Visiting Student--DOE CSGF– MCS – Anderson, Caira– 4.6.26

Argonne National Laboratory • Lemont, IL

2d

About The Position

The student will do a performance study and optimization of a fully implicit Runge-Kutta (FIRK) solver, focusing on temporal-domain vectorization. They will focus on advancing high-performance time integration methods for large-scale simulations of systems arising from compelling problems in areas such as plasma physics, e.g., magnetohydrodynamic (MHD) simulations. The work builds on an existing implementation of a fully implicit Runge--Kutta (FIRK) solver in PETSc, which leverages a shuffled Jacobian representation and the MatKAIJ matrix type for efficient Kronecker-product computations. The improved solver will then be applied to a relevant problem to assess both accuracy and performance. Education and Experience Requirements The entirety of the appointment must be conducted within the United States. Must be 18 years or older at the time the appointment begins. Applicants must be: Currently enrolled in undergraduate or graduate studies at an accredited institution. Graduated from an accredited institution within the past 3 months; or Actively enrolled in a graduate program at an accredited institution.

Requirements

• The entirety of the appointment must be conducted within the United States.
• Must be 18 years or older at the time the appointment begins.
• Currently enrolled in undergraduate or graduate studies at an accredited institution.
• Graduated from an accredited institution within the past 3 months; or Actively enrolled in a graduate program at an accredited institution.

Responsibilities

• Performance study and optimization of a fully implicit Runge-Kutta (FIRK) solver
• Focusing on temporal-domain vectorization
• Advancing high-performance time integration methods for large-scale simulations of systems arising from compelling problems in areas such as plasma physics, e.g., magnetohydrodynamic (MHD) simulations
• Building on an existing implementation of a fully implicit Runge--Kutta (FIRK) solver in PETSc, which leverages a shuffled Jacobian representation and the MatKAIJ matrix type for efficient Kronecker-product computations
• Applying the improved solver to a relevant problem to assess both accuracy and performance

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: No Education Listed
• Number of Employees: 1,001-5,000 employees