An Ultracompact Single‐Ferroelectric Field‐Effect Transistor Binary and Multibit Associative Search Engine

Abstract

Content addressable memory (CAM) is widely used in associative search tasks due to its parallel pattern matching capability. As more complex and data‐intensive tasks emerge, it is becoming increasingly important to enhance CAM density for improved performance and better area efficiency. To reduce the area overheads, various nonvolatile memory (NVM) devices, such as ferroelectric field‐effect transistors (FeFETs), are used in CAM design. Herein, a novel ultracompact 1FeFET CAM design that enables parallel associative search and in‐memory hamming distance calculation is used, as well as a multibit CAM for exact search using the same CAM cell. The proposed CAM design leverages the 1FeFET1R structure, and compact device designs that integrate the series resistor current limiter into the intrinsic FeFET structure are demonstrated to turn the 1FeFET1R structure into an effective 1FeFET cell. A two‐step search operation of the proposed binary and multibit 1FeFET CAM array through both experiments and simulations is proposed, showing a sufficient sensing margin despite unoptimized FeFET device variation. In genome pattern matching applications, using the hyperdimensional computing paradigm, the design results in a 89.9× speedup and 66.5× improvement in energy efficiency over the state‐of‐the‐art alignment tools on GPU.

Content-Addressable Memories and Transformable Logic Circuits Based on Ferroelectric Reconfigurable Transistors for In-Memory Computing

“…CMOS-based binary CAM requires at least 8 transistors per bit, while the ferroelectric reconfigurable transistor is more efficient using only 1 transistor per bit. The search operation is a one-step process (i.e., the search voltage is only applied on the back gate once), as compared with the two-step search operation presented for 1T FeFET CAM . Although binary CAM can suit different computing applications, ternary CAM (TCAM) employs a “don’t care” state, making it easy to achieve wild-card matching.…”

“…CAM is a promising in-memory computing circuit designed for vector storage and comparison, suitable for data-intensive applications such as nearest-neighbor search and few-shot learning. ,,− CAM compares an input vector against a list of stored vectors in memory and in parallel, resulting in a fast search operation and reduced memory traffic. , Utilizing the switchable polarity of ferroelectric reconfigurable transistors, we demonstrate CAM cells with a density of one transistor per bit. The operation of the CAM cell based on the ferroelectric reconfigurable transistor is illustrated in Figure a.…”

“…The search operation is a onestep process (i.e., the search voltage is only applied on the back gate once), as compared with the two-step search operation presented for 1T FeFET CAM. 40 Although binary CAM can suit different computing applications, ternary CAM (TCAM) employs a "don't care" state, making it easy to achieve wildcard matching. Emerging memory resistors have reduced the component in a 1 TCAM cell to 2T or 2T2R.…”