Related papers: Enabling the Reflex Plane with the nanoPU

The nanoPU is a new networking-optimized CPU designed to minimize tail latency for RPCs. By bypassing the cache and memory hierarchy, the nanoPU directly places arriving messages into the CPU register file. The wire-to-wire latency through…

Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. This has sparked recent development of microcontroller-scale…

Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…

In this paper we show that the data plane of commodity programmable (Network Interface Cards) NICs can run neural network inference tasks required by packet monitoring applications, with low overhead. This is particularly important as the…

It is commonly believed that datacenter networking software must sacrifice generality to attain high performance. The popularity of specialized distributed systems designed specifically for niche technologies such as RDMA, lossless…

Large scale cloud data analytics applications are often CPU bound. Most of these cycles are wasted: benchmarks written in C++ run 10-51 times faster than frameworks such as Naiad and Spark. However, calling faster implementations from those…

Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This…

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often…

Emerging applications -- cloud computing, the internet of things, and augmented/virtual reality -- demand responsive, secure, and scalable datacenter networks. These networks currently implement simple, per-packet, data-plane heuristics…

The granularity of distributed computing is limited by communication time: there is no point in farming out smaller and smaller tasks if the communication overhead dominates the decrease in processing time due to the added parallelism. In…

The server central processing unit (CPU) market continues to exhibit robust demand due to the rising global need for computing power. Against this backdrop, CPU benchmark performance prediction is crucial for architecture designers. It…

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…

Packet classification is a vital and complicated task as the processing of packets should be done at a specified line speed. In order to classify a packet as belonging to a particular flow or set of flows, network nodes must perform a…

Neural Processing Units (NPUs) are key to enabling efficient AI inference in resource-constrained edge environments. While peak tera operations per second (TOPS) is often used to gauge performance, it poorly reflects real-world performance…

Machine learning applications are computationally demanding and power intensive. Hardware acceleration of these software tools is a natural step being explored using various technologies. A recurrent processing unit (RPU) is fast and…

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized…

Next-generation datacenters require highly efficient network load balancing to manage the growing scale of artificial intelligence (AI) training and general datacenter traffic. However, existing Ethernet-based solutions, such as Equal Cost…

This paper presents SHARP (Supercomputing for High-speed Avoidance and Reactive Planning), a proof-of-concept study demonstrating how high-performance computing (HPC) can enable millisecond-scale responsiveness in robotic control. While…

The increasing need for compact and low-power computing solutions for machine learning applications has triggered significant interest in energy-efficient neuromorphic systems. However, most of these architectures rely on spiking neural…

The rapidly growing computational demands of deep neural networks require novel hardware designs. Recently, tunable nanoelectronic devices were developed based on hopping electrons through a network of dopant atoms in silicon. These "Dopant…