Sabuj Laskar

[MICRO'26] SYMPHONY: Harmonizing Memory and Communication in LLM Inference on 3D DRAM Accelerators

Sabuj Laskar, Hyojong Kim, Devesh Singh, Mrinmoy Ghosh, Eun Jung Kim

[HPCA'26] Compression-Aware Gradient Splitting for Collective Communications in Distributed Training.

Pranati Majhi, Sabuj Laskar, Abdullah Muzahid, Eun Jung Kim

[MICRO'25] SuperMesh: Energy-Efficient Collective Communications for Accelerators. [Distinguished Artifact Award]

Sabuj Laskar, Pranati Majhi, Abdullah Muzahid, Eun Jung Kim

[HPCA'24] Enhancing Collective Communication in MCM Accelerators for Deep Learning Training.

Sabuj Laskar, Pranati Majhi, Sungkeun Kim, Farabi Mahmud, Abdullah Muzahid, Eun Jung Kim

[IEEE BigData'22] Fast Support Vector Machine Using Singular Value Decomposition.

Sabuj Laskar, Muhammad Abdullah Adnan

[PRDC'22] Characterizing Deep Learning Neural Network Failures between Algorithmic Inaccuracy and Transient Hardware Faults.

Sabuj Laskar, Md Hasanur Rahman, Bohan Zhang, Guanpeng Li

[ISSRE-W'22] TensorFI+: A Scalable Fault Injection Framework for Modern Deep Learning Neural Networks.

Sabuj Laskar, Md Hasanur Rahman, Guanpeng Li