Mariam Rakka

hi

Bio

I am an enthusiastic learner currently pursuing a PhD in Electrical and Computer Engineering at the University of California, Irvine. Having completed my MS in the same field in 2022 with a 4.0/4.0 GPA, my thesis focused on accelerating decision tree inference on in-memory computing architectures. I attained my BE in Computer and Communications Engineering from the American University of Beirut with high distinction in May 2020, along with minors in Mathematics and Business Administration.

Over three consecutive summers at Arm, Inc., I contributed to advancing Arm-based architectures through cutting-edge research and development. My work included characterizing Machine Learning and data analytics workloads to identify bottlenecks, designing a specialized hardware accelerator that leveraged SIMD extensions for performance gains, and conducting software-hardware co-design, which resulted in several pending patents. I also developed a Machine Learning-based framework for optimizing Arm processor configurations and investigated acceleration opportunities through novel architecture extensions, reinforcing my expertise in bridging software and hardware innovation.

Beyond my technical acumen, I am passionate about connecting dots and collaborating with people in interdisciplinary fields. My love for constant learning fuels my drive to stay at the forefront of technological advancements. Currently, I remain actively engaged in diverse research and hardware/software projects within Prof. Fadi J. Kurdahi's group at UCI, where my areas of interest encompass machine learning acceleration, electronics, and software/hardware codesign.

Committed to making a meaningful contribution to the field and society at large, I firmly believe that fostering societal progress is just as vital as achieving personal milestones.

Fun fact: I have a special affinity for transistors.

Experience

Technical Skills

C, C++, Gem5, Python, MATLAB, HDL (Verilog/VHDL), OrCAD PSpice, HSPICE, Cadence, Perl, basic SQL, Microsoft Office programs, HTML, Linux/Windows/MacOS

Interests

Weight Lifting, Writing Articles, Reading Stories, Watching Movies, Hiking, Chasing Sunsets

Publications

Rakka, M., Karami, R., Eltawil, A.M., Fouda, M.E. and Kurdahi, F., 2024. BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration. arXiv preprint arXiv:2411.01417.

Rakka, M., Fouda, M.E., Khargonekar, P. and Kurdahi, F., 2024. A Review of State-of-the-Art Mixed-Precision Neural Network Frameworks. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Rakka, Mariam, Walaa Amer, Hanning Chen, Mohsen Imani, and Fadi Kurdahi. "HDRLPIM: A Simulator for Hyper Dimensional Reinforcement Learning based on Processing In Memory." ACM Journal on Emerging Technologies in Computing Systems.

Rakka, Mariam, Mohamed E. Fouda, Rouwaida Kanj, Ahmed Eltawil, and Fadi J. Kurdahi. "Design exploration of sensing techniques in 2T-2R resistive ternary CAMs." IEEE Transactions on Circuits and Systems II: Express Briefs 68, no. 2 (2020): 762-766.

Rakka, Mariam, Rouwaida Kanj, and Ragheb Raad. "Hybrid importance splitting importance sampling methodology for fast yield analysis of memory designs." In 2020 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5. IEEE, 2020.

Rakka, Mariam, Mohammed E. Fouda, Rouwaida Kanj, and Fadi Kurdahi. "DT2CAM: A Decision Tree to Content Addressable Memory Framework." IEEE Transactions on Emerging Topics in Computing (2023).

Rakka, Mariam. Resistive Content Addressable Memory Design for Decision Tree Acceleration. University of California, Irvine, 2022.

Rakka, Mariam, and Rouwaida Kanj. "Importance Splitting Sample Point Reuse for Efficient Memory Yield Estimation." In 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5. IEEE, 2021.