NVIDIA Jetson AGX Xavier vs. TX2 Thermal + Power

Jetson AGX Xavier thermal and power consumption benchmarking for a future article on Phoronix 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 1812244-SP-JETSON56020
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
Chess Test Suite 2 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 13 Tests
Creator Workloads 4 Tests
Encoding 2 Tests
HPC - High Performance Computing 2 Tests
Multi-Core 5 Tests
Programmer / Developer System Benchmarks 3 Tests
Python 2 Tests
Rust Tests 2 Tests
Server 3 Tests
Server CPU Tests 9 Tests
Single-Threaded 5 Tests
Common Workstation Benchmarks 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 Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Jetson AGX Xavier
December 24 2018
  2 Hours, 13 Minutes
Jetson TX2
December 24 2018
  4 Hours, 23 Minutes
Invert Hiding All Results Option
  3 Hours, 18 Minutes
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):

Jetson AGX Xavier

Processor: ARMv8 rev 0 @ 2.27GHz (8 Cores), Motherboard: jetson-xavier, Memory: 16384MB, Disk: 31GB HBG4a2, Graphics: NVIDIA Tegra Xavier, Monitor: ASUS VP28U

OS: Ubuntu 18.04, Kernel: 4.9.108-tegra (aarch64), Desktop: Unity 7.5.0, Display Server: X Server 1.19.6, Display Driver: NVIDIA 31.0.2, OpenGL: 4.6.0, Vulkan: 1.1.76, Compiler: GCC 7.3.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v
Processor Notes: Scaling Governor: tegra_cpufreq schedutil
Disk Mount Options Notes: data=ordered,relatime,rw
Python Notes: Python 2.7.15rc1 + Python 3.6.5

Jetson TX2

Processor: ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads), Motherboard: quill, Memory: 8192MB, Disk: 31GB 032G34, Graphics: NVIDIA Tegra X2, Monitor: ASUS VP28U

OS: Ubuntu 16.04, Kernel: 4.4.38-tegra (aarch64), Desktop: Unity 7.4.0, Display Server: X Server 1.18.4, Display Driver: NVIDIA 28.2.1, OpenGL: 4.5.0, Compiler: GCC 5.4.0 20160609 + CUDA 9.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --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-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v
Processor Notes: Scaling Governor: tegra_cpufreq schedutil
Disk Mount Options Notes: data=ordered,relatime,rw
Python Notes: Python 2.7.12 + Python 3.5.2

NVIDIA Jetson AGX Xavier vs. TX2 Thermal + PowerProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionJetson AGX XavierJetson TX2ARMv8 rev 0 @ 2.27GHz (8 Cores)jetson-xavier16384MB31GB HBG4a2NVIDIA Tegra XavierASUS VP28UUbuntu 18.044.9.108-tegra (aarch64)Unity 7.5.0X Server 1.19.6NVIDIA 31.0.24.6.01.1.76GCC 7.3.0 + CUDA 10.0ext43840x2160ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads)quill8192MB31GB 032G34NVIDIA Tegra X2Ubuntu 16.044.4.38-tegra (aarch64)Unity 7.4.0X Server 1.18.4NVIDIA 28.2.14.5.0GCC 5.4.0 20160609 + CUDA 9.0OpenBenchmarking.orgCompiler Details- Jetson AGX Xavier: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v - Jetson TX2: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --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-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v Processor Details- Scaling Governor: tegra_cpufreq schedutilDisk Mount Options Details- data=ordered,relatime,rwPython Details- Jetson AGX Xavier: Python 2.7.15rc1 + Python 3.6.5- Jetson TX2: Python 2.7.12 + Python 3.5.2

