mirror of
https://github.com/clearlinux/clear-linux-documentation.git
synced 2026-10-04 07:58:24 +00:00
Update TM&B in guides section of docs (#1187)
* Update TM&B in guides section of docs - Add disclaimers for Intel trademarks - Update/correct product names in text per Intel guidance Signed-off-by: Kristal Dale <kristal.dale@intel.com> * Fix syntax/indent errors. Signed-off-by: Kristal Dale <kristal.dale@intel.com> * - Add link back in (accidental removal) (dlrs-inference.rst) - Minor language clarifications (compatible-kernels.rst) - Correct missed trademark (performance.rst) Signed-off-by: Kristal Dale <kristal.dale@intel.com> * - Correct product name in dlrs-inference.rst (confirmed with original author) - Correct product name in dbrs.rst (confirmed with original author) - Correct product name in compatible-kernels.rst Signed-off-by: Kristal Dale <kristal.dale@intel.com> * Add in missing (r) in dbrs.rst Signed-off-by: Kristal Dale <kristal.dale@intel.com>
This commit is contained in:
Kristal Dale
@@ -12,7 +12,7 @@ Bare metal only
|
||||
|
||||
Kernel native
|
||||
The *kernel-native* bundle focuses on the bare metal platforms. It is
|
||||
optimized for fast booting and performs best on the Intel® architectures
|
||||
optimized for fast booting and performs best on the Intel® Architecture Processors
|
||||
described on the :ref:`supported hardware list<system-requirements>`. The
|
||||
optimization patches are found in our `Linux`_ GitHub\* repo.
|
||||
|
||||
@@ -24,8 +24,8 @@ Also compatible with VMs
|
||||
Kernel LTS
|
||||
The *kernel-lts* bundle focuses on the bare metal platforms but uses the
|
||||
latest :abbr:`LTS (Long Term Support)` Linux kernel. It is optimized for
|
||||
fast booting and performs best on the Intel® architectures described on the
|
||||
:ref:`supported hardware list<system-requirements>`. Additionally, this
|
||||
fast booting and performs best on the Intel® Architecture Processors described
|
||||
on the :ref:`supported hardware list<system-requirements>`. Additionally, this
|
||||
kernel includes the VirtualBox\* kernel modules, see our
|
||||
:ref:`instructions on using Virtualbox<virtualbox-cl-installer>` for more
|
||||
information. The optimization patches are found in our `Linux-LTS`_ GitHub
|
||||
@@ -37,8 +37,8 @@ VM only
|
||||
Kernel KVM
|
||||
The *kernel-kvm* bundle focuses on the Linux
|
||||
:abbr:`KVM (Kernel-based Virtual Machine)`. It is optimized for fast
|
||||
booting and performs best on Virtual Machines running on the Intel®
|
||||
architectures described on the
|
||||
booting and performs best on Virtual Machines running on the Intel® Architecture
|
||||
Processors described on the
|
||||
:ref:`supported hardware list<system-requirements>`. Use this kernel when
|
||||
running |CL| as the guest OS on top of *qemu/kvm*. Use this kernel with
|
||||
**cloud orchestrators** using *qemu/kvm* internally as their **hypervisor**
|
||||
@@ -49,7 +49,7 @@ Kernel KVM
|
||||
Kernel Hyper-V\*
|
||||
The *kernel-hyperv* bundle focuses on running Linux on Microsoft\*
|
||||
Hyper-V. It is optimized for fast booting and performs best on Virtual
|
||||
Machines running on the Intel® architectures described on the
|
||||
Machines running on the Intel® Architecture Processors described on the
|
||||
:ref:`supported hardware list<system-requirements>`.
|
||||
Use this kernel when running |CL| as the guest OS of **Cloud Instances** in
|
||||
projects such as Microsoft `Azure`_\*. This kernel can be used in a
|
||||
@@ -57,6 +57,8 @@ Kernel Hyper-V\*
|
||||
for more information. The optimization patches are found in our
|
||||
`Linux-HyperV`_ GitHub repo.
