AMD FX-8350 Piledriver KVM Linux Virtualization

AMD FX-8350 Vishera used for some KVM (Kernel-based Virtual Machine) Linux benchmarks on Ubuntu 12.10 for a future article on Phoronix.com.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1210277-RA-VIRTPILED42
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

Limit displaying results to tests within:

Audio Encoding 2 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 11 Tests
CPU Massive 17 Tests
Creator Workloads 8 Tests
Cryptography 2 Tests
Encoding 5 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 3 Tests
Common Kernel Benchmarks 3 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 2 Tests
Multi-Core 13 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 2 Tests
Renderers 2 Tests
Scientific Computing 3 Tests
Server 3 Tests
Server CPU Tests 6 Tests
Video Encoding 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Bare Metal Host
October 15 2012
 
KVM
October 15 2012
 
Invert Hiding All Results Option
 
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):


AMD FX-8350 Piledriver KVM Linux VirtualizationProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionSystem LayerBare Metal HostKVMAMD FX-8350 Eight-Core @ 4.00GHz (8 Cores)ASUS Crosshair V FormulaAMD ATI RD890 bridge8192MB60GB OCZ VERTEX2NVIDIA GeForce GTX 680 2048MB (705/3004MHz)Realtek ALC889Intel 82583V Gigabit ConnectionUbuntu 12.103.5.0-17-generic (x86_64)Unity 6.8.0X Server 1.13.0NVIDIA 310.144.3.0 NVIDIA 310.14GCC 4.7ext41920x1080QEMU Virtual 1.2.0 @ 4.01GHz (8 Cores)BochsIntel 440FX- 82441FX PMC6144MB12GBLLVMpipeGeneric 1af4 ID 21Red Hat Virtio devicecirrus 1.5.12.1 Mesa 9.0 Gallium 0.41024x768QEMU 1.2.0OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-arch-32=i686 --with-tune=generic -v Disk Details- DEADLINE / data=ordered,errors=remount-ro,relatime,rwProcessor Details- Bare Metal Host: Scaling Governor: ondemandSystem Details- Disk Scheduler: DEADLINE. Compiz was running on this system.

Bare Metal Host vs. KVM ComparisonPhoronix Test SuiteBaseline+48.5%+48.5%+97%+97%+145.5%+145.5%12%2%P.R.W.S.S.M193.8%T.B.T.P.S125.8%145.9%Blowfish45.5%vpxenc24.8%H.2.V.E18.3%H.2.H.T.N.D15.7%BlurW.O.E.O.D11.6%Time To Compile10.4%Static OMP Speedup10%Time To Compile7.3%S.W.P.S4.6%Resizing3.9%HWB Color Space3.8%L.A.T2.9%Total Time2.3%2.F.C2.2%C.F.DTTSIOD 3D RendererPostgreSQL pgbenchDbenchJohn The RipperVP8 libvpx Encodingx264FFmpegGraphicsMagickOpus Codec EncodingTimed PHP CompilationCLOMPTimed Linux Kernel CompilationApache BenchmarkGraphicsMagickGraphicsMagickGraphicsMagickOpen FMM Nero2DParallel BZIP2 CompressionDolfynBare Metal HostKVM

AMD FX-8350 Piledriver KVM Linux Virtualizationdbench: 1clomp: Static OMP Speedupdolfyn: Computational Fluid Dynamicslammps: Rhodopsin Proteinffte: N=64, 1D Complex FFT Routinejohn-the-ripper: Blowfishttsiod-renderer: Phong Rendering With Soft-Shadow Mappingvpxenc: vpxencx264: H.264 Video Encodinggraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdingbuild-linux-kernel: Time To Compilebuild-php: Time To Compilecompress-pbzip2: 256MB File Compressionencode-mp3: WAV To MP3encode-opus: WAV, Opus Encode, Opus Decodeffmpeg: H.264 HD To NTSC DVnero2d: Total Timepovray: Total Timeopenssl: RSA 4096-bit Performancepgbench: TPC-B Transactions Per Secondapache: Static Web Page ServingBare Metal HostKVM233.892.9637.3958.793073.607152117.1423.84156.661006713216210682.5830.558.0519.7413.4820.24517.2984290.032960.8715935.89160.342.6936.6659.713018.06491539.8719.10132.401126612715610388.5933.738.2319.9115.0423.41529.0085489.701311.1115240.32OpenBenchmarking.org

Dbench

Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1Bare Metal HostKVM50100150200250SE +/- 0.44, N = 3SE +/- 0.36, N = 3233.89160.341. (CC) gcc options: -lpopt
OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1Bare Metal HostKVM4080120160200Min: 233.3 / Avg: 233.89 / Max: 234.74Min: 159.63 / Avg: 160.34 / Max: 160.721. (CC) gcc options: -lpopt

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupBare Metal HostKVM0.6661.3321.9982.6643.33SE +/- 0.00, N = 5SE +/- 0.13, N = 102.962.691. (CC) gcc options: --openmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupBare Metal HostKVM246810Min: 2.95 / Avg: 2.96 / Max: 2.97Min: 1.51 / Avg: 2.69 / Max: 2.861. (CC) gcc options: --openmp -O3 -lm

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsBare Metal HostKVM918273645SE +/- 1.38, N = 6SE +/- 0.04, N = 337.3936.66
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsBare Metal HostKVM816243240Min: 35.92 / Avg: 37.39 / Max: 44.27Min: 36.61 / Avg: 36.66 / Max: 36.74

LAMMPS Molecular Dynamics Simulator

OpenBenchmarking.orgLoop Time, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 1.0Test: Rhodopsin ProteinBare Metal HostKVM1326395265SE +/- 0.05, N = 3SE +/- 0.17, N = 358.7959.711. (CXX) g++ options: -lfftw -lmpich
OpenBenchmarking.orgLoop Time, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 1.0Test: Rhodopsin ProteinBare Metal HostKVM1224364860Min: 58.7 / Avg: 58.79 / Max: 58.86Min: 59.49 / Avg: 59.71 / Max: 60.041. (CXX) g++ options: -lfftw -lmpich

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineBare Metal HostKVM7001400210028003500SE +/- 49.54, N = 6SE +/- 56.35, N = 63073.603018.06-pthread -lmpi_f90 -lmpi_f77 -lmpi -lopen-rte -lopen-pal -ldl -lnsl -lutil -lm-lmpichf90 -lmpich -lopa -lmpl -lrt -lcr -lpthread1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineBare Metal HostKVM5001000150020002500Min: 2902.62 / Avg: 3073.6 / Max: 3262.22Min: 2807.19 / Avg: 3018.06 / Max: 3163.261. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

John The Ripper

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.7.9-jumbo-7Test: BlowfishBare Metal HostKVM15003000450060007500SE +/- 24.00, N = 3SE +/- 523.22, N = 6715249151. (CC) gcc options: -lssl -lcrypto -lm -lz -fopenmp -lcrypt -ldl
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.7.9-jumbo-7Test: BlowfishBare Metal HostKVM12002400360048006000Min: 7128 / Avg: 7152 / Max: 7200Min: 2471 / Avg: 4914.5 / Max: 59521. (CC) gcc options: -lssl -lcrypto -lm -lz -fopenmp -lcrypt -ldl

TTSIOD 3D Renderer

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.2wPhong Rendering With Soft-Shadow MappingBare Metal HostKVM306090120150SE +/- 0.12, N = 3SE +/- 0.10, N = 3117.1439.871. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.2wPhong Rendering With Soft-Shadow MappingBare Metal HostKVM20406080100Min: 116.99 / Avg: 117.14 / Max: 117.38Min: 39.67 / Avg: 39.87 / Max: 39.981. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++

VP8 libvpx Encoding

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencBare Metal HostKVM612182430SE +/- 0.05, N = 3SE +/- 0.01, N = 323.8419.101. (CC) gcc options: -m64 -lvpx -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencBare Metal HostKVM612182430Min: 23.78 / Avg: 23.84 / Max: 23.95Min: 19.07 / Avg: 19.1 / Max: 19.121. (CC) gcc options: -m64 -lvpx -lm -lpthread

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2012-10-03H.264 Video EncodingBare Metal HostKVM306090120150SE +/- 1.44, N = 3SE +/- 2.61, N = 6156.66132.40
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2012-10-03H.264 Video EncodingBare Metal HostKVM306090120150Min: 153.81 / Avg: 156.66 / Max: 158.42Min: 119.43 / Avg: 132.4 / Max: 136.14

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: BlurBare Metal HostKVM306090120150SE +/- 0.00, N = 3SE +/- 0.33, N = 3100112-lSM -lICE -lbz21. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: BlurBare Metal HostKVM20406080100Min: 100 / Avg: 100 / Max: 100Min: 111 / Avg: 111.67 / Max: 1121. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: SharpenBare Metal HostKVM1530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 36766-lSM -lICE -lbz21. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: SharpenBare Metal HostKVM1326395265Min: 67 / Avg: 67 / Max: 67Min: 66 / Avg: 66 / Max: 661. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: ResizingBare Metal HostKVM306090120150SE +/- 0.00, N = 3SE +/- 0.33, N = 3132127-lSM -lICE -lbz21. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: ResizingBare Metal HostKVM20406080100Min: 132 / Avg: 132 / Max: 132Min: 127 / Avg: 127.33 / Max: 1281. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color SpaceBare Metal HostKVM4080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 3162156-lSM -lICE -lbz21. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color SpaceBare Metal HostKVM306090120150Min: 161 / Avg: 161.67 / Max: 162Min: 156 / Avg: 156 / Max: 1561. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive ThresholdingBare Metal HostKVM20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3106103-lSM -lICE -lbz21. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive ThresholdingBare Metal HostKVM20406080100Min: 106 / Avg: 106.33 / Max: 107Min: 102 / Avg: 102.67 / Max: 1031. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lXext -lX11 -lz -lm -lgomp -lpthread

