Growing compute capacity coupled with advances in parallel filesystem performance and stability mean that HPC users will inevitably create and store larger datasets. If data residing on parallel filesystems is not efficiently offloaded to archival storage, disruptions in the compute cycle will occur. Hierarchical storage caches are a vital aspect of the HPC storage machine because they offload and prime the compute engine's parallel filesystem. To keep pace with expanding HPC data systems, these caches must adapt via new scalable architectures. The Pittsburgh Supercomputing Center (PSC) has developed a cooperative caching architecture to act as a distributed front-end cache to a hierarchical storage manager. SLASH, the Scalable Lightweight Archival Storage Hierarchy, provides means for creating parallel caching systems on an otherwise "monolithic" archival storage system without requiring modifications the archival system software.