BookerDeWitt

That 3X performance per watt claim was about the memory subsystem not the entire card. HBM delivers 3x the performance per watt of GDDR5, that's what it means essentially.


 

That 3X performance per watt claim was about the memory subsystem not the entire card. HBM delivers 3x the performance per watt of GDDR5, that's what it means essentially.


 

Active DP 1.2 to HDMI2.0 adapter will be release late this year anyway.

AMD already said that this card will have "significantly more performance" than the R9 290X. So its going to target the GTX 980 and up.
The math is pretty sound, and puts the Nano at a competing level with the GTX 980, maybe a bit faster.
 
 
 Remember that you can't compare AMD and Nvidia cards based on FP32. Nvidia makes up for compute with a stronger geometry engine, so Nvidia GPUs with lower tflops can still keep up with AMD cards with more tflops in games.

Anyone else think that this is a pretty cool reference card?

WCCFTECH did get some things right so can we stop the bashing guys?

I don't want to sound rude but in this particular case I just don't think you know enough about this particular subject to make such a statement.
FX CPUs are nothing like Intel CPUs in terms of overclocking, the "lottery" margin is extremely thin, a golden chip would overclock better than a mediocre chip by 200mhz at best on the same cooling. 32nm SOI is just far more overclocking friendly than Intel's 22nm TriGate.
The 990FX Sabertooth has the best VRM cooling and power delivery, second only to the Crosshair V Formula-Z. In fact the highest overclocks achieved on Vishera CPUs were either on Sabertooth or Formula boards.
http://www.overclock.net/t/1318995/official-fx-8320-fx-8350-vishera-owners-club
 

That's just not true.
#1 He'd only have to swap out the CPU instead of having to change out the motherboard and reformat his SSD.
#2 He'd only have to spend one fifth the cost if your suggestion.
#3 Swapping out a 990FX motherboard for an h81 is a massive DOWNGRADE.
#4 The performance benefit is actually quite significant, easily above 30%. This is dictated by math, 8/6 = 1.33, 4/3 (FPU) = 1.33.
#5 Because the 8350 has 4 FPUs instead of 3, gaming performance does scale up with the two additional cores, even if the game doesn't use the 2 additional cores at all.
http://linustechtips.com/main/topic/48571-intel-amd-architectural-discussion-how-far-ahead-is-intel/

Fiji will probably be the next big contender with 8.6 TFLOPS of single precision and 4.3 TFLOPS of double precision at 300w TDP.

No chip on the market will reach its theoretical compute performance including the Phi. OpenCL isn't as bad as most make it out to be. Most I would figure have no experience in using it as it doesn't take much to establishing a device driver and begin executing kernels. If you dislike it you can always migrate over to OpenACC.
  4096*2*1050 = 8.6 TFLOPS SP + (1/2 ratio DP) = 4.3 TFLOPS DP.

People asking for a new CPU architecture from AMD. Have you somehow missed this ?
 
 

AMD's working on two entirely new beast mode cores.

The 290X is faster than the GTX 970, this is established common knowledge.

The benchmarks provided by s3ns3 are deeply flawed, look at the BF4 benchmark where they're showing the R9 290X tied with an R9 280X. I would hardly call those results reliable or in fact correct.

Based on the latest drivers and in an average of 19 different games the R9 290X was in fact faster than the GTX 970 in 4K, 1440P and tied in 1080p.
http://www.techpowerup.com/reviews/NVIDIA/GeForce_GTX_Titan_X/29.html
Lastly neither the R9 290X or the GTX 970 should even be considered for 1080p gaming, as you'll just waste the performance of such powerful GPUs at 1080p.
Unless you're running a 120Hz monitor an R9 285 or GTX 960 are better choices for 1080p.
 

Better than a 970 on a crap ton of games*
Fixed it for ya!

i seriously doubt anyone is going to make a better (and affordable) HMD than Oculus at this rate. 

I'm sure this will turn out like 3Dvision.
Overpriced and locked to Nvidia hardware.

Nvidia vr goggles,  they actually only have 1.5 screens , the last .5 of screen is really only slightly faster than an etchesketch. 

why is this a revolution of gaming? ummm oculus rift exists already

Thought it couldn't be worst than another useless tablet: I was wrong

Shouldn't  be going around saying it was BS unless you have a 110% proof that it was faked and to me it seems like this  is all old information your using to come up with the conclusion. You don't know what else was being used ran at the time of the demos they ran.
 

Umm, I honestly see no real proof in what you are saying, either way, it wouldn't matter, and I honestly wouldn't care and I still will buy a free-sync monitor.

I don't think many will opt for refunds but I certainly believe that Nvidia's reputation has been irreversibly damaged by this scandal.
Either way you slice it, it looks awful for Nvidia. Because it either means they deliberately lied bout the specifications of the GTX 970 or that their marketing team is so hopelessly incompetent as to make such an "error". And frankly I don't know which is worse.

I'm just going to leave this here.  When the 970 needs to access the vram located on the 500MB section, your effective memory bandwidth does exactly what this gif I found in a comment on pcper shows.
 

They're anti-consumer fanboys. As long as Nvidia is doing well they don't care how they are treated.

holy shit i thought it was a tiny difference of maybe 10GB/sec 50GB/sec at the most but that is massive

Just a few things.
I think it was Linus who said that you won't actually see any FPS drops, just stuttering and frame-pacing issues at higher resolutions. That's a big problem IMO. Why the fuck are people bringing AMD into this!? AMD had nothing to do with this! If you're one of these people, you're just trying to ease the heat on Nvidia.  
I saw this comment on one of PC Per's videos by EmmaCross94, I thought it was good.