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 3.1Time To CompileBare Metal HostKVM20406080100SE +/- 0.79, N = 3SE +/- 1.13, N = 382.5888.59
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 3.1Time To CompileBare Metal HostKVM20406080100Min: 81.73 / Avg: 82.58 / Max: 84.15Min: 87.44 / Avg: 88.59 / Max: 90.85

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileBare Metal HostKVM816243240SE +/- 0.01, N = 3SE +/- 0.05, N = 330.5533.731. (CC) gcc options: -O2 -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileBare Metal HostKVM714212835Min: 30.53 / Avg: 30.55 / Max: 30.56Min: 33.66 / Avg: 33.73 / Max: 33.821. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

Parallel BZIP2 Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.6256MB File CompressionBare Metal HostKVM246810SE +/- 0.01, N = 3SE +/- 0.03, N = 38.058.231. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.6256MB File CompressionBare Metal HostKVM3691215Min: 8.03 / Avg: 8.05 / Max: 8.07Min: 8.18 / Avg: 8.23 / Max: 8.291. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3Bare Metal HostKVM510152025SE +/- 0.03, N = 5SE +/- 0.04, N = 519.7419.91
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3Bare Metal HostKVM510152025Min: 19.68 / Avg: 19.74 / Max: 19.83Min: 19.83 / Avg: 19.91 / Max: 20.05

Opus Codec Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.0.1WAV, Opus Encode, Opus DecodeBare Metal HostKVM48121620SE +/- 0.05, N = 5SE +/- 0.05, N = 513.4815.041. (CC) gcc options: -std=gnu99 -O3 -ffast-math -fPIE -pie -logg -lm -lopus
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.0.1WAV, Opus Encode, Opus DecodeBare Metal HostKVM48121620Min: 13.38 / Avg: 13.48 / Max: 13.65Min: 14.87 / Avg: 15.04 / Max: 15.141. (CC) gcc options: -std=gnu99 -O3 -ffast-math -fPIE -pie -logg -lm -lopus

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.0H.264 HD To NTSC DVBare Metal HostKVM612182430SE +/- 0.24, N = 3SE +/- 0.26, N = 320.2423.41-lbz21. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lrt
OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.0H.264 HD To NTSC DVBare Metal HostKVM510152025Min: 19.92 / Avg: 20.24 / Max: 20.72Min: 23.01 / Avg: 23.41 / Max: 23.911. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lrt

Open FMM Nero2D

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total TimeBare Metal HostKVM110220330440550517.29529.001. (CXX) g++ options: -O2 -lfftw3 -llapack -lblas -lgfortran -lquadmath -lm

POV-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.6.1Total TimeBare Metal HostKVM2004006008001000842854-lXpm -lSM -lICE -lX111. (CXX) g++ options: -pipe -O3 -msse -mfpmath=sse -msse2 -march=k8 -mtune=k8 -malign-double -lz -lm

OpenSSL

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1cRSA 4096-bit PerformanceBare Metal HostKVM20406080100SE +/- 0.33, N = 3SE +/- 0.45, N = 390.0389.701. (CC) gcc options: -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1cRSA 4096-bit PerformanceBare Metal HostKVM20406080100Min: 89.4 / Avg: 90.03 / Max: 90.5Min: 88.8 / Avg: 89.7 / Max: 90.21. (CC) gcc options: -m64 -O3 -lssl -lcrypto -ldl

PostgreSQL pgbench

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 8.4.11TPC-B Transactions Per SecondBare Metal HostKVM6001200180024003000SE +/- 118.84, N = 6SE +/- 14.74, N = 32960.871311.111. (CC) gcc options: -O2 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 8.4.11TPC-B Transactions Per SecondBare Metal HostKVM5001000150020002500Min: 2635.45 / Avg: 2960.87 / Max: 3291.15Min: 1291.24 / Avg: 1311.11 / Max: 1339.91. (CC) gcc options: -O2 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm

Apache Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.3Static Web Page ServingBare Metal HostKVM3K6K9K12K15KSE +/- 30.37, N = 3SE +/- 153.26, N = 315935.8915240.321. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.3Static Web Page ServingBare Metal HostKVM3K6K9K12K15KMin: 15898.93 / Avg: 15935.89 / Max: 15996.12Min: 14933.8 / Avg: 15240.32 / Max: 15395.631. (CC) gcc options: -shared -fPIC -O2 -pthread