A Coursera course from the University of Illinois on parallel programming across heterogeneous hardware such as GPUs, taught mainly with CUDA and also covering OpenCL. It is aimed at learning GPU programming.

Commenters point to it as a strong option for learning GPU programming, with one calling it an excellent class taught by Wen Mei Hwu.

What commenters said (2)

1. Strongly recommendsksml2016in “Ask HN: Best place to learn GPU programing?”

   I found Wen Mei Hwu's "Heterogeneous Parallel Programming" course on Coursera to be an excellent class: https://www.coursera.org/course/hetero

2. Recommendstjaerv2014in “Ask HN: How to learn OpenCL”

   You might wish to check out the University of Illinois's "Heterogeneous Parallel Programming" course, offered through Coursera:

   https://www.coursera.org/course/hetero

   The course is already currently ongoing, but it's not too late to enroll. The course is mainly focused on CUDA (since it's easier to learn, the professor believes), but covers OpenCL as well.

Related courses

• The Elements of Computing Systems (Nand2Tetris)nand2tetris.org · 87 recommenders
• CS50: Introduction to Computer ScienceHarvard University · 72 recommenders
• Human Behavioral Biology (Robert Sapolsky)Stanford University · 26 recommenders
• 6.824 Distributed SystemsMIT OpenCourseWare · 16 recommenders
• 15-213 Introduction to Computer SystemsCarnegie Mellon University · 12 recommenders
• 6.004 Computation StructuresMIT OpenCourseWare · 9 recommenders
• 6.828 Operating System EngineeringMIT OpenCourseWare · 8 recommenders
• CS106A Programming MethodologyStanford University · 10 recommenders