Publications (9)
Differentiating a Tensor Language
Gilbert Bernstein, Michael Mara, Tzu-Mao Li +2
How does one compile derivatives of tensor programs, such that the resulting code is purely functional (hence easier to optimize and parallelize) and provably efficient relative to…
Opt: A Domain Specific Language for Non-linear Least Squares Optimization in Graphics and Imaging
Zachary DeVito, Michael Mara, Michael Zollhöfer +6
Many graphics and vision problems can be expressed as non-linear least squares optimizations of objective functions over visual data, such as images and meshes. The mathematical de…
Piper: A Programmable Distributed Training System
Megan Frisella, Shubham Tiwari, Andy Ruan +5
Large-scale model training increasingly relies on composing multiple parallelism strategies, such as data, pipeline, and expert parallelism, together with memory-saving optimizatio…
Rethinking Collision Detection on GPU Ray Tracing Architecture
Durga Keerthi Mandarapu, Isaac Fuksman, Artem Pelenitsyn +2
Discrete Collision Detection (DCD) is a fundamental task in several domains including particle-based physics simulations. Efficient DCD uses indexing structures such as Bounding Vo…
Exo 2: Growing a Scheduling Language
Yuka Ikarashi, Kevin Qian, Samir Droubi +3
User-schedulable languages (USLs) help programmers productively optimize programs by providing safe means of transforming them. Current USLs are designed to give programmers exactl…
YASPS: A Symbolic Framework for Extensible, High-Performance IPC Simulation
Xuan Tang, Kemeng Huang, Gilbert Bernstein +2
Incremental Potential Contact (IPC) enables robust, contact-rich simulation by casting elasticity and contact as a single energy minimization problem, but high-performance IPC pipe…