SPEC® MPIM2007 Result

Copyright 2006-2010 Standard Performance Evaluation Corporation

NEC

NEC HPC1812Rg-2 (Intel Xeon E5-2650 v4, 2.20 GHz,
DDR4-2400 MHz, SMT ON, Turbo ON)

SPECmpiM_peak2007 = Not Run

MPI2007 license: 055A Test date: Sep-2017
Test sponsor: RWTH University Aachen Hardware Availability: Oct-2016
Tested by: Bo Wang Software Availability: Oct-2016
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 768 11.5 136   10.9 143   10.6 148  
107.leslie3d 768 43.9 119   42.3 123   42.5 123  
113.GemsFDTD 768 253   25.0 253   25.0 252   25.1
115.fds4 768 36.5 53.5 34.2 57.1 36.4 53.6
121.pop2 768 91.2 45.3 88.7 46.6 89.6 46.1
122.tachyon 768 19.7 142   19.4 144   19.6 143  
126.lammps 768 116   25.2 115   25.3 115   25.4
127.wrf2 768 68.6 114   67.8 115   70.5 111  
128.GAPgeofem 768 12.4 166   11.9 174   11.9 173  
129.tera_tf 768 26.8 103   27.2 102   73.2 37.8
130.socorro 768 59.6 64.1 58.4 65.4 81.6 46.8
132.zeusmp2 768 25.8 120   26.1 119   39.4 78.8
137.lu 768 27.8 132   27.3 135   28.8 128  
Hardware Summary
Type of System: Homogeneous
Compute Node: NEC HPC
Interconnects: Omni-Path Architecture(MPI)
Gigabit Ethernet(I/O)
File Server Node: NFSv3
Total Compute Nodes: 32
Total Chips: 64
Total Cores: 768
Total Threads: 1536
Total Memory: 4 TB
Base Ranks Run: 768
Minimum Peak Ranks: --
Maximum Peak Ranks: --
Software Summary
C Compiler: Intel C++ Composer XE 2017 for Linux, Version
17.0.2.174
C++ Compiler: Intel C++ Composer XE 2017 for Linux, Version
17.0.2.174
Fortran Compiler: Intel Fortran Composer XE 2017 for Linux, Version
17.0.2.174
Base Pointers: 64-bit
Peak Pointers: 64-bit
MPI Library: Intel MPI Library 2017 for Linux,
Version 2017.1.132
Other MPI Info: None
Pre-processors: No
Other Software: None

Node Description: NEC HPC

Hardware
Number of nodes: 32
Uses of the node: compute
Vendor: Intel
Model: NEC HPC 1812Rg
CPU Name: Intel Xeon E5-2650 v4
CPU(s) orderable: 1-2 chips
Chips enabled: 2
Cores enabled: 24
Cores per chip: 12
Threads per core: 2
CPU Characteristics: 12 core, 2.2 GHz, 9.6 GT/s QPI
Intel Turbo Boost Technology up to 2.9 GHz
Hyper-Threading Technology enabled
CPU MHz: 2200
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 256 KB I+D on chip per core
L3 Cache: 30 MB I+D on chip per chip
shared / 12 cores
Other Cache: None
Memory: 128 GB (8 x 16 GB 2Rx8 PC4-2400T-R)
Disk Subsystem: SATA, Samsung SM863, 120GB, SSD
Other Hardware: None
Adapter: Intel Omni-Path Host Fabric Interface Adapter 100
Series 1 Port PCIe x8
Number of Adapters: 1
Slot Type: PCI-E x8
Data Rate: 58Gb/s
Ports Used: 1
Interconnect Type: Omni-Path
Software
Adapter: Intel Omni-Path Host Fabric Interface Adapter 100
Series 1 Port PCIe x8
Adapter Driver: Intel Omni-Path Host Fabric Interface
Adapter Firmware: 2.33.5100
Operating System: CentOS Linux release 7.3.1611 (Core)
Kernel 3.10.0-514.26.1.el7.x86_64
Local File System: Linux/xfs
Shared File System: NFSv3
System State: Multi-User, run level 3
Other Software: None

Node Description: NFSv3

Hardware
Number of nodes: 1
Uses of the node: fileserver
Vendor: NETAPP
Model: FAS6240
CPU Name: Intel Xeon CPU X5670
CPU(s) orderable: 1-2 chips
Chips enabled: 2
Cores enabled: 12
Cores per chip: 6
Threads per core: 2
CPU Characteristics: None
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: 12 MB I+D on chip per chip
Other Cache: None
Memory: 96 GB
Disk Subsystem: 216 disks, 2 TB/disk, 432TB total
Other Hardware: None
Adapter: 10 Gigabit Ethernet Controller
IX1-SFP+
Number of Adapters: 2
Slot Type: PCI-Express x8
Data Rate: 10Gbps Ethernet
Ports Used: 2
Interconnect Type: Ethernet
Software
Adapter: 10 Gigabit Ethernet Controller
IX1-SFP+
Adapter Driver: N/A
Adapter Firmware: 1.8-0
Operating System: NetApp Release 8.2.3P2 7-Mode
Local File System: None
Shared File System: NFSv3
System State: Multi-User, run level 3
Other Software: None

Interconnect Description: Omni-Path Architecture(MPI)

Hardware
Vendor: Intel
Model: Intel Omni-Path 100 Series
Switch Model: Intel Omni-Path 100 Series
Number of Switches: 25
Number of Ports: 48
Data Rate: 100Gbps
Firmware: 10.3.0.0.81
Topology: 2:1 Blocking Fat tree
Primary Use: MPI traffic

Interconnect Description: Gigabit Ethernet(I/O)

Hardware
Vendor: Cisco
Model: Ethernet 40 Gbps
Switch Model: Cisco Nexus5020, N5K-C5020P-BF
Number of Switches: 1
Number of Ports: 96
Data Rate: 40Gbps
Firmware: 5.2(1)N1(9a)
Topology: Star
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.

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 
130.socorro:  -assume nostd_intent_in 

Base Optimization Flags

C benchmarks:

 -O3   -xCORE-AVX2   -no-prec-div 

C++ benchmarks:

126.lammps:  -O3   -xCORE-AVX2   -no-prec-div 

Fortran benchmarks:

 -O3   -xCORE-AVX2   -no-prec-div 

Benchmarks using both Fortran and C:

 -O3   -xCORE-AVX2   -no-prec-div 

The flags file that was used to format this result can be browsed at
http://www.spec.org/mpi2007/flags/RWTH-Aachen-CLAIX-MPI-2017-SEP.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/mpi2007/flags/RWTH-Aachen-CLAIX-MPI-2017-SEP.xml.