| MPI2007 license: | 4 | Test date: | Jan-2010 |
|---|---|---|---|
| Test sponsor: | SGI | Hardware Availability: | Sep-2009 |
| Tested by: | SGI | Software Availability: | Dec-2009 |
| 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 | 1024 | 131 | 29.7 | 122 | 31.8 | 123 | 31.8 | |||||||
| 122.tachyon | 1024 | 195 | 9.99 | 139 | 14.0 | 139 | 14.0 | |||||||
| 125.RAxML | 1024 | 272 | 10.7 | 271 | 10.8 | 271 | 10.8 | |||||||
| 126.lammps | 1024 | 103 | 23.9 | 102 | 24.1 | 102 | 24.1 | |||||||
| 128.GAPgeofem | 1024 | 225 | 26.4 | 237 | 25.0 | 249 | 23.8 | |||||||
| 129.tera_tf | 1024 | 101 | 10.9 | 95.9 | 11.5 | 96.4 | 11.4 | |||||||
| 132.zeusmp2 | 1024 | 75.1 | 28.2 | 74.8 | 28.3 | 76.5 | 27.7 | |||||||
| 137.lu | 1024 | 68.1 | 61.7 | 67.9 | 61.8 | 67.8 | 62.0 | |||||||
| 142.dmilc | 1024 | 54.5 | 67.5 | 54.5 | 67.6 | 54.3 | 67.9 | |||||||
| 143.dleslie | 1024 | 76.8 | 40.4 | 76.9 | 40.3 | 76.3 | 40.6 | |||||||
| 145.lGemsFDTD | 1024 | 121 | 36.5 | 121 | 36.3 | 120 | 36.7 | |||||||
| 147.l2wrf2 | 1024 | 213 | 38.5 | 217 | 37.8 | 212 | 38.7 | |||||||
| Hardware Summary | |
|---|---|
| Type of System: | Homogeneous |
| Compute Node: | SGI Altix ICE 8200EX Compute Node |
| Interconnects: | InfiniBand (MPI) InfiniBand (I/O) |
| File Server Node: | SGI InfiniteStorage Nexis 2000 NAS |
| Total Compute Nodes: | 128 |
| Total Chips: | 256 |
| Total Cores: | 1024 |
| Total Threads: | 2048 |
| Total Memory: | 4608 GB |
| Base Ranks Run: | 1024 |
| Minimum Peak Ranks: | -- |
| Maximum Peak Ranks: | -- |
| Software Summary | |
|---|---|
| C Compiler: | Intel C Compiler for Linux Version 11.1, Build 20091130 |
| C++ Compiler: | Intel C++ Compiler for Linux Version 11.1, Build 20091130 |
| Fortran Compiler: | Intel Fortran Compiler for Linux Version 11.1, Build 20091130 |
| Base Pointers: | 64-bit |
| Peak Pointers: | 64-bit |
| MPI Library: | SGI MPT 1.25 |
| Other MPI Info: | OFED-1.4.1 |
| Pre-processors: | None |
| Other Software: | None |
| Hardware | |
|---|---|
| Number of nodes: | 128 |
| Uses of the node: | compute |
| Vendor: | SGI |
| Model: | SGI Altix ICE 8200EX (Intel Xeon X5560, 2.80 GHz) |
| CPU Name: | Intel Xeon X5560 |
| CPU(s) orderable: | 1-2 chips |
| Chips enabled: | 2 |
| Cores enabled: | 8 |
| Cores per chip: | 4 |
| Threads per core: | 2 |
| CPU Characteristics: | Intel Turbo Boost Technology up to 3.2 GHz, 6.4 GT/s QPI, Hyper-Threading enabled |
| CPU MHz: | 2800 |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 256 KB I+D on chip per core |
| L3 Cache: | 8 MB I+D on chip per chip |
| Other Cache: | None |
| Memory: | 36 GB (6*4GB + 6*2GB DDR3-1333 CL9 RDIMMs running at 1066 MHZ. The 4GB DIMM is installed in DIMM slot A in each channel.) |
| Disk Subsystem: | None |
| Other Hardware: | None |
| Adapter: | Mellanox MT26418 ConnectX IB DDR (PCIe x8 Gen2 5 GT/s) |
| Number of Adapters: | 1 |
| Slot Type: | PCIe x8 Gen2 |
| Data Rate: | InfiniBand 4x DDR |
| Ports Used: | 2 |
| Interconnect Type: | InfiniBand |
| Software | |
|---|---|
| Adapter: | Mellanox MT26418 ConnectX IB DDR (PCIe x8 Gen2 5 GT/s) |
| Adapter Driver: | OFED-1.4.1 |
| Adapter Firmware: | 2.6.0 |
| Operating System: | SUSE Linux Enterprise Server 10 (x86_64) SP2 Kernel 2.6.16.60-0.30-smp |
