Related papers: Demystifying Datapath Accelerator Enhanced Off-pat…

As deep neural networks develop significantly more diverse and complex, achieving high performance and efficiency on complicated DNN models faces pressing challenges. Modern DNN workloads are increasingly diverse in operation types, tensor…

With the advent of programmable network hardware, more and more functionality can be moved from software running on general purpose CPUs to the NIC. Early NICs only allowed offloading fixed functions like checksum computation. Recent NICs…

Indirect memory accesses frequently appear in applications where memory bandwidth is a critical bottleneck. Prior indirect memory access proposals, such as indirect prefetchers, runahead execution, fetchers, and decoupled access/execute…

Host CPU resources are heavily consumed by TCP stack processing, limiting scalability in data centers. Existing offload methods typically address only partial functionality or lack flexibility. This paper introduces PnO (Plug & Offload), an…

Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it minimizes data movement and provides large computational parallelism. Similar to machine learning accelerators, application mapping, which determines the…

Next generation high-performance RDMA-capable networks will require a fundamental rethinking of the design and architecture of modern distributed DBMSs. These systems are commonly designed and optimized under the assumption that the network…

The future of artificial intelligence (AI) acceleration demands a paradigm shift beyond the limitations of purely electronic or photonic architectures. Photonic analog computing delivers unmatched speed and parallelism but struggles with…

Latency and energy consumption are key metrics in the performance of deep neural network (DNN) accelerators. A significant factor contributing to latency and energy is data transfers. One method to reduce transfers or data is reusing data…

Federated learning is a distributed machine learning approach where local weight parameters trained by clients locally are aggregated as global parameters by a server. The global parameters can be trained without uploading privacy-sensitive…

The explosively growing communication traffic in datacenters imposes increasingly stringent performance requirements on the underlying networks. Over the last years, researchers have developed innovative optical switching technologies that…

Dataflow scheduling decisions are of vital importance to neural network (NN) accelerators. Recent scalable NN accelerators support a rich set of advanced dataflow techniques. The problems of comprehensively representing and quickly finding…

This work evaluates the benefits of using a "smart" network interface card (SmartNIC) as a compute accelerator for the example of the MiniMD molecular dynamics proxy application. The accelerator is NVIDIA's BlueField-2 card, which includes…

Hardware accelerators for neural networks have shown great promise for both performance and power. These accelerators are at their most efficient when optimized for a fixed functionality. But this inflexibility limits the longevity of the…

Multipath forwarding consists of using multiple paths simultaneously to transport data over the network. While most such techniques require endpoint modifications, we investigate how multipath forwarding can be done inside the network,…

Network function (NF) offloading on SmartNICs has been widely used in modern data centers, offering benefits in host resource saving and programmability. Co-running NFs on the same SmartNICs can cause performance interference due to…

Modern organizations manage their data with a wide variety of specialized cloud database engines (e.g., Aurora, BigQuery, etc.). However, designing and managing such infrastructures is hard. Developers must consider many possible designs…

Non-uniform quantization, such as power-of-two (PoT) quantization, matches data distributions better than uniform quantization, which reduces the quantization error of Deep Neural Networks (DNNs). PoT quantization also allows bit-shift…

The growing volume of data in modern applications has led to significant computational costs in conventional processor-centric systems. Processing-in-memory (PIM) architectures alleviate these costs by moving computation closer to memory,…

Responding to the "datacenter tax" and "killer microseconds" problems for datacenter applications, diverse solutions including Smart NIC-based ones have been proposed. Nonetheless, they often suffer from high overhead of communications over…

Deep learning and signal processing are closely correlated in many IoT scenarios such as anomaly detection to empower intelligence of things. Many IoT processors utilize digital signal processors (DSPs) for signal processing and build deep…