|
||||
|
||||
*Intel and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
.. _Linux: https://github.com/clearlinux-pkgs/linux
|
||||
.. _Linux-LTS: https://github.com/clearlinux-pkgs/linux-lts
|
||||
.. _Linux-KVM: https://github.com/clearlinux-pkgs/linux-kvm
|
||||
|
||||
@@ -138,6 +138,8 @@ some examples:
|
||||
* `Tallow`_, a lightweight service which monitors and blocks suspicious SSH
|
||||
login patterns, is installed with the :command:`openssh-server` bundle.
|
||||
|
||||
*Intel and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
.. _`Security for software update in Clear Linux* OS`: https://clearlinux.org/blogs/security-software-update-clear-linux-os-intel-architecture
|
||||
.. _`Recent GNU* C library improvements`: https://clearlinux.org/blogs/recent-gnu-c-library-improvements
|
||||
.. _`rolling release`: https://en.wikipedia.org/wiki/Rolling_release
|
||||
|
||||
@@ -203,11 +203,10 @@ Better thermal control and performance can be achieved by providing platform
|
||||
specific configuration to :command:`thermald`.
|
||||
|
||||
`Linux DPTF Extract Utility`_ is a companion tool to :command:`thermald`,
|
||||
This tool uses Intel®
|
||||
:abbr:`DPTF (Dynamic Platform and Thermal Framework)` technology and
|
||||
can convert to the :file:`thermal_conf.xml` configuration format used by
|
||||
:command:`thermald`. Closed-source projects, like this one, cannot be packaged
|
||||
as a bundle in |CL|, so you must install it manually:
|
||||
This tool uses Intel® Dynamic Platform and Thermal Framework (Intel® DPTF)
|
||||
technology and can convert to the :file:`thermal_conf.xml` configuration format
|
||||
used by :command:`thermald`. Closed-source projects, like this one, cannot be
|
||||
packaged as a bundle in |CL|, so you must install it manually:
|
||||
|
||||
#. Make sure your machine's BIOS has DPTF feature and is enabled. It will usually be in the :guilabel:`Advanced` or :guilabel:`Advanced>Power` section of the BIOS.
|
||||
|
||||
@@ -248,15 +247,13 @@ The following output means the configuration has already been applied:
|
||||
|
||||
thermald[*]: [WARN]Using generated /etc/thermald/thermal-conf.xml.auto
|
||||
|
||||
.. admonition:: Disclaimer
|
||||
*Intel® Turbo Boost Technology requires a PC with a processor with Intel Turbo
|
||||
Boost Technology capability. Intel Turbo Boost Technology performance varies
|
||||
depending on hardware, software and overall system configuration. Check with
|
||||
your PC manufacturer on whether your system delivers Intel Turbo Boost Technology.
|
||||
For more information, see http://www.intel.com/technology/turboboost*
|
||||
|
||||
Intel® Turbo Boost Technology requires a PC with a processor with Intel
|
||||
Turbo Boost Technology capability. Intel Turbo Boost Technology performance
|
||||
varies depending on hardware, software and overall system configuration.
|
||||
Check with your PC manufacturer on whether your system delivers Intel Turbo
|
||||
Boost Technology. For more information, see http://www.intel.com/technology/turboboost
|
||||
|
||||
Intel SpeedStep is a trademark of Intel Corporation or its subsidiaries.
|
||||
*Intel, Intel SpeedStep, and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
|
||||
.. _`Intel P-state driver`: https://www.kernel.org/doc/Documentation/cpu-freq/intel-pstate.txt
|
||||
|
||||
@@ -24,7 +24,8 @@ The Data Analytics Reference Stack provides two pre-built Docker images,
|
||||
available on `Docker Hub`_:
|
||||
|
||||
* A |CL|-derived `DARS with OpenBlas`_ stack optimized for `OpenBLAS`_
|
||||
* A |CL|-derived `DARS with Intel® MKL`_ stack optimized for `MKL`_ (Intel® Math Kernel Library)
|
||||
* A |CL|-derived `DARS with Intel® MKL`_ stack optimized for
|
||||
`Intel® Math Kernel Library`_ (Intel® MKL)
|
||||
|
||||
We recommend you view the latest component versions for each image in the
|
||||
:file:`releasenote` found in the `Data Analytics Reference Stack`_ GitHub\*
|
||||
@@ -98,7 +99,7 @@ If you choose to build your own DARS container images, you can customize them as
|
||||
|
||||
To construct images with |CL|, start with a |CL| development platform that has the :command:`containers-basic-dev` bundle installed. Learn more about bundles and installing them by using :ref:`swupd-guide`.
