Commercial server applications remain memory bound on modern multiprocessor systems because of their large data footprints, frequent sharing, complex non-strided access patterns, and long chains of dependant misses. To improve memory system performance despite these challenging access patterns, researchers have proposed prefetchers that exploit temporal streams-recurring sequences of memory accesses. Although prior studies show substantial performance improvement from such schemes, they fail to explain why temporal streams arise; that is, they treat commercial applications as a black box and do not identify the specific behaviors that lead to recurring miss sequences. In this paper, we perform an information-theoretic analysis of miss traces from single-chip and multi-chip multiprocessors to identify recurring temporal streams in web serving, online transaction processing, and decision support workloads. Then, using function names embedded in the application binaries and Solaris kernel, we identify the code modules and behaviors that give rise to temporal streams.