Abstract
Heterogeneous system-on-chips (SoC) can increase the energy-efficiency of domain-specific computation by orders of magnitude compared to scalar processors. High-performance systems can be generated procedurally through example-driven inference of a domain of computation to facilitate the design of domain-specific SoCs. This paper focuses on the domain of signal processing as it plays a recurring and important role in automation. The expertise required to build processors well-suited to a specific computation domain, rather than a single application or general computation, is inferred through the statistical analysis of computation, hardware, and their affinity for each other. This paper highlights the development of an ontological inference engine to achieve this goal.
| Original language | English (US) |
|---|---|
| Title of host publication | Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2018 |
| Editors | Raja Suresh |
| Publisher | SPIE |
| ISBN (Electronic) | 9781510626959 |
| DOIs | |
| State | Published - Jan 1 2019 |
| Event | 24th Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation Conference 2018 - Baltimore, United States Duration: Apr 16 2019 → Apr 18 2019 |
Publication series
| Name | Proceedings of SPIE - The International Society for Optical Engineering |
|---|---|
| Volume | 11015 |
| ISSN (Print) | 0277-786X |
| ISSN (Electronic) | 1996-756X |
Conference
| Conference | 24th Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation Conference 2018 |
|---|---|
| Country | United States |
| City | Baltimore |
| Period | 4/16/19 → 4/18/19 |
Fingerprint
Keywords
- Domain-specific SoC (DSSoC)
- Machine learning
- Ontological inference
- Parallel systems
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Cite this
Machine understanding of domain computation for Domain-Specific System-on-Chips (DSSoC). / Uhrie, Richard; Bliss, Daniel W.; Chakrabarti, Chaitali; Ogras, Umit Y.; Brunhaver, John.
Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2018. ed. / Raja Suresh. SPIE, 2019. 110150O (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11015).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Machine understanding of domain computation for Domain-Specific System-on-Chips (DSSoC)
AU - Uhrie, Richard
AU - Bliss, Daniel W.
AU - Chakrabarti, Chaitali
AU - Ogras, Umit Y.
AU - Brunhaver, John
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Heterogeneous system-on-chips (SoC) can increase the energy-efficiency of domain-specific computation by orders of magnitude compared to scalar processors. High-performance systems can be generated procedurally through example-driven inference of a domain of computation to facilitate the design of domain-specific SoCs. This paper focuses on the domain of signal processing as it plays a recurring and important role in automation. The expertise required to build processors well-suited to a specific computation domain, rather than a single application or general computation, is inferred through the statistical analysis of computation, hardware, and their affinity for each other. This paper highlights the development of an ontological inference engine to achieve this goal.
AB - Heterogeneous system-on-chips (SoC) can increase the energy-efficiency of domain-specific computation by orders of magnitude compared to scalar processors. High-performance systems can be generated procedurally through example-driven inference of a domain of computation to facilitate the design of domain-specific SoCs. This paper focuses on the domain of signal processing as it plays a recurring and important role in automation. The expertise required to build processors well-suited to a specific computation domain, rather than a single application or general computation, is inferred through the statistical analysis of computation, hardware, and their affinity for each other. This paper highlights the development of an ontological inference engine to achieve this goal.
KW - Domain-specific SoC (DSSoC)
KW - Machine learning
KW - Ontological inference
KW - Parallel systems
UR - http://www.scopus.com/inward/record.url?scp=85073911218&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073911218&partnerID=8YFLogxK
U2 - 10.1117/12.2519264
DO - 10.1117/12.2519264
M3 - Conference contribution
AN - SCOPUS:85073911218
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2018
A2 - Suresh, Raja
PB - SPIE
ER -