OpenVINO™ Model Server Benchmark Results

OpenVINO™ Model Server is an open-source, production-grade inference platform that exposes a set of models via a convenient inference API over gRPC or HTTP/REST. It employs the OpenVINO™ Runtime libraries from the Intel® Distribution of OpenVINO™ toolkit to extend workloads across Intel® hardware including CPU, GPU and others.

OpenVINO™ Model Server

Measurement Methodology

OpenVINO™ Model Server is measured in multiple-client-single-server configuration using two hardware platforms connected by ethernet network. The network bandwidth depends on the platforms as well as models under investigation and it is set to not be a bottleneck for workload intensity. This connection is dedicated only to the performance measurements. The benchmark setup is consists of four main parts:

OVMS Benchmark Setup Diagram
  • OpenVINO™ Model Server is launched as a docker container on the server platform and it listens (and answers on) requests from clients. OpenVINO™ Model Server is run on the same machine as the OpenVINO™ toolkit benchmark application in corresponding benchmarking. Models served by OpenVINO™ Model Server are located in a local file system mounted into the docker container. The OpenVINO™ Model Server instance communicates with other components via ports over a dedicated docker network.

  • Clients are run in separated physical machine referred to as client platform. Clients are implemented in Python3 programming language based on TensorFlow* API and they work as parallel processes. Each client waits for a response from OpenVINO™ Model Server before it will send a new next request. The role played by the clients is also verification of responses.

  • Load balancer works on the client platform in a docker container. HAProxy is used for this purpose. Its main role is counting of requests forwarded from clients to OpenVINO™ Model Server, estimating its latency, and sharing this information by Prometheus service. The reason of locating the load balancer on the client site is to simulate real life scenario that includes impact of physical network on reported metrics.

  • Execution Controller is launched on the client platform. It is responsible for synchronization of the whole measurement process, downloading metrics from the load balancer, and presenting the final report of the execution.

resnet-50-TF (INT8)

_images/throughput_ovms_resnet50_int8.png

resnet-50-TF (FP32)

_images/throughput_ovms_resnet50_fp32_bs_1.png

googlenet-v4-TF (FP32)

_images/throughput_ovms_googlenet4_fp32.png

yolo-v3-tf (FP32)

_images/throughput_ovms_yolo3_fp32.png

yolo-v4-tf (FP32)

_images/throughput_ovms_yolo4_fp32.png

brain-tumor-segmentation-0002

_images/throughput_ovms_braintumorsegmentation.png

alexnet

_images/throughput_ovms_alexnet.png

mobilenet-v3-large-1.0-224-TF (FP32)

_images/throughput_ovms_mobilenet3large_fp32.png

deeplabv3 (FP32)

_images/throughput_ovms_deeplabv3_fp32.png

bert-small-uncased-whole-word-masking-squad-int8-0002 (INT8)

_images/throughput_ovms_bertsmall_int8.png

bert-small-uncased-whole-word-masking-squad-0002 (FP32)

_images/throughput_ovms_bertsmall_fp32.png

3D U-Net (FP32)

_images/throughput_ovms_3dunet.png

Image Compression for Improved Throughput

OpenVINO Model Server supports compressed binary input data (images in JPEG and PNG formats) for vision processing models. This feature improves overall performance on networks where the bandwidth constitutes a system bottleneck. A good example of such use could be wireless 5G communication, a typical 1 Gbit/sec Ethernet network or a usage scenario with many client machines issuing a high rate of inference requests to one single central OpenVINO model server. Generally the performance improvement increases with increased compressibility of the data/image. The decompression on the server-side is performed by the OpenCV library. Please refer to Supported Image Formats.

googlenet-v4-tf (FP32)

_images/throughput_ovms_1gbps_googlenet4_fp32.png

resnet-50-tf (INT8)

_images/throughput_ovms_1gbps_resnet50_int8.png

resnet-50-tf (FP32)

_images/throughput_ovms_1gbps_resnet50_fp32.png

Platform Configurations

OpenVINO™ Model Server performance benchmark numbers are based on release 2021.4. Performance results are based on testing as of June 17, 2021 and may not reflect all publicly available updates.

Platform with Intel® Xeon® Platinum 8260M

Server Platform Client Platform
Motherboard Inspur YZMB-00882-104 NF5280M5 Intel® Server Board S2600WF H48104-872
Memory Samsung 16 x 16GB @ 2666 MT/s DDR4 Hynix 16 x 16GB @ 2666 MT/s DDR4
CPU Intel® Xeon® Platinum 8260M CPU @ 2.40GHz Intel® Xeon® Gold 6252 CPU @ 2.10GHz
Selected CPU Flags Hyper Threading, Turbo Boost, DL Boost Hyper Threading, Turbo Boost, DL Boost
CPU Thermal Design Power 162 W 150 W
Operating System Ubuntu 20.04.2 LTS Ubuntu 20.04.2 LTS
Kernel Version 5.4.0-54-generic 5.4.0-65-generic
BIOS Vendor American Megatrends Inc. Intel® Corporation
BIOS Version & Release 4.1.16, date: 06/23/2020 SE5C620.86B.02.01, date: 03/26/2020
Docker Version 20.10.3 20.10.3
Network Speed 40 Gb/s

