View source for 17726086. COMPUTE-IN-MEMORY DEVICE AND METHOD simplified abstract (TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD.)

=COMPUTE-IN-MEMORY DEVICE AND METHOD=


==Organization Name==

[[:Category:TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD.|TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD.]]


[[Category:TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD.]]

==Inventor(s)==

[[:Category:Chieh Lee of Hsinchu (TW)|Chieh Lee of Hsinchu (TW)]][[Category:Chieh Lee of Hsinchu (TW)]]

[[:Category:Chia-En Huang of Hsinchu (TW)|Chia-En Huang of Hsinchu (TW)]][[Category:Chia-En Huang of Hsinchu (TW)]]

[[:Category:Yi-Ching Liu of Hsinchu (TW)|Yi-Ching Liu of Hsinchu (TW)]][[Category:Yi-Ching Liu of Hsinchu (TW)]]

[[:Category:Wen-Chang Cheng of Hsinchu (TW)|Wen-Chang Cheng of Hsinchu (TW)]][[Category:Wen-Chang Cheng of Hsinchu (TW)]]

[[:Category:Yih Wang of Hsinchu (TW)|Yih Wang of Hsinchu (TW)]][[Category:Yih Wang of Hsinchu (TW)]]

==COMPUTE-IN-MEMORY DEVICE AND METHOD - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17726086 titled 'COMPUTE-IN-MEMORY DEVICE AND METHOD

==Simplified Explanation==

The patent application describes an integrated circuit device that includes a memory module with a three-dimensional array of memory cells. Each memory cell can store a weight value and generate a signal based on the product of the stored weight value and an input signal.

* The integrated circuit device has an active semiconductor layer with circuitry formed within it.
* Above the active semiconductor layer, there is a region with conductive layers.
* The memory module is formed in this region and consists of a three-dimensional array of memory cells.
* Each memory cell can store a weight value and generate a signal based on the product of the stored weight value and an input signal.
* The memory module can transmit the product signals from the memory cells simultaneously towards the active semiconductor layer.

== Potential Applications ==
* Artificial intelligence and machine learning systems
* Neural networks and deep learning algorithms
* Pattern recognition and image processing
* Data analysis and optimization algorithms

== Problems Solved ==
* Efficient storage and processing of weight values in memory cells
* Simultaneous transmission of product signals for faster computation
* Integration of memory and processing capabilities in a single device

== Benefits ==
* Improved performance and speed in AI and machine learning applications
* Reduced power consumption and energy efficiency
* Compact and integrated design for space-saving in electronic devices
* Faster data processing and analysis capabilities


==Original Abstract Submitted==

In some embodiments, an integrated circuit (IC) device includes an active semiconductor layer, a circuitry formed within the active semiconductor layer, a region including conductive layers formed above the active semiconductor layer, and a memory module formed in the region. The memory device includes a three-dimensional array of memory cells, each adapted to store a weight value, and adapted to generate at each memory cell a signal indicative of a product between the stored weight value and an input signal applied to the memory cell. The memory module is further adapted to transmit the product signals from the memory cell simultaneously in the direction of the active semiconductor layer.



[[Category:H01L27/11597]]
[[Category:G11C11/22]]
[[Category:H01L27/11587]]
[[Category:H01L27/1159]]
[[Category:H01L27/11592]]
[[Category:G11C5/04]]
[[Category:G11C5/06]]