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

• Branimir Dickov Universitat Politècnica de Catalunya / Barcelona Supercomputing Center
• Miquel Pericàs Chalmers University of Technology
• Paul M. Carpenter Barcelona Supercomputing Center
• Nacho Navarro Universitat Politècnica de Catalunya / Barcelona Supercomputing Center
• Eduard Ayguadé Universitat Politècnica de Catalunya / Barcelona Supercomputing Center

Resumo

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.

Palavras-chave: Data compression, Kernel, Bandwidth, Power demand, Energy consumption, Switches, Computer architecture, Parallel Applications, Data Compression, Supercomputing, MPI Performance, Network Energy Savings