IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Benchmarks 2021 2 (#3590)

Browse Source 
* Initial changes

* Updates

* Updates

* Updates

* Fixed graph names

* minor fix

* Fixed link

* Implemented changes according to the review changes

* fixed links

* Updated Legal_Information.md according to review feedback

* Replaced  Uzel* UI-AR8 with Mustang-V100-MX8
This commit is contained in:
Andrey Zaytsev
2020-12-15 13:52:15 +03:00
committed by GitHub
parent f128545a2a
commit 4dfeba454b
6 changed files with 189 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/Legal_Information.md
View File

@@ -4,9 +4,7 @@ This software and the related documents are Intel copyrighted materials, and you
This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps. The products and services described may contain defects or errors known as errata which may cause deviations from published specifications. Current characterized errata are available on request. Copies of documents which have an order number and are referenced in this document may be obtained by calling 1-800-548-4725 or by visiting [www.intel.com/design/literature.htm](https://www.intel.com/design/literature.htm).
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors.
Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit [www.intel.com/benchmarks](https://www.intel.com/benchmarks).
Performance varies by use, configuration and other factors. Learn more at [www.intel.com/PerformanceIndex](https://www.intel.com/PerformanceIndex).
Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure.
@@ -14,7 +12,7 @@ Your costs and results may vary.
Intel technologies may require enabled hardware, software or service activation.
© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. \*Other names and brands may be claimed as the property of others.
© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. \*Other names and brands may be claimed as the property of others.
## OpenVINO™ Logo
To build equity around the project, the OpenVINO logo was created for both Intel and community usage. The logo may only be used to represent the OpenVINO toolkit and offerings built using the OpenVINO toolkit.

173
docs/benchmarks/performance_benchmarks.md
View File

@@ -26,127 +26,174 @@ Measuring inference performance involves many variables and is extremely use-cas
\htmlonly
<script src="bert-large-uncased-whole-word-masking-squad-int8-0001-ov-2021-1-096.js" id="bert-large-uncased-whole-word-masking-squad-int8-0001-ov-2021-1-096"></script>
<script src="bert-large-uncased-whole-word-masking-squad-int8-0001-ov-2021-2-170.js" id="bert-large-uncased-whole-word-masking-squad-int8-0001-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="deeplabv3-tf-ov-2021-1-096.js" id="deeplabv3-tf-ov-2021-1-096"></script>
<script src="deeplabv3-tf-ov-2021-2-170.js" id="deeplabv3-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="densenet-121-tf-ov-2021-1-096.js" id="densenet-121-tf-ov-2021-1-096"></script>
<script src="densenet-121-tf-ov-2021-2-170.js" id="densenet-121-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="faster-rcnn-resnet50-coco-tf-ov-2021-1-096.js" id="faster-rcnn-resnet50-coco-tf-ov-2021-1-096"></script>
<script src="faster-rcnn-resnet50-coco-tf-ov-2021-2-170.js" id="faster-rcnn-resnet50-coco-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="googlenet-v1-tf-ov-2021-1-096.js" id="googlenet-v1-tf-ov-2021-1-096"></script>
<script src="googlenet-v1-tf-ov-2021-2-170.js" id="googlenet-v1-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="inception-v3-tf-ov-2021-1-096.js" id="inception-v3-tf-ov-2021-1-096"></script>
<script src="inception-v3-tf-ov-2021-2-170.js" id="inception-v3-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="mobilenet-ssd-cf-ov-2021-1-096.js" id="mobilenet-ssd-cf-ov-2021-1-096"></script>
<script src="mobilenet-ssd-cf-ov-2021-2-170.js" id="mobilenet-ssd-cf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="mobilenet-v1-1-0-224-tf-ov-2021-1-096.js" id="mobilenet-v1-1-0-224-tf-ov-2021-1-096"></script>
<script src="mobilenet-v1-1-0-224-tf-ov-2021-2-170.js" id="mobilenet-v1-1-0-224-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="mobilenet-v2-pytorch-ov-2021-1-096.js" id="mobilenet-v2-pytorch-ov-2021-1-096"></script>
<script src="mobilenet-v2-pytorch-ov-2021-2-170.js" id="mobilenet-v2-pytorch-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="resnet-18-pytorch-ov-2021-1-096.js" id="resnet-18-pytorch-ov-2021-1-096"></script>
<script src="resnet-18-pytorch-ov-2021-2-170.js" id="resnet-18-pytorch-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="resnet-50-tf-ov-2021-1-096.js" id="resnet-50-tf-ov-2021-1-096"></script>
<script src="resnet-50-tf-ov-2021-2-170.js" id="resnet-50-tf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="se-resnext-50-cf-ov-2021-1-096.js" id="se-resnext-50-cf-ov-2021-1-096"></script>
<script src="se-resnext-50-cf-ov-2021-2-170.js" id="se-resnext-50-cf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="squeezenet1-1-cf-ov-2021-1-096.js" id="squeezenet1-1-cf-ov-2021-1-096"></script>
<script src="squeezenet1-1-cf-ov-2021-2-170.js" id="squeezenet1-1-cf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="ssd300-cf-ov-2021-1-096.js" id="ssd300-cf-ov-2021-1-096"></script>
<script src="ssd300-cf-ov-2021-2-170.js" id="ssd300-cf-ov-2021-2-170"></script>
\endhtmlonly
\htmlonly
<script src="yolo-v3-tf-ov-2021-1-096.js" id="yolo-v3-tf-ov-2021-1-096"></script>
<script src="yolo-v3-tf-ov-2021-2-170.js" id="yolo-v3-tf-ov-2021-2-170"></script>
\endhtmlonly
## Platform Configurations
Intel® Distribution of OpenVINO™ toolkit performance benchmark numbers are based on release 2021.1.
Intel® Distribution of OpenVINO™ toolkit performance benchmark numbers are based on release 2021.2.
Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the OEM or retailer. Performance results are based on testing as of September 25, 2020 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure.
Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the OEM or retailer. Performance results are based on testing as of December 9, 2020 and may not reflect all publicly available updates. See configuration disclosure for details. No product can be absolutely secure.
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information, see [Performance Benchmark Test Disclosure](https://www.intel.com/content/www/us/en/benchmarks/benchmark.html).
Performance varies by use, configuration and other factors. Learn more at [www.intel.com/PerformanceIndex](https://www.intel.com/PerformanceIndex).
Your costs and results may vary.
© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.
Optimization Notice: Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. [Notice Revision #2010804](https://software.intel.com/articles/optimization-notice).
Intel optimizations, for Intel compilers or other products, may not optimize to the same degree for non-Intel products.
Testing by Intel done on: see test date for each HW platform below.
**CPU Inference Engines**
| | Intel® Xeon® E-2124G | Intel® Xeon® Silver 4216R | Intel® Xeon® Gold 5218T | Intel® Xeon® Platinum 8270 |
| ------------------------------- | ----------------------| ---------------------------- | ---------------------------- | ---------------------------- |
| Motherboard | ASUS* WS C246 PRO | Intel® Server Board S2600STB | Intel® Server Board S2600STB | Intel® Server Board S2600STB |
| CPU | Intel® Xeon® E-2124G CPU @ 3.40GHz | Intel® Xeon® Silver 4216R CPU @ 2.20GHz | Intel® Xeon® Gold 5218T CPU @ 2.10GHz | Intel® Xeon® Platinum 8270 CPU @ 2.70GHz |
| Hyper Threading | OFF | ON | ON | ON |
| Turbo Setting | ON | ON | ON | ON |
| Memory | 2 x 16 GB DDR4 2666MHz| 12 x 32 GB DDR4 2666MHz | 12 x 32 GB DDR4 2666MHz | 12 x 32 GB DDR4 2933MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.3.0-24-generic | 5.3.0-24-generic | 5.3.0-24-generic |
| BIOS Vendor | American Megatrends Inc.* | Intel Corporation | Intel Corporation | Intel Corporation |
| BIOS Version | 0904 | SE5C620.86B.02.01.<br>0009.092820190230 | SE5C620.86B.02.01.<br>0009.092820190230 | SE5C620.86B.02.01.<br>0009.092820190230 |
