Latest HPC Challenge Numademo Benchmarks

Latest numademo system tests by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1401114-SO-NUMAHPC6216
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Comparison
Transpose Comparison

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
ACML 5.3.0: Standard
December 28 2013
 
ACML 5.3.0: One Process Per Node
December 31 2013
 
CentOS ATLAS: Standard
January 09 2014
 
CentOS ATLAS: One Process Per Node
January 10 2014
 
Invert Hiding All Results Option
 

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemACML 5.3.0CentOS ATLAS Standard One Process Per Node Standard One Process Per Node32 x AMD Opteron 6380 @ 2.50GHz (256 Cores)Supermicro H8QGLAMD ATI RD890 + SB7x0/SB8x0/SB9x01032192MB2 x 256GB Samsung SSD 840Matrox s MGA G200eW WPCM450Intel 82576 Gigabit ConnectionCentOS 6.43.10.10-advanced+ (x86_64)GCC 4.4.7 20120313 + Open64 4.5.2.1 + PGI C-C++ WorkstationnfsAMD RD890 + SB7x0/SB8x0/SB9x0CentOS 6.53.10.23-advanced+ (x86_64)OpenBenchmarking.orgCompiler Details- --build=x86_64-redhat-linux --disable-dssi --disable-libjava-multilib --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-unique-object --enable-java-awt=gtk --enable-java-maintainer-mode --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-libgcj-multifile --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-cloog --with-ppl --with-tune=generic System Details- SELinux: Enabled.

hpcc: G-HPLhpcc: G-Fftehpcc: EP-DGEMMhpcc: G-Ptranshpcc: EP-STREAM Triadhpcc: G-Rand Accesshpcc: Rand Ring Latencyhpcc: Rand Ring Bandwidthhpcc: Max Ping Pong BandwidthACML 5.3.0CentOS ATLAS Standard One Process Per Node Standard One Process Per Node1485.270006.948728.572511.700281.406790.085257.645320.0075925003.303110.079003.0779117.260100.929957.151460.038492.659300.20727469.267104.833000.612480.478121.835211.512520.041447.706450.006661839.0026.444253.048040.872970.948577.021750.040142.768400.20074470.596OpenBenchmarking.org

HPC Challenge

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.4.3Test / Class: G-HPLStandardOne Process Per Node300600900120015001485.27000110.07900104.833006.444251. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.4.3Test / Class: G-FfteStandardOne Process Per Node2468106.948723.077910.612483.048041. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.4.3Test / Class: EP-DGEMMStandardOne Process Per Node481216208.5725117.260100.478120.872971. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.4.3Test / Class: G-PtransStandardOne Process Per Node0.41290.82581.23871.65162.06451.700280.929951.835210.948571. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.4.3Test / Class: EP-STREAM TriadStandardOne Process Per Node2468101.406797.151461.512527.021751. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGUP/s, More Is BetterHPC Challenge 1.4.3Test / Class: G-Random AccessStandardOne Process Per Node0.01920.03840.05760.07680.0960.085250.038490.041440.040141. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgusecs, Fewer Is BetterHPC Challenge 1.4.3Test / Class: Random Ring LatencyStandardOne Process Per Node2468107.645322.659307.706452.768401. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.4.3Test / Class: Random Ring BandwidthStandardOne Process Per Node0.04660.09320.13980.18640.2330.007590.207270.006660.200741. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect

ACML 5.3.0CentOS ATLASOpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.4.3Test / Class: Max Ping Pong BandwidthStandardOne Process Per Node5K10K15K20K25K25003.30469.271839.00470.601. (F9X) gfortran options: -llapack -lm -pthread -lmpi_f77 -lmpi -ldl -lnuma -lrt -lnsl -lutil2. ATLAS + OpenMPI 1.6.0 NUMA Connect