SPEC(R) MPIM2007 Summary IBM Corporation IBM Power 575 Sat Jun 28 23:29:47 2008 MPI2007 License: 0005 Test date: Jun-2008 Test sponsor: IBM Corporation Hardware availability: May-2008 Tested by: IBM Corporation Software availability: May-2008 Base Base Base Peak Peak Peak Benchmarks Ranks Run Time Ratio Ranks Run Time Ratio -------------- ------ --------- --------- ------ --------- --------- 104.milc 128 199 7.85 S 128 199 7.85 S 104.milc 128 197 7.96 * 128 197 7.96 * 104.milc 128 195 8.02 S 128 195 8.02 S 107.leslie3d 128 336 15.5 * 128 336 15.5 * 107.leslie3d 128 335 15.6 S 128 335 15.6 S 107.leslie3d 128 338 15.5 S 128 338 15.5 S 113.GemsFDTD 128 452 13.9 S 128 452 13.9 S 113.GemsFDTD 128 394 16.0 S 128 394 16.0 S 113.GemsFDTD 128 452 14.0 * 128 452 14.0 * 115.fds4 128 196 9.94 S 128 196 9.94 S 115.fds4 128 194 10.0 * 128 194 10.0 * 115.fds4 128 191 10.2 S 128 191 10.2 S 121.pop2 128 493 8.37 S 128 493 8.37 S 121.pop2 128 556 7.43 S 128 556 7.43 S 121.pop2 128 493 8.37 * 128 493 8.37 * 122.tachyon 128 461 6.07 S 128 461 6.07 S 122.tachyon 128 455 6.15 S 128 455 6.15 S 122.tachyon 128 461 6.07 * 128 461 6.07 * 126.lammps 128 227 12.8 S 128 227 12.8 S 126.lammps 128 230 12.7 * 128 230 12.7 * 126.lammps 128 232 12.6 S 128 232 12.6 S 127.wrf2 128 469 16.6 * 128 469 16.6 * 127.wrf2 128 466 16.7 S 128 466 16.7 S 127.wrf2 128 470 16.6 S 128 470 16.6 S 128.GAPgeofem 128 126 16.4 * 128 126 16.4 * 128.GAPgeofem 128 126 16.3 S 128 126 16.3 S 128.GAPgeofem 128 125 16.5 S 128 125 16.5 S 129.tera_tf 128 447 6.19 S 128 447 6.19 S 129.tera_tf 128 444 6.24 * 128 444 6.24 * 129.tera_tf 128 443 6.25 S 128 443 6.25 S 130.socorro 128 188 20.3 * 128 188 20.3 * 130.socorro 128 241 15.9 S 128 241 15.9 S 130.socorro 128 186 20.5 S 128 186 20.5 S 132.zeusmp2 128 318 9.75 S 128 318 9.75 S 132.zeusmp2 128 319 9.72 * 128 319 9.72 * 132.zeusmp2 128 322 9.63 S 128 322 9.63 S 137.lu 128 243 15.1 S 128 243 15.1 S 137.lu 128 243 15.1 * 128 243 15.1 * 137.lu 128 304 12.1 S 128 304 12.1 S ============================================================================== 104.milc 128 197 7.96 * 128 197 7.96 * 107.leslie3d 128 336 15.5 * 128 336 15.5 * 113.GemsFDTD 128 452 14.0 * 128 452 14.0 * 115.fds4 128 194 10.0 * 128 194 10.0 * 121.pop2 128 493 8.37 * 128 493 8.37 * 122.tachyon 128 461 6.07 * 128 461 6.07 * 126.lammps 128 230 12.7 * 128 230 12.7 * 127.wrf2 128 469 16.6 * 128 469 16.6 * 128.GAPgeofem 128 126 16.4 * 128 126 16.4 * 129.tera_tf 128 444 6.24 * 128 444 6.24 * 130.socorro 128 188 20.3 * 128 188 20.3 * 132.zeusmp2 128 319 9.72 * 128 319 9.72 * 137.lu 128 243 15.1 * 128 243 15.1 * SPECmpiM_base2007 11.4 SPECmpiM_peak2007 11.4 BENCHMARK DETAILS ----------------- Type of System: Homogeneous Total Compute Nodes: 2 Total Chips: 32 Total Cores: 64 Total Threads: 128 Total Memory: 256 GB Base Ranks Run: 128 Minimum Peak Ranks: 128 Maximum Peak Ranks: 128 C Compiler: IBM XL C/C++ Enterprise Edition V9.0 Updated with the Oct2007 PTF C++ Compiler: IBM XL C/C++ Enterprise Edition V9.0 Updated with the Oct2007 PTF Fortran Compiler: IBM XL Fortran Enterprise Edition V11.1 Updated with the Oct2007 PTF Base Pointers: 64-bit Peak Pointers: 64-bit MPI Library: IBM Parallel Environment for AIX V4.3.2.2 Other MPI Info: -- Pre-processors: -- Other Software: None Node Description: IBM Power 575 =============================== HARDWARE -------- Number of nodes: 1 Uses of the node: compute, head, fileserver Vendor: IBM Corporation Model: IBM Power 575 CPU Name: POWER6 CPU(s) orderable: 32 cores Chips enabled: 16 Cores enabled: 32 Cores per chip: 2 Threads per core: 2 CPU Characteristics: CPU MHz: 4700 Primary Cache: 64 KB I + 64 KB D on chip per core Secondary Cache: 4 MB I+D on chip per core L3 Cache: 32 MB I+D off chip per chip Other Cache: None Memory: 128 GB (64x2 GB) DDR2 533 MHz Disk Subsystem: 1x146 GB SFF SAS, 10K RPM Other Hardware: None Adapter: Integrated Number of Adapters: 1 Slot Type: -- Data Rate: 1 Gbps Ports Used: 1 Interconnect Type: Gigabit Ethernet Adapter: IBM Dual 2-port 4x DDR Host Channel Adapter Number of Adapters: 2 Slot Type: GX++ Data Rate: 4x DDR 20 Gbps Ports Used: 4 Interconnect Type: DDR InfiniBand SOFTWARE -------- Adapter: Integrated Adapter Driver: fileset devices.chrp.IBM.lhea.rte 5.3.8.2 Adapter Firmware: -- Adapter: IBM Dual 2-port 4x DDR Host Channel Adapter Adapter Driver: fileset devices.common.IBM.ib.rte 5.3.8.2 Adapter Firmware: -- Operating System: IBM AIX V5.3 with the 5300-08-02 Technology Level Local File System: AIX/JFS2 Shared File System: NFS over ethernet System State: Multi-user Other Software: APAR IZ26983 software update for InfiniBand adapter drivers IBM LoadLeveler for AIX V3.4.3.2 Node Description: IBM Power 575 =============================== HARDWARE -------- Number of nodes: 1 Uses of the node: compute Vendor: IBM Corporation Model: IBM Power 575 CPU Name: POWER6 CPU(s) orderable: 32 cores Chips enabled: 16 Cores enabled: 32 Cores per chip: 2 Threads per core: 2 CPU Characteristics: CPU MHz: 4700 Primary Cache: 64 KB I + 64 KB D on chip per core Secondary Cache: 4 MB I+D on chip per core L3 Cache: 32 MB I+D off chip per chip Other Cache: None Memory: 128 GB (64x2 GB) DDR2 533 MHz Disk Subsystem: 1x146 GB SFF SAS, 10K RPM Other Hardware: None Adapter: Integrated Number of Adapters: 1 Slot Type: -- Data Rate: 1 Gbps Ports Used: 1 Interconnect Type: Gigabit Ethernet Adapter: IBM Dual 2-port 4x DDR Host Channel Adapter Number of Adapters: 2 Slot Type: GX++ Data Rate: 4x DDR 20 Gbps Ports Used: 4 Interconnect Type: DDR InfiniBand SOFTWARE -------- Adapter: Integrated Adapter Driver: fileset devices.chrp.IBM.lhea.rte 5.3.8.2 Adapter Firmware: -- Adapter: IBM Dual 2-port 4x DDR Host Channel Adapter Adapter Driver: fileset devices.common.IBM.ib.rte 5.3.8.2 Adapter Firmware: -- Operating System: IBM AIX V5.3 with the 5300-08-02 Technology Level Local File System: AIX/JFS2 Shared File System: NFS over ethernet System State: Multi-user Other Software: APAR IZ26983 software update for InfiniBand adapter drivers IBM LoadLeveler for AIX V3.4.3.2 Interconnect Description: InfiniBand ==================================== HARDWARE -------- Vendor: QLogic Model: -- Switch Model: QLogic SilverStorm 9024 Number of Switches: 2 Number of Ports: 24 Data Rate: InfiniBand 4x DDR 20 Gbps Firmware: 4.2.1.1.1 Topology: linear Primary Use: MPI Communication Interconnect Description: Gigabit Ethernet ========================================== HARDWARE -------- Vendor: IBM Corporation Model: Cisco Systems WS-C6509-E Catalyst 6500 9-slot Chassis System Switch Model: Cisco Systems WS-X6748-GE-TX CEF720 48 port 10/100/1000mb Ethernet card Cisco Systems WS-SUP720-3B 2 ports Supervisor Engine 720 Rev. 5.2 Number of Switches: 1 Number of Ports: 48 Data Rate: 1 Gbps Firmware: 01ES330_034_034 Topology: -- Primary Use: File system General Notes ------------- 113.GemsFDTD (base): Applied maxprocandstop src.alt 129.tera_tf (base): Applied fixbuffer src.alt 127.wrf2 (base): Applied fixcalling src.alt all ulimits set to unlimited "petaskbind.sh" script used to bind each task to a unique processor POE Environment variables set before executing benchmarks: CWD =/specmpi/mpi2007-1.0 MP_ADAPTER_USE =shared MP_EUILIB =us MP_EUIDEVICE =sn_all MP_SHARED_MEMORY =yes MP_SINGLE_THREAD =yes MP_WAIT_MODE =poll MP_EAGER_LIMIT =65536 MP_BUFFER_MEM =67108864 MP_POLLING_INTERVAL =80000000 MP_USE_BULK_XFER =yes MP_BULK_MIN_MSG_SIZE=65536 MP_STDINMODE =none MP_LABELIO =no MP_HOSTFILE =$CWD/r35.128-2node Other Environment variables MEMORY_AFFINITY =MCM LDR_CNTRL =DATAPSIZE=64K@TEXTPSIZE=64K@STACKPSIZE=64K XLFRTEOTPS =intrinthds=1 submit command uses petaskbind.sh script to bind logical processors to ranks poe $CWD/petaskbind.sh $command -procs $ranks The Gigabit ethernet switch is shared among many nodes, not just the cluster used in this benchmark. Base Compiler Invocation ------------------------ C benchmarks: /usr/bin/mpcc_r C++ benchmarks: 126.lammps: /usr/bin/mpCC_r Fortran benchmarks: /usr/bin/mpxlf95_r Benchmarks using both Fortran and C: /usr/bin/mpcc_r /usr/bin/mpxlf95_r Base Portability Flags ---------------------- 107.leslie3d: -qfixed 115.fds4: -DSPEC_MPI_LC_NO_TRAILING_UNDERSCORE -qfixed 121.pop2: -DSPEC_MPI_AIX 127.wrf2: -DNOUNDERSCORE -DSPEC_MPI_AIX 130.socorro: -DSPEC_NO_UNDERSCORE -qcpluscmt 132.zeusmp2: -qfixed -DSPEC_SINGLE_UNDERSCORE 137.lu: -qfixed Base Optimization Flags ----------------------- C benchmarks: -O4 -qarch=pwr6 -qtune=pwr6 -q64 C++ benchmarks: 126.lammps: -O4 -qarch=pwr6 -qtune=pwr6 -qstrict -q64 Fortran benchmarks: -O4 -qarch=pwr6 -qtune=pwr6 -qalias=nostd -q64 Benchmarks using both Fortran and C: -O4 -qarch=pwr6 -qtune=pwr6 -qalias=nostd -q64 Base Other Flags ---------------- C benchmarks: -w -qsuppress=1500-036 -qipa=noobject -qipa=threads C++ benchmarks: 126.lammps: -w -qsuppress=1500-036 -qipa=noobject -qipa=threads Fortran benchmarks: -w -qsuppress=1500-036 -qsuppress=cmpmsg -qipa=noobject -qipa=threads Benchmarks using both Fortran and C: -w -qsuppress=1500-036 -qsuppress=cmpmsg -qipa=noobject -qipa=threads Peak Optimization Flags ----------------------- C benchmarks: 104.milc: basepeak = yes 122.tachyon: basepeak = yes C++ benchmarks: 126.lammps: basepeak = yes Fortran benchmarks: 107.leslie3d: basepeak = yes 113.GemsFDTD: basepeak = yes 129.tera_tf: basepeak = yes 137.lu: basepeak = yes Benchmarks using both Fortran and C: 115.fds4: basepeak = yes 121.pop2: basepeak = yes 127.wrf2: basepeak = yes 128.GAPgeofem: basepeak = yes 130.socorro: basepeak = yes 132.zeusmp2: basepeak = yes The flags files that were used to format this result can be browsed at http://www.spec.org/mpi2007/flags/MPI2007_flags.20080828.html http://www.spec.org/mpi2007/flags/MPI2007_flags.0.20080828.html http://www.spec.org/mpi2007/flags/MPI2007_flags.1.html You can also download the XML flags sources by saving the following links: http://www.spec.org/mpi2007/flags/MPI2007_flags.20080828.xml http://www.spec.org/mpi2007/flags/MPI2007_flags.0.20080828.xml http://www.spec.org/mpi2007/flags/MPI2007_flags.1.xml SPEC and SPEC MPI are registered trademarks of the Standard Performance Evaluation Corporation. All other brand and product names appearing in this result are trademarks or registered trademarks of their respective holders. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 2006-2010 Standard Performance Evaluation Corporation Tested with SPEC MPI2007 v1.0. Report generated on Tue Jul 22 13:34:41 2014 by MPI2007 ASCII formatter v1463. Originally published on 27 August 2008.