Situla: Studying the Interplay of Sparse Formats and CPU/GPU Libraries
Amirmahdi Namjoo, Sanjali Yadav, Helya Hosseini, Bahar Asgari
IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) Β· 2026
A characterization of sparse-dense and sparse-sparse matrix multiplication across Intel Xeon CPUs, NVIDIA H100 GPUs, and Arm Neoverse processors, studying how sparse format, software library, matrix structure, performance, and energy interact.
@inproceedings{namjoo2026situla,
author = {Namjoo, Amirmahdi and Yadav, Sanjali and Hosseini, Helya and Asgari, Bahar},
title = {Situla: Studying the Interplay of Sparse Formats and CPU/GPU Libraries},
booktitle = {2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)},
year = {2026},
pages = {567--577},
doi = {10.1109/ISPASS69572.2026.00060}
}
ChasoΕ: Supporting Cross HBM Channel Data Migration to Enable Efficient Sparse Algebraic Acceleration
Ubaid Bakhtiar, Amirmahdi Namjoo, Bahar Asgari
58th IEEE/ACM International Symposium on Microarchitecture (MICRO) Β· 2025
An HBM-based streaming accelerator for sparse matrix-vector multiplication that migrates data across HBM channels (Cross-HBM Channel out-of-order scheduling) to mitigate resource underutilization.
@inproceedings{10.1145/3725843.3756086,
author = {Bakhtiar, Ubaid and Namjoo, Amirmahdi and Asgari, Bahar},
title = {Chason: Supporting Cross HBM Channel Data Migration to Enable Efficient Sparse Algebraic Acceleration},
year = {2025},
doi = {10.1145/3725843.3756086},
booktitle = {Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture},
pages = {778--794},
series = {MICRO '25}
}
Misam: Machine Learning Assisted Dataflow Selection in Accelerators for Sparse Matrix Multiplication
Sanjali Yadav, Amirmahdi Namjoo, Bahar Asgari
58th IEEE/ACM International Symposium on Microarchitecture (MICRO) Β· 2025
A machine-learning framework that uses a lightweight decision tree and FPGA reconfiguration to select the optimal dataflow for sparse matrix-matrix multiplication at runtime.
@inproceedings{10.1145/3725843.3756126,
author = {Yadav, Sanjali and Namjoo, Amirmahdi and Asgari, Bahar},
title = {Misam: Machine Learning Assisted Dataflow Selection in Accelerators for Sparse Matrix Multiplication},
year = {2025},
doi = {10.1145/3725843.3756126},
booktitle = {Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture},
pages = {824--838},
series = {MICRO '25}
}
Python
Django
React
Docker
PostgreSQL
Raspberry Pi
Arduino