A total of 40 people attended the Third Workshop on Programming GPUs with CUDA organized by the National Laboratory for High Performance Computing (NLHPC) and the Center for Mathematical Modeling (CMM) of Universidad de Chile. The figure doubles the number of participants from last year, when the first version of this activity took place. In addition, more than 80 people signed up, nearly the triple of 2015.
“This is an indication of a growing awareness about what parallel programming can do and its advantages over sequential programming,” said NLHPC deputy director Ginés Guerrero. “Parallel programming can solve problems faster than traditional sequential code and can even solve problems that were not possible before. There is still a long way to go, in which the NLHPC has much to contribute. ”
CUDA (Compute Unified Device Architecture) is a parallel computing platform and programming model created by NVIDIA and implemented by the graphics processing units (GPUs) that they produce.
Guerrero said that “The course is aimed to show notions about the functioning of the graphic cards for general purpose computing (GPGPU). The idea is to show what they are capable of performing with GPU and how to use it properly”.
Originally, the workshop had places for 30 people, but the high interest required to increase that number to 40. Among those present were representatives of many businesses, university students and many scientists from all over the country.
“It’s great the reception that it had on the scientific community, the public sector and the business community”, said Guerrero.
CUDA fellow Manuel Ujaldón gave this workshop. He has co-authored over 40 publications in international journals and held many conferences on these topics,. In addition, he has imparted over thirty CUDA programming courses on universities all around the world.
Source: CMM U.Chile
Second NLHPC’s CUDA Workshop attracted twice as many attendees than its 2015 version
