18148259. MULTIPLY-ACCUMULATE SUCCESSIVE APPROXIMATION DEVICES AND METHODS simplified abstract (Robert Bosch GmbH)
Contents
MULTIPLY-ACCUMULATE SUCCESSIVE APPROXIMATION DEVICES AND METHODS
Organization Name
Inventor(s)
Kenneth Edward Wojciechowski of Cupertino CA (US)
Sangwoo Lee of Cupertino CA (US)
MULTIPLY-ACCUMULATE SUCCESSIVE APPROXIMATION DEVICES AND METHODS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18148259 titled 'MULTIPLY-ACCUMULATE SUCCESSIVE APPROXIMATION DEVICES AND METHODS
The abstract describes a Multiply-Accumulate Successive Approximation (MASAR) column, which consists of MASAR cells that perform digital multiplication and analog summation to determine a digital output.
- MASAR cells include multipliers for digital multiplication and unit capacitors for storing results as analog charge.
- Digital logic in the MASAR column performs analog summation of the analog charge from unit capacitors to calculate the digital output of the multiplication.
Potential Applications:
- Signal processing applications requiring efficient multiplication and accumulation.
- Neural network accelerators for fast and accurate computations.
- Digital signal processors for high-speed data processing.
Problems Solved:
- Efficiently performing multiplication and accumulation in a single column.
- Converting analog charge to digital output accurately.
- Enhancing the speed and accuracy of mathematical operations.
Benefits:
- Improved efficiency in multiplication and accumulation tasks.
- Faster processing speeds in signal processing applications.
- Enhanced accuracy in neural network computations.
Commercial Applications:
- Integrated circuits for signal processing systems.
- Hardware accelerators for artificial intelligence applications.
- High-performance computing devices for scientific simulations.
Prior Art: Prior research in the field of analog-digital conversion and signal processing systems may provide insights into similar technologies and approaches.
Frequently Updated Research: Stay updated on advancements in integrated circuit design, neural network accelerators, and digital signal processing techniques relevant to MASAR technology.
Questions about MASAR: 1. How does the MASAR column improve efficiency in multiplication and accumulation tasks? 2. What are the potential limitations of MASAR technology in complex mathematical computations?
Original Abstract Submitted
A multiply-accumulate successive approximation (MASAR) column is provided. The MASAR column includes a plurality of MASAR cells, each including a multiplier configured to perform digital multiplication between an input activation received to an input and an operand to compute a result, and a unit capacitor configured to store the result as analog charge. The MASAR column further includes digital logic configured to perform analog summation of the analog charge of the unit capacitors of the plurality of MASAR cells to determine a digital output of the multiplication.
