MPI2007 license: | 13 | Test date: | May-2015 |
---|---|---|---|
Test sponsor: | Intel Corporation | Hardware Availability: | May-2015 |
Tested by: | Pavel Shelepugin | Software Availability: | Apr-2015 |
Benchmark | Base | Peak | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Ranks | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Ranks | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | |
Results appear in the order in which they were run. Bold underlined text indicates a median measurement. | ||||||||||||||
121.pop2 | 576 | 183 | 21.3 | 180 | 21.7 | 180 | 21.6 | |||||||
122.tachyon | 576 | 173 | 11.2 | 150 | 13.0 | 149 | 13.1 | |||||||
125.RAxML | 576 | 173 | 16.9 | 174 | 16.8 | 173 | 16.9 | |||||||
126.lammps | 576 | 138 | 17.8 | 136 | 18.0 | 137 | 18.0 | |||||||
128.GAPgeofem | 576 | 210 | 28.2 | 209 | 28.3 | 211 | 28.1 | |||||||
129.tera_tf | 576 | 100 | 11.0 | 99.8 | 11.0 | 100 | 11.0 | |||||||
132.zeusmp2 | 576 | 106 | 19.9 | 106 | 19.9 | 106 | 20.0 | |||||||
137.lu | 576 | 89.4 | 47.0 | 89.4 | 47.0 | 89.1 | 47.1 | |||||||
142.dmilc | 576 | 146 | 25.2 | 146 | 25.2 | 146 | 25.2 | |||||||
143.dleslie | 576 | 111 | 27.8 | 111 | 27.9 | 112 | 27.8 | |||||||
145.lGemsFDTD | 576 | 161 | 27.5 | 161 | 27.4 | 161 | 27.4 | |||||||
147.l2wrf2 | 576 | 289 | 28.4 | 288 | 28.4 | 289 | 28.4 |
Hardware Summary | |
---|---|
Type of System: | Homogeneous |
Compute Node: | Endeavor Node |
Interconnects: | IB Switch Gigabit Ethernet |
File Server Node: | NFS |
Total Compute Nodes: | 8 |
Total Chips: | 32 |
Total Cores: | 576 |
Total Threads: | 1152 |
Total Memory: | 4 TB |
Base Ranks Run: | 576 |
Minimum Peak Ranks: | -- |
Maximum Peak Ranks: | -- |
Software Summary | |
---|---|
C Compiler: | Intel C++ Composer XE 2015 for Linux, Version 15.0.3.187 Build 20150407 |
C++ Compiler: | Intel C++ Composer XE 2015 for Linux, Version 15.0.3.187 Build 20150407 |
Fortran Compiler: | Intel Fortran Composer XE 2015 for Linux, Version 15.0.3.187 Build 20150407 |
Base Pointers: | 64-bit |
Peak Pointers: | 64-bit |
MPI Library: | Intel MPI Library 5.0.3.048 for Linux |
Other MPI Info: | None |
Pre-processors: | No |
Other Software: | None |
Hardware | |
---|---|
Number of nodes: | 8 |
Uses of the node: | compute |
Vendor: | Intel |
Model: | S4TR2KU1Q |
CPU Name: | Intel Xeon E7-8890 v3 |
CPU(s) orderable: | 1-4 chips |
Chips enabled: | 4 |
Cores enabled: | 72 |
Cores per chip: | 18 |
Threads per core: | 2 |
CPU Characteristics: | Intel Turbo Boost Technology up to 3.3 GHz, 9.6 GT/s QPI, Hyper-Threading enabled |
CPU MHz: | 2500 |
Primary Cache: | 32 KB I + 32 KB D on chip per core |
Secondary Cache: | 256 KB I+D on chip per core |
L3 Cache: | 45 MB I+D on chip per chip, 45 MB shared / 18 cores |
Other Cache: | None |
Memory: | 512 GB (32 x 16 GB 2Rx4 PC4-17000R-15, ECC) |
Disk Subsystem: | ATA INTEL SSDSA2BZ20, SSDSC2BB80 |
Other Hardware: | None |
Adapter: | Intel (ESB2) 82575EB Dual-Port Gigabit Ethernet Controller |
Number of Adapters: | 1 |
Slot Type: | PCI-Express x8 |
Data Rate: | 1Gbps Ethernet |
Ports Used: | 2 |
Interconnect Type: | Ethernet |
Adapter: | Mellanox MCX353A-FCAT ConnectX-3 |
Number of Adapters: | 1 |
Slot Type: | PCIe x8 Gen3 |
Data Rate: | InfiniBand 4x FDR |
Ports Used: | 1 |
