Cluster Scale GPGPU with OpenCL

Previous posts about climate modeling and CESM were required as this post is the crème de la crème of CESM from my point of view. Cluster scale GPGPU seems to be very nice, on paper, but as soon as we

Tagged with: , , , , , , , , ,

CESM – Modeling Earth Future Climate

CESM - High Level Component Diagram

Following the previous post, it is clear why climate modeling is performed using computers. The amount of data and computational needs of climate simulations can be significant, so supercomputers are extensively used to perform the task. In fact, THE strongest

Tagged with: , , , , , ,

Make runtime of your app and life shorter, vectorize!

Vectorization is a first step in optimization process to produce high performance algorithms. Moti and I contended with vectorization for a few days. As mentioned in one of our previous posts, we decided to implement SIMD vectorization using Intel SSE/AVX

Tagged with: , ,

2nd Copenhagen Quiz

It is now time for the 2nd and last quiz from Copenhagen, dedicated to our final project. If you recall our previous post about climate modeling, it introduced some figures of observed climate data. A precise definition of Albedo can

Tagged with: , , , , , , ,

The Butterfly Effect, Chaos and Climate Modeling

Ever wondered what is the connection between the Butterfly effect, Chaos and Supercomputers? One of the the best ways to describe it can be using climate modeling. Geophysics and Climate Modeling Geophysics is a field in exact sciences that tries to

Tagged with: , , , , , , , , , , , , , , ,

When FORTRAN met OpenCL – A Love Story? (of Integration)

Both of the projects Lukas and I are working on, here at NBI Copenhagen, are based on FORTRAN. Either Photon-Plasma simulations or CESM for climate modeling (as most climate modeling software around). Certainly, a vast majority of scientific code is

Tagged with: , , , , , ,

A Week Full of Surprises

Man at Work We arrived at the first day, after a long and peaceful weekend. Lukas went to the beach, but concluded it was too small for him. There are more to look after. Days in Copenhagen can be tricky,

Tagged with: ,

Quiz – clustered data using k-means

Moti and I work on the k-means clustering project, you can read our first post about it. Now we prepared a short and easy quizz related with k-means topic for you. When you cluster dataset using classic k-means algorithm you

Tagged with: ,

First week in Copenhagen

First Meeting and Introduction When Moti and I  met in front of the main building of Niels Bohr Institute (NBI), it was no more than 17 hours since we arrived to Copenhagen. A joint breakfast was waiting for us together

Tagged with: ,
Follow by Email27