Fiji Architecture and High Bandwidth Memory
Fiji is the newest architecture released by AMD in around 2 years. Based on the most recent GCN 1.2 and 28nm process, it aims to bring ‘revolutionary’ performance to the end-user. A close look at the package, we can see the GPU core surrounded by 4 HBM stacks. These stacks are extremely compact, measuring just 5mm x 7mm footprint. The advantages of moving the memory from the PCB to the Interposer is the decreased distance for communications, which increases bandwidth and decreases power and overall reduces the footprint of the PCB; enabling a high-end graphics option to be used in ITX size computer cases. With the integration of the memory chips, it means extra components such as VRMs no longer need to be included on the PCB, again reducing the overall size of the PCB.
This is great for the graphics card market, with HBM v2 introduced more widely in the next generation of cards, but we could also see designs like this enter the CPU market, mobile phones or any other device that currently has separate core and RAM modules.
Thanks for the review.
Why arkham Knight? not to mention no setting shown for it too. Perhaps you guys should benchmark The Witcher 3 instead of arkham knight. I sure hope amd will release a much better driver for fury x. Sad to see a new architecture(hbm) falling behind an old architechture(GDDR5). So much promise yet so much disappointment.
Arkham Knight has been withdrawn by Warner Brothers as the programming is seriously flawed. It is unplayable on DX11. WB will be releasing AK with a DX12 port and patch.
Why AMD why………..
So basically if you are gaming at 1440p or 4K this is worth serious consideration I am a little surprised at the price point, I did expect it to be a little cheaper being an AMD card but things do look promising for team red.
Unfortunately for me all of my gaming is done at 1080p so I personally would buy the 980Ti. Still I am interested in seeing where AMD take HBM.
When will you run the 3dMark API Overhead Feature Test?
@ Rikki Wright
When you last wrote about DX12 benchmarks you pointed out that Radeon 290x was 33% faster than GeForce 980Ti and as fast as Titan X.
So Fury should be 20% faster than Titan X and 50% faster than 980 Ti.
Right? You know, you ran the benchmarks already yet you aren’t telling us.
Peter Odonnell rote this piece 4 months ago.
www dot eteknix.com/amd-r9-290x-goes-head-to-head-with-titan-x-with-dx12/
Your own site knows that nVidia GPU’s are drastically slower than AMD using DX12 yet you lie to your readers by omitting these very important facts.
Don’t consumers have a right to make educated buying choices?
With DX12 Fury x is 50% faster than GTX 980 Ti and crushes Titan X.
nVidia does not have Asynchronous Shader Pipelines nor do they have Asynchronous Compute Engine IP.
nVidia is great with an obsolete API. But it is absolute trash with Mantle or DX12.