MSMusfiqur Rahman Sanim

Musfiqur Rahman Sanim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Musfiqur Rahman Sanim has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations

    by Zhihao Shu, Musfiqur Rahman Sanim, Hangyu Zheng, Kunxiong Zhu, Miao Yin, Gagan Agrawal, Wei Niu

  • Open Access

    SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile

    by Wei Niu, Musfiqur Rahman Sanim, Zhihao Shu, Jiexiong Guan, Xipeng Shen, Miao Yin, Gagan Agrawal, Bin Ren

    This work is motivated by recent developments in Deep Neural Networks, particularly the Transformer architectures underlying applications such as ChatGPT, and the need for performing inference on mobile devices. Focusing on emerging transformers (specifically the ones with computationally efficient Swin-like architectures) and large models (e.g., Stable Diffusion and LLMs) based on transformers, we observe that layout transformations between the computational operators cause a significant slowdown in these applications. This paper presents SmartMem, a comprehensive framework for eliminating most layout transformations, with the idea that multiple operators can use the same tensor layout through careful choice of layout and implementation of operations. Our approach is based on classifying the operators into four groups, and considering combinations of producer-consumer edges between the operators. We develop a set of methods for searching such layouts. Another component of our work is developing efficient memory layouts for 2.5 dimensional memory commonly seen in mobile devices. Our experimental results show that SmartMem outperforms 5 state-of-the-art DNN execution frameworks on mobile devices across 18 varied neural networks, including CNNs, Transformers with both local and global attention, as well as LLMs. In particular, compared to DNNFusion, SmartMem achieves an average speedup of 2.8×, and outperforms TVM and MNN with speedups of 6.9× and 7.9×, respectively, on average.