---
title: 'Docker for DG2'
disqus: hackmd
---
Docker for DG2
===
## Table of Contents
[TOC]
## BKC
OV2022.2
Ubuntu 20.04
Kernel: 5.14.0-1047-oem
libdrm2: 2.4.107
libva2: 2.7.0-2
Media driver for VAAPI: 20.1.1
Mesa: 21.2.6
OpenCL* runtime: 22.39.24347
compute-runtime: https://github.com/intel/compute-runtime/releases
## Docker installation and setup
```
sudo -E apt install docker.io
#Docker proxy setting
sudo mkdir /etc/systemd/system/docker.service.d
sudo vim /etc/systemd/system/docker.service.d/http-proxy.conf
#Add proxy config as below:
[Service]
Environment="HTTP_PROXY=http://proxy02.hd.intel.com:911"
Environment="HTTPS_PROXY=http://proxy02.hd.intel.com:911"
sudo systemctl daemon-reload
sudo systemctl restart docker
```
>If you want to avoid typing sudo whenever you run the docker command, add your username to the docker group:
```
sudo usermod -aG docker ${USER}
```
> log out then re-login
To check whether you can access and download images from Docker Hub, type:
```
docker run hello-world
```
Download OV docker from docker hub
---
Ref: https://hub.docker.com/r/openvino/ubuntu20_dev
```
docker pull openvino/ubuntu20_dev
```
> If your host system is Ubuntu 20, follow the Configuration Guide for the Intel® Graphics Compute Runtime for OpenCL™ on Ubuntu* 20.04.
> https://github.com/openvinotoolkit/docker_ci/blob/master/configure_gpu_ubuntu20.md
Run docker with DG2 and download Intel compute-runtime
---
Make sure DG2 can performance inference out of docker
Run docker with DG2
Ref https://github.com/intel/compute-runtime/releases
```
docker run -it --user root --device /dev/dri --mount type=bind,source=/home/hc-adlp,destination=/home/hc-adlp --name ov2022.2 openvino/ubuntu20_dev
```
>inside docker OV2022.2 download Intel compute-runtime
```
export https_proxy="http://proxy02.hd.intel.com:911"
export http_proxy="http://proxy02.hd.intel.com:911"
apt update
apt install wget dpkg clinfo vainfo
mkdir neo
cd neo
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.12149.1/intel-igc-core_1.0.12149.1_amd64.deb
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.12149.1/intel-igc-opencl_1.0.12149.1_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.39.24347/intel-level-zero-gpu-dbgsym_1.3.24347_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/22.39.24347/intel-level-zero-gpu_1.3.24347_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.39.24347/intel-opencl-icd-dbgsym_22.39.24347_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/22.39.24347/intel-opencl-icd_22.39.24347_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/22.39.24347/libigdgmm12_22.2.0_amd64.deb
dpkg -i *.deb
#check DG2 can be detected
cd /opt/intel/openvino_2022.2.0.7713
source setupvars.sh
python3 samples/python/hello_query_device/hello_query_device.py
```
Run docker with DG2 and download Intel compute-runtime
---
```
#run benchmark_app
root@f26ccd090972:/opt/intel/openvino# benchmark_app -m /home/hc-adlp/Desktop/openvino/yolo-v4-tf/FP16-INT8/yolo-v4-tf.xml -d GPU.1 -hint none
[Step 1/11] Parsing and validating input arguments
[ WARNING ] -nstreams default value is determined automatically for a device. Although the automatic selection usually provides a reasonable performance, but it still may be non-optimal for some cases, for more information look at README.
[Step 2/11] Loading OpenVINO
[ WARNING ] No device GPU.1 performance hint is set.