| BIOS Release | April 12, 2019 | September 28, 2019 | September 28, 2019 | September 28, 2019 |
| BIOS Settings | Select optimized default settings, <br>save & exit | Select optimized default settings, <br>change power policy <br>to "performance", <br>save & exit | Select optimized default settings, <br>change power policy to "performance", <br>save & exit | Select optimized default settings, <br>change power policy to "performance", <br>save & exit |
| Batch size | 1 | 1 | 1 | 1 |
| Precision | INT8 | INT8 | INT8 | INT8 |
| Number of concurrent inference requests | 4 | 32 | 32 | 52 |
| Test Date | September 25, 2020 | September 25, 2020 | September 25, 2020 | September 25, 2020 |
| Power dissipation, TDP in Watt | [71](https://ark.intel.com/content/www/us/en/ark/products/134854/intel-xeon-e-2124g-processor-8m-cache-up-to-4-50-ghz.html#tab-blade-1-0-1) | [125](https://ark.intel.com/content/www/us/en/ark/products/193394/intel-xeon-silver-4216-processor-22m-cache-2-10-ghz.html#tab-blade-1-0-1) | [105](https://ark.intel.com/content/www/us/en/ark/products/193953/intel-xeon-gold-5218t-processor-22m-cache-2-10-ghz.html#tab-blade-1-0-1) | [205](https://ark.intel.com/content/www/us/en/ark/products/192482/intel-xeon-platinum-8270-processor-35-75m-cache-2-70-ghz.html#tab-blade-1-0-1) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [213](https://ark.intel.com/content/www/us/en/ark/products/134854/intel-xeon-e-2124g-processor-8m-cache-up-to-4-50-ghz.html) | [1,002](https://ark.intel.com/content/www/us/en/ark/products/193394/intel-xeon-silver-4216-processor-22m-cache-2-10-ghz.html) | [1,349](https://ark.intel.com/content/www/us/en/ark/products/193953/intel-xeon-gold-5218t-processor-22m-cache-2-10-ghz.html) | [7,405](https://ark.intel.com/content/www/us/en/ark/products/192482/intel-xeon-platinum-8270-processor-35-75m-cache-2-70-ghz.html) |
| | Intel® Xeon® E-2124G | Intel® Xeon® W1290P | Intel® Xeon® Silver 4216R |
| ------------------------------- | ---------------------- | --------------------------- | ---------------------------- |
| Motherboard | ASUS* WS C246 PRO | ASUS* WS W480-ACE | Intel® Server Board S2600STB |
| CPU | Intel® Xeon® E-2124G CPU @ 3.40GHz | Intel® Xeon® W-1290P CPU @ 3.70GHz | Intel® Xeon® Silver 4216R CPU @ 2.20GHz |
| Hyper Threading | OFF | ON | ON |
| Turbo Setting | ON | ON | ON |
| Memory | 2 x 16 GB DDR4 2666MHz | 4 x 16 GB DDR4 @ 2666MHz |12 x 32 GB DDR4 2666MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.3.0-24-generic | 5.3.0-24-generic |
| BIOS Vendor | American Megatrends Inc.* | American Megatrends Inc. | Intel Corporation |
| BIOS Version | 0904 | 607 | SE5C620.86B.02.01.<br>0009.092820190230 |
| BIOS Release | April 12, 2019 | May 29, 2020 | September 28, 2019 |
| BIOS Settings | Select optimized default settings, <br>save & exit | Select optimized default settings, <br>save & exit | Select optimized default settings, <br>change power policy <br>to "performance", <br>save & exit |
| Batch size | 1 | 1 | 1
| Precision | INT8 | INT8 | INT8
| Number of concurrent inference requests | 4 | 5 | 32
| Test Date | December 9, 2020 | December 9, 2020 | December 9, 2020
| Power dissipation, TDP in Watt | [71](https://ark.intel.com/content/www/us/en/ark/products/134854/intel-xeon-e-2124g-processor-8m-cache-up-to-4-50-ghz.html#tab-blade-1-0-1) | [125](https://ark.intel.com/content/www/us/en/ark/products/199336/intel-xeon-w-1290p-processor-20m-cache-3-70-ghz.html) | [125](https://ark.intel.com/content/www/us/en/ark/products/193394/intel-xeon-silver-4216-processor-22m-cache-2-10-ghz.html#tab-blade-1-0-1) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [213](https://ark.intel.com/content/www/us/en/ark/products/134854/intel-xeon-e-2124g-processor-8m-cache-up-to-4-50-ghz.html) | [539](https://ark.intel.com/content/www/us/en/ark/products/199336/intel-xeon-w-1290p-processor-20m-cache-3-70-ghz.html) |[1,002](https://ark.intel.com/content/www/us/en/ark/products/193394/intel-xeon-silver-4216-processor-22m-cache-2-10-ghz.html) |
**CPU Inference Engines (continue)**
| | Intel® Core™ i5-8500 | Intel® Core™ i7-8700T | Intel® Core™ i9-10920X | 11th Gen Intel® Core™ i5-1145G7E |
| -------------------- | ---------------------------------- | ----------------------------------- |--------------------------------------|-----------------------------------|
| Motherboard | ASUS* PRIME Z370-A | GIGABYTE* Z370M DS3H-CF | ASUS* PRIME X299-A II | Intel Corporation<br>internal/Reference Validation Platform |
| CPU | Intel® Core™ i5-8500 CPU @ 3.00GHz | Intel® Core™ i7-8700T CPU @ 2.40GHz | Intel® Core™ i9-10920X CPU @ 3.50GHz | 11th Gen Intel® Core™ i5-1145G7E @ 2.60GHz |
| Hyper Threading | OFF | ON | ON | ON |
| Turbo Setting | ON | ON | ON | ON |
| Memory | 2 x 16 GB DDR4 2666MHz | 4 x 16 GB DDR4 2400MHz | 4 x 16 GB DDR4 2666MHz | 2 x 8 GB DDR4 3200MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.0.0-23-generic | 5.0.0-23-generic | 5.8.0-05-generic |
| BIOS Vendor | American Megatrends Inc.* | American Megatrends Inc.* | American Megatrends Inc.* | Intel Corporation |
| BIOS Version | 2401 | F11 | 505 | TGLIFUI1.R00.3243.A04.2006302148 |
| BIOS Release | July 12, 2019 | March 13, 2019 | December 17, 2019 | June 30, 2020 |
| BIOS Settings | Select optimized default settings, <br>save & exit | Select optimized default settings, <br>set OS type to "other", <br>save & exit | Default Settings | Default Settings |
| Batch size | 1 | 1 | 1 | 1 |
| Precision | INT8 | INT8 | INT8 | INT8 |
| Number of concurrent inference requests | 3 | 4 | 24 | 4 |
| Test Date | September 25, 2020 | September 25, 2020 | September 25, 2020 | September 25, 2020 |
