|
|
|
|
LEADER |
03047nmm a2200361 u 4500 |
001 |
EB002182019 |
003 |
EBX01000000000000001319506 |
005 |
00000000000000.0 |
007 |
cr||||||||||||||||||||| |
008 |
231010 ||| eng |
020 |
|
|
|a 9783031382307
|
100 |
1 |
|
|a Jain, Vikram
|
245 |
0 |
0 |
|a Towards Heterogeneous Multi-core Systems-on-Chip for Edge Machine Learning
|h Elektronische Ressource
|b Journey from Single-core Acceleration to Multi-core Heterogeneous Systems
|c by Vikram Jain, Marian Verhelst
|
250 |
|
|
|a 1st ed. 2024
|
260 |
|
|
|a Cham
|b Springer Nature Switzerland
|c 2024, 2024
|
300 |
|
|
|a XXIII, 186 p. 93 illus., 83 illus. in color
|b online resource
|
505 |
0 |
|
|a Chapter 1: Introduction -- Chapter 2 Algorithmic Background for Machine Learning -- Chapter 3 Scoping the Landscape of (Extreme) Edge Machine Learning Processors -- Chapter 4 Hardware-Software Co-optimization through Design Space Exploration -- Chapter 5 Energy Efficient Single-core Hardware Acceleration -- Chapter 6 TinyVers: A Tiny Versatile All-Digital Heterogeneous Multi-core System-on-Chip -- Chapter 7 DIANA: Digital and ANAlog Heterogeneous Multi-core System-on-Chip -- Chapter 8 Networks-on-chip to Enable Large-scale Multi-core ML Acceleration -- Chapter 9 Conclusion
|
653 |
|
|
|a Machine learning
|
653 |
|
|
|a Embedded Systems
|
653 |
|
|
|a Embedded computer systems
|
653 |
|
|
|a Machine Learning
|
653 |
|
|
|a Electronic circuits
|
653 |
|
|
|a Processor Architectures
|
653 |
|
|
|a Microprocessors
|
653 |
|
|
|a Electronic Circuits and Systems
|
653 |
|
|
|a Computer architecture
|
700 |
1 |
|
|a Verhelst, Marian
|e [author]
|
041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
989 |
|
|
|b Springer
|a Springer eBooks 2005-
|
028 |
5 |
0 |
|a 10.1007/978-3-031-38230-7
|
856 |
4 |
0 |
|u https://doi.org/10.1007/978-3-031-38230-7?nosfx=y
|x Verlag
|3 Volltext
|
082 |
0 |
|
|a 6,213,815
|
520 |
|
|
|a This book explores and motivates the need for building homogeneous and heterogeneous multi-core systems for machine learning to enable flexibility and energy-efficiency. Coverage focuses on a key aspect of the challenges of (extreme-)edge-computing, i.e., design of energy-efficient and flexible hardware architectures, and hardware-software co-optimization strategies to enable early design space exploration of hardware architectures. The authors investigate possible design solutions for building single-core specialized hardware accelerators for machine learning and motivates the need for building homogeneous and heterogeneous multi-core systems to enable flexibility and energy-efficiency. The advantages of scaling to heterogeneous multi-core systems are shown through the implementation of multiple test chips and architectural optimizations. Discusses the need for scaling to multi-core systems for machine learning and several architectural and software optimizations; Covers single-core, homogeneous and heterogeneous multi-core Systems-on-chip for machine learning applications; Discusses the benefits of heterogeneity in the context of machine learning.
|