A technical paper titled “CMOS-based Single-Cycle In-Memory XOR/XNOR” was published by researchers at University of Tennessee, University of Virginia, and Oak Ridge National Laboratory (ORNL).
“Big data applications are on the rise, and so is the number of data centers. The ever-increasing massive data pool needs to be periodically backed up in a secure environment. Moreover, a massive amount of securely backed-up data is required for training binary convolutional neural networks for image classification. XOR and XNOR operations are essential for large-scale data copy verification, encryption, and classification algorithms. The disproportionate speed of existing compute and memory units makes the von Neumann architecture inefficient to perform these Boolean operations. Compute-in-memory (CiM) has proved to be an optimum approach for such bulk computations. The existing CiM-based XOR/XNOR techniques either require multiple cycles for computing or add to the complexity of the fabrication process. Here, we propose a CMOS-based hardware topology for single-cycle in-memory XOR/XNOR operations. Our design provides at least 2 times improvement in the latency compared with other existing CMOS-compatible solutions. We verify the proposed system through circuit/system-level simulations and evaluate its robustness using a 5000-point Monte Carlo variation analysis. This all-CMOS design paves the way for practical implementation of CiM XOR/XNOR at scaled technology nodes.”
Find the technical paper here. Published October 2023 (preprint).
Shamiul Alam, Jack Hutchins, Nikhil Shukla, Kazi Asifuzzaman, and Ahmedullah Aziz. “CMOS-based Single-Cycle In-Memory XOR/XNOR.” arXiv:2310.18375v1 (2023)
Related Reading
Sweeping Changes For Leading-Edge Chip Architectures
Large language models and huge data volumes are prompting innovation at every level.
Ferroelectric Memories Answer Call For Non-Volatile Alternatives
Researchers target NVMs that are compatible with CMOS logic
Leave a Reply