# ADL-P i5-12600HE
### BKC
Ubuntu 20.04.4
Kernel 5.17
OpenVINO 2022.1 release candidate : openvino_2022.1.0.643
sudo add-apt-repository ppa:tuxinvader/lts-mainline -y
sudo apt update
sudo apt-get install linux-generic-5.18
Download ADL-P GUC firmware from https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git/plain/i915/adlp_guc_69.0.3.bin
sudo cp adlp_guc_69.0.3.bin /lib/firmware/i915
```
ease@ease-Alder-Lake-Client-Platform:~/Edge-AI-Scaling-Engine-main$ ls -la /lib/firmware/i915/adl*
-rw-r--r-- 1 root root 44636 六 21 17:33 /lib/firmware/i915/adlp_dmc_ver2_09.bin
-rw-r--r-- 1 root root 44616 六 21 17:33 /lib/firmware/i915/adlp_dmc_ver2_10.bin
-rw-r--r-- 1 root root 72104 六 21 17:33 /lib/firmware/i915/adlp_dmc_ver2_12.bin
-rw-r--r-- 1 root root 336704 六 21 17:33 /lib/firmware/i915/adlp_guc_62.0.3.bin
-rw-r--r-- 1 root root 356416 八 3 09:57 /lib/firmware/i915/adlp_guc_69.0.3.bin
-rw-r--r-- 1 root root 18704 六 21 17:33 /lib/firmware/i915/adls_dmc_ver2_01.bin
```
Run hello_query_device and benchmakr_app in OpenVINO 2022.1 docker
```=bash
docker run -it -v /tmp/.X11-unix/:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v ~/Downloads:/mnt --device /dev/dri:/dev/dri --group-add=$(stat -c "%g" /dev/dri/render*) -u 0 --rm openvino/ubuntu20_dev
```
### Linux 5.18.15 + adlp_guc_69.0.3.bin
```
ease@ease-Alder-Lake-Client-Platform:~/Edge-AI-Scaling-Engine-main$ bash ./run_yolo-v4-tf-int8-gpu_benchmark.sh
Unable to find image 'openvino/ubuntu20_dev:latest' locally
latest: Pulling from openvino/ubuntu20_dev
4d32b49e2995: Pull complete
78e849544284: Pull complete
411e67941194: Pull complete
17aa49426650: Pull complete
72ab56fa1a5a: Pull complete
d8adffee6d1a: Pull complete
b007c88a84bf: Pull complete
5984552a91bf: Pull complete
abe14cd62399: Pull complete
f4cfc712c94f: Pull complete
0c11c7f719aa: Pull complete
5010b5e477bd: Pull complete
b09aac8251a8: Pull complete
b84b10ce4442: Pull complete
6e30a9ddc8c9: Pull complete
634b755f48de: Pull complete
f45e21edd0a2: Pull complete
43162a191a42: Pull complete
3ee2595956b3: Pull complete
723d0062b71d: Pull complete
Digest: sha256:3b16f830655f89639e5a99b172a2db5cbb67e1f9f6f1154423852e9985eb5f05
Status: Downloaded newer image for openvino/ubuntu20_dev:latest
b75147fe24d5672239022430b5e8da7e630e8b981eaed786dbbdb31ca5c38cb8
[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 ] PerformanceMode was not explicitly specified in command line. Device GPU performance hint will be set to THROUGHPUT.
