hcl123 :
Charlei is incorrect.
its not the "The blue arrows above are for coherent memory accesses, yellow for non-coherent traffic"... if he had payed attention and not eager to sell more fish out of the same basket, if he had included the slide "GPU and GPU MMU clients"(http://cdn2.wccftech.com/wp-content/uploads/2013/08/Xbox-One-GPU-Architecture-635x481.png )(edt) as seen here http://wccftech.com/microsoft-xbox-one-architecture-detailed-hot-chip-2013-features-5-billion-transistors/, the second yellow/(green) line from the top for the "Host Guest GPU MMU", totally exposed in the "SoC Components" slide he analyses, but without the *comments*, says: "DRAM Access Non-CPU-Cache-Coherent 68GB/sec peak (incl coherent BW)", and that link goes exclusively to the DRAM controller that has 68GB/s peak, meaning all DRAM (system DRAM) is coherent to the GPU caches at max bandwidth possible, its the CPU block the one restricted to 30GB/sec (~half)... so Durango is hUMA...
And Durango is not 1+ year old design, matter of fact compared with PS4 design that uses Garlic and Onions as seen here http://www.vgleaks.com/playstation-4-architecture-evolution-over-time/ seems more advanced than Orbis( not very fond of M$ like Charlei, but skip the phobia)... thought Orbis will perform better at games( but probably not that much)...
Matter of fact the design is pretty identical to "onion + onion+" of Orbis, most included that remarkable piece of Northbridge in the slide "Soc components" (CPU-Cache-Coherent Memory Access)(edt) that Charlei analyses saying: "Microsoft probably had to beef up the L2 to NB links to almost match that of the L1 to L2 links".. it was most most probably AMD NOT MSFT (perhaps for praising AMD, Charlei tung just sticks lol) since exactly the same thing is highly to suspect on the "Liverpool" SoC , just compare to http://www.vgleaks.com/world-exclusive-orbis-unveiled-2/ with http://www.vgleaks.com/world-exclusive-durango-unveiled-2/ (very identical *unified* Northbridge)... which *may* lead to conclude according the particularities, both SoCs will operate ~2Ghz for the CPU...
Also on that slide "SoC Components", the line from the bottom ESRAM to the CPU block, means that the 32MB ESRAM is visible from the CPU, probably as VGleaks suggested is I/O coherent, meaning the CPU can read it, but cannot write it in a coherent way (for this there is another link directly to GPU caches).
So Durango has a kind of large dedicated cache for the GPU (ESRAM), that is visible from the CPU, and is hUMA at total possible DRAM bandwidth... and is more advanced in some ways than Orbis, and could be a good preview for Kaveri.
hcl123 :
juanrga :
There is no way that AMD (or Nvidia or ARM or Intel) can implement an Uniform Memory Access with discrete.
Perhaps you should get a job at AMD... they and their HSA friends, supposedly experts from top companies are to embark in an impossibility LOL
http://t1.gstatic.com/images?q=tbn:ANd9GcRvGiOpiosFpbI_dQ0Fhf-2w6RanklsgXec8ZHRWDd0vWt-JvHlSQ
The last thing that is supposed to finish the total specification, foreseen for middle next year (mid 2014
http://www.theregister.co.uk/2013/08/25/heterogeneous_system_architecture_deep_dive/?page=3 ) is exactly
"Extend to discrete GPU" for this last push of "system integration" ... just see that image link, damn it lol ... (gee! could it be... HSA dumb juanrga smart!? LOL)
UPDATE :
And according to some analyses ( yes for one thing i would also like more details)
http://mygaming.co.za/news/hardware/53750-amds-plan-for-the-future-huma-fully-detailed.html ... its not only for future, but hUMA of sorts already works with Discrete adapters of the HD7000 family
For bonus points, this works with discrete AMD graphics cards from the HD7000 family as well, although there will be some latency issues when accessing GDDR5 memory. Its possible to have the CPU, integrated GPU and the discrete GPU all working on the same thing.
Though it could be, even with PCIe (cc emulated), i think none of the drivers versions so far really supports this.
As I already said, the HSA specification doesn't mention hUMA in any part. In fact, I have just checked the specification again and there is
no mention to
uniform. The HSA memory model is described as a "
unified memory model". Whereas the memory model in both Kaveri APUs and HSA dGPUs will be
unified, it will be only
uniform in the case of APUs.
unified !=
uniform
It seems some people (including at AMD) is confounding both concepts.
In fact, the confusion that AMD has introduced about hUMA is incredibly funny. What does hUMA mean? Has PS4 hUMA? Has XboxOne hUMA? Sometimes they have sometimes they don't, depending of the day and who replies emails at AMD.
One day AMD claims that PS4 is better than XboxOne because the PS4 has hUMA
http://www.fudzilla.com/home/item/32310-ps4-is-better-because-it-has-a-sense-of-huma-says-amd
Another day AMD claims that is "inaccurate". Then a supposed dev. who never did heard of hUMA before claims that XboxOne has hUMA or "something" as that
http://www.videogamer.com/news/xbox_one_has_implementation_of_huma_memory_system_just_like_ps4_say_dev.html
Pay attention to his exact words, because he confounds
unified with
uniform. Has XboxOne a
unified memory model? Yes. Has a
uniform memory model (
UMA)? No.
But it can be funniest. When asked about the PS4/XboxOne controversy, AMD claims that both the PS4 and Xbox One processors are based on Kabini and that Kabini "doesn't support hUMA"
http://www.pcper.com/news/General-Tech/Sony-PlayStation-4-PS4-will-NOT-utilize-AMD-hUMA-Kabini-based-SoC
So [...] there is no support for a true heterogeneous unified memory architecture in either upcoming console platform.
Note that this uses again "
unified" instead "
uniform". Is this confusing enough? No?
AMD contacted me again to make another comment. Essentially, they said that the correction statement to the original statement claiming hUMA was part PS4 was "inaccurate" but that this correction does NOT mean the opposite claim is true. Even when pressed for a more specific and debate-ending comment, AMD wouldn't give us any more information.
And then more people try to make sense of this pseudo-quantum logic...
http://www.neoseeker.com/news/23716-making-sense-of-who-has-a-sense-of-huma-between-ps4-xbox-one/
by adding more confusion: The XboxOne may not have "AMD's hUMA per se", but does indeed implement a "comparable memory sharing feature".
It seems evident AMD is using two different meaning for hUMA and confounding everyone on Earth about that:
If hUMA is a
uniform memory model for
heterogeneous processors, then both Kaveri and PS4 have hUMA, whereas XboxOne and HSA dGPU don't.
If hUMA is a
unified memory model for
heterogeneous processors, then Kaveri, PS4, XboxOne, and HSA dGPU all them have hUMA.
I suspect AMD is using the last meaning, but UMA stands for
uniform memory model. No strange all the confusion they are generating...