Willow
Ahrens

General Information

Email:
ahrens@gmail.com
Phone:
5054125239
Location - Building:
KACB
Location - Room:
3144
Roles:
Professor (any rank)
Primary Unit:
College of Computing
Website URL
https://willowahrens.net

Details

Degrees with subject and Postdoc Experience:
Degree Type
Postdoctoral Scholar
Subject
Computer Science
Year
2024-2025
Institution
Massachusetts Institute of Technology
Location
Cambridge, MA
Degree Type
Ph.D.
Subject
Computer Science
Year
2024
Institution
Massachusetts Institute of Technology
Location
Cambridge, MA
Degree Type
B.S.
Subject
Electrical Engineering and Computer Science with Minor in Mathematics
Year
2016
Institution
University of California, Berkeley
Location
Berkeley, CA
Statement of Research Interests:

I am inspired to make programming high-performance computers more productive, efficient, and accessible. My research focuses on using compilers to accelerate productive programming languages with state-of-the-art datastructures, algorithms, and architectures, bridging the gap between program flexibility and performance. I’m the author of the Finch sparse tensor programming framework. Finch supports general programs on general tensor formats, such as sparse, run-length-encoded, banded, or otherwise structured tensors.

Statement of Teaching Interests:

My goal in teaching is to empower students to design and implement Domain-Specific programming Languages (DSLs) to solve problems in High-Performance Computing (HPC) contexts. I teach the basics of compiler construction and language design as it relates to the challenges of high-performance computing and performance engineering. I enjoy covering topics such as architectural modelling, optimization techniques, and program analysis, through the context of contemorary DSLs and research in the field. It is my hope that any student taking my courses will leave with the skills to build compilers to solve programming problems in their own HPC research areas.

Selection of recent research, scholarly, and creative activities:

Finch: Sparse and Structured Tensor Programming with Control FlowPermalink

Willow Ahrens, Teodoro Fields Collin, Radha Patel, Kyle Deeds, Changwan Hong, and Saman Amarasinghe, “Finch: Sparse and Structured Tensor Programming with Control Flow,” Proc. ACM Program. Lang., April 2025. Link. Download.

Looplets: A Language for Structured CoiterationPermalink

Willow Ahrens, Daniel Donenfeld, Fredrik Kjolstad, and Saman Amarasinghe, “Looplets: A Language for Structured Coiteration,” CGO, February 2023. Link. Download.

Galley: Modern Query Optimization for Sparse Tensor ProgramsPermalink

Kyle Deeds, Willow Ahrens, Magda Balazinska, and Dan Suciu, “Galley: Modern Query Optimization for Sparse Tensor Programs,” arXiv, August 2024. Link. Download.

Autoscheduling for sparse tensor algebra with an asymptotic cost modelPermalink

Willow Ahrens, Fredrik Kjolstad, and Saman Amarasinghe, “Autoscheduling for sparse tensor algebra with an asymptotic cost model,” PLDI, June 2022. Link. Download.

SySTeC: A Symmetric Sparse Tensor CompilerPermalink

Radha Patel, Willow Ahrens, and Saman Amarasinghe, “SySTeC: A Symmetric Sparse Tensor Compiler,” CGO ‘25, March 2025. Link. Download.