[ INFO ] OpenVINO:
API version............. 2022.1.0-7019-cdb9bec7210-releases/2022/1
[ INFO ] Device info
GPU
Intel GPU plugin........ version 2022.1
Build................... 2022.1.0-7019-cdb9bec7210-releases/2022/1
[Step 3/11] Setting device configuration
[ WARNING ] -nstreams default value is determined automatically for GPU 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 4/11] Reading network files
[ INFO ] Read model took 62.33 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 3813.04 ms
[Step 8/11] Querying optimal runtime parameters
[ INFO ] DEVICE: GPU
[ INFO ] AVAILABLE_DEVICES , ['0']
[ 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 [0x4626] (iGPU)
[ INFO ] OPTIMIZATION_CAPABILITIES , ['FP32', 'BIN', 'FP16', 'INT8']
[ INFO ] GPU_UARCH_VERSION , 12.0.0
[ INFO ] GPU_EXECUTION_UNITS_COUNT , 80
[ INFO ] PERF_COUNT , False
[ INFO ] GPU_ENABLE_LOOP_UNROLLING , True
[ INFO ] CACHE_DIR ,
[ INFO ] COMPILATION_NUM_THREADS , 16
[ INFO ] NUM_STREAMS , 1
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS , 0
[ INFO ] DEVICE_ID , 0
[Step 9/11] Creating infer requests and preparing input data
[ INFO ] Create 2 infer requests took 6.81 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 using 1 streams for GPU, 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 51.87 ms
[Step 11/11] Dumping statistics report
Count: 1368 iterations
Duration: 60110.80 ms
Latency:
Median: 87.64 ms
AVG: 87.69 ms
MIN: 48.70 ms
MAX: 93.42 ms
Throughput: 22.76 FPS
```
### Install Docker Utility
```
sudo apt update
sudo apt-get remove docker docker-engine docker.io containerd runc
sudo apt install curl
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh
sudo usermod -aG docker $USER
## Need to logout or reboot to run docker as non-root user
docker run hello-world
```
### Logs for hello_query_device
```=bash
ease@ease-adl-p:~$ docker run -it -v /tmp/.X11-unix/:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v ~/Downloads:/mnt --device /dev/dri:/dev/dri --group-add=$(stat -c "%g" /dev/dri/render*) -u 0 --rm openvino/ubuntu20_dev
groups: cannot find name for group ID 109
root@bea722e8a3e8:/opt/intel/openvino_2022.1.0.643# cd samples/
root@bea722e8a3e8:/opt/intel/openvino_2022.1.0.643/samples# cd python/hello_query_device/
root@bea722e8a3e8:/opt/intel/openvino_2022.1.0.643/samples/python/hello_query_device# python3 hello_query_device.py
[ INFO ] Available devices:
[E:] [BSL] found 0 ioexpander device
E: [xLinkUsb] [ 474706] [python3] usb_find_device_with_bcd:266 Library has not been initialized when loaded
[ INFO ] CPU :
[ INFO ] SUPPORTED_PROPERTIES:
[ INFO ] AVAILABLE_DEVICES:
[ INFO ] RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1
[ INFO ] RANGE_FOR_STREAMS: 1, 16
[ INFO ] FULL_DEVICE_NAME: 12th Gen Intel(R) Core(TM) i5-12600HE
[ INFO ] OPTIMIZATION_CAPABILITIES: FP32, FP16, INT8, BIN, EXPORT_IMPORT
[ INFO ] CACHE_DIR:
[ INFO ] NUM_STREAMS: 1
[ INFO ] AFFINITY: UNSUPPORTED TYPE
[ INFO ] INFERENCE_NUM_THREADS: 0
[ INFO ] PERF_COUNT: False
[ INFO ] INFERENCE_PRECISION_HINT: UNSUPPORTED TYPE
[ INFO ] PERFORMANCE_HINT: UNSUPPORTED TYPE
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS: 0
[ INFO ]
[ INFO ] GNA :
[ INFO ] SUPPORTED_PROPERTIES:
[ INFO ] AVAILABLE_DEVICES: GNA_SW
[ INFO ] OPTIMAL_NUMBER_OF_INFER_REQUESTS: 1
[ INFO ] RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1
[ INFO ] OPTIMIZATION_CAPABILITIES: INT16, INT8, EXPORT_IMPORT
[ INFO ] FULL_DEVICE_NAME: GNA_SW
[ INFO ] GNA_LIBRARY_FULL_VERSION: 3.0.0.1455