Jetson AGX Xavier vs. Jetson TX2 ComparisonPhoronix Test SuiteBaseline+544.2%+544.2%+1088.4%+1088.4%+1632.6%+1632.6%29.3%AlexNet - INT8 - 32 - Disabled874.2%VGG16 - FP16 - 32 - Disabled572.7%R.4.b.P351.2%AlexNet - FP16 - 32 - Disabled323.3%Total Time - 4.1.R.P.P290.5%GoogleNet - FP16 - 32 - Disabled288.6%P.N.T.T.2.0.0230.4%VGG16 - INT8 - 32 - Disabled2176.7%1.H.M.2.D179.8%WAV To MP3170.6%T.T.C.S.P.M128.2%C.u.1.0.3.s.i.i.C.L.9116.3%GoogleNet - INT8 - 32 - Disabled1132.6%Time To Compile96.7%A.C.P79.9%T.F.A.T.T65.7%T.S.I55.3%T.T.C.C.G.C42.6%P.B.S41.4%WAV To FLAC18.4%P.P.S13.1%NVIDIA TensorRT InferenceNVIDIA TensorRT InferenceOpenSSLNVIDIA TensorRT InferenceC-RayNVIDIA TensorRT InferenceRust Prime BenchmarkNVIDIA TensorRT InferenceasmFishLAME MP3 EncodingRust MandelbrotXZ CompressionNVIDIA TensorRT InferenceTimed Linux Kernel CompilationTSCPPyBenchSQLiteGitPHPBenchScikit-LearnFLAC Audio EncodingHimeno BenchmarkJetson AGX XavierJetson TX2

NVIDIA Jetson AGX Xavier vs. TX2 Thermal + Powertensorrt-inference: AlexNet - INT8 - 32 - Disabledtensorrt-inference: AlexNet - FP16 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 32 - Disabledtensorrt-inference: GoogleNet - FP16 - 32 - Disabledtensorrt-inference: VGG16 - INT8 - 32 - Disabledtensorrt-inference: VGG16 - FP16 - 32 - Disabledc-ray: Total Time - 4K, 16 Rays Per Pixelencode-mp3: WAV To MP3encode-flac: WAV To FLACphpbench: PHP Benchmark Suitepybench: Total For Average Test Timesbuild-linux-kernel: Time To Compilesqlite: Timed SQLite Insertionsasmfish: 1024 Hash Memory, 26 Depthcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9git: Time To Complete Common Git Commandshimeno: Poisson Pressure Solveropenssl: RSA 4096-bit Performancescikit-learn: darktable: Boat - CPU-onlytscp: AI Chess Performancerust-prime: Prime Number Test To 200,000,000rust-mandel: Time To Complete Serial/Parallel MandelbrotJetson AGX XavierJetson TX229811981162789044624716835.4755.16189005323778978.65819346414712.5327757322528.1766026732.5011030646813222919.5936.7265695.9865.3313363853651552122.14292856531817.87245127174367088107.39251OpenBenchmarking.org

NVIDIA TensorRT Inference

This test profile uses any existing system installation of NVIDIA TensorRT for carrying out inference benchmarks with various neural networks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX26001200180024003000SE +/- 145.87, N = 3SE +/- 1.25, N = 32981306
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX25001000150020002500Min: 2688.99 / Avg: 2980.71 / Max: 3129.92Min: 304.21 / Avg: 306.44 / Max: 308.52

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX24080120160200193.7133.98

MinAvgMaxJetson AGX Xavier11.615.419.8Jetson TX25.79.016.4OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor612182430

MinAvgMaxJetson AGX Xavier36.037.739.0Jetson TX243.045.749.0OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor1428425670

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX2400800120016002000SE +/- 23.68, N = 3SE +/- 12.79, N = 31981468
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX230060090012001500Min: 1943.63 / Avg: 1980.72 / Max: 2024.77Min: 448.67 / Avg: 467.96 / Max: 492.17

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX2306090120150113.8853.46

MinAvgMaxJetson AGX Xavier12.217.426.5Jetson TX25.98.815.1OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor816243240

MinAvgMaxJetson AGX Xavier38.039.841.0Jetson TX247.047.649.0OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor1428425670

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX230060090012001500SE +/- 25.05, N = 3SE +/- 1.01, N = 31627132
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX230060090012001500Min: 1581.65 / Avg: 1626.99 / Max: 1668.13Min: 129.93 / Avg: 131.95 / Max: 133.01

