Inside Kepler, Nvidia's Strong Start on 28 nm – Chips

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…

Related Keywords

Hawaii , United States , Neme Vulkan , Fermi Pcie , Kepler Gpus , Nvidia Fermi , Xiuxia Zhang , Yehia Arfa , Xiaowen Chu , Kepler Tesla , Xinxin Mei , Dmitrii Tolmachev , Kepler Skus , Oak Ridge National Laboratory Titan , Nvidia , Real World Tech , Next Generation Streaming , Blender Cycles , Fast Fourier Transforms , Shared Memory , Keplerbill Dally , Hot Chips , Oak Ridge National Laboratory , Achieve Bare Metal Performance , Memory Topology , Overhead Instruction Latency Characterization ,