Related papers: Switch-Less Dragonfly on Wafers: A Scalable Interc…
Transformer-based large language models are increasingly constrained by data movement as communication bandwidth drops sharply beyond the chip boundary. Wafer-scale integration using wafer-on-wafer hybrid bonding alleviates this limitation…
Much like classical supercomputers, scaling up quantum computers requires an optical interconnect. However, signal attenuation leads to irreversible qubit loss, making quantum interconnect design guidelines and metrics different from…
Multichip systems with memory stacks and various processing chips are at the heart of platform based designs such as servers and embedded systems. Full utilization of the benefits of these integrated multichip systems need a seamless, and…
Neuromorphic computing promises brain-like efficiency, yet today's multi-chip systems scale over PCBs and incur orders-of-magnitude penalties in bandwidth, latency, and energy, undermining biological algorithms and system efficiency. We…
Dragonfly interconnect is a crucial network technology for supercomputers. To support exascale systems, network resources are shared such that links and routers are not dedicated to any node pair. While link utilization is increased,…
Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallelization strategy. However, high-performance compute and…
The need for wireless communication has driven the communication systems to high performance. However, the main bottleneck that affects the communication capability is the Fast Fourier Transform (FFT), which is the core of most modulators.…
Multi-plane architectures have become increasingly prevalent in the Fat-Tree networks of AI data centers. By leveraging multiple ports on a single network interface card (NIC) or multiple NICs within a scale-up domain, each port or NIC is…
Hierarchical ring networks, which hierarchically connect multiple levels of rings, have been proposed in the past to improve the scalability of ring interconnects, but past hierarchical ring designs sacrifice some of the key benefits of…
There are increasing number of works addressing the design challenges of fast, scalable solutions for the growing number of new type of applications. Recently, many of the solutions aimed at improving processing element capabilities to…
Novel low-diameter network topologies such as Slim Fly (SF) offer significant cost and power advantages over the established Fat Tree, Clos, or Dragonfly. To spearhead the adoption of low-diameter networks, we design, implement, deploy, and…
To interconnect their growing number of servers, current supercomputers and data centers are starting to adopt low-diameter networks, such as HyperX, Dragonfly and Dragonfly+. These emergent topologies require balancing the load over their…
The Dragonfly topology is currently one of the most popular network topologies in high-performance parallel systems. The interconnection networks of many of these systems are built from components based on the InfiniBand specification.…
The interconnect is one of the most critical components in large scale computing systems, and its impact on the performance of applications is going to increase with the system size. In this paper, we will describe Slingshot, an…
Virtual channel flow control is the de facto choice for modern networks-on-chip to allow better utilization of the link bandwidth through buffering and packet switching, which are also the sources of large power footprint and long per-hop…
Increasingly large AI workloads are calling for hyper-scale infrastructure; however, traditional interconnection network architecture is neither scalable nor cost-effective enough. Tree-based topologies such as the \textit{Rail-optimized}…
The main design principles in computer architecture have recently shifted from a monolithic scaling-driven approach to the development of heterogeneous architectures that tightly co-integrate multiple specialized processor and memory…
We introduce a high-performance cost-effective network topology called Slim Fly that approaches the theoretically optimal network diameter. Slim Fly is based on graphs that approximate the solution to the degree-diameter problem. We analyze…
Conventional hybrid beamforming architectures are often compared with one another and with the fully-digital architecture under the same \emph{radiated} antenna power. However, the physically relevant budget is the power injected by the…
In today's data centers, the performance of interconnects plays a pivotal role. However, many of the underlying technologies for these interconnects have a history of several decades and existed long before data centers came into being.To…