| Local File System: | None |
| Shared File System: | NFSv3 IPoIB |
| System State: | Multi-user, run level 3 |
| Other Software: | SGI ProPack 6 for Linux Service Pack 5, SGI Tempo V 1.9 |
| Hardware | |
|---|---|
| Number of nodes: | 1 |
| Uses of the node: | fileserver |
| Vendor: | SGI |
| Model: | SGI Altix XE 240 (Intel Xeon 5140, 2.33 GHz) |
| CPU Name: | Intel Xeon 5140 |
| CPU(s) orderable: | 1-2 chips |
| Chips enabled: | 2 |
| Cores enabled: | 4 |
| Cores per chip: | 2 |
| Threads per core: | 1 |
| CPU Characteristics: | 1333 MHz FSB |
| CPU MHz: | 2333 |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 4 MB I+D on chip per chip |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 16 GB (8*2GB DDR2-667MHz DIMMS) |
| Disk Subsystem: | 4.3 TB RAID 5 48 x 146 GB SAS (Seagate Cheetah 15K.5) |
| Other Hardware: | None |
| Adapter: | Mellanox MT26418 ConnectX IB DDR (PCIe x8 Gen2 5 GT/s) |
| Number of Adapters: | 2 |
| Slot Type: | PCIe x8 Gen2 |
| Data Rate: | InfiniBand 4x DDR |
| Ports Used: | 2 |
| Interconnect Type: | InfiniBand |
| Software | |
|---|---|
| Adapter: | Mellanox MT26418 ConnectX IB DDR (PCIe x8 Gen2 5 GT/s) |
| Adapter Driver: | OFED-1.4.1 |
| Adapter Firmware: | 2.3.0 |
| Operating System: | SUSE Linux Enterprise Server 10 (x86_64) SP1 Kernel 2.6.16.54-0.2.5-smp |
| Local File System: | xfs |
| Shared File System: | -- |
| System State: | Multi-user, run level 3 |
| Other Software: | SGI ProPack 5 for Linux Service Pack 5 |
| Hardware | |
|---|---|
| Vendor: | Mellanox Technologies |
| Model: | MT26418 ConnectX |
| Switch Model: | Mellanox MT48436 InfiniScale-IV |
| Number of Switches: | 128 |
| Number of Ports: | 36 |
| Data Rate: | InfiniBand 4x QDR |
| Firmware: | 4020001 |
| Topology: | Bristle hypercube with double dimensional links |
| Primary Use: | MPI traffic |
| Hardware | |
|---|---|
| Vendor: | Mellanox Technologies |
| Model: | MT26418 ConnectX |
| Switch Model: | Mellanox MT48436 InfiniScale-IV |
| Number of Switches: | 64 |
| Number of Ports: | 36 |
| Data Rate: | InfiniBand 4x QDR |
| Firmware: | 4020001 |
| Topology: | Bristle hypercube with double dimensional links |
| Primary Use: | I/O traffic |
The config file option 'submit' was used.
Software environment:
export MPI_REQUEST_MAX=65536
export MPI_TYPE_MAX=32768
export MPI_BUFS_THRESHOLD=1
export MPI_DSM_DISTRIBUTE=yes
export MPI_IB_RAILS=2
ulimit -s unlimited
BIOS settings:
AMI BIOS version 8.15
Hyper-Threading Technology enabled (default)
Intel Turbo Boost Technology enabled (default)
Intel Turbo Boost Technology activated in the OS via
/etc/init.d/acpid start
/etc/init.d/powersaved start
powersave -f
Interconnect Data Rate:
The system interconnect has DDR InfiniBand HCAs,
while the switches and cables run up to QDR rate.
Job Placement:
Each MPI job was assigned to a topologically compact set
of nodes, i.e. the minimal needed number of switches was
used for each job: 2 switches for 16/32/64 ranks,
4 switches for 128 ranks, 8 switches for 256 ranks,
16 switches for 512 ranks, 32 switches for 1024 ranks,
64 switches for 2048 ranks and 128 switches for
4096 ranks.
| icc |
| 126.lammps: | icpc |
| ifort |
| icc ifort |
| 121.pop2: | -DSPEC_MPI_CASE_FLAG |