|
||||
|
||||
#. The `Data Analytics Reference Stack`_ is part of the Intel® stacks GitHub\* repository. Clone the :file:`stacks` repository.
|
||||
#. The `Data Analytics Reference Stack`_ is part of the Intel stacks GitHub\* repository. Clone the :file:`stacks` repository.
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
@@ -671,6 +672,7 @@ This exception can be disregarded because DARS does not use hadoop.hive.shims. H
|
||||
|
||||
#. There is an exception message `Exception in thread "Thread-3" java.lang.ExceptionInInitializerError at org.apache.hadoop.hive.conf.HiveConf` This is related to the same issue with |CL| and JDK11 noted above, and does not affect DARS for the same reason.
|
||||
|
||||
*Intel and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
.. _Data Analytics Reference Stack: https://github.com/intel/stacks/tree/master/dars/clearlinux
|
||||
|
||||
@@ -678,7 +680,7 @@ This exception can be disregarded because DARS does not use hadoop.hive.shims. H
|
||||
|
||||
.. _OpenBLAS: http://www.openblas.net/
|
||||
|
||||
.. _MKL: https://software.intel.com/en-us/mkl
|
||||
.. _Intel® Math Kernel Library: https://software.intel.com/en-us/mkl
|
||||
|
||||
.. _CentOS: https://www.centos.org/
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ Overview
|
||||
********
|
||||
|
||||
The Database Reference Stack is integrated, highly-performant, open source,
|
||||
and optimized for 2nd generation Intel® Xeon® Scalable Processors and Intel®
|
||||
and optimized for 2nd generation Intel® Xeon® Scalable processors and Intel®
|
||||
Optane™ persistent memory. This open source community release is part of
|
||||
an effort to ensure developers have easy access to the features and
|
||||
functionality of Intel Platforms.
|
||||
@@ -52,10 +52,10 @@ The release announcement for each release provides more detail about the stack f
|
||||
Hardware Requirements
|
||||
*********************
|
||||
|
||||
* Intel® Xeon Scalable Platform with Intel® C620 chipset series
|
||||
* 2nd Gen Intel® Xeon Scalable processor CPU (Intel® Optane™ PMM-enabled stepping) Provides cache & memory control. Intel® Optane™ PMem works only on systems powered by 2nd Generation Intel® Xeon® Platinum or Gold processors.
|
||||
* Intel Xeon Scalable platform with Intel® C620 series chipset
|
||||
* 2nd Gen Intel Xeon Scalable processor CPU (Intel® Optane™ PMem-enabled stepping). Provides cache & memory control. Intel Optane PMem works only on systems powered by 2nd Generation Intel® Xeon® Platinum or Intel® Xeon® Gold processors.
