Related papers: FlexiNS: A SmartNIC-Centric, Line-Rate and Flexibl…

The rapid evolution of Large Language Models (LLMs) towards long-context reasoning and sparse architectures has pushed memory requirements far beyond the capacity of individual device HBM. While emerging supernode architectures offer…

Contemporary distributed computing workloads, including scientific computation, data mining, and machine learning, increasingly demand OS networking with minimal latency as well as high throughput, security, and reliability. However,…

Many distributed applications implement complex data flows and need a flexible mechanism for routing data between producers and consumers. Recent advances in programmable network interface cards, or SmartNICs, represent an opportunity to…

To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\in\{1,2\}$) of powers of 2. In such…

Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in…

Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…

Emerging deep neural network (DNN) applications require high-performance multi-core hardware acceleration with large data bursts. Classical network-on-chips (NoCs) use serial packet-based protocols suffering from significant protocol…

The deployment of ultra-dense networks (UDNs), particularly cell-free massive MIMO (CF-mMIMO), is mainly hindered by costly and capacity-limited fronthaul links. This work proposes a two-tiered optimization framework for cost-effective…

Emerging 5G/6G use cases span various industries, necessitating flexible solutions that leverage emerging technologies to meet diverse and stringent application requirements under changing network conditions. The standard 5G RAN solution,…

Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem,…

Recurrent Neural Network (RNN) applications form a major class of AI-powered, low-latency data center workloads. Most execution models for RNN acceleration break computation graphs into BLAS kernels, which lead to significant inter-kernel…

Neural Networks (NN) provide a solid and reliable way of executing different types of applications, ranging from speech recognition to medical diagnosis, speeding up onerous and long workloads. The challenges involved in their…

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

Neuromorphic accelerators promise unparalleled energy efficiency and computational density for spiking neural networks (SNNs), especially in edge intelligence applications. However, most existing platforms exhibit rigid architectures with…

Direct-attached accelerators, where application accelerators are directly connected to the datacenter network via a hardware network stack, offer substantial benefits in terms of reduced latency, CPU overhead, and energy use. However, a key…

FPGA overlays are commonly implemented as coarse-grained reconfigurable architectures with a goal to improve designers' productivity through balancing flexibility and ease of configuration of the underlying fabric. To truly facilitate full…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

It is important to design compact language models for efficient deployment. We improve upon recent advances in both the language modeling domain and the model-compression domain to construct parameter and computation efficient language…

Deep neural network inference accelerators are rapidly growing in importance as we turn to massively parallelized processing beyond GPUs and ASICs. The dominant operation in feedforward inference is the multiply-and-accumlate process, where…