• 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.

Poll: ** The AMD VEGA Thread **

On or off the hype train?

  • (off) Train has derailed

    Votes: 207 39.2%

  • (on) Overcrowding, standing room only

    Votes: 100 18.9%

  • (never ever got on) Chinese escalator

    Votes: 221 41.9%
  • Total voters
    528
Status
Not open for further replies.
Frontier will perform worse then the cheaper Rx version btw. None of this is news yet. Whats the chances of 4,8,16,32gb versions or will be it 8,16 for sure (initially + later)
£500 for water seems expensive, all likely just guesses

ed2Gkn7.jpg
 
awaybreaktoday said:
VEGA(1).jpg


Under performing!!!!!
Click to expand...
We know what the naysayers are going to harp on now.. "But it uses more powah so it ***** "
 
Cambofrog said:
Nice CAD results, but shame no Autodesk Inventor results. Could I ask the source please?
Click to expand...


these benchmarks are....worrying

it's certainly not a professional card then, as the quadro p4000 £900 scores mostly higher than that, whilst maintaining a 100w tdp vs 375w tdp.

this is targeted at titan market, deep learning /workstations etc.

but with 125w higher tdp than the titan, this seems a bit DOA.

much like the fury and fury x, the air cooled one is going to throttle HARD , we know the titan struggles out of the box, and this has another 50% power to dissipate. meaning you're going to need the watercooler version so looking at spending £500 over the titan for this...

and, tdp is still important, that aio is still going to struggle with 375w considering hybrid 1080tis sit in the 50c-60c range with half the power
 
akarypid said:
I must say I am not at all impressed...
Click to expand...


I think this explains delays, alongside the hbm2 shortage I think amd knew they couldn't match the tdp/performance of Nvidias cards, whilst also having the much higher cost of hbm2 forcing them to price this so high (500 for an aio? really?)

but I guessed they knew they had to release it at some point.
 
zornyan said:
I think this explains delays, alongside the hbm2 shortage I think amd knew they couldn't match the tdp/performance of Nvidias cards, whilst also having the much higher cost of hbm2 forcing them to price this so high (500 for an aio? really?)

but I guessed they knew they had to release it at some point.
Click to expand...

Strange isn't it. I remember many years ago on many forums when NVIDIA were being slagged for high power usage. Where AMD had the low powered cards. Feels like F1 where teams having a lot of good and bad years. Though AMD feels a bit like McLaren at the moment.
 
N19h7m4r3 said:
Well so much for D.P saying they'll be 2-3K at least.
Click to expand...
Well 1650 is not far from 2-3k. Given exhange rates that is $2100 USD. I think that says a lot about the sales AMD expects of these. Nvidia can sell their HPC/deep learning GPUs for 10K a pop but AMD can only muster a fraction.

Could be good value if you are in the market.

EDIT: seen the price was in pounds and not USD as I reported so the price is close.
 
Last edited:
D.P. said:
Well 1650 is not far from 2k, but yeah,I was wrong. I think that days a lot about the sales AMD expects of these. Nvidia can sell their HPC/deep learning GPUs for 10K a pop but AMD can only muster a fraction.

Could be good value if you are in the market
Click to expand...

these do not compete with the quadros remotely, these are titan competitors. quadros are far faster in professional workload and cheaper than this vega.
 
awaybreaktoday said:
VEGA(1).jpg


Under performing!!!!!
Click to expand...


Those benchmarks are just bogus because they aren't using the correct the drivers for the TitanXP. They need to use a quador with Quadro drivers.


But the whole table is stupid. They are claiming the TitanXp only has 190GFlop half precision which is bogus, all nvidia cards will do half precision at least the same as the single precision, that is self evident. They must be using double precision figures for the Titan and half for Vega, what complete nonsense.


I think the most interesting thing, if true but I don't trust the table at all, is the liquid cooled using 375wnvd 300w.for the air.cooled. 300w is crazy enough, but this must mean the 2 versions have different clock speeds and performance. I'm guessing the liquid cooled 375w card runs at 1600MHz. expect gaming cards to come in at 275-300w and lower clocks.
 
zornyan said:
here's the quadro figures

Catia

P2000 (GP106) - $599 = 105.92

P4000 (Cut GP104) - $899 = 126.54

P5000 (GP104) - $1999 = 152.92

Solidworks

P2000 (GP106) - $599 = 129.95

P4000 (Cut GP104) - $899 = 148.68

P5000 (GP104) - $1999 = 168.11

source


https://www.pcper.com/reviews/Graph...00-P3000-P5000-Tested/General-Compute-Perform

this puts the vega card at around the Maxwell quadro with the 980ti gpu...
Click to expand...


Thanks for posting these.

AMD should be ashamed using gaming drivers for the Titan.
 
zornyan said:
these do not compete with the quadros remotely, these are titan competitors. quadros are far faster in professional workload and cheaper than this vega.
Click to expand...


Yeah, now makes sense that they are priced much lower that I expected. They just don't have the performance. 980ti performance with 375w, oh dear
 
Status
Not open for further replies.
Back
Top Bottom