Related papers: A Highly Scalable LLM Clusters with Optical Interc…
Recent years have witnessed the growing deployment of optical circuit switches (OCS) in commercial GPU clusters (e.g., Google A3 GPU cluster) optimized for machine learning (ML) workloads. Such clusters adopt a three-tier leaf-spine-OCS…
Machine learning training places immense demands on cluster networks, motivating specialized architectures and co-design with parallelization strategies. Recent designs incorporating optical circuit switches (OCSes) are promising, offering…
Optical Circuit Switching (OCS) technology is increasingly being adopted in data centers due to its advantages of low power consumption and low technology refresh costs. Unlike electrical packet switches, OCS provides programmable bandwidth…
The development of a large scale quantum computer is a highly sought after goal of fundamental research and consequently a highly non-trivial problem. Scalability in quantum information processing is not just a problem of qubit…
The many cores design research community have shown high interest in optical crossbars on chip for more than a decade. Key properties of optical crossbars, namely a) contention free data routing b) low latency communication and c) potential…
Network connectedness is indispensable for the normal operation of transmission networks. However, there still remains a lack of efficient constraints that can be directly added to the problem formulation of optimal transmission switching…
Reconfigurable optical topologies are a promising new technology to improve datacenter network performance and cope with the explosive growth of traffic. In particular, these networks allow to directly and adaptively connect racks between…
This paper presents an algorithm to automatically design two-level fat-tree networks, such as ones widely used in large-scale data centres and cluster supercomputers. The two levels may each use a different type of switches from design…
The transient response of power grids to external disturbances influences their stable operation. This paper studies the effect of topology in linear time-invariant dynamics of different power grids. For a variety of objective functions, a…
This paper addresses the Optimal Transmission Switching (OTS) problem in electricity networks, which aims to find an optimal power grid topology that minimizes system operation costs while satisfying physical and operational constraints.…
This paper presents a highly efficient method to obtain high-resolution, near-optimal 3D topologies optimized for minimum compliance on a standard PC. Using an implicit geometry description we derive a single-scale interpretation of optimal…
The many cores design research community have shown high interest in optical crossbars on chip for more than a decade. Key properties of optical crossbars, namely a) contention-free data routing b) low-latency communication and c) potential…
In large-scale distributed LLM training, communication between devices becomes the key performance bottleneck. Chiplet technology can integrate multiple dies into a package to scale-up node performance with higher bandwidth. Meanwhile,…
Modern high-performance computing architectures (Multicore, GPU, Manycore) are based on tightly-coupled clusters of processing elements, physically implemented as rectangular tiles. Their size and aspect ratio strongly impact the achievable…
Designing high-performing networks requires optimizing for functionality while respecting physical, geometric, or budget constraints. Yet, mathematical and computational tools to design such systems remain limited, particularly for…
Topology optimization of modular structures and mechanisms enables balancing the performance of automatically-generated individualized designs, as required by Industry 4.0, with enhanced sustainability by means of component reuse. For…
The state-of-the-art topologies of datacenter networks are fixed, based on electrical switching technology, and by now, we understand their throughput and cost well. For the past years, researchers have been developing novel optical…
Recent proposals in multicast overlay construction have demonstrated the importance of exploiting underlying network topology. However, these topology-aware proposals often rely on incremental and periodic refinements to improve the system…
Topology optimization facilitates the automated design of high-performance structures across various engineering fields but, if unconstrained, often produces designs that are complex and difficult to manufacture. A key attribute of the…
Relying on the flexible-access interconnects to the scalable storage and compute resources, data centers deliver critical communications connectivity among numerous servers to support the housed applications and services. To provide the…