SPEC® MPIM2007 Result

Copyright 2006-2010 Standard Performance Evaluation Corporation

Dell Inc.

PowerEdge M620 (Intel Xeon E5-2680, 2.70 GHz,
DDR3-1600 MHz

SPECmpiM_peak2007 = Not Run

MPI2007 license: 25 Test date: May-2012
Test sponsor: Dell Hardware Availability: Mar-2012
Tested by: Burton Finley Software Availability: Sep-2011
Benchmark results graph

Results Table

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.
104.milc 256 37.7 41.6 31.7 49.4 31.7 49.4
107.leslie3d 256 126   41.4 126   41.5 126   41.4
113.GemsFDTD 256 197   32.0 198   31.9 197   32.1
115.fds4 256 24.5 79.7 24.3 80.4 24.2 80.5
121.pop2 256 255   16.2 259   16.0 260   15.9
122.tachyon 256 60.4 46.3 61.0 45.9 61.0 45.9
126.lammps 256 114   25.5 114   25.6 117   24.9
127.wrf2 256 91.2 85.5 90.9 85.8 90.8 85.9
128.GAPgeofem 256 33.9 60.9 33.8 61.1 34.6 59.6
129.tera_tf 256 67.6 41.0 67.7 40.9 70.6 39.2
130.socorro 256 58.8 64.9 58.8 64.9 61.7 61.9
132.zeusmp2 256 49.9 62.2 49.9 62.2 50.2 61.9
137.lu 256 45.1 81.6 45.1 81.6 45.2 81.4
Hardware Summary
Type of System: Homogeneous
Compute Node: PowerEdge M620
Interconnects: IB Switch
Gigabit Ethernet
File Server Node: PowerEdge R410
Total Compute Nodes: 16
Total Chips: 32
Total Cores: 256
Total Threads: 256
Total Memory: 1 TB
Base Ranks Run: 256
Minimum Peak Ranks: --
Maximum Peak Ranks: --
Software Summary
C Compiler: Intel C++ Composer XE 2011 for Linux, Version
12.0.5.220 Build 20110719
C++ Compiler: Intel C++ Composer XE 2011 for Linux, Version
12.0.5.220 Build 20110719
Fortran Compiler: Intel Fortran Composer XE 2011 for Linux, Version
12.0.5.220 Build 20110719
Base Pointers: 64-bit
Peak Pointers: 64-bit
MPI Library: Intel MPI Library 4.0.3.008 Build 20110824 for
Linux
Other MPI Info: None
Pre-processors: No
Other Software: None

Node Description: PowerEdge M620

Hardware
Number of nodes: 16
Uses of the node: compute
Vendor: Dell
Model: PowerEdge M620 Installed in PowerEdge M1000e
blade chassis
CPU Name: Intel Xeon E5-2680
CPU(s) orderable: 1-2 chips
Chips enabled: 2
Cores enabled: 16
Cores per chip: 8
Threads per core: 1
CPU Characteristics: Intel Turbo Boost Technology up to 3.5 GHz,
8.0 GT/s QPI, Hyper-Threading disabled
CPU MHz: 2700
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 256 KB I+D on chip per core
L3 Cache: 20 MB I+D on chip per chip, 20 MB shared / 8 cores
Other Cache: None
Memory: 64 GB (8 x 8 GB 2Rx4 PC3-12800R-11, ECC)
Disk Subsystem: Seagate 146 GB SAS ST9146803SS
Other Hardware: None
Adapter: Onboard Intel X520-k
Ethernet Controller
Number of Adapters: 1
Slot Type: PCI-Express x16
Data Rate: 1Gbps Ethernet
Ports Used: 1
Interconnect Type: Ethernet
Adapter: Mellanox ConnectX2 Quad Data Rate IB PCIe 2.0
(Installed in Fabric C)
Number of Adapters: 1
Slot Type: PCIe x8 Gen2
Data Rate: InfiniBand 4x QDR
Ports Used: 1
Interconnect Type: InfiniBand
Software
Adapter: Onboard Intel X520-k
Ethernet Controller
Adapter Driver: 3.4.8-k
Adapter Firmware: 13.1.9
Adapter: Mellanox ConnectX2 Quad Data Rate IB PCIe 2.0
(Installed in Fabric C)
Adapter Driver: MLNX_OFED_LINUX-1.5.3-3.0.0-rhel6.2-x86_64
Adapter Firmware: 2.9.1000
Operating System: Red Hat EL 6.2, kernel 2.6.32-220.el6.x86_64
Local File System: Linux/ext2
Shared File System: NFS
System State: Multi-User
Other Software: None

