Linux 4.4 CPU Scaling Driver Governors

Intel P-State and CPUfreq scaling governor benchmarks on Linux 4.4 kernel. Benchmarks 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 1601175-GA-LINUX44CP54
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
Show Result Confidence Charts

Limit displaying results to tests within:

Audio Encoding 2 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 6 Tests
Creator Workloads 5 Tests
Database Test Suite 2 Tests
Desktop Graphics 3 Tests
Encoding 4 Tests
Multi-Core 5 Tests
Server 2 Tests
Server CPU Tests 3 Tests
Single-Threaded 2 Tests
Video Encoding 2 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

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
P-State Powersave
January 17 2016
 
P-State Performance
January 17 2016
 
CPUFreq Performance
January 17 2016
 
CPUFreq Ondemand
January 17 2016
 
CPUFreq Powersave
January 17 2016
 
CPUFreq Conservative
January 17 2016
 
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):


Linux 4.4 CPU Scaling Driver GovernorsOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon E5-2687W v3 @ 3.50GHz (20 Cores)Intel Xeon E5-2687W v3 @ 3.10GHz (20 Cores)MSI X99S SLI PLUS (MS-7885) v1.0Intel Xeon E7 v3/Xeon16384MBPNY CS1211 120GB + 80GB INTEL SSDSCKGW08AMD FirePro V7900 2048MBRealtek ALC892ASUS PB278Intel ConnectionUbuntu 16.044.4.0-040400-generic (x86_64)Unity 7.4.0X Server 1.17.3radeon 7.6.13.3 Mesa 11.0.8 Gallium 0.4GCC 5.3.1 20160112ext42560x1440ProcessorsMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionLinux 4.4 CPU Scaling Driver Governors PerformanceSystem Logs- --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v - DEADLINE / data=ordered,errors=remount-ro,relatime,rw- P-State Powersave: Scaling Governor: intel_pstate powersave- P-State Performance: Scaling Governor: intel_pstate performance- CPUFreq Performance: Scaling Governor: acpi-cpufreq performance- CPUFreq Ondemand: Scaling Governor: acpi-cpufreq ondemand- CPUFreq Powersave: Scaling Governor: acpi-cpufreq powersave- CPUFreq Conservative: Scaling Governor: acpi-cpufreq conservative- EXA

P-State PowersaveP-State PerformanceCPUFreq PerformanceCPUFreq OndemandCPUFreq PowersaveCPUFreq ConservativeResult OverviewPhoronix Test Suite100%149%199%248%298%LAME MP3 EncodingFLAC Audio EncodingFFmpegC-RayTimed Linux Kernel Compilationx264XonoticPostgreSQL pgbenchTesseractSQLiteOpenArena

Linux 4.4 CPU Scaling Driver Governorssqlite: Default Test Directoryopenarena: 2560 x 1440tesseract: 2560 x 1440xonotic: 2560 x 1440 - Lowxonotic: 2560 x 1440 - Highxonotic: 2560 x 1440 - Ultrax264: H.264 Video Encodingbuild-linux-kernel: Time To Compilec-ray: Total Timeencode-flac: WAV To FLACencode-mp3: WAV To MP3ffmpeg: H.264 HD To NTSC DVpgbench: Buffer Test - Single Thread - Read Writepgbench: Buffer Test - Heavy Contention - Read WriteP-State PowersaveP-State PerformanceCPUFreq PerformanceCPUFreq OndemandCPUFreq PowersaveCPUFreq Conservative54.7664.4380.57279.49143.84108.60353.6454.2410.727.1813.0024.55348.165519.8653.5065.2381.81296.12156.41113.41364.7752.0010.746.9313.0710.69452.735580.7855.2864.3081.27249.37142.36108.78310.7453.7210.796.9612.7916.54367.605239.3755.5264.2381.60255.07142.52108.86311.4153.9710.806.9512.9415.90369.885286.7054.7964.4377.63116.7690.5080.05141.60136.1528.4918.9838.0529.15330.054925.6755.3964.2081.43253.25141.64108.52307.2053.9010.786.9612.9916.08368.375080.88OpenBenchmarking.org

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.8.10.2Test Target: Default Test DirectoryP-State PerformanceP-State PowersaveCPUFreq PowersaveCPUFreq PerformanceCPUFreq ConservativeCPUFreq Ondemand1224364860SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 353.5054.7654.7955.2855.3955.521. (CC) gcc options: -O2 -ldl -lpthread

OpenArena

OpenBenchmarking.orgFrames Per Second, More Is BetterOpenArena 0.8.8Resolution: 2560 x 1440P-State PerformanceCPUFreq PowersaveP-State PowersaveCPUFreq PerformanceCPUFreq OndemandCPUFreq Conservative1530456075SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 365.2364.4364.4364.3064.2364.20MIN: 1 / MAX: 285MIN: 4MIN: 3 / MAX: 315MIN: 2 / MAX: 302MIN: 2 / MAX: 300MIN: 2 / MAX: 296

OpenBenchmarking.orgMilliseconds, Fewer Is BetterOpenArena 0.8.8Resolution: 2560 x 1440 - Total Frame TimeP-State PerformanceP-State PowersaveCPUFreq PowersaveCPUFreq OndemandCPUFreq PerformanceCPUFreq Conservative918273645Min: 2 / Avg: 15.3 / Max: 37Min: 3 / Avg: 15.48 / Max: 37Min: 4 / Avg: 15.48 / Max: 46Min: 2 / Avg: 15.5 / Max: 37Min: 2 / Avg: 15.51 / Max: 37Min: 2 / Avg: 15.52 / Max: 38

