In the wake of the success of convolutional neural networks in image classification, object recognition, speech recognition, etc., the demand for deploying these compute-intensive ML models on embedded and mobile systems with tight power and energy constraints at low cost, as well as for boosting throughput in data centers, is growing rapidly. This has sparked a surge of research into specialized hardware accelerators. Their performance is typically limited by I/O bandwidth, power consumption is dominated by I/O transfers to off-chip memory, and on-chip memories occupy a large part of the silicon area.We introduce and evaluate a novel, hardware-friendly, and lossless compression scheme for the feature maps present within convolutional neural networks. We present hardware architectures and synthesis results for the compressor and decompressor in 65 nm. With a throughput of one 8-bit word/cycle at 600 MHz, they fit into 2.8 kGE and 3.0 kGE of silicon area, respectivelytogether the size of less than seven 8-bit multiply-add units at the same throughput.We show that an average compression ratio of 5.1× for AlexNet, 4× for VGG-16, 2.4× for ResNet-34 and 2.2× for MobileNetV2 can be achieved-a gain of 45-70% over existing methods. Our approach also works effectively for various number formats, has a low frame-to-frame variance on the compression ratio, and achieves compression factors for gradient map compression during training that are even better than for inference.

We present a 3.1 POp/s/W fully digital hardware accelerator for ternary neural networks. CUTIE, the Completely Unrolled Ternary Inference Engine, focuses on minimizing noncomputational energy and switching activity so that dynamic power spent on storing (locally or globally) intermediate results is minimized. This is achieved by 1) a data path architecture completely unrolled in the feature map and filter dimensions to reduce switching activity by favoring silencing over iterative computation and maximizing data re-use, 2) targeting ternary neural networks which, in contrast to binary NNs, allow for sparse weights which reduce switching activity, and 3) introducing an optimized training method for higher sparsity of the filter weights, resulting in a further reduction of the switching activity. Compared with state-of-the-art accelerators, CUTIE achieves greater or equal accuracy while decreasing the overall core inference energy cost by a factor of 4.8×-21×.

Tiny Machine Learning (TinyML) applications impose µJ/Inference constraints, with maximum power consumption of a few tens of mW. It is extremely challenging to meet these requirement at a reasonable accuracy level. In this work, we address this challenge with a flexible, fully digital Ternary Neural Network (TNN) accelerator in a RISC-V-based SoC. The design achieves 2.72 µJ/Inference, 12.2 mW, 3200 Inferences/sec at 0.5 V for a non-trivial 9-layer, 96 channels-per-layer network with CIFAR-10 accuracy of 86 %. The peak energy efficiency is 1036 TOp/s/W, outperforming the state-of-the-art in silicon-proven TinyML accelerators by 1.67x.

No abstract