Browse by Subject "General-purpose computing on graphics processing units (GPGPU)"
Now showing items 1-2 of 2
(2012-09-18)This dissertation presents a novel decoupled latency tolerance technique for 1000-core data parallel processors. The approach focuses on developing instruction latency tolerance to improve performance for a single thread. ...
(2010-05-19)There are two venues for many-core machines to gain higher performance: increasing the number of processors and number of vector units in one SIMD processor. A truly scalable algorithm should take advantage for both ...