|
||||
* BIOS with Reference Code
|
||||
* Intel®Optane™ PMem
|
||||
* Intel Optane PMem
|
||||
|
||||
Hardware configuration used in stacks development
|
||||
=================================================
|
||||
@@ -64,12 +64,12 @@ Hardware configuration used in stacks development
|
||||
* BIOS with Reference Code
|
||||
* BIOS ID: SE5C620.86B.0D.01.0438.032620191658
|
||||
* BMC Firmware: 1.94.6b42b91d
|
||||
* Intel® Optane™ PMemFirmware: 1.2.0.5310
|
||||
* 2x Intel® Xeon Platinum 8268 Processor
|
||||
* Intel® SSD DC S5600 Series 960GB 2.5in SATA Drive
|
||||
* Intel Optane PMem Firmware: 1.2.0.5310
|
||||
* 2x Intel Xeon Platinum 8268 Processor
|
||||
* Intel® SSD Data Center Family S5600 Series 960GB 2.5in SATA Drive
|
||||
* 64 GB RAM - Distributed in 4x 16 GB DDR4 DIMM's
|
||||
* 2x Intel® Optane™ PMem 256GB Module
|
||||
* 1-1-1 Layout 8 Optane™ : 1 RAM ratio
|
||||
* 2x Intel Optane PMem 256GB Module
|
||||
* 1-1-1 Layout 8 Intel Optane : 1 RAM ratio
|
||||
|
||||
|
||||
.. list-table:: **Table 1. IMC**
|
||||
@@ -104,7 +104,7 @@ Firmware configuration
|
||||
|
||||
When updating DCPMM Firmware, all DCPMM parts must be in the same mode (you cannot mix 1LM and 2LM parts).
|
||||
|
||||
The latest firmware download for the Intel® Server System S2600WF Family is available at the `Intel Download Center`_
|
||||
The latest firmware download for the Intel® Server Board S2600WF Family is available at the `Intel Download Center`_
|
||||
|
||||
Firmware Update Steps
|
||||
=====================
|
||||
@@ -117,7 +117,7 @@ Firmware Update Steps
|
||||
#. After update BMC firmware, system BIOS, ME firmware,FD, FRUSDR, system will reboot automatically.
|
||||
|
||||
|
||||
If Intel® Optane™ PMem is installed, run startup.nsh a second time after the first reboot to upgrade Intel® Optane™ PMem Firmware:
|
||||
If Intel Optane PMem is installed, run startup.nsh a second time after the first reboot to upgrade Intel Optane PMem Firmware:
|
||||
|
||||
* Boot to EFI shell.
|
||||
* Input "fsx(x:0,1,...):" to enter into your usb disk
|
||||
@@ -134,9 +134,9 @@ Online Resources
|
||||
|
||||
Before going through the configuration steps, we strongly recommend visiting the following resources and wikis to have a broader understanding of what is being done
|
||||
|
||||
* `Quick Start Guide`_ Configure Intel® Optane™ PMem Modules on Linux
|
||||
* `Quick Start Guide`_ Configure Intel Optane PMem Modules on Linux
|
||||
* `Managing NVDIMMs`_
|
||||
* `Configure, Manage, and Profile`_ Intel® Optane™ PMem Modules
|
||||
* `Configure, Manage, and Profile`_ Intel Optane PMem Modules
|
||||
|
||||
Optane™ DIMM Configuration
|
||||
==========================
|
||||
@@ -569,7 +569,7 @@ Eventually all the given nodes will be shown as running using :command:`kubectl
|
||||
Running DBRS with Redis
|
||||
***********************
|
||||
|
||||
The Redis stack application is enabled for a multinode Kubernetes environment using Intel® Optane™ DCPMM PMem DIMMs in fsdax mode for storage.
|
||||
The Redis stack application is enabled for a multinode Kubernetes environment using Intel Optane DCPMM PMem DIMMs in fsdax mode for storage.
|
||||
|
||||
The source code used for this application can be found in the `Github repository`_
|
||||
|
||||
@@ -584,7 +584,7 @@ The following examples will use the `Docker image with Redis`_. You can also bu
|
||||
Single node
|
||||
===========
|
||||
|
||||
Prior to starting the container, you will need to have the Intel® Optane™ DCPMM module in fsdax with a file system and mounted in `/mnt/dax0` as shown above.
|
||||
Prior to starting the container, you will need to have the Intel Optane DCPMM module in fsdax with a file system and mounted in `/mnt/dax0` as shown above.
|
||||
|
||||
Use the following to start the container, replacing ${DOCKER_IMAGE} with the name of the image you are using.