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX220406080100105.8513.66

MinAvgMaxJetson AGX Xavier11.815.438.9Jetson TX25.39.716.0OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor1122334455

MinAvgMaxJetson AGX Xavier39.041.543.5Jetson TX246.548.752.0OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor1530456075

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX22004006008001000SE +/- 17.85, N = 3SE +/- 7.62, N = 3890229
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX2160320480640800Min: 863.52 / Avg: 890.11 / Max: 924.04Min: 213.77 / Avg: 229 / Max: 236.86

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX2122436486053.0223.97

MinAvgMaxJetson AGX Xavier12.016.842.7Jetson TX26.09.615.4OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor1224364860

MinAvgMaxJetson AGX Xavier42.544.546.5Jetson TX248.550.252.5OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor1530456075

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX2100200300400500SE +/- 11.20, N = 3SE +/- 0.03, N = 3446.0019.59
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX280160240320400Min: 434.17 / Avg: 446.33 / Max: 468.71Min: 19.55 / Avg: 19.59 / Max: 19.65

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX251015202518.551.42

MinAvgMaxJetson AGX Xavier12.624.143.9Jetson TX25.613.817.5OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor1224364860

MinAvgMaxJetson AGX Xavier44.547.350.5Jetson TX249.556.261.0OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor20406080100

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX250100150200250SE +/- 0.65, N = 3SE +/- 0.13, N = 3247.0036.72
OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX24080120160200Min: 245.84 / Avg: 246.64 / Max: 247.94Min: 36.58 / Avg: 36.72 / Max: 36.98

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX XavierJetson TX236912159.602.99

MinAvgMaxJetson AGX Xavier11.925.747.1Jetson TX25.812.316.4OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA TensorRT InferenceSystem Power Consumption Monitor1428425670

MinAvgMaxJetson AGX Xavier42.545.448.0Jetson TX252.556.560.0OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA TensorRT InferenceSystem Temperature Monitor1632486480

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 Time - 4K, 16 Rays Per PixelJetson AGX XavierJetson TX2140280420560700SE +/- 0.94, N = 3SE +/- 43.48, N = 31686561. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelJetson AGX XavierJetson TX2120240360480600Min: 166.91 / Avg: 168.21 / Max: 170.03Min: 568.75 / Avg: 655.65 / Max: 701.951. (CC) gcc options: -lm -lpthread -O3

MinAvgMaxJetson AGX Xavier11.825.926.4Jetson TX26.59.19.4OpenBenchmarking.orgWatts, Fewer Is BetterC-Ray 1.1System Power Consumption Monitor816243240

MinAvgMaxJetson AGX Xavier46.548.649.0Jetson TX252.053.959.0OpenBenchmarking.orgCelsius, Fewer Is BetterC-Ray 1.1System Temperature Monitor1632486480

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 3.100WAV To MP3Jetson AGX XavierJetson TX220406080100SE +/- 0.26, N = 3SE +/- 0.14, N = 335.4795.981. (CC) gcc options: -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Jetson AGX XavierJetson TX220406080100Min: 35.01 / Avg: 35.47 / Max: 35.89Min: 95.83 / Avg: 95.98 / Max: 96.271. (CC) gcc options: -lm

MinAvgMaxJetson AGX Xavier12.815.315.7Jetson TX25.77.07.1OpenBenchmarking.orgWatts, Fewer Is BetterLAME MP3 Encoding 3.100System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier40.541.242.0Jetson TX248.049.451.0OpenBenchmarking.orgCelsius, Fewer Is BetterLAME MP3 Encoding 3.100System Temperature Monitor1530456075

FLAC Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACJetson AGX XavierJetson TX21530456075SE +/- 0.34, N = 5SE +/- 0.16, N = 555.1665.331. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACJetson AGX XavierJetson TX21326395265Min: 54.44 / Avg: 55.16 / Max: 56.45Min: 64.88 / Avg: 65.33 / Max: 65.751. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

