The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Student: Valen Yamamoto (Lawrence Livermore National Laboratory)
Supervisor: Ian Karlin (Lawrence Livermore National Laboratory)
Abstract: Current material interface reconstruction methods provide inaccurate reconstructions; a neural network provides more accurate reconstructions. The initial model architecture was too large to provide the required throughput. Reducing the size of the model shows a smaller model could be used and provide similar accuracy. The throughput of the reduced model reaches the target throughput and increases throughput by 15x on NVIDIA A100 GPUs. Further work is being done porting the full model to SambaNova systems.
ACM-SRC Semi-Finalist: no
Poster: PDF
Poster Summary: PDF
Back to Poster Archive Listing