Vega 64 F@H PPD

[Markfw]

I googled this, and many were getting over one million ppd. And the cheapest one is $620, vs $800 for the 1080TI. Anybody here that can confirm the PPD@1247 mhz core ? (most on newegg start at that) boost clock like 1546

 

[StefanR5R]

There is a Vega FE entry in the OCN PPD database now. But unfortunately it's useless because it is from a single sample.

(The 1080Ti, Titan Xp, and Titan X(Pascal) entries in that database are garbage too. Far higher than realistic averages.)

 

[StefanR5R]

computing benchmarks of Vega RX (not FE) directly versus Fury X show that the performance factor of 1.5 is more of an upper bound, with real factors anywhere between 1.0 and 1.5:

http://www.anandtech.com/show/11717/the-amd-radeon-rx-vega-64-and-56-review/17
https://www.computerbase.de/2017-08/radeon-rx-vega-64-56-test/4/#diagramm-compubench​

Computing performance per Watt seems to be slightly improved relative to Fury X if you don't raise the power target of Vega RX.

1.0...1.5-fold performance of Vega RX compared to Fury X in GPGPU benchmarks indicates that 1 M PPD in F@H with Vega RX may be from cherry-picked WUs, while realistic averages could be far less than that.

 

[Markfw]

1.0...1.5-fold performance of Vega RX compared to Fury X in GPGPU benchmarks indicates that 1 M PPD in F@H with Vega RX may be from cherry-picked WUs, while realistic averages could be far less than that.

thats exactly why I am asking before I chunk out $620.

 

[crashtech]

They're supposed to be $499, and Vega 56 is supposed to be $399. I hope they both come down closer to the MSRP, right now they aren't the best value.

 

[indydude345]

I'm working on saving for either a 1080Ti or a Titan X (Pascal). I don't personally see the price of Vega decreasing anytime soon. And I know that the Pascal cards are more expensive than Vega, however, I think the performance gains are significantly worth it.