Comments for GPGPU» :: GPGPU.org

Comment on CLyther = Python + OpenCL by Scott Spinella

Scott Spinella — Wed, 10 Mar 2010 07:06:27 +0000

Awesome..Tool…It is very helpful to me…
Scott Spinella

Comment on Harnessing Graphics Processors for the Fast Computation of Acoustic Likelihoods in Speech Recognition by pyCUDA on Windows and Mac for super-fast Python math using CUDA | Entrepreneurial Geekiness

Fri, 05 Mar 2010 16:41:36 +0000

[...] – There are lots of interesting papers for CUDA surfacing like this one showing a 3* speed-up for voice recognition tasks (using CPU and GPU together) and yet another way to improve fluid dynamic simulations. This [...]

Comment on Lattice-Boltzmann Simulation of the Shallow-Water Equations with Fluid-Structure Interaction on Multi- and Manycore Processors by Gaelan

Gaelan — Thu, 04 Mar 2010 19:45:58 +0000

Yes, I wanted to read this article, where can I find a full copy?

Comment on GPU-accelerated Monte Carlo simulation of the 2D and 3D Ising model by azadeh

azadeh — Tue, 02 Mar 2010 19:36:03 +0000

physics-2D ising model simulation

Comment on nHD – A Full Godunov Euler Equations Solver with CUDA/MPI by nHD – A Full Godunov Euler Equations Solver with CUDA/MPI

nHD – A Full Godunov Euler Equations Solver with CUDA/MPI — Mon, 01 Mar 2010 00:54:40 +0000

[...] Full Story [...]

Comment on OpenNL 3.0: CUDA sparse linear solvers by OpenNL 3.0

OpenNL 3.0 — Mon, 15 Feb 2010 05:44:49 +0000

[...] GPGPU.org takes note that OpenNL 3.0 has just been released and that this new version comes support for CUDA. That’s certainly interesting, but for me the biggest news is that the library is now under the BSD license and thus can be used in a wider range of projects. I guess it’s time to drop my own sparse matrix solvers. This entry was posted in General. Bookmark the permalink. Post a comment or leave a trackback: Trackback URL. « Pâté [...]

Comment on Molecular Workshop Series at Stanford by Daniel

Daniel — Wed, 03 Feb 2010 12:41:43 +0000

I’m abroad. Will there be vids posted online?

Thanks

Comment on Coordinating the Use of GPU and CPU for Improving Performance of Compute Intensive Applications by dom2

dom2 — Wed, 03 Feb 2010 00:58:29 +0000

yeah, the related work section of that paper is relatively weak (while the contribution of the paper is nice, don’t get me wrong). All “GPU cluster” papers at this point employ some kind of CPU/GPU interaction, and many papers contain some language why for this and that application domain, a hybrid solver doesn’t make sense: As the GPUs are so fast, there’s no point in going hybrid. The relevant quantity is the GPU/core ratio in current clusters. Shameless plug: My own work. I should probably re-tag all such news posts with “MPI” just to make sure they don’t slip unnoticed.