# APEmille: a parallel processor in the teraflop range

## TL;DR

APEmille is a SIMD parallel processor designed for high-performance lattice QCD computations, achieving teraflop-scale performance with custom hardware and a specialized programming language.

## Contribution

The paper introduces APEmille, a novel SIMD parallel processor with a custom architecture and language optimized for lattice QCD applications, reaching teraflop performance.

## Key findings

- Peak performance of 800 Mflop at 100MHz per node
- Array of 2048 nodes can potentially reach Tflops performance
- Custom language TAO is optimized for QCD computations

## Abstract

APEmille is a SIMD parallel processor under development at the Italian National Institute for Nuclear Physics (INFN). APEmille is very well suited for Lattice QCD applications, both for its hardware characteristics and for its software and language features. APEmille is an array of custom arithmetic processors arranged on a tridimensional torus. The replicated processor is a pipelined VLIW device performing integer and single/double precision IEEE floating point operations. The processor is optimized for complex computations and has a peak performance of 528Mflop at 66MHz and of 800Mflop at 100MHz. In principle an array of 2048 nodes is able to break the Tflops barrier. A powerful programming language named TAO is provided and is highly optimized for QCD. A C++ compiler is foreseen. Specific data structures, operators and even statements can be defined by the user for each different application. Effort has been made to define the language constructs for QCD.