| Power dissipation, TDP in Watt | [65](https://ark.intel.com/content/www/us/en/ark/products/129939/intel-core-i5-8500-processor-9m-cache-up-to-4-10-ghz.html#tab-blade-1-0-1) | [35](https://ark.intel.com/content/www/us/en/ark/products/129948/intel-core-i7-8700t-processor-12m-cache-up-to-4-00-ghz.html#tab-blade-1-0-1) | [165](https://ark.intel.com/content/www/us/en/ark/products/198012/intel-core-i9-10920x-x-series-processor-19-25m-cache-3-50-ghz.html) | [28](https://ark.intel.com/content/www/us/en/ark/products/208081/intel-core-i5-1145g7e-processor-8m-cache-up-to-4-10-ghz.html) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [192](https://ark.intel.com/content/www/us/en/ark/products/129939/intel-core-i5-8500-processor-9m-cache-up-to-4-10-ghz.html) | [303](https://ark.intel.com/content/www/us/en/ark/products/129948/intel-core-i7-8700t-processor-12m-cache-up-to-4-00-ghz.html) | [700](https://ark.intel.com/content/www/us/en/ark/products/198012/intel-core-i9-10920x-x-series-processor-19-25m-cache-3-50-ghz.html) | [309](https://mysamples.intel.com/SAM_U_Product/ProductDetail.aspx?InputMMID=99A3D1&RequestID=0&ProductID=1213750) |
| | Intel® Xeon® Gold 5218T | Intel® Xeon® Platinum 8270 |
| ------------------------------- | ---------------------------- | ---------------------------- |
| Motherboard | Intel® Server Board S2600STB | Intel® Server Board S2600STB |
| CPU | Intel® Xeon® Gold 5218T CPU @ 2.10GHz | Intel® Xeon® Platinum 8270 CPU @ 2.70GHz |
| Hyper Threading | ON | ON |
| Turbo Setting | ON | ON |
| Memory | 12 x 32 GB DDR4 2666MHz | 12 x 32 GB DDR4 2933MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.3.0-24-generic |
| BIOS Vendor | Intel Corporation | Intel Corporation |
| BIOS Version | SE5C620.86B.02.01.<br>0009.092820190230 | SE5C620.86B.02.01.<br>0009.092820190230 |
| BIOS Release | September 28, 2019 | September 28, 2019 |
| BIOS Settings | Select optimized default settings, <br>change power policy to "performance", <br>save & exit | Select optimized default settings, <br>change power policy to "performance", <br>save & exit |
| Batch size | 1 | 1 |
| Precision | INT8 | INT8 |
| Number of concurrent inference requests |32 | 52 |
| Test Date | December 9, 2020 | December 9, 2020 |
| Power dissipation, TDP in Watt | [105](https://ark.intel.com/content/www/us/en/ark/products/193953/intel-xeon-gold-5218t-processor-22m-cache-2-10-ghz.html#tab-blade-1-0-1) | [205](https://ark.intel.com/content/www/us/en/ark/products/192482/intel-xeon-platinum-8270-processor-35-75m-cache-2-70-ghz.html#tab-blade-1-0-1) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [1,349](https://ark.intel.com/content/www/us/en/ark/products/193953/intel-xeon-gold-5218t-processor-22m-cache-2-10-ghz.html) | [7,405](https://ark.intel.com/content/www/us/en/ark/products/192482/intel-xeon-platinum-8270-processor-35-75m-cache-2-70-ghz.html) |
**CPU Inference Engines (continue)**
| | Intel® Core™ i7-8700T | Intel® Core™ i9-10920X | Intel® Core™ i9-10900TE<br>(iEi Flex BX210AI)| 11th Gen Intel® Core™ i7-1185G7 |
| -------------------- | ----------------------------------- |--------------------------------------| ---------------------------------------------|---------------------------------|
| Motherboard | GIGABYTE* Z370M DS3H-CF | ASUS* PRIME X299-A II | iEi / B595 | Intel Corporation<br>internal/Reference<br>Validation Platform |
| CPU | Intel® Core™ i7-8700T CPU @ 2.40GHz | Intel® Core™ i9-10920X CPU @ 3.50GHz | Intel® Core™ i9-10900TE CPU @ 1.80GHz | 11th Gen Intel® Core™ i7-1185G7 @ 3.00GHz |
| Hyper Threading | ON | ON | ON | ON |
| Turbo Setting | ON | ON | ON | ON |
| Memory | 4 x 16 GB DDR4 2400MHz | 4 x 16 GB DDR4 2666MHz | 2 x 8 GB DDR4 @ 2400MHz | 2 x 8 GB DDR4 3200MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.3.0-24-generic | 5.8.0-05-generic | 5.8.0-05-generic |
| BIOS Vendor | American Megatrends Inc.* | American Megatrends Inc.* | American Megatrends Inc.* | Intel Corporation |
| BIOS Version | F11 | 505 | Z667AR10 | TGLSFWI1.R00.3425.<br>A00.2010162309 |
| BIOS Release | March 13, 2019 | December 17, 2019 | July 15, 2020 | October 16, 2020 |
| BIOS Settings | Select optimized default settings, <br>set OS type to "other", <br>save & exit | Default Settings | Default Settings | Default Settings |
| Batch size | 1 | 1 | 1 | 1 |
| Precision | INT8 | INT8 | INT8 | INT8 |
| Number of concurrent inference requests |4 | 24 | 5 | 4 |
| Test Date | December 9, 2020 | December 9, 2020 | December 9, 2020 | December 9, 2020 |
| Power dissipation, TDP in Watt | [35](https://ark.intel.com/content/www/us/en/ark/products/129948/intel-core-i7-8700t-processor-12m-cache-up-to-4-00-ghz.html#tab-blade-1-0-1) | [165](https://ark.intel.com/content/www/us/en/ark/products/198012/intel-core-i9-10920x-x-series-processor-19-25m-cache-3-50-ghz.html) | [35](https://ark.intel.com/content/www/us/en/ark/products/203901/intel-core-i9-10900te-processor-20m-cache-up-to-4-60-ghz.html) | [28](https://ark.intel.com/content/www/us/en/ark/products/208081/intel-core-i5-1145g7e-processor-8m-cache-up-to-4-10-ghz.html) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [303](https://ark.intel.com/content/www/us/en/ark/products/129948/intel-core-i7-8700t-processor-12m-cache-up-to-4-00-ghz.html) | [700](https://ark.intel.com/content/www/us/en/ark/products/198012/intel-core-i9-10920x-x-series-processor-19-25m-cache-3-50-ghz.html) | [444](https://ark.intel.com/content/www/us/en/ark/products/203901/intel-core-i9-10900te-processor-20m-cache-up-to-4-60-ghz.html) | [426](https://mysamples.intel.com/SAM_U_Product/ProductDetail.aspx?InputMMID=99A3D1&RequestID=0&ProductID=1213750) |
**CPU Inference Engines (continue)**
| | Intel® Core™ i5-8500 | Intel® Core™ i5-10500TE | Intel® Core™ i5-10500TE<br>(iEi Flex-BX210AI)|
| -------------------- | ---------------------------------- | ----------------------------------- |-------------------------------------- |
| Motherboard | ASUS* PRIME Z370-A | GIGABYTE* Z490 AORUS PRO AX | iEi / B595 |
| CPU | Intel® Core™ i5-8500 CPU @ 3.00GHz | Intel® Core™ i5-10500TE CPU @ 2.30GHz | Intel® Core™ i5-10500TE CPU @ 2.30GHz |