Platform with Intel® Xeon® Gold 6252

Server Platform Client Platform
Motherboard Intel® Server Board S2600WF H48104-872 Inspur YZMB-00882-104 NF5280M5
Memory Hynix 16 x 16GB @ 2666 MT/s DDR4 Samsung 16 x 16GB @ 2666 MT/s DDR4
CPU Intel® Xeon® Gold 6252 CPU @ 2.10GHz Intel® Xeon® Platinum 8260M CPU @ 2.40GHz
Selected CPU Flags Hyper Threading, Turbo Boost, DL Boost Hyper Threading, Turbo Boost, DL Boost
CPU Thermal Design Power 150 W 162 W
Operating System Ubuntu 20.04.2 LTS Ubuntu 20.04.2 LTS
Kernel Version 5.4.0-65-generic 5.4.0-54-generic
BIOS Vendor Intel® Corporation American Megatrends Inc.
BIOS Version and Release Date SE5C620.86B.02.01, date: 03/26/2020 4.1.16, date: 06/23/2020
Docker Version 20.10.3 20.10.3
Network Speed 40 Gb/s

Platform with Intel® Core™ i9-10920X

Server Platform Client Platform
Motherboard ASUSTeK COMPUTER INC. PRIME X299-A II ASUSTeK COMPUTER INC. PRIME Z370-P
Memory Corsair 4 x 16GB @ 2666 MT/s DDR4 Corsair 4 x 16GB @ 2133 MT/s DDR4
CPU Intel® Core™ i9-10920X CPU @ 3.50GHz Intel® Core™ i7-8700T CPU @ 2.40GHz
Selected CPU Flags Hyper Threading, Turbo Boost, DL Boost Hyper Threading, Turbo Boost
CPU Thermal Design Power 165 W 35 W
Operating System Ubuntu 20.04.1 LTS Ubuntu 20.04.1 LTS
Kernel Version 5.4.0-52-generic 5.4.0-56-generic
BIOS Vendor American Megatrends Inc. American Megatrends Inc.
BIOS Version and Release Date 0603, date: 03/05/2020 2401, date: 07/15/2019
Docker Version 19.03.13 19.03.14
Network Speed 10 Gb/s

Platform with Intel® Core™ i7-8700T

Server Platform Client Platform
Motherboard ASUSTeK COMPUTER INC. PRIME Z370-P ASUSTeK COMPUTER INC. PRIME X299-A II
Memory Corsair 4 x 16GB @ 2133 MT/s DDR4 Corsair 4 x 16GB @ 2666 MT/s DDR4
CPU Intel® Core™ i7-8700T CPU @ 2.40GHz Intel® Core™ i9-10920X CPU @ 3.50GHz
Selected CPU Flags Hyper Threading, Turbo Boost Hyper Threading, Turbo Boost, DL Boost
CPU Thermal Design Power 35 W 165 W
Operating System Ubuntu 20.04.1 LTS Ubuntu 20.04.1 LTS
Kernel Version 5.4.0-56-generic 5.4.0-52-generic
BIOS Vendor American Megatrends Inc. American Megatrends Inc.
BIOS Version and Release Date 2401, date: 07/15/2019 0603, date: 03/05/2020
Docker Version 19.03.14 19.03.13
Network Speed 10 Gb/s

Platform with Intel® Core™ i5-8500

Server Platform Client Platform
Motherboard ASUSTeK COMPUTER INC. PRIME Z370-A Gigabyte Technology Co., Ltd. Z390 UD
Memory Corsair 2 x 16GB @ 2133 MT/s DDR4 029E 4 x 8GB @ 2400 MT/s DDR4
CPU Intel® Core™ i5-8500 CPU @ 3.00GHz Intel® Core™ i3-8100 CPU @ 3.60GHz
Selected CPU Flags Turbo Boost -
CPU Thermal Design Power 65 W 65 W
Operating System Ubuntu 20.04.1 LTS Ubuntu 20.04.1 LTS
Kernel Version 5.4.0-52-generic 5.4.0-52-generic
BIOS Vendor American Megatrends Inc. American Megatrends Inc.
BIOS Version and Release Date 2401, date: 07/12/2019 F10j, date: 09/16/2020
Docker Version 19.03.13 20.10.0
Network Speed 40 Gb/s

Platform with Intel® Core™ i3-8100

Server Platform Client Platform
Motherboard Gigabyte Technology Co., Ltd. Z390 UD ASUSTeK COMPUTER INC. PRIME Z370-A
Memory 029E 4 x 8GB @ 2400 MT/s DDR4 Corsair 2 x 16GB @ 2133 MT/s DDR4
CPU Intel® Core™ i3-8100 CPU @ 3.60GHz Intel® Core™ i5-8500 CPU @ 3.00GHz
Selected CPU Flags - Turbo Boost
CPU Thermal Design Power 65 W 65 W
Operating System Ubuntu 20.04.1 LTS Ubuntu 20.04.1 LTS
Kernel Version 5.4.0-52-generic 5.4.0-52-generic
BIOS Vendor American Megatrends Inc. American Megatrends Inc.
BIOS Version and Release Date F10j, date: 09/16/2020 2401, date: 07/12/2019
Docker Version 20.10.0 19.03.13
Network Speed 40 Gb/s

Supported Image Formats for OVMS Compression

  • Always supported:

    • Portable image format - *.pbm, *.pgm, *.ppm *.pxm, *.pnm

    • Radiance HDR - *.hdr, *.pic

    • Sun rasters - *.sr, *.ras

    • Windows bitmaps - *.bmp, *.dib

  • Limited support (please see OpenCV documentation):

    • Raster and Vector geospatial data supported by GDAL

    • JPEG files - *.jpeg, *.jpg, *.jpe

    • Portable Network Graphics - *.png

    • TIFF files - *.tiff, *.tif

    • OpenEXR Image files - *.exr

    • JPEG 2000 files - *.jp2

    • WebP - *.webp