MinAvgMaxJetson AGX Xavier12.215.415.7Jetson TX25.47.17.2OpenBenchmarking.orgWatts, Fewer Is BetterFLAC Audio Encoding 1.3.2System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier36.538.740.5Jetson TX246.047.348.0OpenBenchmarking.orgCelsius, Fewer Is BetterFLAC Audio Encoding 1.3.2System Temperature Monitor1428425670

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteJetson AGX XavierJetson TX240K80K120K160K200KSE +/- 2893.66, N = 3SE +/- 1322.96, N = 3189005133638
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteJetson AGX XavierJetson TX230K60K90K120K150KMin: 183734 / Avg: 189004.67 / Max: 193710Min: 131042 / Avg: 133638.33 / Max: 135378

OpenBenchmarking.orgScore Per Watt, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteJetson AGX XavierJetson TX24K8K12K16K20K12317.1819097.64

MinAvgMaxJetson AGX Xavier11.715.315.7Jetson TX25.37.07.2OpenBenchmarking.orgWatts, Fewer Is BetterPHPBench 0.8.1System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier36.537.238.0Jetson TX245.546.547.0OpenBenchmarking.orgCelsius, Fewer Is BetterPHPBench 0.8.1System Temperature Monitor1428425670

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesJetson AGX XavierJetson TX212002400360048006000SE +/- 8.74, N = 3SE +/- 2.91, N = 332375365
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesJetson AGX XavierJetson TX29001800270036004500Min: 3220 / Avg: 3237.33 / Max: 3248Min: 5360 / Avg: 5364.67 / Max: 5370

MinAvgMaxJetson AGX Xavier12.815.515.7Jetson TX25.57.07.2OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier35.536.537.5Jetson TX244.545.746.5OpenBenchmarking.orgCelsius, Fewer Is BetterPyBench 2018-02-16System Temperature Monitor1428425670

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileJetson AGX XavierJetson TX230060090012001500SE +/- 5.38, N = 3SE +/- 3.04, N = 37891552
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileJetson AGX XavierJetson TX230060090012001500Min: 781.03 / Avg: 788.6 / Max: 799.01Min: 1548.83 / Avg: 1552.06 / Max: 1558.13

MinAvgMaxJetson AGX Xavier12.023.925.0Jetson TX25.58.99.3OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 4.18System Power Consumption Monitor816243240

MinAvgMaxJetson AGX Xavier35.545.147.0Jetson TX243.550.752.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 4.18System Temperature Monitor1530456075

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 3.22Timed SQLite InsertionsJetson AGX XavierJetson TX2306090120150SE +/- 0.97, N = 3SE +/- 0.01, N = 378.65122.141. (CC) gcc options: -O2 -lz -ldl -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.22Timed SQLite InsertionsJetson AGX XavierJetson TX220406080100Min: 77.51 / Avg: 78.65 / Max: 80.57Min: 122.13 / Avg: 122.14 / Max: 122.151. (CC) gcc options: -O2 -lz -ldl -lpthread

MinAvgMaxJetson AGX Xavier12.013.013.4Jetson TX25.25.35.4OpenBenchmarking.orgWatts, Fewer Is BetterSQLite 3.22System Power Consumption Monitor48121620

MinAvgMaxJetson AGX Xavier35.536.938.5Jetson TX242.044.347.0OpenBenchmarking.orgCelsius, Fewer Is BetterSQLite 3.22System Temperature Monitor1428425670

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthJetson AGX XavierJetson TX22M4M6M8M10MSE +/- 59696.43, N = 3SE +/- 47318.56, N = 381934642928565
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthJetson AGX XavierJetson TX21.4M2.8M4.2M5.6M7MMin: 8130176 / Avg: 8193463.67 / Max: 8312783Min: 2848889 / Avg: 2928565 / Max: 3012629

OpenBenchmarking.orgNodes/second Per Watt, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthJetson AGX XavierJetson TX270K140K210K280K350K322296.99322497.70

MinAvgMaxJetson AGX Xavier11.625.425.8Jetson TX28.19.19.3OpenBenchmarking.orgWatts, Fewer Is BetterasmFish 2018-07-23System Power Consumption Monitor816243240

