path: root/Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn
diff options
authorJulien Cristau <>2014-10-12 16:47:54 +0200
committerJulien Cristau <>2014-10-12 16:47:54 +0200
commit1e432a507eef4cce9ca64311a2f40138306e9bbc (patch)
tree42d3d8165853829c2dcb0572283d55686b99d3fc /Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn
parent79ff206095dfd3eb0c2a8e6551f956c8a7c4b85e (diff)
Add links to some videos
Diffstat (limited to 'Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn')
1 files changed, 1 insertions, 0 deletions
diff --git a/Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn b/Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn
index b45f63ad..77045312 100644
--- a/Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn
+++ b/Events/XDC2014/XDC2014PitoisetOpenCLSimulation.mdwn
@@ -3,3 +3,4 @@
A molecular dynamics (MD) simulation involves computing the evolution of a system of particles in time. It is mainly used in physics where applications need to track several millions of particles. Due to the compute-intensive nature of MD simulations, researchers tend to use highly parallel computing architectures and accelerators (e.g. NVIDIA GPU & Intel Xeon Phi). In this presentation, I attempt to showcase an efficient OpenCL simulation of short-range particle interactions on heterogeneous architectures. This multi-accelerators approach aims to distribute the workload among the devices and to overlap data transfer and code execution in order to reduce the latency.