|
||||
|
||||
@@ -664,6 +664,8 @@ where:
|
||||
For more information please refer to this `blog post`_ from `Memcached`_
|
||||
|
||||
|
||||
*Intel, Xeon, Intel Optane, and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
|
||||
.. _Intel Download Center: https://downloadcenter.intel.com/download/28695/Intel-Server-Board-S2600WF-Family-BIOS-and-Firmware-Update-Package-for-UEFI
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ Overview
|
||||
|
||||
The solution covered here requires the following software components:
|
||||
|
||||
* `Deep Learning Reference Stack`_ which is a |CL-ATTR| based Docker\* container providing deep learning frameworks and is optimized for Intel Xeon Scalable platforms.
|
||||
* `Deep Learning Reference Stack`_ which is a |CL-ATTR| based Docker\* container providing deep learning frameworks and is optimized for Intel® Xeon® Scalable processors.
|
||||
* `Kubeflow`_ is the machine learning toolkit for Kubernetes that helps with deployment of Seldon Core and Istio components.
|
||||
* `Seldon Core`_ is a software platform for deploying machine learning models. We use the DLRS container to serve the OpenVino\* framework for inference with the Seldon Core.
|
||||
* The OpenVino Model Server is included in DLRS and provides the OpenVino framework for inference. From OpenVino, the `OpenVino Toolkit`_ provides improved neural network performance on a variety of Intel processors. For this guide, we converted pre-trained Caffe models into the `Intermediate Representation(IR)`_ of ResNet50 with the OpenVino toolkit.
|
||||
@@ -85,7 +85,7 @@ Although this guide assumes a |CL| host system, it has also been validated with
|
||||
Recommended Hardware
|
||||
====================
|
||||
|
||||
We validated this guide on an `Intel Cascade Lake`_ server and this is recommended to get optimal performance and take advantage of the built in Intel® Deep Learning Boost functionality.
|
||||
We validated this guide on a server with a `2nd Generation Intel Xeon Scalable processor`_, formerly Cascade Lake, and this is recommended to get optimal performance and take advantage of the built in Intel® Deep Learning Boost (Intel® DL Boost) functionality.
|
||||
|
||||
Required Software
|
||||
=================
|
||||
@@ -917,7 +917,7 @@ To find out how to assign the cores and memory properly run :command:`numactl -H
|
||||
1: 21 10
|
||||
|
||||
|
||||
In this case, the tests are run on Intel(R) Xeon(R) Platinum 6260L with 2 sockets(nodes) and 24 cores (CPUs) on each socket.
|
||||
In this case, the tests are run on Intel® Xeon® Platinum 6260L processor with 2 sockets(nodes) and 24 cores (CPUs) on each socket.
|
||||
Running the inference serving the application with :command:`numactl --membind=0 --cpubind=0-3` forces the system to use 0,1,2,3 cores and memory located on the same socket (0). To use all available cores there is a need to create more service deployments assigned to the remaining cores.
|
||||
|
||||
The `ai-inferencing` repository contains an example deployment script with 2 cores per instance assignment.
