# Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems

arXiv: https://arxiv.org/abs/1810.08869 · HTML: https://mlsanity.com/paper/1810.08869/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2018.

## Built on by (most cited first, 8 of 8)

- [A Survey of Machine Learning for Computer Architecture and Systems](https://mlsanity.com/paper/2102.07952/) (2021)
- [Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2110.06980/) (2021)
- [Preference-Aware Constrained Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2303.13034/) (2023)
- [SHIELD: Sustainable Hybrid Evolutionary Learning Framework for Carbon, Wastewater, and Energy-Aware Data Center Management](https://mlsanity.com/paper/2308.13086/) (2023)
- [HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration](https://mlsanity.com/paper/2408.03397/) (2024)
- [MOELA: A Multi-Objective Evolutionary/Learning Design Space Exploration Framework for 3D Heterogeneous Manycore Platforms](https://mlsanity.com/paper/2303.06169/) (2023)
- [PerOS: Personalized Self-Adapting Operating Systems in the Cloud](https://mlsanity.com/paper/2404.00057/) (2024)
- [ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts](https://mlsanity.com/paper/2607.17074/) (2026)

## Abstract (arXiv)

The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a promising direction. However, as systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it becomes more pertinent to address the distinct and likely conflicting communication requirements (e.g., CPU memory access latency or GPU network throughput) that arise from such heterogeneity. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate tradeoffs between these heterogeneous requirements. To address these challenges, we propose the design of a 3D Network-on-Chip (NoC) for heterogeneous manycore platforms that considers the appropriate design objectives for a 3D heterogeneous system and explores various tradeoffs using an efficient ML-based multi-objective optimization technique. The proposed design space exploration considers the various requirements of its heterogeneous components and generates a set of 3D NoC architectures that efficiently trades off these design objectives. Our findings show that by jointly considering these requirements (latency, throughput, temperature, and energy), we can achieve 9.6% better Energy-Delay Product on average at nearly iso-temperature conditions when compared to a thermally-optimized design for 3D heterogeneous NoCs. More importantly, our results suggest that our 3D NoCs optimized for a few applications can be generalized for unknown applications as well. Our results show that these generalized 3D NoCs only incur a 1.8% (36-tile system) and 1.1% (64-tile system) average performance loss compared to application-specific NoCs.