• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD VEGA confirmed for 2017 H1

Status
Not open for further replies.
, a 590 which is the cut down Vega
They wont mix such different technology on the same numbering. They said Vega will be released as RX Vega so it wont be called a 590 then which is related to technology we already know about. Maybe the lower card is sx vega, my guess is its not a number.
I see 580 as a release by AMD for AMD in that production is cheaper from the changes and eventually allows them to offer ever cheaper cards, naturally it forms their mainstream offering. Vega works well on laptops some vid said, thats where I see the lower Vega appear first or best suited perhaps, is it cooler or more compact.
True but at how many times the cost?
Price performance ratio is where they should do well but it then depends how well that performance is used in games. I guess if they worked with Prey devs thats the place to be judging it most harshly on release and maybe other games can follow that lead in time with driver development etc.

The other take would be is the card is primarily a VR card or a Deep Learning product which also then gives a boost to game performance, it then maybe wont be the best price performance in conventional games

Maybe if its a card reaching 3 different markets it'll not immediately please anyone as 'the best'. I like to think AMD is not racing for some superficial short term target, gaming the benchmark figures etc but has a larger game plan forward looking that is way more interesting but maybe delayed by necessary development in software. Also that might also mean on release its not the flashy top dog card people imagined


As many have said GPUs are so fast because they are so efficient for matrix multiplication and convolution, but nobody gave a real explanation why this is so. The real reason for this is memory bandwidth and not necessarily parallelism.

First of all you have to understand that CPUs are latency optimized while GPUs are bandwidth optimized. You can visualize this as a CPU being a Ferrari and a GPU being a big truck.

So in other words the CPU is good at fetching small amounts of memory quickly (5 * 3 * 7) while the GPU is good at fetching large amounts of memory (Matrix multiplication: (A*B)*C). The best CPUs have about 50GB/s while the best GPUs have 750GB/s memory bandwidth. So the larger your computational operations are in terms of memory, the larger the advantage of GPUs over CPUs.
https://www.quora.com/Why-are-GPUs-well-suited-to-deep-learning

http://www.nvidia.com/object/deep-learning-system.html
 
He can't talk about what he can't talk about. Kapish? :D

Matt has told me privately that Vega is expected to blow the doors off even the 1080Ti. See he can't deny this because if he does it means to expect lower performance ;) :p :D

Uh oh I can see the WCCF article now,

STOP THE PRESS

It really is Poor Volta, My insider sourced information confims Vega is a Beast,
Thanks to my source who will remain unnamed we now know Vega's faster than
the 1080ti and the new Titan, We're looking at an 1800mhz behemoth for
just under 500 dollars.
Remember you heard it here first folks*.

* Unless it's not true in which case Ahh forget about it!
 
Status
Not open for further replies.
Back
Top Bottom