A three dimension memory device and a ternary content addressable memory cell are provided. The ternary content addressable memory cell includes a first memory cell, a second memory cell, a first search switch, and a second search switch. The first memory cell is disposed in a first AND type flash memory line. The second memory cell is disposed in a second AND type flash memory line. The first search switch is coupled between a first bit line corresponding to the first AND type flash memory line and a match line, and is controlled by a first search signal to be turned on or cut off. The second search switch is coupled between a second bit line corresponding to the second AND type flash memory line and the match line, and is controlled by a second search signal to be turned on or cut off.

The application provides a content addressable memory (CAM) cell, a CAM memory device and an operation method thereof, and a method for searching and comparing data. The CAM cell includes a first flash memory cell having a first terminal for receiving a first search voltage; and a second flash memory cell having a first terminal for receiving a second search voltage, a second terminal of the first flash memory cell electrically connected to a second terminal of the second flash memory cell, wherein the first flash memory cell and the second flash memory cell are serially connected; and a storage data of the CAM cell is based on a combination of a plurality of threshold voltages of the first flash memory cell and the second flash memory cell.

Examples described herein relate to a decision tree computation system in which a hardware accelerator for a decision tree is implemented in the form of an analog Content Addressable Memory (a-CAM) array. The hardware accelerator accesses a decision tree. The decision tree comprises of multiple paths and each path of the multiple paths includes a set of nodes. Each node of the decision tree is associated with a feature variable of multiple feature variables of the decision tree. The hardware accelerator combines multiple nodes among the set of nodes with a same feature variable into a combined single node. Wildcard values are replaced for feature variables not being evaluated in each path. Each combined single node associated with each feature variable is mapped to a corresponding column in the a-CAM array and the multiple paths of the decision tree to rows of the a-CAM array.

A method for storing data includes determining, using a first match line, that a match word satisfies a first content addressable memory (CAM) word stored in a CAM array, wherein the CAM array is configured to store a second CAM word that matches the first CAM word. The method further includes determining that a first parity bit associated with the first CAM word matches a first parity of the first CAM word. The method further includes, in response to determining that the first parity bit associated with the first CAM word matches the first parity determining, using the first match line, a first random access memory (RAM) word stored in a RAM array and outputting the first RAM word.

A method for storing data includes determining, using a first match line, that a match word satisfies a first content addressable memory (CAM) word stored in a CAM array, wherein the CAM array is configured to store a second CAM word that matches the first CAM word. The method further includes determining that a first parity bit associated with the first CAM word matches a first parity of the first CAM word. The method further includes, in response to determining that the first parity bit associated with the first CAM word matches the first parity determining, using the first match line, a first random access memory (RAM) word stored in a RAM array and outputting the first RAM word.

In some embodiments, an in-memory-computing SRAM macro based on capacitive-coupling computing (C3) (which is referred to herein as “C3SRAM”) is provided. In some embodiments, a C3SRAM macro can support array-level fully parallel computation, multi-bit outputs, and configurable multi-bit inputs. The macro can include circuits embedded in bitcells and peripherals to perform hardware acceleration for neural networks with binarized weights and activations in some embodiments. In some embodiments, the macro utilizes analog-mixed-signal capacitive-coupling computing to evaluate the main computations of binary neural networks, binary-multiply-and-accumulate operations. Without needing to access the stored weights by individual row, the macro can assert all of its rows simultaneously and form an analog voltage at the read bitline node through capacitive voltage division, in some embodiments. With one analog-to-digital converter (ADC) per column, the macro cab realize fully parallel vector-matrix multiplication in a single cycle in accordance with some embodiments.

In some embodiments, an in-memory-computing SRAM macro based on capacitive-coupling computing (C3) (which is referred to herein as “C3SRAM”) is provided. In some embodiments, a C3SRAM macro can support array-level fully parallel computation, multi-bit outputs, and configurable multi-bit inputs. The macro can include circuits embedded in bitcells and peripherals to perform hardware acceleration for neural networks with binarized weights and activations in some embodiments. In some embodiments, the macro utilizes analog-mixed-signal capacitive-coupling computing to evaluate the main computations of binary neural networks, binary-multiply-and-accumulate operations. Without needing to access the stored weights by individual row, the macro can assert all of its rows simultaneously and form an analog voltage at the read bitline node through capacitive voltage division, in some embodiments. With one analog-to-digital converter (ADC) per column, the macro cab realize fully parallel vector-matrix multiplication in a single cycle in accordance with some embodiments.

The application provides a Content Addressable Memory (CAM) cell, a CAM memory device and an operation method thereof. The CAM cell includes: a plurality of parallel-coupled flash memory cells: wherein a storage data of the CAM cell is based on a combination of a plurality of threshold voltages of the parallel-coupled flash memory cells.

The application provides a Content Addressable Memory (CAM) cell, a CAM memory device and an operation method thereof. The CAM cell includes: a plurality of parallel-coupled flash memory cells: wherein a storage data of the CAM cell is based on a combination of a plurality of threshold voltages of the parallel-coupled flash memory cells.

An analog content addressable memory (aCAM) that enables parallel searching of analog ranges of values and generates analog outputs that quantify matches between input data and stored data is disclosed. The input data can be compared with the stored data, and the input data can be determined to match the stored data based on a value associated with the input data being within a range associated with the stored data. The aCAM can generate an analog output that represents a number of matches and a number of mismatches between the input data and the stored data. Based on the analog output, whether the input data matches the stored data and a degree to which the input data matches the stored data can be determined.