Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Free module

GPU and parallel computing

Learn GPU and parallel computing hands on: speed-up, vectorising, splitting work, GPU threads and kernels, and memory bottlenecks, without a GPU.

6 lessons375 min lessonCore computer science

The lessons

Each lesson is free to read in full. Create a free account to run its commands in a live lab and to sit its quizzes and tasks.

  1. 1 · Container lab

    Speed-up and Amdahl's law

    I can estimate the speed-up from using more workers.

    Read the lesson

  2. 2 · Container lab

    Vectorising a loop with NumPy

    I can replace a loop by one operation on a whole array.

    Read the lesson

  3. 3 · Container lab

    Splitting work across processes

    I can split a job into chunks, run them in separate processes and merge the answers.

    Read the lesson

  4. 4 · Container lab

    How a GPU organises its threads

    I can say how a GPU organises its threads and work out the global index of one.

    Read the lesson

  5. 5 · Container lab

    Writing a GPU kernel

    I can write a kernel for a simple job and launch it over enough threads.

    Read the lesson

  6. 6 · Container lab

    Compute-bound and memory-bound jobs

    I can tell whether a job is limited by compute or by memory.

    Read the lesson

Worked in a real lab

Every lesson of this module is worked in a lab started for you alone. The labs it uses:

Teaching a class? Set this module for your students with a teacher guide, marked assignments and a lab for every student.