17515379. IN-MEMORY DATABASE (IMDB) ACCELERATION THROUGH NEAR DATA PROCESSING simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
IN-MEMORY DATABASE (IMDB) ACCELERATION THROUGH NEAR DATA PROCESSING
Organization Name
Inventor(s)
Andrew Zhenwen Chang of Los Altos CA (US)
Jaemin Jung of San Jose CA (US)
IN-MEMORY DATABASE (IMDB) ACCELERATION THROUGH NEAR DATA PROCESSING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17515379 titled 'IN-MEMORY DATABASE (IMDB) ACCELERATION THROUGH NEAR DATA PROCESSING
Simplified Explanation
The abstract describes an accelerator that includes an on-chip memory to store data from a database. The on-chip memory has two memory banks, with the first bank storing the data which includes a first value and a second value. A computational engine executes commands on both the first and second values in parallel. Additionally, the on-chip memory can load a second set of data from the database into the second memory bank while the computational engine is executing the commands.
- The accelerator has an on-chip memory with two memory banks.
- The first memory bank stores data from a database, including a first value and a second value.
- A computational engine executes commands on both the first and second values in parallel.
- The on-chip memory can load a second set of data from the database into the second memory bank while the computational engine is executing the commands.
Potential Applications
- High-performance computing
- Data analytics
- Artificial intelligence and machine learning
Problems Solved
- Efficient execution of commands on data stored in on-chip memory
- Simultaneous loading of data into memory while computation is ongoing
Benefits
- Improved performance and speed in executing commands on data
- Reduced latency in loading data into memory
- Enhanced efficiency in high-performance computing and data-intensive applications
Original Abstract Submitted
An accelerator is disclosed. The accelerator may include an on-chip memory to store a data from a database. The on-chip memory may include a first memory bank and a second memory bank. The first memory bank may store the data, which may include a first value and a second value. A computational engine may execute, in parallel, a command on the first value in the data and the command on the second value in the data in the on-chip memory. The on-chip memory may be configured to load a second data from the database into the second memory bank in parallel with the computation engine executing the command on the first value in the data and executing the command on the second value in the data.