In response to innovations in machine learning (ML) models, production workloads changed
radically and rapidly. TPU v4 is the fifth Google domain specific architecture (DSA) and its …

This article provides background information about interconnection networks, an analysis of
previous developments, and an overview of the state of the art. The main contribution of this …

TPUv4 (Tensor Processing Unit) is Google's 3rd generation accelerator for machine learning
training, deployed as a 4096-node supercomputer with a custom 3D torus interconnect. In …

This paper describes INSEE, a simulation framework developed at the University of the
Basque Country. INSEE is designed to carry out performance-related studies of …

The growing demand for performance observed in many organisations can still be
considered the main motivator for the evolution of high performance computing and, more …

Nowadays, the interconnection network is considered as an important architectural choice
for the future parallel system in many processors owing to the scalable nature of the …

In this work, using ab initio many-body theory and inspired by an idea suggested by GD
Mahan for an abstract N-dimensional chain composed of s-type atoms (Phys. Rev. Lett …

Torus network topology offers many advantages such as higher speed, lower latency, better
fairness, and lower energy consumption. For these kinds of benefits, nowadays, it is used to …

Massively parallel computers (MPCs) are currently being actively studied. Interconnection
networks are used for the connection of a significant number of processors in such parallel …

A complete family of Cayley graphs of degree four, denoted as L-networks, is considered in
this paper. L-networks are 2D mesh-based topologies with wrap-around connections. L …