Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Data Parallel Programming - Concepts and Challenges in Java
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 What is "data parallel" computing?
- 3 Running example: sum of C+A+B
- 4 Can a coder dream of electric chips ?
- 5 An ordinary load-store machine
- 6 working assumption: data = arrays
- 7 Load-store machine, with arrays
- 8 How the Java VM virtualizes a CPU
- 9 Old school multi-threading
- 10 Threads can step on each others' toes
- 11 What went wrong?
- 12 In search of the right notation
- 13 Timing can be everything
- 14 Partition the data, not the code
- 15 Partitioned data is naturally simple
- 16 Split the data, keep one code stream
- 17 What could go wrong?
- 18 Communication dominates eventually
- 19 Let's stripe the data across the CPUs
- 20 Options for localizing data (2)
- 21 What is a Java "GPU thread"? (2)
- 22 Issue: Placed data needs to be aligned
- 23 Mesh computing, with private memory
- 24 Regarding vectorization
- 25 Summary: Java liabilities / challenges
- 26 Summary: Java assets
