Results (OpenCL): GPGPU Benchmarks
The Radeon R9 290’s results are basically the same as what we reported for the 290X. Hawaii possesses a lot of theoretical performance, but it’s often diminished by the card's reference design, which is forced to scale back significantly under the load of a compute-oriented workload. This is not what we'd want to see from a GPU otherwise celebrated for its potential in OpenCL-accelerated apps.
It's also worth noting that AMD artificially handicaps Hawaii's FP64 throughput with a 1/8, compared to Tahiti's 1/4, rate. This is to allow FirePro cards based on the same GPU to offer another differentiator (we hear they'll be full-speed, or 1/2).
Chris, these results differ drastically from real world results from 290X owners at OCN... I understand that your observations are anecdotal and based on a very small sample size but do you mind looking into this matter further because putting such a statement in bold in the conclusion even though it contradicts real world experiences of owners just provides a false assumption to the uninformed reader...
The above claim has already escalated further than it should... A Swiss site actually has already rebutted by testing their own press sample with a retail model and concluded the following:
Now to wait for the non-reference cards at the end of the month!
It looks like a good card for the price as it even keeps up with the $100 more GTX780. This is good as NVidia may drop prices even more which means we could also see a price drop on the 290X and I wouldn't mind a new 290X Toxic for sub $500.
Best to wait a month or two before buying to see how this all goes down