Benchmark Results

The following graph shows the efficiency/speedup of Cluster VM for Java on the applications described below: The benchmarks used are: N-Body Simulates the motion of n particles due to gravitational forces over ts number of simulation time steps, using m threads. n = 640, m = 4 and ts = 10 were used. The program follows the algorithm of Barnes & Hut in "A Hierarchical O(n log n) Force Calculation Algorithm" J. Barnes and P. Hut, Nature, v. 324(4), pages 446--449, December 1986. The N-Body benchmark pBOB Implements a TPC-C inspired business logic kernel. Creates m threads that generate transactions concurrently. m = 4 was used. In accordance with the TPC's fair use policy we note that pBOB deviates from the TPC-C specification and is not comparable to any official TPC results. A modified version of pBOB was adopted by SPEC as SPECjbb2000. SPECjbb2000 is not identical to pBOB. TSP Find in parallel the shortest route among n cities using m threads. n = 14 and m = 4 was used. The algorithm follows the one described in Richard M. Karp and Yanjun Zhang, "Randomized Parallel Algorithms for Backtrack Search and Branch-and-bound Computation", Journal of the ACM, 40(3):765-789, July 1993. The TSP benchmark