In this technical report we describe a storage system aimed on supporting collaborative applications in large-scale environments that include mobile computers. To maximize availability, it uses weakly consistent server replication and client caching with a read any/write any model of data access. To allow easy management of concurrent updates it provides an object framework that isolates the pr...

We present TritonSort, a highly efficient, scalable sorting system. It is designed to process large datasets, and has been evaluated against as much as 100 TB of input data spread across 832 disks in 52 nodes at a rate of 0.916 TB/min. When evaluated against the annual Indy GraySort sorting benchmark, TritonSort is 60% better in absolute performance and has over six times the per-node efficienc...

This paper presents a large scale audio fingerprinting system, which can be used to retrieve intended song from more than a million audio tracks. A time offset of several milliseconds could cause a number of audio fingerprints disappear. To decrease this effect, the query clip is converted to several copies with different start times. The audio fingerprints are mapped to hashes. Based on the st...

This paper describes a software tool called GROMIT and associated methods being developed by the Statistical Sciences Group (D-1) at Los Alamos National Laboratory in support of determining dependency structures describing large system behavior. While focused on the problem of reliability prediction, the discussion is relevant to other analytic situations such as determining the actors and beha...