NVIDIA Corporation

Fecha: Miércoles 19 de Septiembre de 2012 / Hora : 11:00 a 11:30
Lugar: Aula 0.5 (Edificio Altabix)

Inside Kepler

Manuel Ujaldón Martínez
(Nvidia CUDA Fellow)

Comprising 7.1 billion transistors, Kepler GK110 is not only the fastest, but also the most architecturally complex microprocessor ever built. Adding many new innovative features focused on compute performance, GK110 was designed to be a parallel processing powerhouse for Tesla and the HPC market. Kepler GK110 will provide over one teraflop of double precision throughput with greater than 80% DGEMM efficiency versus 60‐65% on the prior Fermi architecture. In addition to greatly improved performance, the Kepler architecture offers a huge leap forward in power efficiency, delivering up to three times the performance per watt of Fermi. Equally, the newest release of the CUDA software platform has been enhanced to match the new hardware with many new possibilities opened up to the programmer.