[ INFO ] GNA_SCALE_FACTOR_PER_INPUT: UNSUPPORTED TYPE
[ INFO ] GNA_FIRMWARE_MODEL_IMAGE:
[ INFO ] GNA_DEVICE_MODE: GNA_SW_EXACT
[ INFO ] GNA_HW_EXECUTION_TARGET: UNSUPPORTED TYPE
[ INFO ] GNA_HW_COMPILE_TARGET: UNSUPPORTED TYPE
[ INFO ] GNA_PWL_DESIGN_ALGORITHM: UNSUPPORTED TYPE
[ INFO ] GNA_PWL_MAX_ERROR_PERCENT: 1.000000
[ INFO ] PERFORMANCE_HINT: UNSUPPORTED TYPE
[ INFO ] INFERENCE_PRECISION_HINT: UNSUPPORTED TYPE
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS: 1
[ INFO ] LOG_LEVEL: LOG_NONE
[ INFO ]
[ INFO ] GPU :
[ INFO ] SUPPORTED_PROPERTIES:
[ INFO ] AVAILABLE_DEVICES: 0
[ 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 [0x4626] (iGPU)
[ INFO ] DEVICE_TYPE: UNSUPPORTED TYPE
[ INFO ] DEVICE_GOPS: UNSUPPORTED TYPE
[ INFO ] OPTIMIZATION_CAPABILITIES: FP32, BIN, FP16, INT8
[ INFO ] GPU_DEVICE_TOTAL_MEM_SIZE: UNSUPPORTED TYPE
[ INFO ] GPU_UARCH_VERSION: 12.0.0
[ INFO ] GPU_EXECUTION_UNITS_COUNT: 80
[ INFO ] GPU_MEMORY_STATISTICS: UNSUPPORTED TYPE
[ INFO ] PERF_COUNT: False
[ INFO ] MODEL_PRIORITY: UNSUPPORTED TYPE
[ INFO ] GPU_HOST_TASK_PRIORITY: UNSUPPORTED TYPE
[ INFO ] GPU_QUEUE_PRIORITY: UNSUPPORTED TYPE
[ INFO ] GPU_QUEUE_THROTTLE: UNSUPPORTED TYPE
[ INFO ] GPU_ENABLE_LOOP_UNROLLING: True
[ INFO ] CACHE_DIR:
[ INFO ] PERFORMANCE_HINT: UNSUPPORTED TYPE
[ INFO ] COMPILATION_NUM_THREADS: 16
[ INFO ] NUM_STREAMS: 1
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS: 0
[ INFO ] DEVICE_ID: 0
[ INFO ]
root@bea722e8a3e8:/opt/intel/openvino_2022.1.0.643/samples/python/hello_query_device#
```
### Logs for benchmark_app
```=bash
root@bea722e8a3e8:~# benchmark_app -m /mnt/Edge-AI-Scaling-Engine/openvino_models/public/yolo-v3-tf/FP16-INT8/yolo-v3-tf.xml
[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 ] PerformanceMode was not explicitly specified in command line. Device CPU performance hint will be set to THROUGHPUT.
[ INFO ] OpenVINO:
API version............. 2022.1.0-7019-cdb9bec7210-releases/2022/1
[ INFO ] Device info
CPU
openvino_intel_cpu_plugin version 2022.1
Build................... 2022.1.0-7019-cdb9bec7210-releases/2022/1
[Step 3/11] Setting device configuration
[ WARNING ] -nstreams default value is determined automatically for CPU 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 4/11] Reading network files
[ INFO ] Read model took 67.30 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 'input_1' precision u8, dimensions ([N,C,H,W]): 1 3 416 416
[ INFO ] Model output 'conv2d_58/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 13 13
[ INFO ] Model output 'conv2d_66/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 26 26
[ INFO ] Model output 'conv2d_74/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 52 52
[Step 7/11] Loading the model to the device
[ INFO ] Compile model took 244.65 ms
[Step 8/11] Querying optimal runtime parameters
[ INFO ] DEVICE: CPU
[ INFO ] AVAILABLE_DEVICES , ['']
[ INFO ] RANGE_FOR_ASYNC_INFER_REQUESTS , (1, 1, 1)
[ INFO ] RANGE_FOR_STREAMS , (1, 16)
[ INFO ] FULL_DEVICE_NAME , 12th Gen Intel(R) Core(TM) i5-12600HE
[ INFO ] OPTIMIZATION_CAPABILITIES , ['FP32', 'FP16', 'INT8', 'BIN', 'EXPORT_IMPORT']
[ INFO ] CACHE_DIR ,
[ INFO ] NUM_STREAMS , 4
[ INFO ] INFERENCE_NUM_THREADS , 0
[ INFO ] PERF_COUNT , False
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS , 0
[Step 9/11] Creating infer requests and preparing input data
[ INFO ] Create 4 infer requests took 0.35 ms
[ WARNING ] No input files were given for input 'input_1'!. This input will be filled with random values!
