer.

says who? istanbul is coming in a month and it will be a 6 core cpu plus they will make a mcm chip that will be 12 cores just like core 2 is so you could have up to 48 cores on one system. to me i think that alone will compete fairly just because of the abundance of cores. also amd is doing fine on the server side right now they have been doing better than intel there for years.

[STaRGaZeR]

I don't think you need an AMD engineer to tell you that lol

LOL indeed.

[madcho]

says who? istanbul is coming in a month and it will be a 6 core cpu plus they will make a mcm chip that will be 12 cores just like core 2 is so you could have up to 48 cores on one system. to me i think that alone will compete fairly just because of the abundance of cores. also amd is doing fine on the server side right now they have been doing better than intel there for years.

You're right amd is far better on server market.

intel don't have anything good in 4P

[Chad Boga]

says who? istanbul is coming in a month and it will be a 6 core cpu plus they will make a mcm chip that will be 12 cores just like core 2 is so you could have up to 48 cores on one system. to me i think that alone will compete fairly just because of the abundance of cores.

That will help in the server market but will do nothing for 99% of desktop users.

also amd is doing fine on the server side right now they have been doing better than intel there for years.

Another outright distortion.

No professional analyst/observer of the server market(i.e. IDC, Mercury etc) gives AMD a larger share of the server market than Intel.

What you have done at best, is redefine the term "server market" to that tiny niche where AMD does better, but that is not how it works in the real world where terminology is universally accepted so that meaningful Apples to Apples comparions can take place, rather than fanboy worship.

[Glow9]

According to an AMD engineer that I know, AMD doesn't have a chance to compete with Intel in absolute performance until Bulldozer.

And thats why I ask cause I'm not gonna hop to AM3 if its gonna go nowhere when I can just pop in a e8400 to tide me over

[Macadamia]

That will help in the server market but will do nothing for 99% of desktop users.

That's a really fitting description for Nehalem too.

[Chad Boga]

That's a really fitting description for Nehalem too.

No, but it does apply to the 6 core Westmere that is getting here before the higher clocked Westmere Quad.

[informal]

Agner Fog's comment on this from Ace's hw:

Thanks for posting the reference to the new AMD manual, indicating that AMD have changed their SSE5 codes for the sake of compatibility with Intel AVX and FMA.

The present situation shows once again that such a committee is desperately needed. Unfortunately this is not gonna happen unless somebody can legally force Intel and AMD to cooperate rather than keeping secrets to each other.

If Intel and AMD had communicated better we wouldn't have this mess now.

The new instruction space that has been opened with Intel's introduction of the VEX coding scheme is HUGE. It has room for all kinds of extensions and new instuctions for many years to come without making instruction codes longer. It would be absolutely no problem to reserve a small part of this new instruction space to AMD so that they could invent new instructions without risking that Intel has something else in their pipeline that happens to use the same code for something else. However, the new spec. of AMD instructions indicates that it has been impossible for AMD to get such an agreement with Intel. Rather than coding their new instructions according to the VEX scheme, they have invented yet another prefix called XOP. The AMD XOP prefix (8F) works in exactly the same way as Intel's VEX prefix (C4). This makes instruction decoding easier than if AMD had sticked to their SSE5 coding scheme. If some of the new instructions invented by AMD happen to be so popular that Intel have to copy them, then Intel can just treat 8F and C4 as equivalent, and the new instruction fits into the VEX scheme. The codes do not overlap, even if 8F and C4 are treated as equivalent. (8F would overlap with POP instructions if used instead of C4 on some Intel instructions).

The blame here is really on Intel. They have changed their specifications for FMA instructions without informing AMD in time. They must have known that AMD had plans about changing their coding scheme to make it compatible with Intel's because there have been patent-clearing negotiations between the two companies about this issue.

Intel should also be blamed for refusing to assign part of the opcode space to AMD, thereby forcing them to invent yet another prefix.