|
||||
@@ -1029,7 +1029,7 @@ The test performed on a 2 node cluster with 48 cores per node showed that there
|
||||
KMP_BLOCKTIME=1
|
||||
|
||||
|
||||
|
||||
*Intel, Xeon, and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
|
||||
.. _Deep Learning Reference Stack: https://clearlinux.org/stacks/deep-learning
|
||||
@@ -1040,7 +1040,7 @@ The test performed on a 2 node cluster with 48 cores per node showed that there
|
||||
.. _Istio: https://istio.io/
|
||||
.. _Source-to-Image: https://github.com/openshift/source-to-image
|
||||
.. _Min.io: https://min.io/
|
||||
.. _Intel Cascade Lake: https://www.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/cascade-lake/2nd-gen-intel-xeon-scalable-processors.html
|
||||
.. _2nd Generation Intel Xeon Scalable processor: https://www.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/cascade-lake/2nd-gen-intel-xeon-scalable-processors.html
|
||||
.. _Docker 18.09: https://kubernetes.io/docs/setup/production-environment/container-runtimes/
|
||||
.. _Kubernetes 1.15.3: https://kubernetes.io/docs/setup/production-environment/tools/kubeadm/install-kubeadm/
|
||||
.. _gsutil: https://cloud.google.com/storage/docs/gsutil_install#linux
|
||||
|
||||
@@ -14,7 +14,7 @@ Overview
|
||||
********
|
||||
|
||||
We created the Deep Learning Reference Stack to help AI developers deliver
|
||||
the best experience on Intel® Architecture. This stack reduces complexity
|
||||
the best experience on Intel® architecture. This stack reduces complexity
|
||||
common with deep learning software components, provides flexibility for
|
||||
customized solutions, and enables you to quickly prototype and deploy Deep
|
||||
Learning workloads. Use this guide to run benchmarking workloads on your
|
||||
@@ -28,16 +28,18 @@ The latest release of the Deep Learning Reference Stack (`DLRS V6.0`_ ) supports
|
||||
* Transformers* which is a state-of-the-art Natural Language Processing (NLP) library for TensorFlow 2.0 and PyTorch
|
||||
* Flair*, a PyTorch NLP framework
|
||||
* OpenVINO™ model server version 2020.1, delivering improved neural network performance on Intel processors, helping unlock cost-effective, real-time vision applications.
|
||||
* Intel® Deep Learning Boost (Intel® DL Boost) with AVX-512 Vector Neural Network Instruction (Intel® AVX-512 VNNI), designed to accelerate deep neural network-based algorithms.
|
||||
* Intel® Deep Learning Boost (Intel® DL Boost) with Intel® Advanced Vector
|
||||
Extensions 512 (Intel® AVX-512) Vector Neural Network Instruction , designed to
|
||||
accelerate deep neural network-based algorithms.
|
||||
* Deep Learning Compilers (TVM* 0.6), an end-to-end compiler stack.
|
||||
|
||||
|
||||
.. important::
|
||||
|
||||
To take advantage of the Intel® AVX-512 and VNNI functionality (including the Intel® oneAPI Deep Neural Network Library (oneDNN), found at `oneDNN`_. with the Deep Learning Reference Stack, you must use the following hardware:
|
||||
To take advantage of the Intel AVX-512 and VNNI functionality (including the Intel® oneAPI Deep Neural Network Library (oneDNN), found at `oneDNN`_, with the Deep Learning Reference Stack, you must use the following hardware:
|
||||
|
||||
* Intel® AVX-512 images require an Intel® Xeon® Scalable processor
|
||||
* VNNI requires a 2nd generation Intel® Xeon® Scalable processor
|
||||
* Intel AVX-512 images require an Intel® Xeon® Scalable processor
|
||||
* VNNI requires a 2nd generation Intel Xeon Scalable processor
|
||||
|
||||
|
||||
Releases
|
||||
@@ -194,7 +196,7 @@ TensorFlow.
|
||||
TensorFlow benchmarks.
|
||||
|
||||
If you are using an FP32 based model, it can be converted to an int8 model
|
||||
using `Intel® quantization tools`_.
|
||||
using `Intel® AI Quantization Tools for TensorFlow`_.
|
||||
|
||||
PyTorch single and multi-node benchmarks
|
||||
****************************************
|
||||
@@ -237,8 +239,8 @@ TensorFlow Training (TFJob) with Kubeflow and DLRS
|
||||
|
||||
.. warning::
|
||||
|
||||
If you choose the Intel® oneDNN image, your platform
|
||||
must support the Intel® AVX-512 instruction set. Otherwise, an
|
||||
If you choose the Intel oneDNN image, your platform
|
||||
must support the Intel AVX-512 instruction set. Otherwise, an
|
||||
*illegal instruction* error may appear, and you won’t be able to complete this guide.
|
||||
|
||||
A `TFJob`_ is Kubeflow's custom resource used to run TensorFlow training jobs on Kubernetes. This example shows how to use a TFJob within the DLRS container.
