Performance

NVIDIA DeepStream SDK

Development Guide

4.0 Release

Performance

Tesla

Jetson Performance

This topic provides details about configuration settings and measured performance for the DeepStream SDK.

Tesla

System Configuration

Application Configuration

Achieved Performance

This section describes configuration and settings for the DeepStream SDK on NVIDIA® Tesla®.

System Configuration

The system configuration for the DeepStream SDK is listed below:

System Configuration	Specification
CPU	Dual Intel® Xeon® CPU E5-2650 v4 @ 2.20GHz (48 threads total)
GPU	Tesla T4
System Memory	128 GB DDR4, 2400MHz
Ubuntu	Ubuntu 18.04
GPU Driver	418+
CUDA	10.1
TensorRT	5.1.6
GPU clock frequency	1.3 GHz

Application Configuration

The application configuration for the DeepStream SDK is listed below:

Application Configuration	Specification
N×1080p 30 fps stream	sample_1080p_h265.mp4 (provided with the SDK) N=68 sample_1080p_h264.mp4 (provided with the SDK) N=35
Primary GIE	• Resnet10 (480×272) • Batch Size = N • Interval=0
Tracker	Enabled. Processing at 480×272 resolution, IOU tracker enabled.
3 × Secondary GIEs	All batches size 32. Asynchronous mode enabled. • Secondary_VehicleTypes (224×224—Resnet18) • Secondary_CarColor (224×224—Resnet18) • Secondary_CarMake (224×224—Resnet18)
Tiled Display	Disabled
Rendering	Disabled

Achieved Performance

The achieved performance of the DeepStream SDK under the specified system and application configuration are as follows:

Stream Type	No. of Streams @ 30 FPS	CPU Utilization	GPU Utilization
H.265	68	8% to 10%	68%
H.264	35	5%	35%

Jetson Performance

This section describes configuration and settings for the DeepStream SDK on NVIDIA® Jetson® platforms.

System Configuration

For the performance test:

1. Max power mode is enabled:

$ sudo nvpmodel -m 0

2. The GPU clocks are stepped to maximum:

$ sudo jetson_clocks

For information about supported power modes, see “Supported Modes and Power Efficiency” in the power management topics of NVIDIA Tegra Linux Driver Package Development Guide, e.g. “Power Management for Jetson AGX Xavier Devices.”

Jetson Nano

The following tables describe performance results for the NVIDIA® Jetson™ Nano.

Pipeline Configuration (deepstream-app)
Application Configuration	Specification
N×1080p 30 fps streams	sample_1080p_h265.mp4 (provided with the SDK) N = 8 sample_1080p_h264.mp4 (provided with the SDK) N = 8
Primary GIE	• Resnet10 (480×272) • Batch Size = N • Interval = 4
Tracker	Enabled; processing at 480×272 resolution, KLT tracker enabled.
OSD/tiled display	Disabled
Renderer	Disabled

Achieved Performance
Stream Type	No. of Streams @ 30 FPS	CPU Utilization	GPU Utilization
H.265	8	33%	53%
H.264	8	33%	53%

Jetson AGX Xavier

The following tables describe performance results for the NVIDIA® Jetson AGX Xavier™.

Pipeline Configuration (deepstream-app)
Application Configuration	Specification
N×1080p 30 fps streams	sample_1080p_h265.mp4 (provided with the SDK) N=49 sample_1080p_h264.mp4 (provided with the SDK) N=32
Primary GIE	• Resnet10 (480×272) • Batch Size = N • Interval = 0
Tracker	Enabled; processing at 480×272 resolution, IOU tracker enabled.
3× secondary GIEs	All batches are size 32. • Secondary_VehicleTypes (224×224—Resnet18) • Secondary_CarColor (224×224—Resnet18) • Secondary_CarMake (224×224—Resnet18)
OSD/tiled display	Disabled
Renderer	Disabled

Achieved Performance
Stream Type	No. of Streams @ 30 FPS	CPU Utilization	GPU Utilization
H.265	49	17%	95%
H.264	32	17%	72%

NVIDIA Jetson TX2

The following tables describe performance results for the NVIDIA® Jetson™ TX2.

Pipeline Configuration (deepstream-app)
Application Configuration	Specification
N×1080p 30 fps streams	sample_1080p_h265.mp4 (provided with the SDK) N = 14 sample_1080p_h264.mp4 (provided with the SDK) N = 14
Primary GIE	• Resnet10 (480×272) • Batch Size = N • Interval = 4
Tracker	Enabled; processing at 480×272 resolution, KLT tracker enabled.
OSD/tiled display	Disabled
Renderer	Disabled

Achieved Performance
Stream Type	No. of Streams @ 30 FPS	CPU Utilization	GPU Utilization
H.265	14	37%	40%
H.264	14	37%	40%

NVIDIA Jetson TX1

The following tables describe performance results for the NVIDIA® Jetson™ TX1.

Pipeline Configuration (deepstream-app)
Application Configuration	Specification
N×1080p 30 fps streams	sample_1080p_h265.mp4 (provided with the SDK) N = 8 sample_1080p_h264.mp4 (provided with the SDK) N = 8
Primary GIE	• Resnet10 (480×272) • Batch Size = N • Interval = 4
Tracker	Enabled; processing at 480×272 resolution, KLT tracker enabled.
OSD/tiled display	Disabled
Renderer	Disabled

Achieved Performance
Stream Type	No. of Streams @ 30 FPS	CPU Utilization	GPU Utilization
H.265	8	37%	30%
H.264	8	37%	30%