Wang, Yuke | Search NASA

DOE OSTI2025

A 1-year study on SARS-CoV-2 variant shifts in wastewater using dPCR: comparison with clinical and GISAID data

Wastewater testing can be used to monitor SARS-CoV-2 infections in communities. Data from PCR-based wastewater testing are usually available to public health authorities within 5–7 days after excreta and other body fluids enter the sewer. While PCR-based methods can accurately detect and quantify SARS-CoV-2, sequencing-based methods are usually required to distinguish between variants, delaying the results and adding cost to the process. We developed and assessed a novel, customizable digital PCR (dPCR)-based genotyping method for SARS-CoV-2 variant detection in wastewater, which is more cost-effective, faster, and more accessible than sequencing. This approach was applied to more than 1,400 wastewater samples

Wilton, Rose↗

DOE OSTI2024

OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

With the sharp increasing volume of user data, Deep Learning Recommendation Model (DLRM) becomes an indispensable infrastructure in large technology companies. However, large-scale DLRM on the multi-GPU platform is still inefficient due to unbalanced workload partitioning and intensive inter-GPU communication. To this end, we propose OPER, an OPtimality guided Embedding table placement for large-scale Recommendation model training and inference. OPER explores the potential of mitigating remote memory access latency in DLRM through fine-grained embedding table placement. Specifically, OPER proposes a theoretical modeling that builds up the relationship between EMT placement and the embedding communication latency in both training and inference. OPER proves the NP hardness of finding the optimal embedding table placement and proposes a heuristic algorithm that yields near optimal placement. OPER implements a SHMEM-based embedding table training system and a unified embedding index mapping to support fine-grained embedding table sharding and placement. Comprehensive experiments reveal that OPER achieves on average 3.4× and 5.1× speedup on training and inference respectively over state-of-the-art DLRM frameworks.

Wang, Zheng↗