MinAvgMaxJetson AGX Xavier34.545.947.5Jetson TX245.050.352.0OpenBenchmarking.orgCelsius, Fewer Is BetterasmFish 2018-07-23System Temperature Monitor1530456075

XZ Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Jetson AGX XavierJetson TX270140210280350SE +/- 0.55, N = 3SE +/- 1.96, N = 31473181. (CC) gcc options: -pthread -fvisibility=hidden -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Jetson AGX XavierJetson TX260120180240300Min: 146.26 / Avg: 147.03 / Max: 148.09Min: 313.68 / Avg: 317.51 / Max: 320.161. (CC) gcc options: -pthread -fvisibility=hidden -O2

MinAvgMaxJetson AGX Xavier12.419.021.7Jetson TX25.78.78.9OpenBenchmarking.orgWatts, Fewer Is BetterXZ Compression 5.2.4System Power Consumption Monitor612182430

MinAvgMaxJetson AGX Xavier39.541.644.0Jetson TX248.050.150.5OpenBenchmarking.orgCelsius, Fewer Is BetterXZ Compression 5.2.4System Temperature Monitor1428425670

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsJetson AGX XavierJetson TX248121620SE +/- 0.17, N = 3SE +/- 0.10, N = 312.5317.871. Jetson AGX Xavier: git version 2.17.12. Jetson TX2: git version 2.7.4
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsJetson AGX XavierJetson TX2510152025Min: 12.36 / Avg: 12.53 / Max: 12.87Min: 17.73 / Avg: 17.87 / Max: 18.051. Jetson AGX Xavier: git version 2.17.12. Jetson TX2: git version 2.7.4

MinAvgMaxJetson AGX Xavier11.514.615.6Jetson TX25.66.77.2OpenBenchmarking.orgWatts, Fewer Is BetterGitSystem Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier37.038.139.0Jetson TX248.048.249.0OpenBenchmarking.orgCelsius, Fewer Is BetterGitSystem Temperature Monitor1428425670

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverJetson AGX XavierJetson TX260120180240300SE +/- 0.18, N = 3SE +/- 1.76, N = 32772451. (CC) gcc options: -O3
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverJetson AGX XavierJetson TX250100150200250Min: 277.1 / Avg: 277.41 / Max: 277.74Min: 242.19 / Avg: 245.23 / Max: 248.291. (CC) gcc options: -O3

OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverJetson AGX XavierJetson TX281624324019.0534.98

MinAvgMaxJetson AGX Xavier12.414.614.9Jetson TX25.57.07.2OpenBenchmarking.orgWatts, Fewer Is BetterHimeno Benchmark 3.0System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier35.536.437.0Jetson TX246.547.448.0OpenBenchmarking.orgCelsius, Fewer Is BetterHimeno Benchmark 3.0System Temperature Monitor1428425670

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceJetson AGX XavierJetson TX2120240360480600SE +/- 5.74, N = 3SE +/- 0.36, N = 35731271. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceJetson AGX XavierJetson TX2100200300400500Min: 564.4 / Avg: 573.47 / Max: 584.1Min: 126.3 / Avg: 127 / Max: 127.51. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgSigns Per Second Per Watt, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceJetson AGX XavierJetson TX261218243026.1716.38

MinAvgMaxJetson AGX Xavier12.421.924.0Jetson TX25.47.88.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 1.1.1System Power Consumption Monitor816243240

MinAvgMaxJetson AGX Xavier34.540.041.5Jetson TX247.048.048.5OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1System Temperature Monitor1428425670

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Jetson AGX XavierJetson TX250100150200250SE +/- 0.11, N = 3SE +/- 0.70, N = 3225174
OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Jetson AGX XavierJetson TX24080120160200Min: 224.99 / Avg: 225.21 / Max: 225.36Min: 173.22 / Avg: 174.36 / Max: 175.65

