AMD Polaris Project F GPU Revealed

With Polaris only months away, more details about what Polaris 10 and 11 will look like are coming out. According to an ex-AMD employee profile on LinkedIn, a dGPU codenamed Project F is set to be built on GlobalFounrdies and Samsung 14nm LPP process. What’s more, the Project F GPU will be 232mm², making the chips similar in size to the 232mm² of Pitcairn and Curacao from the 28nm generation of GCN.

At 232mm², Project F is a relatively small chip for a new process. This should give AMD a low-risk option to evaluate the 2nd generation 14nm process from GlobalFounrdies and Samsung focused on performance. With the use of the new process, the number of transistors will grow massively due to the increased transistor density over 28nm. This should let Project F to pack in at least 4-5 million transistors, putting it at least into the R9 380 and 380X (359mm²) performance range before considering any architectural improvements.

Finally, by using 14nm, Project F is most likely the GPU that AMD showed off back at CES that severely trounced the GTX 950 in performance per watt. With the larger die size, it stands to reason that the demo unit was likely underclocked a bit or not allowed to turbo, letting it be much more efficient. Even at full power, AMD likely has a card that will be much more efficient than Maxwell while offering significantly improved performance over the last generation at a similar cost.