Abstract As part of the DOE SciDAC ”National Infrastructure for

operates production clusters for lattice QCD simulations. This paper will describe these clusters. The design of lattice QCD clusters requires careful at-tention to balancing memory bandwidth, floating point throughput, and network performance. We will discuss our investigations of various commodity processors, including Pentium 4E, Xeon, Opteron, and PPC970. We will also discuss our early experiences with the emerging Infiniband and PCI Express architectures. Finally, we will present our predictions and plans for future clusters. CURRENT PRODUCTION CLUSTERS The production clusters for lattice QCD simulations at Fermilab all share a common architecture. User access to these facilities always occurs through a head node, which resides on the public internet, and well as on the clus