Macronix International Co., Ltd.

Hsiang-Lan Lung

Erh-Kun Lai

Chao-I Wu

Ming-Hsiu Lee

Chih-Hsiang Yang

Wei-Cheng Su

Yu-Hsuan Lin

Yu-Yu Lin

Tien-Yen Wang

Huai-Yu Cheng

I-Ting Kuo

Yen-Hao Shih

The application provides a method and a memory device for performing wear leveling in a memory device. The method includes: receiving data to be written transmitted by a host in the memory device; predicting the data to be written as a first type of data or a second type of data; referencing an erase count table in an erase count table buffer of the memory device; and when the data to be written is predicted as the first type of data, writing the data to be written into the block with a highest erase count among these blocks, and when the data to be written is predicted as the second type of data, writing the data to be written into the block with a lowest erase count among these blocks.

Method and memory device for performing wear leveling

A memory device includes a substrate, a first conductive stripe disposed on the substrate and extending along a first direction, a second conductive stripe disposed on the first conductive stripe, a first pillar element and a spacer. The second conductive stripe extends along a second direction intersected with the first direction. A thickness of the second conductive stripe is greater than a thickness of the first conductive stripe, and the second conductive stripe is an integral structure. The first pillar element is disposed at an intersection between the first conductive stripe and the second conductive stripe, and extends from a top surface of the first conductive stripe to a bottom surface of the second conductive stripe along a third direction intersected with the first direction and the second direction. The first pillar element includes a switching layer and a memory layer corresponding to a first level.

Memory device and method for manufacturing the same

An artificial neural network operation circuit and an in-memory computation device of the artificial neural network operation circuit are proposed. The in-memory computation device includes a memory cell array, a compensation memory cell string, and an operator. The memory cell array has a plurality of memory cells to store a plurality of weight values. The memory cell array has a plurality of word lines and a plurality of bit lines. Each compensation memory cell of the compensation memory cell string stores a unit weight value. The operator multiplies a signal on a compensation bit line by peak weight information of the weight values to generate a first signal and adds the first signal to each signal on the bit lines to obtain a plurality of computation results, respectively.

Artificial neural network operation circuit and in-memory computation device thereof

The application discloses a semiconductor memory device and a data storage method. When determining that an input data conforms to a target format, an input data vector is generated based on the input data. When determining that the input data is similar to a stored data in a target block of the memory array, the input data is written to a blank target memory page of the target block of the memory array.

Semiconductor memory device and data storage method thereof

An inductor structure and a manufacturing method for the same are provided. The inductor structure includes conductive layers and conductive elements. The conductive layers overlap in a vertical direction. Each of the conductive elements is coupled between two conductive layers of the conductive layers.

Growing community of inventors

Kaohsiung, Taiwan

Hsiang-Lan Lung