The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have significantly mitigated the memory and computation bottleneck, they do so assuming high power platforms such as GPUs and server-class FPGAs with large off-chip memory bandwidths and employ a generalized matrix multiplication (GEMM) execution of all the layers in the decoder. In such a GEMM-based execution, data is fetched from an off-chip memory, computed and stored back. However, at reduced off-chip memory capacities, as is the case with low-power edge devices, this implementation strategy significantly increases the attention computation latency owing to the repeated storage and fetch of large intermediate tokens to and from the off-chip memory. Moreover, fetching the weight matrices from a bandwidth constrained memory further aggravates the memory bottleneck problem. To this end, we introduce MEADOW, a framework that significantly reduces the off-chip memory access for LLMs with a novel token-parallel head-sequential (TPHS) dataflow. Additionally, MEADOW applies weight packing that performs loss-less decomposition of large weight matrices to their unique elements thereby, reducing the enormous weight fetch latency. MEADOW demonstrates 1.5x and 2.5x lower decode and prefill latency, respectively, compared to a GEMM-based LLM implementation on the low power Xilinx ZCU102 FPGA platform that consumes less than 10W. Additionally, MEADOW achieves an end-to-end latency improvement of over 40%, compared to prior LLM optimization works.

Transformers have revolutionized various real-world applications from natural language processing to computer vision. However, traditional von-Neumann computing paradigm faces memory and bandwidth limitations in accelerating transformers owing to their massive model sizes. To this end, In-memory Computing (IMC) crossbars based on Non-volatile Memories (NVMs), due to their ability to perform highly parallelized Matrix-Vector-Multiplications (MVMs) with high energy-efficiencies, have emerged as a promising solution for accelerating transformers. However, analog MVM operations in crossbars introduce non-idealities, such as stochastic read & write noise, which affect the inference accuracy of the deployed transformers. Specifically, we find pre-trained Vision Transformers (ViTs) to be vulnerable on crossbars due to the impact of write noise on the dynamically-generated Key (K) and Value (V) matrices in the attention layers, an effect not accounted for in prior studies. We, thus, propose ClipFormer, a transformation on the K and V matrices during inference, to boost the non-ideal accuracies of pre-trained ViT models. ClipFormer requires no additional hardware and training overhead and is amenable to transformers deployed on any memristive crossbar platform. Our experiments on Imagenet-1k dataset using pre-trained DeiT-S transformers, subjected to standard training and variation-aware-training, show >10-40% higher non-ideal accuracies at the high write noise regime by applying ClipFormer.

In practical cloud-edge scenarios, where a resource constrained edge performs data acquisition and a cloud system (having sufficient resources) performs inference tasks with a deep neural network (DNN), adversarial robustness is critical for reliability and ubiquitous deployment. Adversarial detection is a prime adversarial defence technique used in prior literature. However, in prior detection works, the detector is attached to the classifier model and both detector and classifier work in tandem to perform adversarial detection that requires a high computational overhead which is not available at the low-power edge. Therefore, prior works can only perform adversarial detection at the cloud and not at the edge. This means that in case of adversarial attacks, the unfavourable adversarial samples must be communicated to the cloud which leads to energy wastage at the edge device. Therefore, a low-power edge-friendly adversarial detection method is required to improve the energy efficiency of the edge and robustness of the cloud-based classifier. To this end, RobustEdge proposes Quantization-enabled Energy Separation (QES) training with "early detection and exit" to perform edge-based low cost adversarial detection. The QES-trained detector implemented at the edge blocks adversarial data transmission to the classifier model, thereby improving adversarial robustness and energy-efficiency of the Cloud-Edge system.

In-Memory Computing (IMC) platforms such as analog crossbars are gaining focus as they facilitate the acceleration of low-precision Deep Neural Networks (DNNs) with high area- & compute-efficiencies. However, the intrinsic non-idealities in crossbars, which are often non-deterministic and non-linear, degrade the performance of the deployed DNNs. In addition to quantization errors, most frequently encountered non-idealities during inference include crossbar circuit-level parasitic resistances and device-level non-idealities such as stochastic read noise and temporal drift. In this work, our goal is to closely examine the distortions caused by these non-idealities on the dot-product operations in analog crossbars and explore the feasibility of a nearly training-less solution via crossbar-aware fine-tuning of batchnorm parameters in real-time to mitigate the impact of the non-idealities. This enables reduction in hardware costs in terms of memory and training energy for IMC noise-aware retraining of the DNN weights on crossbars.