| Hyper Threading | OFF | ON | ON |
| Turbo Setting | ON | ON | ON |
| Memory | 2 x 16 GB DDR4 2666MHz | 2 x 16 GB DDR4 @ 2666MHz | 1 x 8 GB DDR4 @ 2400MHz |
| Operating System | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS | Ubuntu* 18.04 LTS |
| Kernel Version | 5.3.0-24-generic | 5.3.0-24-generic | 5.3.0-24-generic |
| BIOS Vendor | American Megatrends Inc.* | American Megatrends Inc.* | American Megatrends Inc.* |
| BIOS Version | 2401 | F3 | Z667AR10 |
| BIOS Release | July 12, 2019 | March 25, 2020 | July 17, 2020 |
| BIOS Settings | Select optimized default settings, <br>save & exit | Select optimized default settings, <br>set OS type to "other", <br>save & exit | Default Settings |
| Batch size | 1 | 1 | 1 |
| Precision | INT8 | INT8 | INT8 |
| Number of concurrent inference requests | 3 | 4 | 4 |
| Test Date | December 9, 2020 | December 9, 2020 | December 9, 2020 |
| Power dissipation, TDP in Watt | [65](https://ark.intel.com/content/www/us/en/ark/products/129939/intel-core-i5-8500-processor-9m-cache-up-to-4-10-ghz.html#tab-blade-1-0-1)| [35](https://ark.intel.com/content/www/us/en/ark/products/203891/intel-core-i5-10500te-processor-12m-cache-up-to-3-70-ghz.html) | [35](https://ark.intel.com/content/www/us/en/ark/products/203891/intel-core-i5-10500te-processor-12m-cache-up-to-3-70-ghz.html) |
| CPU Price on September 29, 2020, USD<br>Prices may vary | [192](https://ark.intel.com/content/www/us/en/ark/products/129939/intel-core-i5-8500-processor-9m-cache-up-to-4-10-ghz.html) | [195](https://ark.intel.com/content/www/us/en/ark/products/203891/intel-core-i5-10500te-processor-12m-cache-up-to-3-70-ghz.html) | [195](https://ark.intel.com/content/www/us/en/ark/products/203891/intel-core-i5-10500te-processor-12m-cache-up-to-3-70-ghz.html) |
**CPU Inference Engines (continue)**
@@ -166,7 +213,7 @@ Testing by Intel done on: see test date for each HW platform below.
| Batch size | 1 | 1 |
| Precision | INT8 | INT8 |
| Number of concurrent inference requests | 4 | 4 |
| Test Date | September 25, 2020 | September 25, 2020 |
| Test Date | December 9, 2020 | December 9, 2020 |
| Power dissipation, TDP in Watt | [9.5](https://ark.intel.com/content/www/us/en/ark/products/96485/intel-atom-x5-e3940-processor-2m-cache-up-to-1-80-ghz.html) | [65](https://ark.intel.com/content/www/us/en/ark/products/126688/intel-core-i3-8100-processor-6m-cache-3-60-ghz.html#tab-blade-1-0-1)|
| CPU Price on September 29, 2020, USD<br>Prices may vary | [34](https://ark.intel.com/content/www/us/en/ark/products/96485/intel-atom-x5-e3940-processor-2m-cache-up-to-1-80-ghz.html) | [117](https://ark.intel.com/content/www/us/en/ark/products/126688/intel-core-i3-8100-processor-6m-cache-3-60-ghz.html) |
@@ -174,7 +221,7 @@ Testing by Intel done on: see test date for each HW platform below.
**Accelerator Inference Engines**
| | Intel® Neural Compute Stick 2 | Intel® Vision Accelerator Design<br>with Intel® Movidius™ VPUs (Uzel* UI-AR8) |
| | Intel® Neural Compute Stick 2 | Intel® Vision Accelerator Design<br>with Intel® Movidius™ VPUs (Mustang-V100-MX8) |
| --------------------------------------- | ------------------------------------- | ------------------------------------- |
| VPU | 1 X Intel® Movidius™ Myriad™ X MA2485 | 8 X Intel® Movidius™ Myriad™ X MA2485 |
| Connection | USB 2.0/3.0 | PCIe X4 |
@@ -182,7 +229,7 @@ Testing by Intel done on: see test date for each HW platform below.
| Precision | FP16 | FP16 |
| Number of concurrent inference requests | 4 | 32 |
| Power dissipation, TDP in Watt | 2.5 | [30](https://www.mouser.com/ProductDetail/IEI/MUSTANG-V100-MX8-R10?qs=u16ybLDytRaZtiUUvsd36w%3D%3D) |
| CPU Price, USD<br>Prices may vary | [69](https://ark.intel.com/content/www/us/en/ark/products/140109/intel-neural-compute-stick-2.html) (from September 29, 2020) | [768](https://www.mouser.com/ProductDetail/IEI/MUSTANG-V100-MX8-R10?qs=u16ybLDytRaZtiUUvsd36w%3D%3D) (from May 15, 2020) |
| CPU Price, USD<br>Prices may vary | [69](https://ark.intel.com/content/www/us/en/ark/products/140109/intel-neural-compute-stick-2.html) (from December 9, 2020) | [214](https://www.arrow.com/en/products/mustang-v100-mx8-r10/iei-technology?gclid=Cj0KCQiA5bz-BRD-ARIsABjT4ng1v1apmxz3BVCPA-tdIsOwbEjTtqnmp_rQJGMfJ6Q2xTq6ADtf9OYaAhMUEALw_wcB) (from December 9, 2020) |
| Host Computer | Intel® Core™ i7 | Intel® Core™ i5 |
| Motherboard | ASUS* Z370-A II | Uzelinfo* / US-E1300 |
| CPU | Intel® Core™ i7-8700 CPU @ 3.20GHz | Intel® Core™ i5-6600 CPU @ 3.30GHz |
@@ -194,9 +241,9 @@ Testing by Intel done on: see test date for each HW platform below.
| BIOS Vendor | American Megatrends Inc.* | American Megatrends Inc.* |
| BIOS Version | 411 | 5.12 |
| BIOS Release | September 21, 2018 | September 21, 2018 |
| Test Date | September 25, 2020 | September 25, 2020 |
| Test Date | December 9, 2020 | December 9, 2020 |
Please follow this link for more detailed configuration descriptions: [Configuration Details](https://docs.openvinotoolkit.org/resources/benchmark_files/system_configurations_2021.1.html)
Please follow this link for more detailed configuration descriptions: [Configuration Details](https://docs.openvinotoolkit.org/resources/benchmark_files/system_configurations_2021.2.html)
\htmlonly
<style>
@@ -207,7 +254,7 @@ Please follow this link for more detailed configuration descriptions: [Configura
<div class="opt-notice-wrapper">
<p class="opt-notice">
\endhtmlonly
For more complete information about performance and benchmark results, visit: [www.intel.com/benchmarks](https://www.intel.com/benchmarks) and [Optimization Notice](https://software.intel.com/articles/optimization-notice). [Legal Information](../Legal_Information.md).
Results may vary. For workloads and configurations visit: [www.intel.com/PerformanceIndex](https://www.intel.com/PerformanceIndex) and [Legal Information](../Legal_Information.md).
\htmlonly
</p>
</div>

