cfaed Publications

@InProceedings{khan_asplos25,
author = {Khan, Asif Ali and Farzaneh, Hamid and Friebel, Karl F. A. and Fournier, Clement and Chelini, Lorenzo and Castrillon, Jeronimo},
booktitle = {Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'25), Volume 4},
title = {CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms},
doi = {10.1145/3622781.3674189},
isbn = {9798400703911},
location = {Rotterdam, The Netherlands},
pages = {31--46},
publisher = {Association for Computing Machinery},
series = {ASPLOS '25},
url = {https://dl.acm.org/doi/pdf/10.1145/3622781.3674189},
abstract = {The rise of data-intensive applications exposed the limitations of conventional processor-centric von-Neumann architectures that struggle to meet the off-chip memory bandwidth demand. Therefore, recent innovations in computer architecture advocate compute-in-memory (CIM) and compute-near-memory (CNM), non-von-Neumann paradigms achieving orders-of-magnitude improvements in performance and energy consumption. Despite significant technological breakthroughs in the last few years, the programmability of these systems is still a serious challenge. Their programming models are too low-level and specific to particular system implementations. Since such future architectures are predicted to be highly heterogeneous, developing novel compiler abstractions and frameworks becomes necessary. To this end, we present CINM (Cinnamon), a first end-to-end compilation flow that leverages the hierarchical abstractions to generalize over different CIM and CNM devices and enable device-agnostic and device-aware optimizations. Cinnamon progressively lowers input programs and performs optimizations at each level in the lowering pipeline. To show its efficacy, we evaluate CINM on a set of benchmarks for a real CNM system (UPMEM) and the memristors-based CIM accelerators. We show that Cinnamon, supporting multiple hardware targets, generates high-performance code comparable to or better than state-of-the-art implementations.},
month = mar,
numpages = {16},
year = {2025},
}