|
||||
@@ -1059,7 +1061,7 @@ Related topics
|
||||
* `Jupyter Notebook`_
|
||||
|
||||
|
||||
OpenVINO is a trademark of Intel Corporation or its subsidiaries
|
||||
*Intel, OpenVINO, Xeon, and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
.. _TensorFlow: https://www.tensorflow.org/
|
||||
|
||||
@@ -1132,7 +1134,7 @@ OpenVINO is a trademark of Intel Corporation or its subsidiaries
|
||||
.. _Distributed TensorFlow: https://www.tensorflow.org/deploy/distributed
|
||||
.. _TFJobs: https://www.kubeflow.org/docs/components/tftraining/
|
||||
|
||||
.. _Intel® quantization tools: https://github.com/IntelAI/tools/blob/master/tensorflow_quantization/README.md#quantization-tools
|
||||
.. _Intel® AI Quantization Tools for TensorFlow: https://github.com/IntelAI/tools/blob/master/tensorflow_quantization/README.md#quantization-tools
|
||||
|
||||
.. _OpenCV open model zoo: https://github.com/opencv/open_model_zoo
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Enable AWS Greengrass\* and OpenVINO™ toolkit
|
||||
This guide explains how to enable AWS Greengrass\* and OpenVINO™ toolkit.
|
||||
Specifically, the guide demonstrates how to:
|
||||
|
||||
* Set up the Intel® edge device with |CL-ATTR|
|
||||
* Set up the Intel edge device with |CL-ATTR|
|
||||
* Install the OpenVINO™ toolkit and Amazon Web Services\* (AWS\*)
|
||||
Greengrass\* software stacks
|
||||
* Use AWS Greengrass\* and AWS Lambda\* to deploy the FaaS samples from
|
||||
@@ -20,19 +20,19 @@ Overview
|
||||
********
|
||||
|
||||
Hardware accelerated Function-as-a-Service (FaaS) enables cloud developers to
|
||||
deploy inference functionalities [1] on Intel® IoT edge devices with
|
||||
deploy inference functionalities [1] on Intel IoT edge devices with
|
||||
accelerators (CPU, Integrated GPU, Intel® FPGA, and Intel® Movidius™
|
||||
technology). These functions provide a great developer experience and
|
||||
seamless migration of visual analytics from cloud to edge in a secure manner
|
||||
using a containerized environment. Hardware-accelerated FaaS provides the
|
||||
best-in-class performance by accessing optimized deep learning libraries on
|
||||
Intel® IoT edge devices with accelerators.
|
||||
Intel IoT edge devices with accelerators.
|
||||
|
||||
Supported platforms
|
||||
*******************
|
||||
|
||||
* Operating System: |CL| latest release
|
||||
* Hardware: Intel® core platforms (that support inference on CPU only)
|
||||
* Hardware: Intel® Core™ processors (that support inference on CPU only)
|
||||
|
||||
Sample description
|
||||
==================
|
||||
@@ -111,7 +111,7 @@ for the OpenVINO software stack:
|
||||
Learn more about how to :ref:`swupd-guide`.
|
||||
|
||||
The :command:`computer-vision-basic` bundle installs the OpenVINO™ toolkit,
|
||||
and the sample models optimized for Intel® edge platforms.
|
||||
and the sample models optimized for Intel edge platforms.
|
||||
|
||||
.. _convert-dl-models:
|
||||
|
||||
@@ -130,7 +130,7 @@ download the BVLC AlexNet model files `bvlc_alexnet.caffemodel`_ and
|
||||
:file:`/usr/share/openvino/models`. Any custom pre-trained classification models
|
||||
can be used with the classification sample.
|
||||
|
||||
For object detection, the sample models optimized for Intel® edge platforms
|
||||
For object detection, the sample models optimized for Intel edge platforms
|
||||
are included with the computer-vision-basic bundle installation at
|
||||
:file:`/usr/share/openvino/models`. These models are provided as an example;
|
||||
you may also use a custom SSD model with the Greengrass object detection sample.