2
docs/benchmarks/performance_benchmarks_faq.md
View File

@@ -49,7 +49,7 @@ Intel partners with various vendors all over the world. Visit the [Intel® AI: I
We published a set of guidelines and recommendations to optimize your models available in an [introductory](../IE_DG/Intro_to_Performance.md) guide and an [advanced](../optimization_guide/dldt_optimization_guide.md) guide. For further support, please join the conversation in the [Community Forum](https://software.intel.com/en-us/forums/intel-distribution-of-openvino-toolkit).
#### 9. Why are INT8 optimized models used for benchmarking on CPUs with no VNNI support?
The benefit of low-precision optimization using the OpenVINO™ toolkit model optimizer extends beyond processors supporting VNNI through Intel® DL Boost. The reduced bit width of INT8 compared to FP32 allows Intel® CPU to process the data faster and thus offers better throughput on any converted model agnostic of the intrinsically supported low-precision optimizations within Intel® hardware. Please refer to [INT8 vs. FP32 Comparison on Select Networks and Platforms](./performance_int8_vs_fp32.html) for comparison on boost factors for different network models and a selection of Intel® CPU architectures, including AVX-2 with Intel® Core™ i7-8700T, and AVX-512 (VNNI) with Intel® Xeon® 5218T and Intel® Xeon® 8270.
The benefit of low-precision optimization using the OpenVINO™ toolkit model optimizer extends beyond processors supporting VNNI through Intel® DL Boost. The reduced bit width of INT8 compared to FP32 allows Intel® CPU to process the data faster and thus offers better throughput on any converted model agnostic of the intrinsically supported low-precision optimizations within Intel® hardware. Please refer to [INT8 vs. FP32 Comparison on Select Networks and Platforms](performance_int8_vs_fp32.md) for comparison on boost factors for different network models and a selection of Intel® CPU architectures, including AVX-2 with Intel® Core™ i7-8700T, and AVX-512 (VNNI) with Intel® Xeon® 5218T and Intel® Xeon® 8270.
#### 10. Previous releases included benchmarks on googlenet-v1-CF (Caffe). Why is there no longer benchmarks on this neural network model?
We replaced googlenet-v1-CF to resnet-18-pytorch due to changes in developer usage. The public model resnet-18 is used by many developers as an Image Classification model. This pre-optimized model was also trained on the ImageNet database, similar to googlenet-v1-CF. Both googlenet-v1-CF and resnet-18 will remain part of the Open Model Zoo. Developers are encouraged to utilize resnet-18-pytorch for Image Classification use cases.

