Nathan Russell Tallent

E-mail:	tallent at pnnl dot gov
Office:	CSF 1720
Telephone:	509.372.4206
Home Page:	https://hpc.pnnl.gov/people/tallent https://www.pnnl.gov/people/nathan-tallent [google scholar] [research gate]
Postal Address:	Pacific Northwest National Laboratory PO Box 999 MSIN: J4-30 Richland WA 99352
Delivery Address:	Pacific Northwest National Laboratory 902 Battelle Blvd MS-J4-30 Richland, WA 99354

Nathan Tallent is a chief computer scientist and lead for the Continuum Computing Team in the Future Computing Technologies Group within the Advanced Computing, Mathematics, and Data Division. He joined PNNL in 2011.

Dr. Tallent's research is motivated by emerging challenges in distributed systems, scientific workflows, machine learning, and data management. He leads the Performance Lab for EXtreme Computing and daTa where his contributions have spanned the challenges of performance measurement, modeling, bottleneck diagnosis, and optimization; and includes special attention to bottlenecks in networks, storage, and memory. He has made notable contributions to performance tools, both for performance modeling and for parallel performance analysis. He has more than 60 peer-reviewed publications, serves on several reviewing committees, and received a DOE Early Career award. He received a Ph.D. in 2010 from Rice University.

Dr. Tallent has led development of several research software prototypes for distributed scientific workflows, distributed AI services, and performance analysis and prediction.

• DataFlowDrs
• DataLife, DaYu, FastFlow: FlowForecaster: Measurement and analysis toolsets for distributed scientific workflows that use I/O and storage for task composition.
• TAZeR, BigFlowSim: Remote I/O framework; and workflow I/O simulator-emulator and trace generator.
• Distributed AI Services
• MassiveGNN: Performant and productive training for massively connected (distributed) GNNs within the state-of-the-art Amazon DistDGL(distributed Deep Graph Library).
• SamIAm: Microstructure segmentation for transmission electron microscopy that recognizes geometric and textural features and that is based on semantic boosting of the Segment Anything Model (SAM).
• Application Performance Analysis and Prediction
• MemGaze/MemFriend, a memory analysis toolset that combines high-resolution trace analysis and low overhead measurement, both with respect to time and space.
• Palm: Palm is a suite of performance modeling tools (Palm, Palm-Task, Representative-Paths, Palm/FastFootprints, MIAMI-NW) to assist performance analysis and predictive model generation.
• Workload Benchmarking and Characterization
• SEAK Suite: The SEAK Suite is a collection of constraining problem for common embedded computing challenges.
• PERFECT Suite: The PERFECT Suite consists of kernels and applications for evaluating tradeoffs between performance, power, and architecture within the domains of radar and image processing.

He is one of the original developers of HPCToolkit, a widely used suite of performance tools on supercomputers.

He contributed to OpenAD, a tool for automatic differentiation (AD) of numerical computer programs.