CUDA: Week In Review

Welcome to CUDA: Week In Review, news and resources for the worldwide GPU and parallel programming community.

CUDA Pro Tip: Parallel reduction is a common building block for many parallel algorithms. On Parallel Forall, learn about features of the Kepler GPU architecture which make reductions even faster: the shuffle (SHFL) instruction and fast device memory atomic operations.

CUDA NEWS
CUDA 6 RC Available CUDA 6 Release Candidate (RC) is now available to Registered Developers. New features include Unified Memory; Drop-in Libraries; and Multi-GPU Scaling in cuBLAS and cuFFT Libraries. Sign up for the CUDA 6 Overview webinar (Wed., Feb. 26). PGI 2014 Released PGI 2014, a suite of high-performance parallelizing compilers and development tools, features industry-leading OpenMP performance, new OpenACC 2.0 features, CUDA Fortran debugging, updated MPI support and more. Download a free trial.
GPU TECHNOLOGY CONFERENCE
Register for GTC 2014 The GPU Tech Conference (March 24-27) will feature 500 sessions, tutorials, labs and opportunities for interaction with experts and peers (20% discount code: GM20CD).
UPCOMING GPU WEBINARS	back to the top
Feb. 25: GPUs for Visualization and Analysis of MD Simulations with VMD, J. Stone, Univ. of Illinois Feb. 26: CUDA 6 New Features Overview, M. Ebersole, NVIDIA Feb. 27: Installed Antenna Performance Sims Using GPUs, M. Miller, T. Courtney, Delcross Feb. 27: Massively Parallel Acceleration with GPUs (ACM Webinar), M. Ebersole, NVIDIA
UPCOMING GPU MEETUPS	back to the top
Feb. 19: Singapore Feb. 24: Silicon Valley Feb. 27: Brisbane Note: New GPU Meetups have launched in Russia and Norway.