HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark

Abstract

HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous attention by automating the design of DNNs deployed in more resource-constrained daily life devices. Despite its promising performance, developing optimal HW-NAS solutions can be prohibitively challenging as it requires cross-disciplinary knowledge in the algorithm, micro-architecture, and device-specific compilation. First, to determine the hardware-cost to be incorporated into the NAS process, existing works mostly adopt either pre-collected hardware-cost look-up tables or device-specific hardware-cost models. Both of them limit the development of HW-NAS innovations and impose a barrier-to-entry to non-hardware experts. Second, similar to generic NAS, it can be notoriously difficult to benchmark HW-NAS algorithms due to their significant required computational resources and the differences in adopted search spaces, hyperparameters, and hardware devices. To this end, we develop HW-NAS-Bench, the first public dataset for HW-NAS research which aims to democratize HW-NAS research to non-hardware experts and make HW-NAS research more reproducible and accessible. To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i.e., commercial edge devices, FPGA, and ASIC). Furthermore, we provide a comprehensive analysis of the collected measurements in HW-NAS-Bench to provide insights for HW-NAS research. Finally, we demonstrate exemplary user cases to (1) show that HW-NAS-Bench allows non-hardware experts to perform HW-NAS by simply querying it and (2) verify that dedicated device-specific HW-NAS can indeed lead to optimal accuracy-cost trade-offs. The codes and all collected data are available at https://github.com/RICE-EIC/HW-NAS-Bench.

Accepted at ICLR 2021 (Spotlight)

References in corpus (11)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• DARTS: Differentiable Architecture Search
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• NAS evaluation is frustratingly hard
• AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
• A Systematic Approach to Blocking Convolutional Neural Networks
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
• S3NAS: Fast NPU-aware Neural Architecture Search Methodology
• Discovering Multi-Hardware Mobile Models via Architecture Search

Cited by in corpus (7)

• Towards Green Automated Machine Learning: Status Quo and Future Directions
• One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
• EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
• Discovering Multi-Hardware Mobile Models via Architecture Search
• Bag of Tricks for Neural Architecture Search
• NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters
• A multi-objective perspective on jointly tuning hardware and hyperparameters