Category «CUDA»

Dominoes Talk in GTC 2016

In the last week I attended the GPU Technology Conference (GTC), which took places in San Jose, California. As expected, a lot of information and research have been presented, including the new GPU model to be release, called Pascal. I will address some of these new functionalities in another post. Dominoes has been presented on the GTC and …

GPU Technology Conference!

Last year I submitted a talk proposal about Dominoes to GTC, the biggest GPU conference in the word brought by Nvidia. Dominoes is an application that was developed as part of my Ph.D. research for allowing exploratory data analysis over repositories using GPU. After the period of analysis, I received an email saying that it was …

Coalesced Memory in CUDA

As I always say in my CUDA lectures, taking care of accessing global memory in CUDA is always needed. In this article, Mark Harris presents an study about the consequences of misaligned access in this kind of memory. As is possible to see, absent from stride access, newest GPU architecture are becoming less sensitive to …

CUDA Lecture on Uberlândia

In the last Thursday and Friday, I went to Uberlândia (MG) to present a lecture about CUDA in the XV Encontro de Modelagem Computacional (XV Computational modeling meeting) , invited by professor Fran Sergio Lobato. The conference was good and the audience very interested about the topic covered. Unfortunately, due to time, only the basic …