Inside Kepler, Nvidia's Strong Start on 28 nm – Chips and Cheese
Nvidia's Fermi architecture was ambitious and innovative, offering advances in GPU compute along with features like high tessellation performance. However Terascale 2's more traditional approach delivered better power efficiency. Fermi's GTX 500 series refresh narrowed the efficiency gap, but then AMD hit back with the GCN architecture on 28 nm. In developing their first 28…
Source: chipsandcheese.com