8350rocks :
Quick question, in 2035 when ARM still has not "won" are you still going to screen shot that slide?
I can promise you that then I will have better slides to share.
![Sarcastic :sarcastic: :sarcastic:](/data/assets/smilies/sarcastic.gif)
Cazalan :
Death always wins in the end too, but we don't have to repeat it every day ad nauseam.
What's that about 20 times now the same slide has been linked? The forums really need an ignore button.
What's that about 20 times now the same slide has been linked? The forums really need an ignore button.
Have you considered that the AMD slide is repeated because there is a bunch of posters that continue pretending that it doesn't exist, that AMD doesn't think that, and that AMD never said that?
If they stop pretending that AMD never said "ARM will win", then the "ARM will win" slide from AMD doesn't need to be linked again. It is easy, isn't?
Before someone misinterpret my words again, I want to do it clear that people here can disagree with the AMD slide, what I cannot accept is the pretension of some that the AMD claim is from mine and not from an AMD slide. It is called false attribution.
de5_Roy :
AMD plans new architecture for 2016
http://www.fudzilla.com/home/item/34769-amd-plans-new-architecture-for-2016
fudzilla's back up, so reposted gamerk's link. hints at SMT design. but no confirmation... more like a logical speculation, which, considers bd's module design ineffective. here's another "logical conjecture" if this SMT hint holds water - 3 integer ALUs per core like sandy/ivy bridge.
http://www.fudzilla.com/home/item/34769-amd-plans-new-architecture-for-2016
fudzilla's back up, so reposted gamerk's link. hints at SMT design. but no confirmation... more like a logical speculation, which, considers bd's module design ineffective. here's another "logical conjecture" if this SMT hint holds water - 3 integer ALUs per core like sandy/ivy bridge.
FUD link was discussed above. As I mentioned then FUD got wrong some aspects of the x86 core. I also gave a link with more accurate info, check it here
http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-265#13321573
FUD got the hint about abandoning CMT from other source, which itself got it from another source, which said me that Keller is abandoning the CMT architecture.
FUD claim about CMT was already covered in other sites before
http://www.xbitlabs.com/news/cpu/display/20140510165441_AMD_to_Introduce_New_High_Performance_Micro_Architecture_in_2015_Report.html
Not a lot of details about the new micro-architecture are known at present. What is recognized for sure is that it will drop CMT in favour of some kind of SMT (something akin to Intel’s HyperThreading) technology to improve performance in both single-threaded and multi-threaded cases.
The XbitLABS link and the quote were given by me two or three pages ago. And it was then commented by some here.
About your suggestion about using 3 integer ALUs per core... it is entirely possible, but I have a die shot that shows 4 integer ALUs per core. I would expect AMD to maintain that design. Time will say which is the final architecture.