[ INFO ] OpenVINO:
API version............. 2022.2.0-7713-af16ea1d79a-releases/2022/2
[ INFO ] Device info
GPU
Intel GPU plugin........ version 2022.2
Build................... 2022.2.0-7713-af16ea1d79a-releases/2022/2
[Step 3/11] Setting device configuration
[Step 4/11] Reading network files
[ INFO ] Read model took 63.82 ms
[Step 5/11] Resizing network to match image sizes and given batch
[ INFO ] Network batch size: 1
[Step 6/11] Configuring input of the model
[ INFO ] Model input 'image_input' precision u8, dimensions ([N,H,W,C]): 1 608 608 3
[ INFO ] Model output 'Func/StatefulPartitionedCall/output/_542:0' precision f32, dimensions ([...]): 1 38 38 255
[ INFO ] Model output 'Func/StatefulPartitionedCall/output/_543:0' precision f32, dimensions ([...]): 1 19 19 255
[ INFO ] Model output 'Func/StatefulPartitionedCall/output/_544:0' precision f32, dimensions ([...]): 1 76 76 255
[Step 7/11] Loading the model to the device
[ INFO ] Compile model took 6280.09 ms
[Step 8/11] Querying optimal runtime parameters
[ INFO ] DEVICE: GPU.1
[ INFO ] AVAILABLE_DEVICES , ['0', '1']
[ INFO ] RANGE_FOR_ASYNC_INFER_REQUESTS , (1, 2, 1)
[ INFO ] RANGE_FOR_STREAMS , (1, 2)
[ INFO ] OPTIMAL_BATCH_SIZE , 1
[ INFO ] MAX_BATCH_SIZE , 1
[ INFO ] FULL_DEVICE_NAME , Intel(R) Graphics [0x56a0] (dGPU)
[ INFO ] DEVICE_TYPE , Type.DISCRETE
[ INFO ] OPTIMIZATION_CAPABILITIES , ['FP32', 'BIN', 'FP16', 'INT8', 'GPU_HW_MATMUL']
[ INFO ] GPU_UARCH_VERSION , 12.7.1
[ INFO ] GPU_EXECUTION_UNITS_COUNT , 512
[ INFO ] PERF_COUNT , False
[ INFO ] MODEL_PRIORITY , Priority.MEDIUM
[ INFO ] GPU_HOST_TASK_PRIORITY , Priority.MEDIUM
[ INFO ] GPU_QUEUE_PRIORITY , Priority.MEDIUM
[ INFO ] GPU_QUEUE_THROTTLE , Priority.MEDIUM
[ INFO ] GPU_ENABLE_LOOP_UNROLLING , True
[ INFO ] CACHE_DIR ,
[ INFO ] PERFORMANCE_HINT , PerformanceMode.UNDEFINED
[ INFO ] COMPILATION_NUM_THREADS , 24
[ INFO ] NUM_STREAMS , 1
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS , 0
[ INFO ] DEVICE_ID , 1
[Step 9/11] Creating infer requests and preparing input data
[ INFO ] Create 2 infer requests took 16.46 ms
[ WARNING ] No input files were given for input 'image_input'!. This input will be filled with random values!
[ INFO ] Fill input 'image_input' with random values
[Step 10/11] Measuring performance (Start inference asynchronously, 2 inference requests, inference only: True, limits: 60000 ms duration)
[ INFO ] Benchmarking in inference only mode (inputs filling are not included in measurement loop).
[ INFO ] First inference took 39.40 ms
[Step 11/11] Dumping statistics report
Count: 5734 iterations
Duration: 60029.51 ms
Latency:
Median: 20.80 ms
AVG: 20.82 ms
MIN: 20.40 ms
MAX: 32.75 ms
Throughput: 95.52 FPS
```
>-d GPU.1 -hint none
Count: 5734 iterations
Duration: 60029.51 ms
Latency:
Median: 20.80 ms
AVG: 20.82 ms
MIN: 20.40 ms
MAX: 32.75 ms
Throughput: 95.52 FPS
>-d GPU.1 -b 8 -nstream 4 -hint none
Count: 1320 iterations
Duration: 60334.69 ms
Latency:
Median: 364.93 ms
AVG: 364.83 ms
MIN: 172.10 ms
MAX: 389.45 ms
Throughput: 175.02 FPS
>-d GPU.1 -b 12 -nstream 4 -hint none
Count: 848 iterations
Duration: 60848.08 ms
Latency:
Median: 573.37 ms
AVG: 572.47 ms
MIN: 277.51 ms
MAX: 596.19 ms
Throughput: 167.24 FPS
>-d GPU.1 -b 16 -nstream 4 -hint none
Count: 32 iterations
Duration: 84140.84 ms
Latency:
Median: 20823.73 ms
AVG: 19729.30 ms
MIN: 10623.74 ms
MAX: 21496.96 ms
Throughput: 6.09 FPS
>-d GPU.1 -b 8 -nstream 8 -hint none
Count: 1344 iterations
Duration: 61195.22 ms
Latency:
Median: 727.54 ms
AVG: 724.85 ms
MIN: 164.20 ms
MAX: 747.46 ms
Throughput: 175.70 FPS
Sign in with Wallet
Connect another wallet