Siva Rajamanickam

Siva Rajamanickam

Researcher

Sandia National Laboratories

Siva Rajamanickam is a distinguished member of technical staff at Sandia National Laboratories. His interest is broadly in the areas of high performance computing, specifically in machine learning for science, performance portable algorithms, codesign of algorithms and architectures and combinatorial scientific computing. Most of his works are in the intersection of these areas where interesting opportunities lie to solve problems that are of importance to computational science use cases.

Interests
  • High Performance Computing
  • Machine Learning for Science
  • Performance Portable Algorithms
  • Codesign of Algorithms and Architectures
  • Combinatorial Scientific Computing
Education

  • PhD in Computer Science and Engineering, 2009

    University of Florida

  • BE in Computer Science and Engineering, 1999

    Madurai Kamaraj University

Featured Publications

Do AI Models Perform Human-like Abstract Reasoning Across Modalities?
Claas Beger, Ryan Yi, Shuhao Fu, Kaleda Denton, Arseny Moskvichev, Sarah W Tsai, Sivasankaran Rajamanickam, Melanie Mitchell
Breaking the Molecular Dynamics Timescale Barrier Using a Wafer-Scale System
Kylee Santos, Stan Moore, Tomas Oppelstrup, Amirali Sharifian, Ilya Sharapov, Aidan Thompson, Delyan Z Kalchev, Danny Perez, Robert Schreiber, Scott Pakin, Edgar a Leon, James H Laros III, Michael James, Sivasankaran Rajamanickam
Predicting electronic structures at any length scale with machine learning
Lenz Fiedler, Normand Modine, Steve Scmerler, Dayton J Vogel, Gabriel Popoola, Aidan P Thompson, Sivasankaran Rajamanickam, Attila Cangi
Accelerating finite-temperature Kohn-Sham density functional theory with deep neural networks
J Austin Ellis, Lenz Fiedler, Gabriel a Popoola, Normand a Modine, J Adam Stephens, Aidan P Thompson, Attila Cangi, Sivasankaran Rajamanickam
Kokkos 3: Programming model extensions for the exascale era
Christian R Trott, Damien Lebrun-Grandie, Daniel Arndt, Jan Ciesko, Vinh Dang, Nathan Ellingwood, Rahulkumar Gayatri, Evan Harvey, Daisy S Hollman, Dan Ibanez, Others
The Kokkos EcoSystem: Comprehensive Performance Portability For High Performance Computing
Christian R Trott, Luc Berger-Vergiat, David Poliakoff, Sivasankaran Rajamanickam, Damien Lebrun-Grandie, Jonathan Madsen, Nader Al Awar, Milos Gligoric, Galen Shipman, Geoff Womeldorff

Recent Publications

Trilinos: Enabling scientific computing across diverse hardware architectures at scale
Matthias Mayr, Alexander Heinlein, Christian Glusa, Sivasankaran Rajamanickam,, Et Al.
ShyLU-node: On-node scalable solvers and preconditioners: Recent progress and current performance
Ichitaro Yamazaki, Nathan Ellingwood, Sivasankaran Rajamanickam
Breaking the mold: Overcoming the time constraints of molecular dynamics on general-purpose hardware
Danny Perez, Aidan Thompson, Stan Moore, Tomas Oppelstrup, Ilya Sharapov, Kylee Santos, Amirali Sharifian, Delyan Z Kalchev, Robert Schreiber, Scott Pakin, Edgar a Leon, James H Laros, Michael James, Sivasankaran Rajamanickam
LAPIS: A Performance Portable, High Productivity Compiler Framework
Brian Kelley, Sivasankaran Rajamanickam
Beyond Exascale: Dataflow Domain Translation on a Cerebras Cluster
Tomas Oppelstrup, Nicholas Giamblanco, Delyan Z Kalchev, Ilya Sharapov, Mark Taylor, Dirk Van Essendelft, Sivasankaran Rajamanickam, Michael James
See all publications

Recent & Upcoming Talks

Batched Linear Solvers in Kokkos Kernels
Mar 2, 2023 12:00 AM Amsterdam, Netherlands.
Scientific Machine Learning and Data flow acceleration: ASCR HQ Update
Mar 1, 2023 12:00 AM Albuquerque
Recent Experiences on Accelerating Machine Learning Workloads on SambaNova Systems
Feb 3, 2023 12:00 AM Atlanta
Kokkos Kernels: Then and Now
Jan 19, 2023 12:00 AM Houston
Accelerating Selected DOE Machine Learning Workloads on SambaNova Systems
Nov 15, 2022 12:00 AM Dallas
See all events

Projects

Instead of listing all the funded projects that I lead, this is a summary of all the areas I am interested in. All my projects fall into one or more of these areas.

Codesign of Algorithms and Architectures

As architectures evolve from one generation to next generation and when new paradigms such as data flow emerge there are lots of opportunities to not just develop new algorithms for these architectures but to co-design both architectures and algorithms to relaize gains that are otherwise not possible.
Combinatorial Scientific Computing

Combinatorial scientific computing (CSC) has served as the foundation of several scientific simulations for the past three decades. Several of the problems in the field of deal with an interesting mix of combinatorial, numerical, and computer architecture issues.
Performance Portability

Computational science applications that I work with represent diverse science needs from climate, circuit simulations, mechanics and fluid simulations, electromagnetics simulations.

Computational science applications that I work with are expected to run on the top 500 supercomputers in the world and on capacity clusters. These systems represent diverse architectures from different vendors each relying on their own programming models and architectural quirks. Designing algorithms and developing implementations of these algorithms that can perform well on all these architectures has been a challenging problem.
Machine Learning for Science

Machine learning has resulted in several advances for several industry use cases and offers potential to accelerate science simulations and new scientific discoveries.

My specific interests lie in developing machine learning based surrogate models for scientific simulations, especially on problems that require very large amount of data and/or compute. The science data sets the I work with involves heterogeneous systems with different materials, and physical properties such as temeperature, and density. I am also interested in accelerating machine learning approaches on novel hardware architectures including but not limited to GPUs.

Software

Instead of listing all the software projects that I am involved with, this is a summary of large frameworks that I contribute to.

Kokkos Kernels

See Kokkos Kernels Website for more details.

Jan 8, 2022
Mala

See Mala Website for more details.

Jan 8, 2022
Trilinos

Trilinos is large framework that serves as the foundation for several computational science applications. It provides capabilities for building portable, high performance, parallel science codes. The basic functionality provided include distributed linear algebra, portable sparse/dense linear algebra kernels, load balancing utilites, sparse linear solvers, non-linear solvers, discretization and meshing utilities.
Jan 8, 2022

Contact