Highly irregular data accesses with hot spots on a coarse-grained parallel machine

This paper describes deterministic communication-efficient algorithms for performing highly irregular data accesses with hot spots on a coarse-grained parallel machine. The general random access read/write operations with hot spots can be completed in C μn/p (+ lower order terms) time and is optimal and scalable provided n⩾O(p ³+p²τ/μ) (n is the number of elements distributed across p processors, τ is the start-up overhead and 1/μ is the data transfer rate). C is a small constant between 3 and 4 for the random access write operation, slightly higher for the random access read operation. Monotonic random access reads/writes can be completed with smaller constants and are optimal for smaller n as well