Interconnect Type: | InfiniBand |
Software | |
---|---|
Adapter: | Intel (ESB2) 82575EB Dual-Port Gigabit Ethernet Controller |
Adapter Driver: | e1000 |
Adapter Firmware: | None |
Adapter: | Mellanox MCX353A-FCAT ConnectX-3 |
Adapter Driver: | OFED 3.5-2-MIC-rc1 |
Adapter Firmware: | 2.31.5050 |
Operating System: | Red Hat EL 6.5, kernel 2.6.32-358 |
Local File System: | Linux/xfs |
Shared File System: | NFS |
System State: | Multi-User |
Other Software: | IBM Platform LSF Standard 9.1.1.1 |
Hardware | |
---|---|
Number of nodes: | 1 |
Uses of the node: | fileserver |
Vendor: | Intel |
Model: | S7000FC4UR |
CPU Name: | Intel Xeon CPU |
CPU(s) orderable: | 1-4 chips |
Chips enabled: | 4 |
Cores enabled: | 16 |
Cores per chip: | 4 |
Threads per core: | 2 |
CPU Characteristics: | -- |
CPU MHz: | 2926 |
Primary Cache: | 32 KB I + 32 KB D on chip per core |
Secondary Cache: | 8 MB I+D on chip per chip, 4 MB shared / 2 cores |
L3 Cache: | None |
Other Cache: | None |
Memory: | 64 GB |
Disk Subsystem: | 8 disks, 500GB/disk, 2.7TB total |
Other Hardware: | None |
Adapter: | Intel 82563GB Dual-Port Gigabit Ethernet Controller |
Number of Adapters: | 1 |
Slot Type: | PCI-Express x8 |
Data Rate: | 1Gbps Ethernet |
Ports Used: | 1 |
Interconnect Type: | Ethernet |
Software | |
---|---|
Adapter: | Intel 82563GB Dual-Port Gigabit Ethernet Controller |
Adapter Driver: | e1000e |
Adapter Firmware: | N/A |
Operating System: | RedHat EL 5 Update 4 |
Local File System: | None |
Shared File System: | NFS |
System State: | Multi-User |
Other Software: | None |
Hardware | |
---|---|
Vendor: | Mellanox |
Model: | Mellanox MSX6025F-1BFR |
Switch Model: | Mellanox MSX6025F-1BFR |
Number of Switches: | 46 |
Number of Ports: | 36 |
Data Rate: | InfiniBand 4x FDR |
Firmware: | 9.2.8000 |
Topology: | Fat tree |
Primary Use: | MPI traffic |
Hardware | |
---|---|
Vendor: | Force10 Networks, Cisco Systems |
Model: | Force10 S50N, Force10 C300, Cisco WS-C4948E-F |
Switch Model: | Force10 S50N, Force10 C300, Cisco WS-C4948E-F |
Number of Switches: | 13 |
Number of Ports: | 48 |
Data Rate: | 1Gbps Ethernet, 10Gbps Ethernet |
Firmware: | 8.3.2.0, 12.2(54)WO |
Topology: | Star |
Primary Use: | Cluster File System |
The config file option 'submit' was used.
MPI startup command: mpiexec.hydra command was used to start MPI jobs. BIOS settings: Intel Hyper-Threading Technology (SMT): Enabled (default is Enabled) Intel Turbo Boost Technology (Turbo) : Enabled (default is Enabled) RAM configuration: Compute nodes have 4x16-GB RDIMM on each memory channel. Network: Forty six 36-port switches: 18 core switches and 28 leaf switches. Each leaf has one link to each core. Remaining 18 ports on 25 of 28 leafs are used for compute nodes. On the remaining 3 leafs the ports are used for FS nodes and other peripherals. Job placement: Each MPI job was assigned to a topologically compact set of nodes, i.e. the minimal needed number of leaf switches was used for each job: 1 switch for 144/288/576 ranks. IBM Platform LSF was used for job submission. It has no impact on performance. Information can be found at: http://www.ibm.com
mpiicc |
126.lammps: | mpiicpc |
mpiifort |
mpiicc mpiifort |
121.pop2: | -DSPEC_MPI_CASE_FLAG |
126.lammps: | -DMPICH_IGNORE_CXX_SEEK |