TY - GEN
T1 - GPU-accelerated molecular visualization on petascale supercomputing platforms
AU - Stone, John E.
AU - Vandivort, Kirby L.
AU - Schulten, Klaus
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2013
Y1 - 2013
N2 - Petascale supercomputers create new opportunities for the study of the structure and function of large biomolecular complexes such as viruses and photosynthetic organelles, permitting all-atom molecular dynamics simulations of tens to hundreds of millions of atoms. Together with simulation and analysis, visualization provides researchers with a powerful "computational microscope". Petascale molecular dynamics simulations produce tens to hundreds of terabytes of data that can be impractical to transfer to remote facilities, making it necessary to perform visualization and analysis tasks in-place on the supercomputer where the data are generated. We describe the adaptation of key visualization features of VMD, a widely used molecular visualization and analysis tool, for GPU-accelerated petascale computers. We discuss early experiences adapting ray tracing algorithms for GPUs, and compare rendering performance for recent petas-cale molecular simulation test cases on Cray XE6 (CPU-only) and XK7 (GPU-accelerated) compute nodes. Finally, we highlight opportunities for further algorithmic improvements and optimizations.
AB - Petascale supercomputers create new opportunities for the study of the structure and function of large biomolecular complexes such as viruses and photosynthetic organelles, permitting all-atom molecular dynamics simulations of tens to hundreds of millions of atoms. Together with simulation and analysis, visualization provides researchers with a powerful "computational microscope". Petascale molecular dynamics simulations produce tens to hundreds of terabytes of data that can be impractical to transfer to remote facilities, making it necessary to perform visualization and analysis tasks in-place on the supercomputer where the data are generated. We describe the adaptation of key visualization features of VMD, a widely used molecular visualization and analysis tool, for GPU-accelerated petascale computers. We discuss early experiences adapting ray tracing algorithms for GPUs, and compare rendering performance for recent petas-cale molecular simulation test cases on Cray XE6 (CPU-only) and XK7 (GPU-accelerated) compute nodes. Finally, we highlight opportunities for further algorithmic improvements and optimizations.
KW - GPU
KW - Many-core
KW - Molecular surface
KW - Molecular visualization
KW - Parallel rendering
KW - Ray tracing
UR - https://www.scopus.com/pages/publications/84892962345
UR - https://www.scopus.com/pages/publications/84892962345#tab=citedBy
U2 - 10.1145/2535571.2535595
DO - 10.1145/2535571.2535595
M3 - Conference contribution
AN - SCOPUS:84892962345
SN - 9781450325004
T3 - Proc. of UltraVis 2013: 8th Int. Workshop on Ultrascale Visualization - Held in Conjunction with SC 2013: The Int. Conference for High Performance Computing, Networking, Storage and Analysis
BT - Proc. of UltraVis 2013
T2 - 8th International Workshop on Ultrascale Visualization, UltraVis 2013 - Held in Conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2013
Y2 - 17 November 2013 through 17 November 2013
ER -