Jetson Xavier AGX Graphics GLMark2 + TensorRT

ARMv8 rev 0 testing with a jetson-xavier and NVIDIA Tegra Xavier on Ubuntu 18.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1812242-SYST-JETSONX39
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Jetson AGX Xavier
December 23 2018
  6 Hours, 30 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: 1920x1080

Processor Notes: Scaling Governor: tegra_cpufreq schedutil

Jetson Xavier AGX Graphics GLMark2 + TensorRTOpenBenchmarking.orgPhoronix Test SuiteARMv8 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 10.0ext41920x1080ProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionJetson Xavier AGX Graphics GLMark2 + TensorRT BenchmarksSystem Logs- Scaling Governor: tegra_cpufreq schedutil

Jetson Xavier AGX Graphics GLMark2 + TensorRTglmark2: 1920 x 1080tensorrt-inference: VGG16 - FP16 - 4 - Disabledtensorrt-inference: VGG16 - FP16 - 8 - Disabledtensorrt-inference: VGG16 - INT8 - 4 - Disabledtensorrt-inference: VGG16 - INT8 - 8 - Disabledtensorrt-inference: VGG19 - FP16 - 4 - Disabledtensorrt-inference: VGG19 - FP16 - 8 - Disabledtensorrt-inference: VGG19 - INT8 - 4 - Disabledtensorrt-inference: VGG19 - INT8 - 8 - Disabledtensorrt-inference: VGG16 - FP16 - 16 - Disabledtensorrt-inference: VGG16 - FP16 - 32 - Disabledtensorrt-inference: VGG16 - INT8 - 16 - Disabledtensorrt-inference: VGG16 - INT8 - 32 - Disabledtensorrt-inference: VGG19 - FP16 - 16 - Disabledtensorrt-inference: VGG19 - FP16 - 32 - Disabledtensorrt-inference: VGG19 - INT8 - 16 - Disabledtensorrt-inference: VGG19 - INT8 - 32 - Disabledtensorrt-inference: AlexNet - FP16 - 4 - Disabledtensorrt-inference: AlexNet - FP16 - 8 - Disabledtensorrt-inference: AlexNet - INT8 - 4 - Disabledtensorrt-inference: AlexNet - INT8 - 8 - Disabledtensorrt-inference: AlexNet - FP16 - 16 - Disabledtensorrt-inference: AlexNet - FP16 - 32 - Disabledtensorrt-inference: AlexNet - INT8 - 16 - Disabledtensorrt-inference: AlexNet - INT8 - 32 - Disabledtensorrt-inference: ResNet50 - FP16 - 4 - Disabledtensorrt-inference: ResNet50 - FP16 - 8 - Disabledtensorrt-inference: ResNet50 - INT8 - 4 - Disabledtensorrt-inference: ResNet50 - INT8 - 8 - Disabledtensorrt-inference: GoogleNet - FP16 - 4 - Disabledtensorrt-inference: GoogleNet - FP16 - 8 - Disabledtensorrt-inference: GoogleNet - INT8 - 4 - Disabledtensorrt-inference: GoogleNet - INT8 - 8 - Disabledtensorrt-inference: ResNet152 - FP16 - 4 - Disabledtensorrt-inference: ResNet152 - FP16 - 8 - Disabledtensorrt-inference: ResNet152 - INT8 - 4 - Disabledtensorrt-inference: ResNet152 - INT8 - 8 - Disabledtensorrt-inference: ResNet50 - FP16 - 16 - Disabledtensorrt-inference: ResNet50 - FP16 - 32 - Disabledtensorrt-inference: ResNet50 - INT8 - 16 - Disabledtensorrt-inference: ResNet50 - INT8 - 32 - Disabledtensorrt-inference: GoogleNet - FP16 - 16 - Disabledtensorrt-inference: GoogleNet - FP16 - 32 - Disabledtensorrt-inference: GoogleNet - INT8 - 16 - Disabledtensorrt-inference: GoogleNet - INT8 - 32 - Disabledtensorrt-inference: ResNet152 - FP16 - 16 - Disabledtensorrt-inference: ResNet152 - FP16 - 32 - Disabledtensorrt-inference: ResNet152 - INT8 - 16 - Disabledtensorrt-inference: ResNet152 - INT8 - 32 - DisabledJetson AGX Xavier2861195.45215.68286.64341.20172.15184.43262.17296.94228.75246.76381.33449.96180.03201.53362.08390.57799.421246.70975.181236.731434.821900.361879.492665.62542.80582.36865.46944.46546.10863.23651.851049.23219.08234.84350.28407.01593.33613.051106.131184.50857.89955.661339.831622.46224.60253.34445.22485.22OpenBenchmarking.org

GLmark2

This is a test of any system-installed GLMark2 OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2Resolution: 1920 x 1080Jetson AGX Xavier60012001800240030002861

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: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier4080120160200SE +/- 3.17, N = 12195.45

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 3.36, N = 5215.68

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier60120180240300SE +/- 3.98, N = 3286.64

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier70140210280350SE +/- 1.08, N = 3341.20

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier4080120160200SE +/- 1.25, N = 3172.15

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier4080120160200SE +/- 2.36, N = 3184.43

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier60120180240300SE +/- 0.96, N = 3262.17

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier60120180240300SE +/- 1.42, N = 3296.94

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 1.63, N = 3228.75

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 0.17, N = 3246.76

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier80160240320400SE +/- 10.09, N = 12381.33

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier100200300400500SE +/- 4.97, N = 10449.96

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier4080120160200SE +/- 11.67, N = 10180.03

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier4080120160200SE +/- 1.68, N = 3201.53

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier80160240320400SE +/- 0.66, N = 3362.08

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier80160240320400SE +/- 1.67, N = 3390.57

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 97.79, N = 9799.42

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 45.66, N = 121246.70

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 55.83, N = 12975.18

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 99.61, N = 121236.73

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 89.56, N = 91434.82

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier400800120016002000SE +/- 23.33, N = 31900.36

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier400800120016002000SE +/- 91.41, N = 121879.49

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier6001200180024003000SE +/- 248.85, N = 92665.62

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier120240360480600SE +/- 0.39, N = 3542.80

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier130260390520650SE +/- 0.24, N = 3582.36

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 14.20, N = 3865.46

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 40.28, N = 12944.46

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier120240360480600SE +/- 96.56, N = 9546.10

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 14.25, N = 12863.23

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier140280420560700SE +/- 140.60, N = 12651.85

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 121.56, N = 101049.23

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 3.18, N = 3219.08

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 0.36, N = 3234.84

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson AGX Xavier80160240320400SE +/- 5.48, N = 3350.28

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson AGX Xavier90180270360450SE +/- 6.98, N = 3407.01

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier130260390520650SE +/- 7.03, N = 3593.33

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier130260390520650SE +/- 9.12, N = 3613.05

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 11.53, N = 121106.13

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 6.54, N = 31184.50

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 55.00, N = 9857.89

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier2004006008001000SE +/- 14.46, N = 12955.66

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 152.29, N = 91339.83

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier30060090012001500SE +/- 5.04, N = 31622.46

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier50100150200250SE +/- 15.50, N = 9224.60

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier60120180240300SE +/- 2.84, N = 3253.34

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson AGX Xavier100200300400500SE +/- 4.04, N = 3445.22

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson AGX Xavier110220330440550SE +/- 1.47, N = 3485.22

49 Results Shown

GLmark2
NVIDIA TensorRT Inference:
  VGG16 - FP16 - 4 - Disabled
  VGG16 - FP16 - 8 - Disabled
  VGG16 - INT8 - 4 - Disabled
  VGG16 - INT8 - 8 - Disabled
  VGG19 - FP16 - 4 - Disabled
  VGG19 - FP16 - 8 - Disabled
  VGG19 - INT8 - 4 - Disabled
  VGG19 - INT8 - 8 - Disabled
  VGG16 - FP16 - 16 - Disabled
  VGG16 - FP16 - 32 - Disabled
  VGG16 - INT8 - 16 - Disabled
  VGG16 - INT8 - 32 - Disabled
  VGG19 - FP16 - 16 - Disabled
  VGG19 - FP16 - 32 - Disabled
  VGG19 - INT8 - 16 - Disabled
  VGG19 - INT8 - 32 - Disabled
  AlexNet - FP16 - 4 - Disabled
  AlexNet - FP16 - 8 - Disabled
  AlexNet - INT8 - 4 - Disabled
  AlexNet - INT8 - 8 - Disabled
  AlexNet - FP16 - 16 - Disabled
  AlexNet - FP16 - 32 - Disabled
  AlexNet - INT8 - 16 - Disabled
  AlexNet - INT8 - 32 - Disabled
  ResNet50 - FP16 - 4 - Disabled
  ResNet50 - FP16 - 8 - Disabled
  ResNet50 - INT8 - 4 - Disabled
  ResNet50 - INT8 - 8 - Disabled
  GoogleNet - FP16 - 4 - Disabled
  GoogleNet - FP16 - 8 - Disabled
  GoogleNet - INT8 - 4 - Disabled
  GoogleNet - INT8 - 8 - Disabled
  ResNet152 - FP16 - 4 - Disabled
  ResNet152 - FP16 - 8 - Disabled
  ResNet152 - INT8 - 4 - Disabled
  ResNet152 - INT8 - 8 - Disabled
  ResNet50 - FP16 - 16 - Disabled
  ResNet50 - FP16 - 32 - Disabled
  ResNet50 - INT8 - 16 - Disabled
  ResNet50 - INT8 - 32 - Disabled
  GoogleNet - FP16 - 16 - Disabled
  GoogleNet - FP16 - 32 - Disabled
  GoogleNet - INT8 - 16 - Disabled
  GoogleNet - INT8 - 32 - Disabled
  ResNet152 - FP16 - 16 - Disabled
  ResNet152 - FP16 - 32 - Disabled
  ResNet152 - INT8 - 16 - Disabled
  ResNet152 - INT8 - 32 - Disabled

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: 1920x1080

Processor Notes: Scaling Governor: tegra_cpufreq schedutil

Testing initiated at 23 December 2018 16:20 by user system.