MinAvgMaxJetson AGX Xavier11.816.016.3Jetson TX25.67.17.2OpenBenchmarking.orgWatts, Fewer Is BetterScikit-Learn 0.17.1System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier35.036.637.5Jetson TX245.546.347.0OpenBenchmarking.orgCelsius, Fewer Is BetterScikit-Learn 0.17.1System Temperature Monitor1428425670

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Boat - Acceleration: CPU-onlyJetson AGX Xavier714212835SE +/- 2.12, N = 328.17

MinAvgMaxJetson AGX Xavier11.824.630.7OpenBenchmarking.orgWatts, Fewer Is BetterDarktableSystem Power Consumption Monitor918273645

MinAvgMaxJetson AGX Xavier35.541.944.5OpenBenchmarking.orgCelsius, Fewer Is BetterDarktableSystem Temperature Monitor1224364860

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceJetson AGX XavierJetson TX2140K280K420K560K700KSE +/- 1845.75, N = 5SE +/- 213.20, N = 56602673670881. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceJetson AGX XavierJetson TX2110K220K330K440K550KMin: 654908 / Avg: 660267 / Max: 665190Min: 366452 / Avg: 367087.6 / Max: 3674301. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterTSCP 1.81AI Chess PerformanceJetson AGX XavierJetson TX213K26K39K52K65K48371.2160776.16

MinAvgMaxJetson AGX Xavier12.413.714.3Jetson TX25.26.06.4OpenBenchmarking.orgWatts, Fewer Is BetterTSCP 1.81System Power Consumption Monitor510152025

MinAvgMaxJetson AGX Xavier37.037.337.5Jetson TX244.044.344.5OpenBenchmarking.orgCelsius, Fewer Is BetterTSCP 1.81System Temperature Monitor1224364860

Rust Prime Benchmark

Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000Jetson AGX XavierJetson TX220406080100SE +/- 0.07, N = 3SE +/- 0.11, N = 332.50107.391. (CC) gcc options: -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000Jetson AGX XavierJetson TX220406080100Min: 32.35 / Avg: 32.5 / Max: 32.6Min: 107.19 / Avg: 107.39 / Max: 107.561. (CC) gcc options: -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

MinAvgMaxJetson AGX Xavier12.818.619.4Jetson TX25.37.57.7OpenBenchmarking.orgWatts, Fewer Is BetterRust Prime BenchmarkSystem Power Consumption Monitor612182430

MinAvgMaxJetson AGX Xavier37.538.539.0Jetson TX243.545.746.0OpenBenchmarking.orgCelsius, Fewer Is BetterRust Prime BenchmarkSystem Temperature Monitor1224364860

Rust Mandelbrot

This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotJetson AGX XavierJetson TX250100150200250SE +/- 2.50, N = 3SE +/- 0.83, N = 31102511. (CC) gcc options: -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotJetson AGX XavierJetson TX250100150200250Min: 107.22 / Avg: 109.8 / Max: 114.79Min: 249.35 / Avg: 251.01 / Max: 251.881. (CC) gcc options: -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm

MinAvgMaxJetson AGX Xavier13.317.321.8Jetson TX25.67.58.3OpenBenchmarking.orgWatts, Fewer Is BetterRust MandelbrotSystem Power Consumption Monitor612182430

MinAvgMaxJetson AGX Xavier35.537.540.0Jetson TX244.546.347.5OpenBenchmarking.orgCelsius, Fewer Is BetterRust MandelbrotSystem Temperature Monitor1428425670

Meta Performance Per Watt

OpenBenchmarking.orgPerformance Per Watt, More Is BetterMeta Performance Per WattPerformance Per WattJetson AGX XavierJetson TX2200K400K600K800K1000K822887.13311895.90

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringJetson AGX XavierJetson TX21020304050Min: 11.5 / Avg: 20.65 / Max: 47.1Min: 5.1 / Avg: 8.99 / Max: 17.5

System Temperature Monitor

OpenBenchmarking.orgCelsiusSystem Temperature MonitorPhoronix Test Suite System MonitoringJetson AGX XavierJetson TX21224364860Min: 34 / Avg: 42.47 / Max: 50.5Min: 42 / Avg: 50.5 / Max: 61

