Advanced algorithmic techniques for GPUs
University of Illinois, , Prof. Wen-mei Hwu
Added to favorite list
Updated On 02 Feb, 19
4.1 ( 11 )
This section discusses the particular limitations and constraints of many-core hardware, and which computational patterns are desirable or undesirable, from the architectural point of view. Among the main obstacles to performance, discussion includes conflicts in critical resources leading to serialization, load imbalance, and memory bandwidth bottlenecks.
Sep 12, 2018
Excellent course helped me understand topic that i couldn't while attendinfg my college.
March 29, 2019
Great course. Thank you very much.