[ INFO ] Fill input 'input_1' with random values
[Step 10/11] Measuring performance (Start inference asynchronously, 4 inference requests using 4 streams for CPU, 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 71.65 ms
[Step 11/11] Dumping statistics report
Count: 1980 iterations
Duration: 60104.05 ms
Latency:
Median: 93.36 ms
AVG: 121.31 ms
MIN: 69.35 ms
MAX: 242.61 ms
Throughput: 32.94 FPS
root@bea722e8a3e8:~# benchmark_app -m /mnt/Edge-AI-Scaling-Engine/openvino_models/public/yolo-v3-tf/FP16-INT8/yolo-v3-tf.xml -d GPU
[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 ] PerformanceMode was not explicitly specified in command line. Device GPU performance hint will be set to THROUGHPUT.
[ INFO ] OpenVINO:
API version............. 2022.1.0-7019-cdb9bec7210-releases/2022/1
[ INFO ] Device info
GPU
Intel GPU plugin........ version 2022.1
Build................... 2022.1.0-7019-cdb9bec7210-releases/2022/1
[Step 3/11] Setting device configuration
[ WARNING ] -nstreams default value is determined automatically for GPU 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 4/11] Reading network files
[ INFO ] Read model took 32.22 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 'input_1' precision u8, dimensions ([N,C,H,W]): 1 3 416 416
[ INFO ] Model output 'conv2d_58/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 13 13
[ INFO ] Model output 'conv2d_66/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 26 26
[ INFO ] Model output 'conv2d_74/Conv2D/YoloRegion' precision f32, dimensions ([...]): 1 255 52 52
[Step 7/11] Loading the model to the device
[ INFO ] Compile model took 2506.88 ms
[Step 8/11] Querying optimal runtime parameters
[ INFO ] DEVICE: GPU
[ INFO ] AVAILABLE_DEVICES , ['0']
[ 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 [0x4626] (iGPU)
[ INFO ] OPTIMIZATION_CAPABILITIES , ['FP32', 'BIN', 'FP16', 'INT8']
[ INFO ] GPU_UARCH_VERSION , 12.0.0
[ INFO ] GPU_EXECUTION_UNITS_COUNT , 80
[ INFO ] PERF_COUNT , False
[ INFO ] GPU_ENABLE_LOOP_UNROLLING , True
[ INFO ] CACHE_DIR ,
[ INFO ] COMPILATION_NUM_THREADS , 16
[ INFO ] NUM_STREAMS , 1
[ INFO ] PERFORMANCE_HINT_NUM_REQUESTS , 0
[ INFO ] DEVICE_ID , 0
[Step 9/11] Creating infer requests and preparing input data
[ INFO ] Create 2 infer requests took 3.59 ms
[ WARNING ] No input files were given for input 'input_1'!. This input will be filled with random values!
[ INFO ] Fill input 'input_1' with random values
[Step 10/11] Measuring performance (Start inference asynchronously, 2 inference requests using 1 streams for GPU, 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 25.35 ms
[Step 11/11] Dumping statistics report
Count: 3012 iterations
Duration: 60073.86 ms
Latency:
Median: 39.73 ms
AVG: 39.72 ms
MIN: 23.40 ms
MAX: 46.89 ms
Throughput: 50.14 FPS
root@bea722e8a3e8:~#
```
### Logs for lscpu
```=bash
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 46 bits physical, 48 bits virtual
CPU(s): 16
On-line CPU(s) list: 0-15
Thread(s) per core: 1
Core(s) per socket: 12
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 154
Model name: 12th Gen Intel(R) Core(TM) i5-12600HE
Stepping: 3
CPU MHz: 2600.000
CPU max MHz: 4500.0000
CPU min MHz: 400.0000
BogoMIPS: 5222.40
Virtualization: VT-x
L1d cache: 288 KiB
L1i cache: 192 KiB
L2 cache: 7.5 MiB
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch
_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pc
id sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l2 invpcid_single cdp_l2 ssbd ibrs ibpb st
ibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdt_a rdseed adx smap clflushopt clwb intel_pt sha_ni
xsaveopt xsavec xgetbv1 xsaves split_lock_detect avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req umip pku ospke waitpkg gfni vaes vpclm
ulqdq tme rdpid movdiri movdir64b fsrm md_clear serialize pconfig arch_lbr flush_l1d arch_capabilities
```
Sign in with Wallet
Connect another wallet