NVIDIA Jetson TensorRT inference benchmarks by Michael Larabel for a future article on Phoronix.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1812240-SP-XAVIER80657
Jetson AGX Xavier vs. Jetson TX2 TensorRT
NVIDIA Jetson TensorRT inference benchmarks by Michael Larabel for a future article on Phoronix.
,,"Jetson AGX Xavier","Jetson TX2"
Processor,,ARMv8 rev 0 @ 2.27GHz (8 Cores),ARMv8 rev 3 @ 2.04GHz (4 Cores / 6 Threads)
Motherboard,,jetson-xavier,quill
Memory,,16384MB,8192MB
Disk,,31GB HBG4a2,31GB 032G34
Graphics,,NVIDIA Tegra Xavier,NVIDIA Tegra X2
Monitor,,ASUS VP28U,VE228
OS,,Ubuntu 18.04,Ubuntu 16.04
Kernel,,4.9.108-tegra (aarch64),4.4.38-tegra (aarch64)
Desktop,,Unity 7.5.0,Unity 7.4.0
Display Server,,X Server 1.19.6,X Server 1.18.4
Display Driver,,NVIDIA 31.0.2,NVIDIA 28.2.1
OpenGL,,4.6.0,4.5.0
Vulkan,,1.1.76,
Compiler,,GCC 7.3.0 + CUDA 10.0,GCC 5.4.0 20160609 + CUDA 9.0
File-System,,ext4,ext4
Screen Resolution,,1920x1080,1920x1080
,,"Jetson AGX Xavier","Jetson TX2"
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,184.43,27.02
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,201.53,29.57
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,246.76,37.24
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,172.15,26.49
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,215.68,33.68
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,234.84,36.71
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,228.75,36.44
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,219.08,35.60
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,195.45,32.30
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,253.34,41.87
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,582.36,99.05
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,542.80,93.61
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,593,106
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,613,110
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,863,198
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,956,230
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: FP16 - Batch Size: 32 (Images/sec)",HIB,1900,472
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,390.57,15.99
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,449.96,19.87
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,362.08,16.38
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,485.22,22.05
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,445.22,20.77
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,407.01,19.48
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,1184.50,59.45
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,350.28,17.97
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,1106.13,57.18
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,296.94,16.02
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,262.17,14.62
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,865.46,50.39
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,341.20,19.89
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,286.64,17.98
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,1622,130
"GLmark2 - Resolution: 1920 x 1080 (Score)",HIB,2861,
"NVIDIA TensorRT Inference - Neural Network: ResNet152 - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,224.60,40.19
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,1340,125
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,858,218
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,1049,117
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,652,114
"NVIDIA TensorRT Inference - Neural Network: GoogleNet - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,546,202
"NVIDIA TensorRT Inference - Neural Network: ResNet50 - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,944.46,51.07
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: INT8 - Batch Size: 32 (Images/sec)",HIB,2666,307
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,1879,258
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,1435,370
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: INT8 - Batch Size: 8 (Images/sec)",HIB,1237,222
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: INT8 - Batch Size: 4 (Images/sec)",HIB,975,179
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: FP16 - Batch Size: 8 (Images/sec)",HIB,1247,300
"NVIDIA TensorRT Inference - Neural Network: AlexNet - Precision: FP16 - Batch Size: 4 (Images/sec)",HIB,799,261
"NVIDIA TensorRT Inference - Neural Network: VGG19 - Precision: FP16 - Batch Size: 16 (Images/sec)",HIB,180.03,28.97
"NVIDIA TensorRT Inference - Neural Network: VGG16 - Precision: INT8 - Batch Size: 16 (Images/sec)",HIB,381.33,20.50