Parallel Programming with NVIDIA CUDA
If parallelization of your algorithm is possible, using CUDA will speed up your computations dramatically, allowing you to make the most out of your hardware.
The main challenge consists in deciding how to partition your problem into chunks suitable for parallel execution. As with so many other aspects in parallel programming, this is where experience and—why not—imagination come into play.
Additional techniques offer room for even more improvement. In particular, the on-chip shared memory of each compute node allows further speedup of the computation process.
Alejandro Segovia is a parallel programming advisor for CoroWare. He is also a contributing partner at RealityFrontier. He works in 3-D graphic development and GPU acceleration. Alejandro was recently a visiting scientist at the University of Delaware where he investigated CUDA from an academic standpoint. His findings were published at the IEEE IPCCC Conference in 2009.
|Non-Linux FOSS: Install Windows? Yeah, Open Source Can Do That.||Nov 24, 2015|
|Cipher Security: How to harden TLS and SSH||Nov 23, 2015|
|Web Stores Held Hostage||Nov 19, 2015|
|diff -u: What's New in Kernel Development||Nov 17, 2015|
|Recipy for Science||Nov 16, 2015|
|Firefox's New Feature for Tighter Security||Nov 13, 2015|
- Cipher Security: How to harden TLS and SSH
- Non-Linux FOSS: Install Windows? Yeah, Open Source Can Do That.
- Web Stores Held Hostage
- Firefox's New Feature for Tighter Security
- diff -u: What's New in Kernel Development
- Libreboot on an x60, Part II: the Installation
- November 2015 Issue of Linux Journal: System Administration
- It's a Bird. It's Another Bird!
- How Will the Big Data Craze Play Out?
- IBM LinuxONE Provides New Options for Linux Deployment