A Client-Server type remote visualization software based on Particle-Based Volume Rendering (PBVR). The server program works on massively parallel environments such as the K-computer, FX10, and Linux clusters and on PCs (Win/Mac/Linux). The client program works on PCs. The server program compresses large-scale volume data into small particle data and transfers it to the client program by the socket communication via ssh tunnel. The client program renders the particle data with interactive frame rates. In addition to volume rendering visualization, iso-surface, slice surface, and multivariate visualization are possible by designing multi-dimensional transfer functions.
※ The latest version is 1.17.2
In-Situ PBVR is an In-Situ Visualization Framework based on Particle-Based Volume Rendering, consisting of parallel visualization libraries, communication tool, and display applications. Interactive remote visualization is realized by avoiding the output of large-scale simulation results and converting it into compressed visualization particles for transfer. In addition, advanced transfer function design enables flexible visualization processing such as isosurface, cross section, multivariate data analysis as well as volume rendering.
※ The latest version is 1.2
The remote visualization software PBVR (hereinafter referred to as PBVR) enables interactive remote visualization of large-scale data, which was difficult with conventional visualization software, due to its high parallel processing performance and compressed data transfer amount. PBVR is developed using the general-purpose visualization library KVS. This program is an extension of KVS for the head mounted display Oculus Rift, and can output the visualization results generated by KVS including PBVR for Oculus Rift. By building a visualization application using this program, it will be possible to visualize VR for large-scale data using PBVR.
※ The latest version is 2.9
The PARallel Computing ELements (PARCEL) library provides highly efficient parallel Krylov subspace solvers for modern massively parallel supercomputers, which are characterized by accelerated computation and less performance improvement in inter-node communication. The PARCEL is based on a hybrid parallel programing model with MPI+OpenMP, and supports the latest communication avoiding (CA) Krylov methods (the Chebyshev basis CACG method and the CA-GMRES method) in addition to the conventional Krylov subspace methods (the CG method, the BiCGstab method, and the GMRES method). The PARCEL supports two matrix formats (Compressed Row Storage (CRS) formant and Diagonal (DIA) format), two data types (Double precision and Quad precision), and can be called from programs written in C and Fortran.
※ The latest version is 1.1
A quadruple precision version of the Basic Linear Algebra Subroutines (BLAS). It is expected that, when a simulation that requires the K computer or very-large-scale parallel computers of the future to run at their maximum performance is conducted, the accuracy of the calculation can be significantly reduced in some cases. It is necessary to improve accuracy of calculation in this situation and quadruple precision with higher speed of basic linear calculation can be achieved by using this software.
※ The latest version is 1.0
A quadruple precision version of the Basic Linear Algebra Subroutines (BLAS) on GPUs. By simply replacing the conventional BLAS routines with corresponding QPBLAS-GPU routines, quadruple precision with higher speed can be achieved. In addition, not only basic operations but also applications that support GPUs can utilize quadruple precision calculations, and users can easily conduct quadruple precision calculations on GPUs.
※ The latest version is 1.0
This is a general software for ab initio molecular simulation, published an open source code written in MPI Fortran 90 . A variety of simulation methods is implemented, such as geometry optimization, normal mode analysis, phonon calculations, reaction path calculations (string method, path integral method), classical statistics (replica exchange), quantum statistics (path integral method) semiclassical dynamics (centroid and ring polymer molecular dynamics), nonadiabatic dynamics (mean field dynamics method, surface hopping method), free energy calculations (metadynamics, constrained molecular dynamics), etc. Each of them employs algorithms suited for massively parallel computers.
※ The latest version is 2.5.0