155
docs/benchmarks/performance_int8_vs_fp32.md
View File

@@ -9,40 +9,36 @@ The table below illustrates the speed-up factor for the performance gain by swit
<th>Intel® Core™ <br>i7-8700T</th>
<th>Intel® Xeon® <br>Gold <br>5218T</th>
<th>Intel® Xeon® <br>Platinum <br>8270</th>
<th>Intel® Core™ <br>i7-1065G7</th>
<th>Intel® Core™ <br>i5-1145G7E</th>
<th>Intel® Core™ <br>i7-1185G7</th>
</tr>
<tr align="left">
<th>OpenVINO <br>benchmark <br>model name</th>
<th>Dataset</th>
<th colspan="4" align="center">Throughput speed-up FP16-INT8 vs FP32</th>
<th colspan="3" align="center">Throughput speed-up FP16-INT8 vs FP32</th>
</tr>
<tr>
<td>bert-large-<br>uncased-whole-word-<br>masking-squad-0001</td>
<td>SQuAD</td>
<td>1.6</td>
<td>2.5</td>
<td>2.7</td>
<td>2.0</td>
<td>N/A</td>
<td>2.8</td>
<td>2.6</td>
</tr>
<tr>
<td>brain-tumor-<br>segmentation-<br>0001-MXNET</td>
<td>BraTS</td>
<td>1.5</td>
<td>1.7</td>
<td>1.6</td>
<td>1.9</td>
<td>1.7</td>
<td>1.8</td>
</tr>
<tr>
<td>deeplabv3-TF</td>
<td>VOC 2012<br>Segmentation</td>
<td>1.4</td>
<td>1.5</td>
<td>2.4</td>
<td>2.6</td>
<td>2.8</td>
<td>2.9</td>
<td>3.1</td>
</tr>
<tr>
<td>densenet-121-TF</td>
@@ -50,7 +46,6 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>1.6</td>
<td>3.2</td>
<td>3.2</td>
<td>3.0</td>
<td>3.2</td>
</tr>
<tr>
@@ -59,17 +54,15 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>2.0</td>
<td>3.6</td>
<td>3.5</td>
<td>3.2</td>
<td>3.5</td>
<td>3.4</td>
</tr>
<tr>
<td>faster_rcnn_<br>resnet50_coco-TF</td>
<td>MS COCO</td>
<td>1.7</td>
<td>3.5</td>
<td>3.4</td>
<td>3.6</td>
<td>3.6</td>
<td>3.4</td>
<td>3.4</td>
</tr>
<tr>
<td>googlenet-v1-TF</td>
@@ -78,7 +71,6 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>3.6</td>
<td>3.7</td>
<td>3.5</td>
<td>3.6</td>
</tr>
<tr>
<td>inception-v3-TF</td>
@@ -86,43 +78,38 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>1.8</td>
<td>3.8</td>
<td>4.0</td>
<td>3.7</td>
<td>3.7</td>
<td>3.5</td>
</tr>
<tr>
<td>mobilenet-<br>ssd-CF</td>
<td>VOC2012</td>
<td>1.5</td>
<td>3.0</td>
<td>3.3</td>
<td>3.1</td>
<td>3.3</td>
<td>3.6</td>
<td>3.1</td>
</tr>
<tr>
<td>mobilenet-v1-1.0-<br>224-TF</td>
<td>ImageNet</td>
<td>1.5</td>
<td>3.2</td>
<td>3.9</td>
<td>2.9</td>
<td>3.2</td>
<td>4.1</td>
<td>3.1</td>
</tr>
<tr>
<td>mobilenet-v2-1.0-<br>224-TF</td>
<td>ImageNet</td>
<td>1.3</td>
<td>2.7</td>
<td>3.8</td>
<td>2.2</td>
<td>4.3</td>
<td>2.5</td>
</tr>
<tr>
<td>mobilenet-v2-<br>pytorch</td>
<td>ImageNet</td>
<td>1.4</td>
<td>2.6</td>
<td>3.6</td>
<td>2.3</td>
<td>2.8</td>
<td>4.6</td>
<td>2.4</td>
</tr>
<tr>
@@ -132,61 +119,54 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>3.7</td>
<td>3.8</td>
<td>3.6</td>
<td>3.6</td>
</tr>
<tr>
<td>resnet-50-<br>pytorch</td>
<td>ImageNet</td>
<td>1.8</td>
<td>3.6</td>
<td>3.8</td>
<td>3.5</td>
<td>3.6</td>
<td>3.9</td>
<td>3.4</td>
</tr>
<tr>
<td>resnet-50-<br>TF</td>
<td>ImageNet</td>
<td>1.8</td>
<td>3.5</td>
<td>3.8</td>
<td>3.6</td>
<td>3.9</td>
<td>3.4</td>
<td>4.0</td>
</tr>
<tr>
<td>squeezenet1.1-<br>CF</td>
<td>ImageNet</td>
<td>1.6</td>
<td>2.9</td>
<td>3.2</td>
<td>3.0</td>
<td>3.4</td>
<td>3.2</td>
</tr>
<tr>
<td>ssd_mobilenet_<br>v1_coco-tf</td>
<td>VOC2012</td>
<td>1.6</td>
<td>3.0</td>
<td>3.4</td>
<td>3.1</td>
<td>3.3</td>
<td>3.7</td>
<td>3.0</td>
</tr>
<tr>
<td>ssd300-CF</td>
<td>MS COCO</td>
<td>1.8</td>
<td>3.7</td>
<td>3.6</td>
<td>3.7</td>
<td>3.8</td>
<td>4.0</td>
</tr>
<tr>
<td>ssdlite_<br>mobilenet_<br>v2-TF</td>
<td>MS COCO</td>
<td>1.4</td>
<td>2.3</td>
<td>3.1</td>
<td>2.4</td>
<td>2.6</td>
<td>3.9</td>
<td>2.5</td>
</tr>
<tr>
<td>yolo_v3-TF</td>
@@ -194,8 +174,7 @@ The table below illustrates the speed-up factor for the performance gain by swit
<td>1.8</td>
<td>3.8</td>
<td>3.9</td>
<td>3.7</td>
<td>3.8</td>
<td>3.6</td>
</tr>
</table>
@@ -208,21 +187,14 @@ The following table shows the absolute accuracy drop that is calculated as the d
<th></th>
<th>Intel® Core™ <br>i9-10920X CPU<br>@ 3.50GHZ (VNNI)</th>
<th>Intel® Core™ <br>i9-9820X CPU<br>@ 3.30GHz (AVX512)</th>
<th>Intel® Core™ <br>i7-8700 CPU<br>@ 3.20GHz (AVX2)</th>
<th>Intel® Core™ <br>i7-6700 CPU<br>@ 4.0GHz (AVX2)</th>
<th>Intel® Core™ <br>i7-1185G7 CPU<br>@ 4.0GHz (TGL VNNI)</th>
</tr>
<tr align="left">
<th>OpenVINO Benchmark <br>Model Name</th>
<th>Dataset</th>
<th>Metric Name</th>
<th colspan="3" align="center">Absolute Accuracy Drop, %</th>
</tr>
<tr>
<td>bert-large-<br>uncased-whole-word-<br>masking-squad-0001</td>
<td>SQuAD</td>
<td>F1</td>
<td>0.65</td>
<td>0.57</td>
<td>0.83</td>
<th colspan="4" align="center">Absolute Accuracy Drop, %</th>
</tr>
<tr>
<td>brain-tumor-<br>segmentation-<br>0001-MXNET</td>
@@ -230,23 +202,26 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>Dice-index@ <br>Mean@ <br>Overall Tumor</td>
<td>0.08</td>
<td>0.08</td>
<td>0.9</td>
<td>0.08</td>
<td>0.08</td>
</tr>
<tr>
<td>deeplabv3-TF</td>
<td>VOC 2012<br>Segmentation</td>
<td>mean_iou</td>
<td>0.73</td>
<td>1.10</td>
<td>1.10</td>
<td>0.73</td>
<td>1.11</td>
</tr>
<tr>
<td>densenet-121-TF</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.74</td>
<td>0.74</td>
<td>0.76</td>
<td>0.73</td>
<td>0.72</td>
<td>0.72</td>
<td>0.73</td>
</tr>
<tr>
<td>facenet-<br>20180408-<br>102900-TF</td>
@@ -255,22 +230,25 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.02</td>
<td>0.02</td>
<td>0.02</td>
<td>0.47</td>
</tr>
<tr>
<td>faster_rcnn_<br>resnet50_coco-TF</td>
<td>MS COCO</td>
<td>coco_<br>precision</td>
<td>0.21</td>
<td>0.21</td>
<td>0.20</td>
<td>0.20</td>
<td>0.21</td>
</tr>
<tr>
<td>googlenet-v1-TF</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.03</td>
<td>0.03</td>
<td>0.01</td>
<td>0.01</td>
<td>0.03</td>
</tr>
<tr>
<td>inception-v3-TF</td>
@@ -279,6 +257,7 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.03</td>
<td>0.01</td>
<td>0.01</td>
<td>0.03</td>
</tr>
<tr>
<td>mobilenet-<br>ssd-CF</td>
@@ -287,6 +266,7 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.35</td>
<td>0.34</td>
<td>0.34</td>
<td>0.35</td>
</tr>
<tr>
<td>mobilenet-v1-1.0-<br>224-TF</td>
@@ -295,22 +275,25 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.27</td>
<td>0.20</td>
<td>0.20</td>
<td>0.27</td>
</tr>
<tr>
<td>mobilenet-v2-1.0-<br>224-TF</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.45</td>
<td>0.94</td>
<td>0.94</td>
<td>0.44</td>
<td>0.92</td>
<td>0.92</td>
<td>0.44</td>
</tr>
<tr>
<td>mobilenet-v2-<br>PYTORCH</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.35</td>
<td>0.63</td>
<td>0.63</td>
<td>0.25</td>
<td>7.42</td>
<td>7.42</td>
<td>0.25</td>
</tr>
<tr>
<td>resnet-18-<br>pytorch</td>
@@ -319,6 +302,7 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.26</td>
<td>0.25</td>
<td>0.25</td>
<td>0.26</td>
</tr>
<tr>
<td>resnet-50-<br>PYTORCH</td>
@@ -327,58 +311,65 @@ The following table shows the absolute accuracy drop that is calculated as the d
<td>0.18</td>
<td>0.19</td>
<td>0.19</td>
<td>0.18</td>
</tr>
<tr>
<td>resnet-50-<br>TF</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.15</td>
<td>0.11</td>
<td>0.11</td>
<td>0.15</td>
<td>0.10</td>
</tr>
<tr>
<td>squeezenet1.1-<br>CF</td>
<td>ImageNet</td>
<td>acc@top-1</td>
<td>0.66</td>
<td>0.66</td>
<td>0.64</td>
<td>0.64</td>
<td>0.66</td>
</tr>
<tr>
<td>ssd_mobilenet_<br>v1_coco-tf</td>
<td>VOC2012</td>
<td>COCO mAp</td>
<td>0.24</td>
<td>0.24</td>
<td>3.07</td>
<td>3.07</td>
<td>0.24</td>
</tr>
<tr>
<td>ssd300-CF</td>
<td>MS COCO</td>
<td>COCO mAp</td>
<td>0.06</td>
<td>0.06</td>
<td>0.05</td>
<td>0.05</td>
<td>0.06</td>
</tr>
<tr>
<td>ssdlite_<br>mobilenet_<br>v2-TF</td>
<td>MS COCO</td>
<td>COCO mAp</td>
<td>0.14</td>
<td>0.43</td>
<td>0.43</td>
<td>0.14</td>
<td>0.47</td>
</tr>
<tr>
<td>yolo_v3-TF</td>
<td>MS COCO</td>
<td>COCO mAp</td>
<td>0.20</td>
<td>0.20</td>
<td>0.36</td>
<td>0.12</td>
<td>0.35</td>
<td>0.35</td>
<td>0.12</td>
</tr>
</table>
![INT8 vs FP32 Comparison](img/int8vsfp32.png "INT8 vs FP32 Comparison on Select Networks and Platforms")
![INT8 vs FP32 Comparison](img/int8vsfp32.png)
\htmlonly
<style>

