I remember years ago, at aceshardware there were discussions how much benefit in terms of power a custom design gives... it was Intel vs AMD...
Are the yields so bad, that AMD is unable to make enough cards?
so, its confirmed that AMD failed to implement successfully tile-based rendering in Vega?
You should get 25-26 mh from 290... running at 950/1250, and 330-350 sol/s for equichash
There are mem strap mods @techpowerup forums give'em a...
Is there solid info how big are caches in Vega?
9 years ago AMD had 2x R&D vs Nvidia
Now they have almost 2x less, even tho they make CPUs too
Wanna give brief how-to for trading?
I tried several times... But when realized that long-term the best I achieved was "no big losses" i stopped :D
heh .. an year and half ago ROI was like 4-5 months... but I was too afraid of implosion :( and invested only 1k euro.
And then reinvested half of...
Its not clear from his posts what cards he has, but given that AMD supposedly fixed their drivers for Vega,Fiji &Polaris (increasing ethereum...
70-100 is bullshit
We have some anonymous guy vs Claymore who made best miners for AMD
So 30MH@100W for 1070 vs 35MH@300W, not even funny
Looks like Vega is DOA for end users.
Everything will go for pro-market, they'll sell 1000 cards worldwide to review sites and amd fans...
still slower than 1080
there is no bad marketing
What if AMD is going to show us the impossible - make a PR event and admit they have inferior product which is twice...
No, best chance (for vega&amd) is if these pro-cards are from 1st chip revision which was faulty somehow, and game-cards will be later, fixed one...
And whats the point in overclocking Vega, unless one needs to warm his room?
1 year later, more power draw and less gamespeed per mm2 ... people Do expect something improved after so many PR events and announcements
IF Vega is using tiling, the performance is even more embarrassing...
- not faster than gddr5x/gddr6
Its rambus all again
One has to wonder why AMD had chosen to use HBM ...
The card is selling with 2*8-pin power connectors, so the power is as expected
Can you try the new genoil miner optimised for Nvidia? Pretty big pump for 3GB 1060 (10%+) https://github.com/Genoil/cpp-ethereum/pull/228
Will Vega be a match for 1080? (see above for power usage)
Do you suggest that Vega is not GCN-X, but a new/different arch?
2 8-pin power connectors vs 1080 ... who said power hungry?
well, it is not faster, but is in same league.
And +40% for 6752 is not bad at all. Too bad both have only single channel memory path - this will...
Well, so far I have no idea what are differencies between gpu in 6752 and 6732 ... maybe frequencies...maybe not
But I saw claims that 6732 is...
The problem is - I can't find any other becnhmark/test which has results for these......
Can someone compare gpus in 6732 and qualcomm 615?
T760-mp2 vs adreno 405.
On paper it seems adreno 405 is faster, tho first benchmark results for...
My question is about theoretical math speed of cores, eg if there is any comparison of achievable speed in units.
Say maybe GCN 1.0 can...
Are GCN cores in all "new" chips equal?
e.g. if we have 1 "bonaire" (260) core and comapre to 1 tahiti/hawaii core, will the theoretical...
Is there anyone left who believes buying ATi instead of "merging" with NVidia was the smarter move?
Years after... NV still has BETTER GPGPU...
Any idea why AMD is losing GPU market share ?
For God's sake, GPU-Z uses DB , it does not read configuration from the chip.
If it doesn't recognize GK104 correctly (DB not updated) it will...
Let the leaks start :):runaway:
afaik, journalists were introduced to Kepler arch few days ago, and now they are back :P
Because what dnavas wrote is not true? :???:
LOL, too many hints :P
my 2 cents: 3.4 bln
Just yesterday, AMD payed hundreds of millions to GF, because they cancelled CPU orders, and wanted to become GF-free :/
and why not 3-3-3 or 4-4-4?!
Damn :), it took me 5min to understand that I'm looking at review on my own language which was translated to chinese and then to english :D
GCN 2.0 ?
That should come end of 2012.
Then the chip is 110-120 ?
Are CV sizes from external measurments, or "official" AMD data?
What if these 700Mhz are "base" clock, with max clock being only power-limited, with expected max sustained clock ~ 900-1000MHz?
How could they cancel a non-existing product? :D
Is anyone able to provide some reasoning for going 4-3-3 with CUs?
I just don't see any gain for non-symetrycal units by design.
more grim news from AMD HQ :(
Who says die size is same?
Who says bandwidth balance is similar to Tahiti? Any review with detailed review how bandwidth limited is Tahiti in...