Microsoft technology licensing, llc (20240126617). DEEP FUSION OF KERNEL EXECUTION simplified abstract
Contents
- 1 DEEP FUSION OF KERNEL EXECUTION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DEEP FUSION OF KERNEL EXECUTION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
DEEP FUSION OF KERNEL EXECUTION
Organization Name
microsoft technology licensing, llc
Inventor(s)
Haishan Zhu of Bellevue WA (US)
Preyas Janak Shah of Tampa FL (US)
Tiyasa Mitra of San Jose CA (US)
Eric S. Chung of Woodinville WA (US)
DEEP FUSION OF KERNEL EXECUTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240126617 titled 'DEEP FUSION OF KERNEL EXECUTION
Simplified Explanation
The present disclosure involves configuring functional modules on a machine learning processor to execute multiple machine learning operations during different time segments. Some operations are processed serially while others are executed concurrently during the majority of each time segment.
- Machine learning processor configured for executing multiple machine learning operations during different time segments
- Some operations processed serially, while others executed concurrently during the majority of each time segment
Potential Applications
This technology can be applied in various fields such as natural language processing, image recognition, predictive analytics, and autonomous systems.
Problems Solved
This innovation addresses the challenge of optimizing machine learning processing by efficiently executing multiple operations in parallel during different time segments.
Benefits
- Improved efficiency in machine learning processing - Enhanced performance in executing multiple operations simultaneously - Increased speed and accuracy in processing complex data sets
Potential Commercial Applications
This technology can be utilized in industries such as healthcare for medical image analysis, finance for fraud detection, and manufacturing for predictive maintenance.
Possible Prior Art
One possible prior art could be the use of parallel processing techniques in machine learning to optimize performance and efficiency.
Unanswered Questions
How does this technology compare to existing parallel processing methods in machine learning?
This article does not provide a direct comparison to other parallel processing methods in machine learning.
What are the specific machine learning operations that can be executed concurrently during the majority of each time segment?
The article does not specify the exact machine learning operations that can be executed concurrently during the majority of each time segment.
Original Abstract Submitted
embodiments of the present disclosure include techniques for machine language processing. in one embodiment, the present disclosure includes configuring functional modules on a machine learning processor to execute a plurality of machine learning (ml) operations during a plurality of time segments. during the time segments, a first portion of the ml operations execute serially and at least one other ml operation executes during at least a majority of the time of each of the time segments. serial ml operations may be processed simultaneously with the at least one other ml operation.