It seems that AMD are the nice guys in this case. They have made great sacrifices by dropping their SSE5/DREX coding scheme and replacing it with Intel's scheme for the sake of compatibility. And then Intel have blown it all by changing their specs once again. Arghhhhh!!!!!!

How long shall we live with this race between Intel and AMD on inventing new instructions and the resulting problems of incompatibility, a bloating and complicated opcode map, and instructions that are rarely used becaused the competitor has invented something better? These obsolete instructions will have to be supported in all future for the sake of compatibility with legacy software.

[Brother Esau]

I see the Intel Fan Club is in the House and crapping on yet another AMD thread.


When is this crap going to end? Its the same people over and over who could care less of AMD and their Products but yet they continue to come into AMD threads and ruin it every time.



HEY MODS!!! When or should I say Are You going to do anything about this?

[GAR]

I am hoping amd can make a comeback for the sake of fast cpu's.

[ajaidev]

[QUOTE=Shintai;3766463]So now having it doesnt matter now How is it big news then

Plus what happens when you compile and use say SSSE3. But lack one instruction because you didnt fully support it in your CPU Thats right, it doesnt run in that mode. It changes to a former more legacy mode.
If you didnt have full SSE2 support you couldnt run 64bit Windows either.

Alot of applications uses the newest instructions. Just because Crysis or some other popular title doesnt use it. Doesnt mean its not used at all in large amounts. And you will never see it really unless you bench it. Because then you just run it with SSE3 etc instead or so.[QUOTE]


I know that AVX is really easy to get along with. You can convert SSE4 Ins. to AVX in a few days instead of a full rewrite but the thing is AVX will be not supported by majority of processors in 2010 Eg Few people have i7 platform in 09. Yes the app will try and use a lower instruction set such as SSE4 but then again AVX is not entirely compatible with SSE4 so you have to double write coding which willadd to the weight of the application,complexity, etc.

In english-

AVX can do C = A+B and D = A+B+C but only if your processor supports AVX otherwise you will have to write more instructions instead like A = A+B ALSO C = A+C... The break down can also be done by the software itself which is slower because it happens in real time.

[Chad Boga]

Agner Fog's comment on this from Ace's hw:

Paul DeMone's apt response to Agner

It is up to the parasite to adapt to changes in its host, not the other
way around.

AMD is free to extend x86 as it wishes, or even better, create an all
new ISA on its own. If it wants a free ride by slip streaming behind
Intel then it has no choice but to follow closely behind. Intel has no
legal or moral obligation at all to assist AMD in competing with it and
IMO anyone who thinks otherwise is a sad product of a society gone
mad with entitlement mentality.

[Hornet331]

I see the Intel Fan Club is in the House and crapping on yet another AMD thread.


When is this crap going to end? Its the same people over and over who could care less of AMD and their Products but yet they continue to come into AMD threads and ruin it every time.



HEY MODS!!! When or should I say Are You going to do anything about this?

How is that and amd thread when the titel mentions both?... oh well, seems I forgot the amd fanboy rule #1: AMD in the title means amd exclusiv, even mentioning the name intel is thread crapping...

When you call for mods, how about changing the thread title itself, it's an invitation for flaming... informal could easily have chosen another thread title, but it wouldn't have caused that much of a stir up... (talk about double standards)

[informal]

Paul DeMone's apt response to Agner

Professor Fog is much more into instruction set analysis than Paul ever was or will be. Anyway,Paul will do anything to bash AMD,it is the thing he does.
The fact is the very second AMD made adjustments to SSE5 and made it compatible to AVX back in January,intel changed the spec again and made it incompatible again. This is imo a clear sign of weakness on intel's part since they know that initial avx with no FMA instruction in 1st iteration of SB will be no match for new avx-like AMD instruction set in BD cores in 2011.SO they made it incompatible again by changing the spec on the fly after AMD posted their revised specification.

In the end MS will probably have a say in this matter too.Will be interesting to see how this one turns out.