2
docs/doxygen/openvino_docs.xml
View File

@@ -76,7 +76,7 @@
<!-- Performance Benchmarks -->
<tab type="usergroup" title="Performance Measures" url="@ref openvino_docs_performance_benchmarks">
<tab type="user" title="Performance Information Frequently Asked Questions" url="@ref openvino_docs_performance_benchmarks_faq"/>
<tab type="user" title="Download Performance Data Spreadsheet in MS Excel* Format" url="https://docs.openvinotoolkit.org/downloads/benchmark_files/OV-2021.1-Download-Excel.xlsx"/>
<tab type="user" title="Download Performance Data Spreadsheet in MS Excel* Format" url="https://docs.openvinotoolkit.org/downloads/benchmark_files/OV-2021.2-Download-Excel.xlsx"/>
<tab type="user" title="INT8 vs. FP32 Comparison on Select Networks and Platforms" url="@ref openvino_docs_performance_int8_vs_fp32"/>
</tab>
<tab type="user" title="Performance Optimization Guide" url="@ref openvino_docs_optimization_guide_dldt_optimization_guide"/>

4
docs/img/int8vsfp32.png
View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:304869bcbea000f6dbf46dee7900ff01aa61a75a3787969cc307f2f54d57263c
size 32185
oid sha256:0109b9cbc2908f786f6593de335c725f8ce5c800f37a7d79369408cc47eb8471
size 25725