AMD Works on At Least Three Radeon RX Vega SKUs, Slowest Faster than GTX 1070?

[btarunr]

AMD could be working on at least three SKUs based on its upcoming "Vega 10" silicon to make up its Radeon RX Vega series. Leaked 3DMark validations point to a device ID that's third in a series of possible device IDs of graphics cards based on the "Vega 10" silicon, the 687F:C1, 687F:C2, and 687F:C3. All three SKUs feature 8 GB of HBM2 memory, and according to leaked 3DMark TimeSpy scores, the "slowest" SKU is faster than NVIDIA GeForce GTX 1070. The fastest SKU is in the same league as the GTX 1080 Ti.

The three SKUs could differ with core-configuration and clock speeds. AMD carved four SKUs out of its "Fiji" silicon, the liquid-cooled R9 Fury X, the air-cooled R9 Fury (with 12.5% fewer shaders), the SFF-friendly R9 Nano (full core-config, but aggressive power-management), and the halo dual-GPU Radeon Pro Duo (1st gen). AMD could take a similar approach with "Vega 10." AMD is expected to launch its Radeon RX Vega series within Q2-2017.



View at TechPowerUp Main Site

 

[RejZoR]

Nano Vega, Small Vega and Big Vega

 

[MrAMD]

Interesting.

 

[btarunr]

Nano Vega, Small Vega and Big Vega

You forgot Lou Vega Mambo #5.

 

[jigar2speed]

You forgot Lou Vega Mambo #5.

LOL, nice

 

[Nordic]

I would be disappointed if the 1080ti competitor was a dual gpu card.

 

[RejZoR]

I would be disappointed if the 1080ti competitor was a dual gpu card.

Pro Duo is not a consumer gaming card...

 

[MrGenius]

Oh...is it suddenly ok to discuss this topic now? Really? Says who? Double standard much?

 

[the54thvoid]

Oh...is it suddenly ok to discuss this topic now? Really? Says who? Double standard much?

It appears negative AMD rumours are terrible and bad. But it's really okay to accept positive rumours as gospel. Such is the way.

Just deliver the card AMD so we can judge with our wallets.

 

[erocker]

Oh...is it suddenly ok to discuss this topic now? Really? Says who? Double standard much?

When was it not okay?

 

[Markosz]

So it begins... the daily dose of bullshit leaks, guesses, theories from every tech channel until the cards are released...

 

[intelzen]

as expected - a GTX 1070 performance level - and Vega price will determine if it will be good (for example a gtx 1070 level Vega for gtx 1060 price is a winner all day long, but a a little higher than gtx 1070 performance level Vega for price of GTX 1080 - is a looser all day long). it was clear that Vega was nothing that could beat gtx 1080 even year ago (when AMD showed first cherry picked benches), but one thing that bothers me now is this RX 580 rebrand thing - why AMD did released it? when they will release a roughly 40% more powerful and efficient Vega for same price point just few weeks later - there is only two options: A) Vega will be priced uncompetitive (gtx 1070 level of performance for full gtx 1070 price - just something for hyped fanbois to be happy about) or B) Vega release is more than 3 months away (no matter paperlaunches)... and I do not like any of these

 

[Boosnie]

as expected - a GTX 1070 performance level - and Vega price will determine if it will be good (for example a gtx 1070 level Vega for gtx 1060 price is a winner all day long, but a a little higher than gtx 1070 performance level Vega for price of GTX 1080 - is a looser all day long). it was clear that Vega was nothing that could beat gtx 1080 even year ago (when AMD showed first cherry picked benches), but one thing that bothers me now is this RX 580 rebrand thing - why AMD did released it? when they will release a roughly 40% more powerful and efficient Vega for same price point just few weeks later - there is only two options: A) Vega will be priced uncompetitive (gtx 1070 level of performance for full gtx 1070 price - just something for hyped fanbois to be happy about) or B) Vega release is more than 3 months away (no matter paperlaunches)... and I do not like any of these

I don't get the connection you draw between a rebranding and a release given that the former happened on a completely different and separate segment of the AMD offering.
Also where did you get the numbers you reason about?

 

[ZoneDymo]

oh come on, AMD is often faster in benchmark programs like this, lets not fuel some disappointment train with already threaded to death territory.

 

[Liviu Cojocaru]

I hope this is true as this will fill the void where there is no competition for Nvidia atm and hopefully this will result in a decrease of price for Nvidia cards

 

[Caring1]

You forgot Lou Vega Mambo #5.

Who can forget Chevy Vega

 

[Camm]

is anyone surprised at this. At all? Of course Amd would target cards at the three market segments NVidia has

 

[fore1gn]

as expected - a GTX 1070 performance level - and Vega price will determine if it will be good (for example a gtx 1070 level Vega for gtx 1060 price is a winner all day long, but a a little higher than gtx 1070 performance level Vega for price of GTX 1080 - is a looser all day long). it was clear that Vega was nothing that could beat gtx 1080 even year ago (when AMD showed first cherry picked benches), but one thing that bothers me now is this RX 580 rebrand thing - why AMD did released it? when they will release a roughly 40% more powerful and efficient Vega for same price point just few weeks later - there is only two options: A) Vega will be priced uncompetitive (gtx 1070 level of performance for full gtx 1070 price - just something for hyped fanbois to be happy about) or B) Vega release is more than 3 months away (no matter paperlaunches)... and I do not like any of these

Don't hope that Vega will start at GTX 1060 price. It will be around $349 launch price, with aftermarket cards going as high as $400+. Middle Vega will probably be $499 and high-end Vega $649. Low- and mid-Vega will be beating the competition, but high-end Vega won't. /speculation

 

[uuuaaaaaa]

That first screenshot (9753 score) is forged... it was done by one of the guys at the wccftech comment section, I've seen it when it first popped. I immediately searched through 3dmark's database and basically the only 9753 score that was there was for a 1080ti. For the second screenshot at least there is a validation link...

 

[rainzor]

Isn't that the same SKU with 3 different board revisions, C1 being the earliest?
9000 something score is probably a fake as there is no evidence of it in 3dmark result database.

 

[Caring1]

Isn't that the same SKU with 3 different board revisions, C1 being the earliest?
9000 something score is probably a fake as there is no evidence of it in 3dmark result database.

Congrats, you're late to the party.

 

[Tsukiyomi91]

Now we'll wait & see. Scratch that... release the sample cards AMD & let the benchers do their magic.

 

[Frick]

So it begins... the daily dose of bullshit leaks, guesses, theories from every tech channel until the cards are released...

That has been going on since Polaris.

 

[drzoidberg33]

How does a screenshot from a random user on a forum make this anywhere close to legitimate news?

 

[Boosnie]

How does a screenshot from a random user on a forum make this anywhere close to legitimate news?

Legit