83 Results Shown

NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  AlexNet - INT8 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  AlexNet - FP16 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  GoogleNet - INT8 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  GoogleNet - FP16 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  VGG16 - INT8 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
NVIDIA TensorRT Inference
NVIDIA TensorRT Inference:
  VGG16 - FP16 - 32 - Disabled
  System Power Consumption Monitor
  System Temp Monitor
C-Ray
C-Ray:
  System Power Consumption Monitor
  System Temp Monitor
LAME MP3 Encoding
LAME MP3 Encoding:
  System Power Consumption Monitor
  System Temp Monitor
FLAC Audio Encoding
FLAC Audio Encoding:
  System Power Consumption Monitor
  System Temp Monitor
PHPBench
PHPBench:
  PHP Benchmark Suite
  System Power Consumption Monitor
  System Temp Monitor
PyBench
PyBench:
  System Power Consumption Monitor
  System Temp Monitor
Timed Linux Kernel Compilation
Timed Linux Kernel Compilation:
  System Power Consumption Monitor
  System Temp Monitor
SQLite
SQLite:
  System Power Consumption Monitor
  System Temp Monitor
asmFish
asmFish:
  1024 Hash Memory, 26 Depth
  System Power Consumption Monitor
  System Temp Monitor
XZ Compression
XZ Compression:
  System Power Consumption Monitor
  System Temp Monitor
Git
Git:
  System Power Consumption Monitor
  System Temp Monitor
Himeno Benchmark
Himeno Benchmark:
  Poisson Pressure Solver
  System Power Consumption Monitor
  System Temp Monitor
OpenSSL
OpenSSL:
  RSA 4096-bit Performance
  System Power Consumption Monitor
  System Temp Monitor
Scikit-Learn
Scikit-Learn:
  System Power Consumption Monitor
  System Temp Monitor
Darktable
Darktable:
  System Power Consumption Monitor
  System Temp Monitor
TSCP
TSCP:
  AI Chess Performance
  System Power Consumption Monitor
  System Temp Monitor
Rust Prime Benchmark
Rust Prime Benchmark:
  System Power Consumption Monitor
  System Temp Monitor
Rust Mandelbrot
Rust Mandelbrot:
  System Power Consumption Monitor
  System Temp Monitor
  Performance Per Watt
  Phoronix Test Suite System Monitoring
  Phoronix Test Suite System Monitoring

Jetson AGX Xavier

Processor: ARMv8 rev 0 @ 2.27GHz (8 Cores), Motherboard: jetson-xavier, Memory: 16384MB, Disk: 31GB HBG4a2, Graphics: NVIDIA Tegra Xavier, Monitor: ASUS VP28U

OS: Ubuntu 18.04, Kernel: 4.9.108-tegra (aarch64), Desktop: Unity 7.5.0, Display Server: X Server 1.19.6, Display Driver: NVIDIA 31.0.2, OpenGL: 4.6.0, Vulkan: 1.1.76, Compiler: GCC 7.3.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v
Processor Notes: Scaling Governor: tegra_cpufreq schedutil
Disk Mount Options Notes: data=ordered,relatime,rw
Python Notes: Python 2.7.15rc1 + Python 3.6.5

Testing initiated at 24 December 2018 09:23 by user NVIDIA.

Jetson TX2

Processor: ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads), Motherboard: quill, Memory: 8192MB, Disk: 31GB 032G34, Graphics: NVIDIA Tegra X2, Monitor: ASUS VP28U

OS: Ubuntu 16.04, Kernel: 4.4.38-tegra (aarch64), Desktop: Unity 7.4.0, Display Server: X Server 1.18.4, Display Driver: NVIDIA 28.2.1, OpenGL: 4.5.0, Compiler: GCC 5.4.0 20160609 + CUDA 9.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --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-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v
Processor Notes: Scaling Governor: tegra_cpufreq schedutil
Disk Mount Options Notes: data=ordered,relatime,rw
Python Notes: Python 2.7.12 + Python 3.5.2

Testing initiated at 24 December 2018 20:59 by user NVIDIA.