Completed
GPGPU Programming
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
The Design of Functional Numerical Software - Dr. Richard Mortier, University of Cambridge
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Why, What, When, Where?
- 3 Motivating Application: Databox
- 4 Owl's Architecture
- 5 Indexing & Slicing
- 6 Core Functor Stack
- 7 Advanced Uses of Algorithmic Differentiation
- 8 Laziness & Dataflow
- 9 Incremental Computation
- 10 GPGPU Programming
- 11 Expressiveness
- 12 Google Inception v3 in 150 LOC
- 13 Actor, Parallel and Distributed Processing
- 14 Owl & Actor: Neural Network Example
- 15 Actor & the Synchronous Parallel Machine
- 16 Barrier Synchronisation
- 17 Three Main Schemes: A 10,000 Foot View
- 18 Simple Analytical Model
- 19 Decomposing Synchronous Parallel Machine
- 20 Key Insights from System Decomposition
- 21 Probabilistic Synchronous Parallel
- 22 Sampling Primitive
- 23 Adding the Completeness Dimension
- 24 Reducing Sample Size
- 25 Revisit System Decomposition
- 26 Comparing Synchronisation Methods
- 27 Step Distribution
- 28 Effect of Sample Size
- 29 Tightening Bounds
- 30 Scalability
- 31 Ongoing: Integration with App Development Kit
