A Reconfigurable Time-Domain In-Memory Computing Macro using FeFET-Based CAM with Multilevel Delay Calibration in 28 nm CMOS
By: Jeries Mattar , Mor M. Dahan , Stefan Dunkel and more
Potential Business Impact:
Makes computers compute faster and use less power.
Time-domain nonvolatile in-memory computing (TD-nvIMC) offers a promising pathway to reduce data movement and improve energy efficiency by encoding computation in delay rather than voltage or current. This work presents a fully integrated and reconfigurable TD-nvIMC macro, fabricated in 28 nm CMOS, that combines a ferroelectric FET (FeFET)-based content-addressable memory array, a cascaded delay element chain, and a time-to-digital converter. The architecture supports binary multiply-and-accumulate (MAC) operations using XOR- and AND-based matching, as well as in-memory Boolean logic and arithmetic functions. Sub-nanosecond MAC resolution is achieved through experimentally demonstrated 550 ps delay steps, representing a 2000$\times$ improvement over prior FeFET TD-nvIMC work, enabled by multilevel-state calibration with $\leq$100 ps resolution. Write-disturb resilience is ensured via isolated triple-well bulks. The proposed macro achieves a measured throughput of 222.2 MOPS/cell and energy efficiency of 1887 TOPS/W at 0.85 V, establishing a viable path toward scalable, energy-efficient TD-nvIMC accelerators.
Similar Papers
A Novel 8T SRAM-Based In-Memory Computing Architecture for MAC-Derived Logical Functions
Hardware Architecture
Makes computers do math and logic faster.
FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration
Hardware Architecture
Makes tiny computers learn faster and use less power.
Single-Ferroelectric Memcapacitor-Based Time-Domain Content-Addressable Memory for Highly Precise Distance Function Computation
Emerging Technologies
Finds information in computers much faster.