Fiber Scattering Simulation on GPUs



Cellulose is one of the most promising energy resources that is waiting to be tapped. Harvesting energy from cellulose requires decoding its atomic structure. Some structural information can be exposed by modeling data produced by X-ray scattering.

In this work, we accelerate a molecular scattering algorithm by leveraging a GPU cluster. The optimization approach considers memory utilization, math intrinsics, concurrent kernel execution and workload partitioning, using CUDA, OpenMP and MPI.

Leveraging accelerators hosted on a cluster, we have reduced days/weeks of intensive simulation to parallel execution of just a few minutes/seconds. Our GPU-integrated cluster solution can potentially support concurrent modeling of hundreds of cellulose fibril structures, opening up new avenues for energy research.

source code