PAR Class 13, Mon 2019-02-25

Source

Table of contents::

1   Thrust

  1. The github repository, with demo is https://github.com/thrust/thrust.git .

    Nvidia's proprietary version is slightly newer.

  2. The most comprehensive doc is online at http://thrust.github.io/doc/index.html

    It is badly written and slightly obsolete.

  3. There are various tutorials online, most obsolescent. E.g., they don't use C++-11 lambdas, which are a big help.

  4. Look at some Thrust programs in /parallel-class/cuda/thrust

  5. Continue Stanford's parallel course notes.

    1. Lecture 8-: Thrust ctd.

  6. One Nvidia-sponsored alternative is agency, at https://github.com/agency-library/ .

  7. There are other alternatives that I'll mention later.

  8. The alternatives are lower-level (= faster and harder to use) and newer (= possibly less debugged, fewer users).