Abstract | ||
---|---|---|
The number of cores in future CPUs is expected to increase steadily. Balanced CPU designs scale hardware cache coherency functionality according to the number of cores, in order to minimize bottlenecks in parallel applications. An alternative approach is to do away with hardware coherence entirely; the Single-chip Cloud Computer (SCC), a 48 core experimental processor from Intel labs, does exactly that. A wait-free protocol for message passing on non-coherent buffers was introduced with the RCKMPI library, in order to support MPI on the SCC. In this work, the message passing performance of the protocol is modeled. Additionally, a port for symmetric multi-processors is introduced and used for comparison with MPICH2-Nemesis and Open MPI. Performance is analyzed based on statistics collected on a 4-dimensional space composed of source rank, target rank, message size and frequency. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33518-1_19 | EuroMPI |
Keywords | Field | DocType |
scale hardware cache coherency,4-dimensional space,non-coherent shared memory architecture,open mpi,hardware coherence,source rank,wait-free message,wait-free protocol,balanced cpu,message size,intel lab,target rank,message passing,communication protocol,mpi | Shared memory,MESIF protocol,Computer science,Parallel computing,Message broker,Coherence (physics),Message passing,Cache coherence,Cloud computing,Communications protocol | Conference |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Isaías A. Comprés Ureña | 1 | 28 | 2.25 |
Michael Gerndt | 2 | 570 | 83.39 |
Carsten Trinitis | 3 | 151 | 29.80 |