apenext: A Multi-Tflops LQCD Computing Project

TL;DR

The paper proposes the apeNEXT project, aiming to build large-scale, multi-TFlops lattice QCD computing engines with high sustained performance for advanced scientific simulations.

Contribution

It introduces the design and motivation for a next-generation LQCD computing system with multi-TFlops performance, advancing computational capabilities in lattice QCD research.

Findings

Design concepts for multi-TFlops LQCD engines

Projected peak performance of tens of TFlops

Expected sustained performance of about 50% of peak on key kernels

Abstract

This paper is a slightly modified and reduced version of the proposal of the {\bf apeNEXT} project, which was submitted to DESY and INFN in spring 2000. .It presents the basic motivations and ideas of a next generation lattice QCD (LQCD) computing project, whose goal is the construction and operation of several large scale Multi-TFlops LQCD engines, providing an integrated peak performance of tens of TFlops, and a sustained (double precision) performance on key LQCD kernels of about 50% of peak speed.