Node Description: PowerEdge R410

Hardware
Number of nodes: 1
Uses of the node: fileserver
Vendor: Intel
Model: PowerEdge R410
CPU Name: Intel Xeon X5570 CPU
CPU(s) orderable: 1-2 chips
Chips enabled: 2
Cores enabled: 8
Cores per chip: 4
Threads per core: 1
CPU Characteristics: N/A
CPU MHz: 2930
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: 32 GB
Disk Subsystem: 1 disks, 500GB/disk
Other Hardware: None
Adapter: Dual port Broadcom BCM 5716
Ethernet Controller
Number of Adapters: 1
Slot Type: Integrated
Data Rate: 1Gbps Ethernet
Ports Used: 1
Interconnect Type: Ethernet
Software
Adapter: Dual port Broadcom BCM 5716
Ethernet Controller
Adapter Driver: 2.1.11
Adapter Firmware: 9-6.2.0.17.fw
Operating System: Red Hat EL 6.2, kernel 2.6.32-220.el6.x86_64
Local File System: None
Shared File System: NFS
System State: Multi-User
Other Software: None

Interconnect Description: IB Switch

Hardware
Vendor: Mellanox
Model: Mellanox M3601Q
Switch Model: Mellanox M3601Q Installed in PowerEdge M1000e
blade chassis (Installed in slot C1)
Number of Switches: 1
Number of Ports: 32
Data Rate: InfiniBand 4x QDR
Firmware: 7.4.0000
Topology: Fat tree
Primary Use: MPI traffic

Interconnect Description: Gigabit Ethernet

Hardware
Vendor: Dell Inc.
Model: Intel X520-k Ethernet Controller
Switch Model: PowerConnect M6220 (Modular Layer 3 blade switch
for PowerEdge M1000e blade chassis) in slot A1
Number of Switches: 1
Number of Ports: 20
Data Rate: 1Gbps Ethernet
Firmware: 3.1.3.9
Topology: Fat tree
Primary Use: Cluster File System

Submit Notes

The config file option 'submit' was used.

General Notes

130.socorro (base): "nullify_ptrs" src.alt was used.

 MPI startup command:
   mpiexec.hydra command was used to start MPI jobs.

 BIOS settings:
   Intel Hyper-Threading Technology (SMT): Disabled (default is Enabled)
   Intel Turbo Boost Technology (Turbo)  : Enabled (default is Enabled)

 RAM configuration:
   Compute nodes have 2x8-GB RDIMM on each memory channel.

 Network:
   One 20-port switch

 Compute Node Environment:
   ulimit -s = unlimited
   ulimit -l = unlimited
   File "/etc/modprobe.d/mlx4_core.conf" modified to contain "options
   mlx4_core log_mtts_per_seg=5"






Base Compiler Invocation

C benchmarks:

 mpiicc 

C++ benchmarks:

126.lammps:  mpiicpc 

Fortran benchmarks:

 mpiifort 

Benchmarks using both Fortran and C:

 mpiicc   mpiifort 

Base Portability Flags

121.pop2:  -DSPEC_MPI_CASE_FLAG 
126.lammps:  -DMPICH_IGNORE_CXX_SEEK 
127.wrf2:  -DSPEC_MPI_CASE_FLAG   -DSPEC_MPI_LINUX 

Base Optimization Flags

C benchmarks:

 -O3   -xAVX   -no-prec-div 

C++ benchmarks:

126.lammps:  -O3   -xAVX   -no-prec-div 

Fortran benchmarks:

 -O3   -xAVX   -no-prec-div 

Benchmarks using both Fortran and C:

 -O3   -xAVX   -no-prec-div 

The flags file that was used to format this result can be browsed at
http://www.spec.org/mpi2007/flags/EM64T_Intel121_flags.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/mpi2007/flags/EM64T_Intel121_flags.xml.