Performance Characteristics of Large SMP Machines

Different types of shared memory machines with large core counts exist today. Standard x86-based servers are build with up to eight sockets per machine. To obtain larger machines, some companies, like SGI or Bull, invented special interconnects to couple a bunch of small servers into one larger SMP, Scalemp uses a special software layer on top of a standard cluster for the same purpose. There is also a trend to couple many small and simple cores into one chip, like in the Intel Xeon Phi chip. In this work we want to highlight different performance attributes of these machine types. Therefor we use some kernel benchmarks to look at basic performance characteristics and we compare the performance for real application codes. We will show different scaling behaviors for the applications which we explain with the use of the kernel benchmarks used before.

[1]  David H. Bailey,et al.  The Nas Parallel Benchmarks , 1991, Int. J. High Perform. Comput. Appl..

[2]  Carl Staelin,et al.  lmbench: Portable Tools for Performance Analysis , 1996, USENIX Annual Technical Conference.

[3]  Rudolf Eigenmann,et al.  SPEComp: A New Benchmark Suite for Measuring Parallel Computer Performance , 2001, WOMPAT.

[4]  C. Bischof,et al.  Nested OpenMP for Efficient Computation of 3D Critical Points in Multi-Block CFD Datasets , 2006, ACM/IEEE SC 2006 Conference (SC'06).

[5]  Lipo Wang,et al.  Dissipation element analysis of scalar fields in turbulence , 2006 .

[6]  J. M. Bull,et al.  Measuring Synchronisation and Scheduling Overheads in OpenMP , 2007 .

[7]  Bronis R. de Supinski,et al.  OpenMP Shared Memory Parallel Programming - International Workshops, IWOMP 2005 and IWOMP 2006, Eugene, OR, USA, June 1-4, 2005, Reims, France, June 12-15, 2006. Proceedings , 2008, IWOMP.

[8]  Alejandro Duran,et al.  Barcelona OpenMP Tasks Suite: A Set of Benchmarks Targeting the Exploitation of Task Parallelism in OpenMP , 2009, 2009 International Conference on Parallel Processing.

[9]  Dirk Schmidl,et al.  Towards NUMA Support with Distance Information , 2011, IWOMP.

[10]  William Gropp,et al.  OpenMP in the Petascale Era - 7th International Workshop on OpenMP, IWOMP 2011, Chicago, IL, USA, June 13-15, 2011. Proceedings , 2011, IWOMP.

[11]  Dirk Schmidl,et al.  Trajectory-Search on ScaleMP's vSMP Architecture , 2011, International Conference on Parallel Computing.