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 2560 x 1440P-State PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceP-State PowersaveCPUFreq Powersave20406080100SE +/- 0.21, N = 3SE +/- 0.43, N = 3SE +/- 0.21, N = 3SE +/- 0.23, N = 3SE +/- 0.08, N = 3SE +/- 0.37, N = 381.8181.6081.4381.2780.5777.63

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8Resolution: 2560 x 1440 - Effects Quality: LowP-State PerformanceP-State PowersaveCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceCPUFreq Powersave60120180240300SE +/- 4.43, N = 6SE +/- 4.84, N = 6SE +/- 2.50, N = 3SE +/- 4.28, N = 4SE +/- 4.15, N = 4SE +/- 0.15, N = 3296.12279.49255.07253.25249.37116.76MIN: 128 / MAX: 543MIN: 119 / MAX: 518MIN: 122 / MAX: 459MIN: 122 / MAX: 462MIN: 112 / MAX: 457MIN: 73 / MAX: 240

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8Resolution: 2560 x 1440 - Effects Quality: HighP-State PerformanceP-State PowersaveCPUFreq OndemandCPUFreq PerformanceCPUFreq ConservativeCPUFreq Powersave306090120150SE +/- 0.89, N = 3SE +/- 0.60, N = 3SE +/- 0.86, N = 3SE +/- 0.32, N = 3SE +/- 0.39, N = 3SE +/- 0.15, N = 3156.41143.84142.52142.36141.6490.50MIN: 55 / MAX: 231MIN: 55 / MAX: 234MIN: 59 / MAX: 230MIN: 54 / MAX: 231MIN: 59 / MAX: 230MIN: 50 / MAX: 208

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8Resolution: 2560 x 1440 - Effects Quality: UltraP-State PerformanceCPUFreq OndemandCPUFreq PerformanceP-State PowersaveCPUFreq ConservativeCPUFreq Powersave306090120150SE +/- 0.16, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3SE +/- 0.38, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3113.41108.86108.78108.60108.5280.05MIN: 38 / MAX: 188MIN: 38 / MAX: 191MIN: 39 / MAX: 190MIN: 36 / MAX: 188MIN: 39 / MAX: 190MIN: 38 / MAX: 165

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2015-11-02H.264 Video EncodingP-State PerformanceP-State PowersaveCPUFreq OndemandCPUFreq PerformanceCPUFreq ConservativeCPUFreq Powersave80160240320400SE +/- 2.17, N = 5SE +/- 3.70, N = 10SE +/- 0.81, N = 5SE +/- 0.94, N = 5SE +/- 1.72, N = 5SE +/- 0.57, N = 5364.77353.64311.41310.74307.20141.601. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.3Time To CompileP-State PerformanceCPUFreq PerformanceCPUFreq ConservativeCPUFreq OndemandP-State PowersaveCPUFreq Powersave306090120150SE +/- 0.85, N = 3SE +/- 0.83, N = 3SE +/- 0.37, N = 3SE +/- 0.82, N = 4SE +/- 0.88, N = 3SE +/- 2.03, N = 352.0053.7253.9053.9754.24136.15

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeP-State PowersaveP-State PerformanceCPUFreq ConservativeCPUFreq PerformanceCPUFreq OndemandCPUFreq Powersave714212835SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.7210.7410.7810.7910.8028.491. (CC) gcc options: -lm -lpthread -O3

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format three times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.1WAV To FLACP-State PerformanceCPUFreq OndemandCPUFreq PerformanceCPUFreq ConservativeP-State PowersaveCPUFreq Powersave510152025SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.06, N = 5SE +/- 0.00, N = 56.936.956.966.967.1818.981. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

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 MP3CPUFreq PerformanceCPUFreq OndemandCPUFreq ConservativeP-State PowersaveP-State PerformanceCPUFreq Powersave918273645SE +/- 0.08, N = 5SE +/- 0.02, N = 5SE +/- 0.02, N = 5SE +/- 0.06, N = 5SE +/- 0.06, N = 5SE +/- 0.13, N = 512.7912.9412.9913.0013.0738.051. (CC) gcc options: -O3 -ffast-math -funroll-loops -pipe -lm

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 2.8.1H.264 HD To NTSC DVP-State PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceP-State PowersaveCPUFreq Powersave714212835SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 310.6915.9016.0816.5424.5529.151. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lxcb -lxcb-xfixes -lxcb-render -lxcb-shape -lasound -lSDL -lm -llzma -pthread -std=c99 -fomit-frame-pointer -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize

PostgreSQL pgbench

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.4.3Scaling: Buffer Test - Test: Single Thread - Mode: Read WriteP-State PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceP-State PowersaveCPUFreq Powersave100200300400500SE +/- 1.60, N = 3SE +/- 0.61, N = 3SE +/- 1.15, N = 3SE +/- 1.16, N = 3SE +/- 4.96, N = 3SE +/- 0.77, N = 3452.73369.88368.37367.60348.16330.051. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -pthread -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.4.3Scaling: Buffer Test - Test: Heavy Contention - Mode: Read WriteP-State PerformanceP-State PowersaveCPUFreq OndemandCPUFreq PerformanceCPUFreq ConservativeCPUFreq Powersave12002400360048006000SE +/- 6.03, N = 3SE +/- 8.02, N = 3SE +/- 31.10, N = 3SE +/- 56.33, N = 3SE +/- 140.83, N = 6SE +/- 1.32, N = 35580.785519.865286.705239.375080.884925.671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -pthread -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm