2 papers
cs.PL2026
Tensor Seeks Layout: Formalizing Layout Selection for ML Compilers
Clemens Eisenhofer, Yuwen Jia, Daniel Kroening +1
Modern machine learning compilers select tensor memory layouts to minimize execution cost under hardware constraints. Layout selection is global: an operator may be fastest under o…
cs.PL2024
Stale Profile Matching
Amir Ayupov, Maksim Panchenko, Sergey Pupyrev
Profile-guided optimizations rely on profile data for directing compilers to generate optimized code. To achieve the maximum performance boost, profile data needs to be collected o…