18331310. APPARATUS AND METHOD WITH IN-MEMORY COMPUTING simplified abstract (Samsung Electronics Co., Ltd.)
Contents
APPARATUS AND METHOD WITH IN-MEMORY COMPUTING
Organization Name
Inventor(s)
Yoonmyung Lee of Seongnam-si (KR)
APPARATUS AND METHOD WITH IN-MEMORY COMPUTING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18331310 titled 'APPARATUS AND METHOD WITH IN-MEMORY COMPUTING
The abstract describes an apparatus and method utilizing in-memory computing (IMC), where a self-timed circuit operates asynchronously with a clock to access memory rows based on input values.
- Memory includes rows, self-timed circuit has sub-circuits corresponding to rows, and a control circuit manages the self-timed circuit.
- Depending on input values, sub-circuits either skip accessing memory rows or perform operations on values and weights stored in memory to generate output signals.
- The apparatus allows for asynchronous operation and efficient processing of data based on input values and memory contents.
Potential Applications: - High-speed data processing applications - Real-time computing tasks - Artificial intelligence and machine learning algorithms
Problems Solved: - Improving processing speed and efficiency in computing tasks - Enabling asynchronous operation for better resource utilization - Enhancing memory access and data manipulation capabilities
Benefits: - Faster data processing and computation - Reduced latency in accessing and manipulating data - Improved performance in complex computing tasks
Commercial Applications: Title: "Advanced In-Memory Computing Apparatus for High-Speed Data Processing" This technology can be utilized in industries such as finance, healthcare, and telecommunications for real-time data analysis, pattern recognition, and predictive modeling. It can also benefit cloud computing providers by enhancing the efficiency of data processing and storage systems.
Prior Art: Readers can explore prior research on in-memory computing, asynchronous circuits, and memory access optimization to understand the evolution of this technology and its applications.
Frequently Updated Research: Stay updated on advancements in in-memory computing, asynchronous circuit design, and memory management techniques to leverage the latest innovations in high-speed data processing and computation.
Questions about In-Memory Computing: 1. How does in-memory computing differ from traditional computing methods? In-memory computing processes data directly in memory, eliminating the need to transfer data between memory and processing units, leading to faster computation.
2. What are the key advantages of using self-timed circuits in in-memory computing? Self-timed circuits allow for asynchronous operation, enabling efficient utilization of resources and reducing latency in data processing tasks.
Original Abstract Submitted
An apparatus and method with in-memory computing (IMC) is provided. An apparatus includes a memory including rows; a self-timed circuit including sub-circuits corresponding to the respective rows, and operates asynchronously with a clock; and a control circuit configured to control the self-timed circuit. Based on input to a first sub-circuit being a first value, the first sub-circuit skips accessing a first row of memory, corresponding to the first sub-circuit and transfer a first output signal received from a first neighboring sub-circuit, to a second neighboring sub-circuit among the sub-circuits. Based on input to the first sub-circuit being a second value, the first sub-circuit accesses the first row of memory, performs an operator-based operation on the second value and weights stored in the first row, generates a second output signal based on the performed operation, and transfers the second output signal to the second neighboring sub-circuit.