High Performance Molecular Visualization: In-Situ and Parallel Rendering with EGL

Abstract

Large scale molecular dynamics simulations produce terabytes of data that is impractical to transfer to remote facilities. It is therefore necessary to perform visualization tasks in-situ as the data are generated, or by running interactive remote visualization sessions and batch analyses co-located with direct access to high performance storage systems. A significant challenge for deploying visualization software within clouds, clusters, and supercomputers involves the operating system software required to initialize and manage graphics acceleration hardware. Recently, it has become possible for applications to use the Embedded-system Graphics Library (EGL) to eliminate the requirement for windowing system software on compute nodes, thereby eliminating a significant obstacle to broader use of high performance visualization applications. We outline the potential benefits of this approach in the context of visualization applications used in the cloud, on commodity clusters, and supercomputers. We discuss the implementation of EGL support in VMD, a widely used molecular visualization application, and we outline benefits of the approach for molecular visualization tasks on petascale computers, clouds, and remote visualization servers. We then provide a brief evaluation of the use of EGL in VMD, with tests using developmental graphics drivers on conventional workstations and on Amazon EC2 G2 GPU-accelerated cloud instance types. We expect that the techniques described here will be of broad benefit to many other visualization applications.

Biomolecular modeling thrives in the age of technology

“…3d). A high-performance version of the popular visualization program VMD has been implemented on the Amazon cloud 140 , as well as the MD toolkit QwikMD 141 and the molecular dynamics flexible fitting (MDFF) method for structure refinement from cryo-electron microscopy densities 142 . These efforts allow scientists worldwide to access powerful computational equipment and software packages in a cost-effective way.…”

Early Experiences Porting the NAMD and VMD Molecular Simulation and Analysis Software to GPU-Accelerated OpenPOWER Platforms

“…At the time of writing, it was not yet possible to evaluate the performance benefits associated with peer-to-peer GPU transfers as they are not yet implemented by CUDA 7.5 for OpenPOWER. Several GPU-accelerated graphics-related features of VMD were similarly unavailable for testing due to lack of OpenPOWER versions of the OpenGL or Vulkan APIs for rasterization, and the associated GLX or EGL context management APIs [14], the OptiX GPU ray tracing framework [22], or the NVENC GPU-accelerated video encoding library.…”

“…In concert with a sophisticated atom selection language and a wide variety of data structures and algorithms for visualization, analysis, and structure manipulation, VMD incorporates built-in Tcl and Python scripting that can be used to perform large scale molecular modeling and analysis tasks in parallel on clouds [14], clusters, and petascale computers [9, 15–17, 10]. VMD provides a wide variety of tools for assembling large macromolecular complexes from constituent proteins, and combining these with solvent and ions to replicate biological conditions in vivo, and it can emit the completed system for simulation with popular GPU-accelerated MD simulation tools such as NAMD [6, 7, 18] and GROMACS [19, 20].…”

GPU-Based In Situ Visualization for Large-Scale Discrete Element Simulations

“…However, DEM simulation is a parallel program running on the cluster computer, with no screen as the output device. Therefore, solving the problem of parallel off-screen rendering is the first problem to realize in situ visualization [16].…”