Performance Numbers of MVAPICH on Opteron Barcelona Platform (11/14/08)

• Experimental Testbed: Each node of our testbed has 16 AMD Opteron 1.95 Ghz processors with 512 KB L2 cache. Each node also has 16 Gigabyte memory and PCI-Express bus. They are equipped with MT25418 HCAs with PCI-Ex interfaces. A 24-port Mellanox switch is used to connect all the nodes. The operating system used was RedHat Enterprise Linux Server 5.

• MVAPICH currently delivers the following performance: one-way latency of 0.52 microsec and unidirectional bandwidth of up to 1271 Million Bytes/sec for intra-chip transfer; one-way latency of 0.70 microsec and unidirectional bandwidth of up to 1246 Million Bytes/sec for intra-socket (1-hop) transfer; one-way latency of 0.87 microsec and unidirectional bandwidth of up to 1151 Million Bytes/sec for inter-socket (2-hops) transfer on the above testbed. (1 Mega Byte = 1,048,576 Bytes; 1 Million Byte = 1,000,000 Bytes)