Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
Mohanad Odema, Luke Chen, Hyoukjun Kwon, Mohammad Abdullah Al Faruque
University of California, Irvine, USA
We study the application of emerging chiplet-based Neural Processing Units to accelerate vehicular AI perception workloads in constrained automotive settings. The motivation stems from how chiplets technology is becoming integral to emerging vehicular architectures, providing a cost-effective trade-off between performance, modularity, and customization; and from perception models being the most computationally demanding workloads in a autonomous driving system. Using the Tesla Autopilot perception pipeline as a case study, we first breakdown its constituent models and profile their performance on different chiplet accelerators. From the insights, we propose a novel scheduling strategy to efficiently deploy perception workloads on multi-chip AI accelerators. Our experiments using a standard DNN performance simulator, MAESTRO, show our approach realizes 82% and 2.8x increase in throughput and processing engines utilization compared to monolithic accelerator designs.
Related Technical Papers
- Multi-Chiplet Marvels: Exploring Chip-Centric Thermal Analysis
- SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
- Chiplets on Wheels : Review Paper on holistic chiplet solutions for autonomous vehicles
- MFIT : Multi-FIdelity Thermal Modeling for 2.5D and 3D Multi-Chiplet Architectures
Latest Technical Papers
- Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
- ChipAI: A scalable chiplet-based accelerator for efficient DNN inference using silicon photonics
- Advanced Packaging and Chiplets Can Be for Everyone
- Interfacing silicon photonics for high-density co-packaged optics
- System-Technology Co-Optimization for Dense Edge Architectures using 3D Integration and Non-Volatile Memory