Jetson TX2

ARMv8 rev 3 testing with a quill and NVIDIA TEGRA on Ubuntu 16.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1812243-SP-JETSONTX207.

Jetson TX2ProcessorMotherboardMemoryDiskGraphicsOSKernelDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionJetsonARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads)quill8192MB31GB 032G34NVIDIA TEGRAUbuntu 16.044.4.38-tegra (aarch64)X Server 1.18.4NVIDIA 1.0.0GCC 5.4.0 20160609 + CUDA 9.0ext4640x960OpenBenchmarking.org- Scaling Governor: tegra_cpufreq schedutil

Jetson TX2tensorrt-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 - DisabledJetson32.6034.3517.2620.0126.6028.0114.5716.1736.3237.5220.6620.1128.9429.5416.5116.04281.60314.27185.75220.27357.10469.83266.68299.4894.3099.8050.5252.26196.39208.49110.39117.3735.7938.0118.1619.50106.98109.3155.5060.12230.32232.84123.93130.2640.1542.0620.8922.11OpenBenchmarking.org

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson816243240SE +/- 0.45, N = 632.60

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson816243240SE +/- 0.51, N = 334.35

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson48121620SE +/- 0.20, N = 1217.26

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson510152025SE +/- 0.03, N = 320.01

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson612182430SE +/- 0.07, N = 326.60

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson714212835SE +/- 0.29, N = 328.01

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson48121620SE +/- 0.15, N = 1114.57

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson48121620SE +/- 0.04, N = 316.17

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson816243240SE +/- 0.27, N = 336.32

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson918273645SE +/- 0.07, N = 337.52

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson510152025SE +/- 0.01, N = 320.66

NVIDIA TensorRT Inference

Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG16 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson510152025SE +/- 0.02, N = 320.11

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson714212835SE +/- 0.19, N = 328.94

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson714212835SE +/- 0.16, N = 329.54

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson48121620SE +/- 0.01, N = 316.51

NVIDIA TensorRT Inference

Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: VGG19 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson48121620SE +/- 0.02, N = 316.04

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson60120180240300SE +/- 4.86, N = 3281.60

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson70140210280350SE +/- 3.41, N = 12314.27

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson4080120160200SE +/- 2.01, N = 10185.75

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson50100150200250SE +/- 2.64, N = 12220.27

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson80160240320400SE +/- 8.64, N = 12357.10

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson100200300400500SE +/- 6.63, N = 6469.83

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson60120180240300SE +/- 2.74, N = 3266.68

NVIDIA TensorRT Inference

Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: AlexNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson70140210280350SE +/- 4.29, N = 5299.48

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson20406080100SE +/- 1.41, N = 1294.30

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson20406080100SE +/- 1.38, N = 399.80

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson1122334455SE +/- 0.83, N = 350.52

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson1224364860SE +/- 0.30, N = 352.26

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson4080120160200SE +/- 0.58, N = 3196.39

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson50100150200250SE +/- 1.78, N = 3208.49

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson20406080100SE +/- 1.59, N = 5110.39

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson306090120150SE +/- 1.08, N = 3117.37

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 4 - DLA Cores: DisabledJetson816243240SE +/- 0.52, N = 535.79

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 8 - DLA Cores: DisabledJetson918273645SE +/- 0.42, N = 338.01

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 4 - DLA Cores: DisabledJetson48121620SE +/- 0.05, N = 318.16

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: INT8 - Batch Size: 8 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 8 - DLA Cores: DisabledJetson510152025SE +/- 0.06, N = 319.50

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson20406080100SE +/- 1.18, N = 3106.98

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson20406080100SE +/- 0.95, N = 3109.31

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson1224364860SE +/- 0.66, N = 355.50

NVIDIA TensorRT Inference

Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet50 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson1326395265SE +/- 0.06, N = 360.12

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson50100150200250SE +/- 0.59, N = 3230.32

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson50100150200250SE +/- 3.57, N = 4232.84

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson306090120150SE +/- 1.27, N = 3123.93

NVIDIA TensorRT Inference

Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: GoogleNet - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson306090120150SE +/- 0.61, N = 3130.26

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 16 - DLA Cores: DisabledJetson918273645SE +/- 0.09, N = 340.15

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: FP16 - Batch Size: 32 - DLA Cores: DisabledJetson1020304050SE +/- 0.04, N = 342.06

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: INT8 - Batch Size: 16 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 16 - DLA Cores: DisabledJetson510152025SE +/- 0.06, N = 320.89

NVIDIA TensorRT Inference

Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: Disabled

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA TensorRT InferenceNeural Network: ResNet152 - Precision: INT8 - Batch Size: 32 - DLA Cores: DisabledJetson510152025SE +/- 0.04, N = 322.11

Phoronix Test Suite v10.8.4