Ohio State University

Sandy Bridge | IntraNode | Performance | Network-Based Computing Laboratory

Intra-node performance numbers of MVAPICH2 on Sandy Bridge Architecture (05/06/13)

  • Experimental Testbed: Each node of our testbed has two 8-core 2.6 GHz Intel Xeon E5-2670 (Sandy Bridge) processors and 32 GB main memory. The nodes support 16x PCI Express Gen3 interfaces and are equipped with Mellanox ConnectX FDR HCAs with PCI Express Gen3 interfaces. The operating system used was RedHat Enterprise Linux Server release 5.4 (Tikanga). The processes were bound to core 1 on both nodes
  • MVAPICH2 currently delivers one-way latency of .19 microseconds within the socket for 4 bytes and .44 microseconds between sockets for 4 bytes; unidirectional bandwidth upto 12143.15 Million Bytes/sec within the socket and 11841.00 Million Bytes/sec between sockets; bidirectional bandwidth upto 22513.80 Million Bytes/sec within the socket, 22340.98 Million Bytes/sec between sockets on the above testbed. (1 Mega Byte = 1,048,576 Bytes; 1 Million Byte = 1,000,000 Bytes)
  • Processes were mapped onto cores 1 and 2 to take the intra socket numbers and onto 1 and 9 to take the inter socket numbers.