Spiking Neural Networks (SNNs) have recently attracted widespread research interest as an efficient alternative to traditional Artificial Neural Networks (ANNs) because of their capability to process sparse and binary spike information and avoid expensive multiplication operations. Although the efficiency of SNNs can be realized on the In-Memory Computing (IMC) architecture, we show that the energy cost and latency of SNNs scale linearly with the number of timesteps used on IMC hardware. Therefore, in order to maximize the efficiency of SNNs, we propose input-aware Dynamic Timestep SNN (DT-SNN), a novel algorithmic solution to dynamically determine the number of timesteps during inference on an input-dependent basis. By calculating the entropy of the accumulated output after each timestep, we can compare it to a predefined threshold and decide if the information processed at the current timestep is sufficient for a confident prediction. We deploy DT-SNN on an IMC architecture and show that it incurs negligible computational overhead. We demonstrate that our method only uses 1.46 average timesteps to achieve the accuracy of a 4-timestep static SNN while reducing the energy-delay-product by 80%.

Due to increasing interest in adapting models on resource-constrained edges, parameter-efficient transfer learning has been widely explored. Among various methods, Visual Prompt Tuning (VPT), prepending learnable prompts to input space, shows competitive fine-tuning performance compared to training of full network parameters. However, VPT increases the number of input tokens, resulting in additional computational overhead. In this paper, we analyze the impact of the number of prompts on fine-tuning performance and self-attention operation in a vision transformer architecture. Through theoretical and empirical analysis we show that adding more prompts does not lead to linear performance improvement. Further, we propose a Prompt Condensation (PC) technique that aims to prevent performance degradation from using a small number of prompts. We validate our methods on FGVC and VTAB-1k tasks and show that our approach reduces the number of prompts by ~70% while maintaining accuracy.

Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute-efficiencies. However, the intrinsic non-idealities associated with the analog nature of computing in crossbars limits the performance of the deployed DNNs. Furthermore, DNNs are shown to be vulnerable to adversarial attacks leading to severe security threats in their large-scale deployment. Thus, finding adversarially robust DNN architectures for non-ideal crossbars is critical to the safe and secure deployment of DNNs on the edge. This work proposes a two-phase algorithm-hardware co-optimization approach called XploreNAS that searches for hardware-efficient & adversarially robust neural architectures for non-ideal crossbar platforms. We use the one-shot Neural Architecture Search (NAS) approach to train a large Supernet with crossbar-awareness and sample adversarially robust Subnets therefrom, maintaining competitive hardware-efficiency. Our experiments on crossbars with benchmark datasets (SVHN, CIFAR10 & CIFAR100) show upto ~8-16% improvement in the adversarial robustness of the searched Subnets against a baseline ResNet-18 model subjected to crossbar-aware adversarial training. We benchmark our robust Subnets for Energy-Delay-Area-Products (EDAPs) using the Neurosim tool and find that with additional hardware-efficiency driven optimizations, the Subnets attain ~1.5-1.6x lower EDAPs than ResNet-18 baseline.

With ever increasing depth and width in deep neural networks to achieve state-of-the-art performance, deep learning computation has significantly grown, and dot-products remain dominant in overall computation time. Most prior works are built on conventional dot-product where weighted input summation is used to represent the neuron operation. However, another implementation of dot-product based on the notion of angles and magnitudes in the Euclidean space has attracted limited attention. This paper proposes DeepCAM, an inference accelerator built on two critical innovations to alleviate the computation time bottleneck of convolutional neural networks. The first innovation is an approximate dot-product built on computations in the Euclidean space that can replace addition and multiplication with simple bit-wise operations. The second innovation is a dynamic size content addressable memory-based (CAM-based) accelerator to perform bit-wise operations and accelerate the CNNs with a lower computation time. Our experiments on benchmark image recognition datasets demonstrate that DeepCAM is up to 523x and 3498x faster than Eyeriss and traditional CPUs like Intel Skylake, respectively. Furthermore, the energy consumed by our DeepCAM approach is 2.16x to 109x less compared to Eyeriss.