Addr. 2-12-1 O-okayama, Meguroku, Tokyo
152-8550 JAPAN
Email Contact this mail address.

Grand Challenge (Large Scale GPU applications)

Large scale Phase-Field simulation for metal dendritic solidification by multi-GPU computing

The phase-field method is applied to study dendritic solidification of Si-Al binary alloy. The performance reaches 2.0000045 PFLOPS for 4,096x6,500x10,400 mesh, which is the first over peta-scale result as a real stencil application we know to date.
(See more details)

Multiphysics Biofluidics Simulation

Multiphysics Biofluidics Simulation is gaining a deeper insight of blood circulation that is a necessary step to improve our understanding of cardiovascular diseases.
(See more details)

Ultra-fast computing pipeline for metagenome analysis with next-generation DNA sequencers (NEW!)

Metagenome analysis is the study of the genomes of uncultured microbes obtained directly from microbial communities in their natural habitats. GHOSTM (K=4) as a homology search program, the pipeline achieves to process about 60 million reads per an hour with 2,520 GPUs (840 computing nodes) . Our results indicate the pipeline can process genome information obtained from a single run of next generation sequencers in a few hours.
(See more details)

Turbulence Simulation using FMM

The fast multipole method (FMM) enables highly parallelized execution of turbulence simulation compared to traditional spectral method (based on FFT).
(See more details)

High Performance Seismic Simulation with GPGPU

Improvement of checkpointing overhead achieve better performance of GPGPU version of SPECFEM3D, which is one of the leading applications to simulate seismic wave propagations.
(See more details)

Molecular Dynamics Simulation of a Biomolecule with High Speed, Low Power and Accuracy using GPGPU

Using GPUs could yield a great improvement in both the calculation speed and energy consumption. Comparing 8 nodes 16 GPUs result and 8 nodes 96 CPU cores result, we could achieve about 10 times acceleration and 75 % energy reduction. The results of GPU molecular dynamics was consistent with that of CPU molecular dynamics within acceptable range.
(See more details)