DEVICE AND METHOD WITH IN-MEMORY COMPUTING

Organization Name

samsung electronics co., ltd.

Inventor(s)

Wooseok Yi of Suwon-si (KR)

Soon-Wan Kwon of Suwon-si (KR)

Seungchul Jung of Suwon-si (KR)

DEVICE AND METHOD WITH IN-MEMORY COMPUTING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240231757 titled 'DEVICE AND METHOD WITH IN-MEMORY COMPUTING

Simplified Explanation

The memory device described in the patent application includes a computing module and an in-memory computing (imc) macro. The imc macro consists of a memory with bit cells storing fraction data from a first data set. An imc computing module performs operations between the fraction data from the first data set and fraction data from a second data set.

The memory device has a computing module and an in-memory computing macro.
The memory stores fraction data from a first data set in bit cells.
An imc computing module operates on the fraction data from the first data set and a second data set.
Pieces of data in the first set share a common exponent, as do pieces in the second set.

Key Features and Innovation

Utilizes in-memory computing for processing data directly within the memory.
Operates on fraction data from different data sets efficiently.
Shares exponents among pieces of data to streamline computations.
Enhances performance and speed of data processing tasks.

Potential Applications

The technology can be applied in:

High-performance computing systems
Data analytics and processing applications
Artificial intelligence and machine learning tasks
Financial modeling and simulations
Scientific research and calculations

Problems Solved

Improves efficiency in processing large datasets.
Reduces the need for data movement between memory and processing units.
Enhances accuracy and precision in mathematical computations.
Speeds up complex calculations involving fractions.

Benefits

Faster data processing and computation speeds.
Reduced energy consumption due to in-memory computing.
Improved accuracy and reliability in mathematical operations.
Enhanced performance in various computing tasks.

Commercial Applications

The technology can be utilized in supercomputers, data centers, and cloud computing environments.
It can benefit industries such as finance, healthcare, research, and engineering.
Offers a competitive edge in high-performance computing markets.
Enables real-time data analysis and decision-making processes.

Questions about the Technology

What are the potential drawbacks of in-memory computing in this context?

In-memory computing may require specialized hardware and software, leading to higher initial costs for implementation. Additionally, the complexity of managing data directly in memory could pose challenges for some applications.

How does sharing exponents among pieces of data improve computational efficiency?

Sharing exponents allows for streamlined operations on data with similar characteristics, reducing the computational overhead of handling different exponents individually. This optimization enhances the overall performance of the memory device.

Original Abstract Submitted

a memory device includes: a computing module; and an in-memory computing (imc) macro comprising: a memory comprising a plurality of bit cells storing pieces of fraction data of a first data set; and an imc computing module configured to perform an operation between the pieces of fraction data of the first data set read from the memory and pieces of fraction data of a second data set received from an input control module, wherein a plurality of pieces of data included in the first data set share a first exponent, and wherein a plurality of pieces of data included in the second data set share a second exponent.