|
||||
@@ -181,7 +181,7 @@ In these examples:
|
||||
Configure AWS Greengrass group
|
||||
******************************
|
||||
|
||||
For each Intel® edge platform, you must create a new AWS Greengrass group
|
||||
For each Intel edge platform, you must create a new AWS Greengrass group
|
||||
and install AWS Greengrass core software to establish the connection between
|
||||
cloud and edge.
|
||||
|
||||
@@ -278,7 +278,8 @@ configuring the Lambda function for AWS Greengrass.
|
||||
- Value
|
||||
* - PARAM_MODEL_XML
|
||||
- <MODEL_DIR>/<IR.xml>, where <MODEL_DIR> is user specified and
|
||||
contains IR.xml, the Intermediate Representation file from Intel® Model Optimizer.
|
||||
contains IR.xml, the Intermediate Representation file from the
|
||||
OpenVINO™ Model Optimizer.
|
||||
For this guide, <MODEL_DIR> should be set to '/usr/share/openvino/models'
|
||||
or one of its subdirectories.
|
||||
* - PARAM_INPUT_SOURCE
|
||||
@@ -396,6 +397,10 @@ References
|
||||
#. AWS Lambda: https://aws.amazon.com/lambda/
|
||||
#. AWS Kinesis: https://aws.amazon.com/kinesis/
|
||||
|
||||
|
||||
*Intel, OpenVINO, and the Intel logo are trademarks of Intel Corporation or its subsidiaries.*
|
||||
|
||||
|
||||
.. _Edge-Analytics-FaaS: https://github.com/intel/Edge-Analytics-FaaS/tree/v1.0/AWS%20Greengrass
|
||||
|
||||
.. _bvlc_alexnet.caffemodel: http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel
|
||||
|
||||
@@ -82,9 +82,9 @@ image and aims to support the latest |CL| version.
|
||||
|MERS| provides the following libraries and drivers:
|
||||
|
||||
.. list-table::
|
||||
:widths: auto
|
||||
:widths: 15 85
|
||||
|
||||
* - SVT-HEVC*
|
||||
* - SVT-HEVC
|
||||
- Scalable Video Technology for HEVC encoding, also known as H.265
|
||||
* - SVT-AV1
|
||||
- Scalable Video Technology for AV1 encoding
|
||||
@@ -103,8 +103,8 @@ image and aims to support the latest |CL| version.
|
||||
* - gmmlib
|
||||
- `Intel® Graphics Memory Management Library
|
||||
<https://github.com/intel/gmmlib>`_ provides device specific and buffer
|
||||
management for the Intel® Graphics Compute Runtime for OpenCL(TM) and
|
||||
the Intel® Media Driver for VAAPI.
|
||||
management for the Intel® Graphics Compute Runtime for oneAPI Level Zero
|
||||
and OpenCL™ Driver and the Intel Media Driver for VAAPI.
|
||||
|
||||
Components of the |MERS| include:
|
||||
|
||||
@@ -130,7 +130,7 @@ Components of the |MERS| include:
|
||||
|
||||
.. note::
|
||||
|
||||
The |MERS| is validated on 11th generation Intel® Processor Graphics and
|
||||
The |MERS| is validated on 11th generation Intel Processor Graphics and
|
||||
newer. Older generations should work but are not tested against.
|
||||
|
||||
.. note::
|
||||
@@ -559,5 +559,6 @@ following the same steps in this tutorial by substituting the image name with
|
||||
*sysstacks/mers-clearlinux:aom*.
|
||||
|
||||
|
||||
**Intel, Xeon, OpenVINO, and the Intel logo are trademarks of Intel
|
||||
Corporation or its subsidiaries.**
|
||||
*Intel, Xeon, OpenVINO, and the Intel logo are trademarks of Intel
|
||||
Corporation or its subsidiaries. OpenCL and the OpenCL logo are trademarks of
|
||||
Apple Inc. used by permission by Khronos.*
|
||||
|
||||
Reference in New Issue
Block a user