New research paper titled “Deep Reinforcement Learning Enabled Self-Configurable Networks-on-Chip for High-Performance and Energy-Efficient Computing Systems” from Md Farhadur Reza at Eastern Illinois University.
Find the open access technical paper here. Published June 2022.
M. F. Reza, “Deep Reinforcement Learning Enabled Self-Configurable Networks-on-Chip for High-Performance and Energy-Efficient Computing Systems,” in EEE Access, 2022, doi: 10.1109/ACCESS.2022.3182500.
Visit Semiconductor Engineering’s Technical Paper library here and discover many more chip industry academic papers.
Further Reading:
Optimizing NoC-Based Designs
Further optimization of RTL repartitioning with switching from crossbar interconnects to NoCs.
How To Optimize A Processor
There are at least three architectural layers to processor design, each of which plays a significant role.
AI-Based Method To Prune The Design Space Of Heterogeneous NoCs
Researchers propose “an approach based on generative AI to help pruning complex design spaces for heterogeneous NoCs, according to configurable performance objectives.”
100% inspection, more data, and traceability will reduce assembly defects plaguing automotive customer returns.
Engineers are finding ways to effectively thermally dissipate heat from complex modules.
Increased transistor density and utilization are creating memory performance issues.
Lots of unknowns will persist for decades across multiple market segments.
FPGAs, CPUs, and equipment receive funding in China; 98 startups raise over $2 billion.
Suppliers are investing new 300mm capacity, but it’s probably not enough. And despite burgeoning 200mm demand, only Okmetic and new players in China are adding capacity.
100% inspection, more data, and traceability will reduce assembly defects plaguing automotive customer returns.
From low resistance vias to buried power rails, it takes multiple strategies to usher in 2nm chips.
Some of the less common considerations for assessing the suitability of a system for high-performance workloads.
Manufacturing 3D structures will require atomic-level control of what’s removed and what stays on a wafer.
Different interconnect standards and packaging options being readied for mass chiplet adoption.
Engineers are finding ways to effectively thermally dissipate heat from complex modules.
Disaggregation and the wind-down of Moore’s Law have changed everything.
Leave a Reply