CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Analyzing Performance Improvements and Energy Savings in Infiniband Architecture using Network Compression

B. Dickov ; Miquel Pericàs (Institutionen för data- och informationsteknik, Datorteknik (Chalmers)) ; P.M. Carpenter ; N. Navarro ; E. Ayguade
Computer Architecture and High Performance Computing (SBAC-PAD), 2014 IEEE 26th International Symposium on (1550-6533). p. 73-80. (2014)
[Konferensbidrag, refereegranskat]

One of the greatest challenges in HPC is total system power and energy consumption. Whereas HPC interconnects have traditionally been designed with a focus on bandwidth and latency, there is an increasing interest in minimising the interconnect's energy consumption. This paper complements ongoing efforts related to power reduction and energy proportionality, by investigating the potential benefits from MPI data compression. We apply lossy compression to two common communication patterns in HPC kernels, in conjunction with recently introduced InfiniBand (IB) power saving modes. The results for the Alya CG kernel and Gromacs PME solver kernels show improvements in both performance and energy. While performance improvements are strongly influenced and changable depending on the type of communication pattern, energy savings in IB links are more consistent and proportional to achievable compression rates. We estimated an upper bound for link energy savings of up to 71% for the ALYA CG kernel, while for the Gromacs PME solver we obtained savings up to 63% compared to nominal energy when compression rate of 50% is used. We conclude that lossy compression is not always useful for performance improvements, but that it does reduce average IB link energy consumption

Nyckelord: Data Compression, MPI Performance, Network Energy Savings, Parallel Applications, Supercomputing

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2014-12-15. Senast ändrad 2017-10-05.
CPL Pubid: 208188


Läs direkt!

Länk till annan sajt (kan kräva inloggning)