GPU Programming with Modern C++

This talk introduces parallelism and shows how to recognize when to use it and apply patterns such as map, reduce, and scan. It extends those patterns from C++ threading and parallel algorithms to heterogeneous devices using SYCL on a GPU.

Syllabus

Introduction
Michaels background
Why Im here
Outline
Recap
Right abstraction
Task vs data parallelism
Latency and bandwidth
DMV example
Flynns Taxonomy
CPU vs GPU
Multicore CPU
Architectures
Memory bound problem
Memory optimization
Pad properly
Data layout
Power of computing
What happened
What happened in 2011
CPU vs GPU performance
GPU explosion
Hardware
GPU programming
Parallelization and concurrency
Heterogeneity
Consumer AI
GPU languages
C executives
How GPUs work
How CPUs work
How GPU work
Memory regions
Multiple work items
Wavefronts
Lockstep
Kernel barriers
Summary
Code
SpinD
ND Range
Sickle
Chronos