Stop Thinking, Just Do!

Sung-Soo Kim's Blog

GTC On-Demand

tagsTags

20 May 2014


Article Source

GPU Technology Conference 2014: Opening

GTC: NVIDIA co-founder and CEO Jen-Hsun Huang describes the growth of the company’s annual GPU Technology Conference, in San Jose, Calif., and kicks things off by announcing NVLink, the world’s first high-speed GPU interconnect. For more NVIDIA news.

Algorithms & Numerical Techniques

Portability, Scalability, and Numerical Stability in Accelerated Kernels

John Stratton (University of Illinois at Urbana-Champaign)

Keywords: Algorithms & Numerical Techniques, GTC Express 2012 - ID GTCE019
Download: FLV PDF

Understanding Parallel Graph Algorithms

Michael Garland (NVIDIA), Duane Merrill (NVIDIA)

Keywords: Algorithms & Numerical Techniques, GTC Express 2013 - ID GTCE027
Download: MP4 PDF


Bioinformatics & Genomics

Accelerating Computational Genomics and Other Best Practices Using OpenACC

Florent Lebeau (CAPS Entreprise), Stephane Chauveau (CAPS Entreprise)

Keywords: Bioinformatics & Genomics, Programming Languages & Compilers, GTC Express 2012 - ID GTCE016 Download: FLV PDF

Introduction to SeqAn, an Open-source C++ Template Library

Knut Reinert (Freie University Berlin)

SeqAn (www.seqan.de) is an open-source C++ template library (BSD license) that implements many efficient and generic data structures and algorithms for Next-Generation Sequencing (NGS) analysis. It contains gapped k-mer indices, enhanced suffix arrays (ESA) or an FM-index, as well algorithms for fast and accurate alignment or read mapping. Based on those data types and fast I/O routines, users can easily develop tools that are extremely efficient and easy to maintain. Besides multi-core, the research team at Freie Universität Berlin has started generic support for distinguished accelerators such as NVIDIA GPUs.

In this webinar, Knut Reinert, Professor, Freie Universität Berlin will introduce SeqAn and string indices, then explain his team’s generic parallelization concept and end with details on how they achieved an up to 47 speedup using an FM-index on a NVIDIA Tesla K20.

Keywords: Bioinformatics & Genomics, GTC Express 2013 - ID GTCE059
Download: MP4 PDF

Folding@home and OpenMM: Using a Cluster of 50,000 GPUs to Simulate Disease Relevant Protein Dynamics

Vijay Pande (Stanford University)

With the combined power of large-scale distributed computing resources such as Folding@home or supercomputers such as Blue Waters or Titan, one can now routinely simulate atomistic protein dynamics on the milliseconds timescale. Join Professor Vijay Pande, Stanford University as he presents efforts to push the limits of this methodology even further to the seconds timescale for protein folding, as well as to a variety of new applications in protein conformational change. The results of these simulations suggest novel targets for disease intervention (for Alzheimer’s and Cancer), as well as new biophysical insights into protein dynamics.

Keywords: Bioinformatics & Genomics, GTC Express 2014 - ID GTCE071
Download: MP4


comments powered by Disqus