Merge pull request #1166 from ArmDeveloperEcosystem/main

Merge to production

content/install-guides/aperf.md

@@ -15,7 +15,7 @@ weight: 1
 
 APerf (AWS Perf) is an open source command line performance analysis tool which saves time by collecting information which is normally collected by multiple tools such as `perf`, `sysstat`, and `sysctl`.
 
-APerf was recently created by AWS to help with Linux performance analysis.
+APerf was created by AWS to help with Linux performance analysis.
 
 In addition to the CLI, APerf includes an HTML view to visualize the collected data. 
 
@@ -50,19 +50,19 @@ Visit the [releases page](https://github.com/aws/aperf/releases/) to see a list
 You can also download a release from the command line:
 
 ```bash { target="ubuntu:latest" }
-wget https://github.com/aws/aperf/releases/download/v0.1.9-alpha/aperf-v0.1.9-alpha-aarch64.tar.gz
+wget https://github.com/aws/aperf/releases/download/v0.1.12-alpha/aperf-v0.1.12-alpha-aarch64.tar.gz
 ```
 
 Extract the release:
 
 ```bash { target="ubuntu:latest" }
-tar xvfz aperf-v0.1.9-alpha-aarch64.tar.gz
+tar xvfz aperf-v0.1.12-alpha-aarch64.tar.gz
 ```
 
 Add the path to `aperf` in your `.bashrc` file. 
 
 ```console
-echo 'export PATH="$PATH:$HOME/aperf-v0.1.9-alpha-aarch64"' >> ~/.bashrc
+echo 'export PATH="$PATH:$HOME/aperf-v0.1.12-alpha-aarch64"' >> ~/.bashrc
 source ~/.bashrc
 ```
 
@@ -81,7 +81,7 @@ aperf --version
 The output should print the version:
 
 ```output
-aperf 0.1.0 (0c4f58c)
+aperf 0.1.0 (4b910d2)
 ```
 
 ## Verify APerf is working

content/install-guides/docker/docker-woa.md

@@ -44,8 +44,8 @@ Additional models of Windows on Arm computers are expected to be available in mi
 
 ### How do I install and test Docker Desktop for Windows on Arm?
 
-The current version is 4.31.0 and you can
-download [Docker Desktop for Windows on Arm](https://desktop.docker.com/win/main/arm64/153195/Docker%20Desktop%20Installer.exe) and run the installer.
+The current version is 4.33.1 and you can
+download [Docker Desktop for Windows on Arm](https://desktop.docker.com/win/main/arm64/161083/Docker%20Desktop%20Installer.exe) and run the installer.
 
 Check the [Docker Desktop release notes](https://docs.docker.com/desktop/release-notes/) for the latest release information.
 

content/learning-paths/servers-and-cloud-computing/PMUv3_plugin_learning_path/_index.md

@@ -1,6 +1,6 @@
 ---
 title: Code level Performance Analysis using the PMUv3 plugin 
-draft: false
+draft: true
 minutes_to_complete: 60
 
 who_is_this_for: Engineers who want to do C/C++ performance analysis by instrumenting code at the block level.

content/learning-paths/servers-and-cloud-computing/codec1/_index.md

@@ -0,0 +1,35 @@
+---
+title: Run the AV1 and VP9 codecs on Arm Linux
+draft: true
+author_primary: Odin Shen
+
+minutes_to_complete: 30
+
+who_is_this_for: This is an introductory topic for software developers who want to
+  build and run the VP9 and AV1 codecs on Arm servers and measure performance.
+
+learning_objectives:
+- Build the AV1 and VP9 codecs on Arm Linux.
+- Run the AV1 and VP9 codecs on Arm Linux using example videos with various resolutions and encodings.
+
+armips:
+- Neoverse
+- Cortex-A
+
+prerequisites:
+- An Arm Linux system or an [Arm based instance](/learning-paths/servers-and-cloud-computing/csp/) from a 
+  cloud service provider. 
+
+skilllevels: Introductory
+subjects: Libraries
+
+test_images:
+- ubuntu:latest
+test_link: null
+test_maintenance: false
+
+tools_software_languages:
+
+weight: 1
+layout: learningpathall
+---

content/learning-paths/servers-and-cloud-computing/codec1/_next-steps.md

@@ -0,0 +1,39 @@
+---
+# ================================================================================
+#       Edit
+# ================================================================================
+
+next_step_guidance: >
+    You can continue learning about porting cloud applications to the Arm architecture for increased performance and cost savings. The Learning Path on MongoDB is a great next step.
+# 1-3 sentence recommendation outlining how the reader can generally keep learning about these topics, and a specific explanation of why the next step is being recommended.
+
+recommended_path: "/learning-paths/servers-and-cloud-computing/mongodb/"
+# Link to the next learning path being recommended.
+
+
+# further_reading links to references related to this path. Can be:
+    # Manuals for a tool / software mentioned   (type: documentation)
+    # Blog about related topics                 (type: blog)
+    # General online references                 (type: website) 
+
+further_reading:
+    - resource:
+        title: Ampere Altra Max Delivers Sustainable High-Resolution H.265 Encoding
+        link: https://community.arm.com/arm-community-blogs/b/infrastructure-solutions-blog/posts/ampere-altra-max-delivers-sustainable-high-resolution-h-265-video-encoding-without-compromise
+        type: blog
+    - resource:
+        title: Optimized Video Encoding with FFmpeg on AWS Graviton Processors
+        link: https://aws.amazon.com/blogs/opensource/optimized-video-encoding-with-ffmpeg-on-aws-graviton-processors/
+        type: blog
+    - resource:
+        title: OCI Ampere A1 Compute instances can significantly reduce video encoding costs versus modern CPUs
+        link: https://community.arm.com/arm-community-blogs/b/operating-systems-blog/posts/oracle-cloud-infrastructure-arm-based-a1
+        type: blog
+
+# ================================================================================
+#       FIXED, DO NOT MODIFY
+# ================================================================================
+weight: 21                  # set to always be larger than the content in this path, and one more than 'review'
+title: "Next Steps"         # Always the same
+layout: "learningpathall"   # All files under learning paths have this same wrapper
+---

content/learning-paths/servers-and-cloud-computing/codec1/_review.md

@@ -0,0 +1,49 @@
+---
+# ================================================================================
+#       Edit
+# ================================================================================
+
+# Always 3 questions. Should try to test the reader's knowledge, and reinforce the key points you want them to remember.
+    # question:         A one sentence question
+    # answers:          The correct answers (from 2-4 answer options only). Should be surrounded by quotes.
+    # correct_answer:   An integer indicating what answer is correct (index starts from 0)
+    # explanation:      A short (1-3 sentence) explanation of why the correct answer is correct. Can add additional context if desired
+
+
+review:
+    - questions:
+        question: >
+            Does AV1 run on Arm servers?
+        answers:
+            - "Yes"
+            - "No"
+        correct_answer: 1                     
+        explanation: >
+            libaom codec is fully supported on 64-bit Arm servers running Linux.
+    - questions:
+        question: >
+            Does VP9 run on Arm servers?
+        answers:
+            - "Yes"
+            - "No"
+        correct_answer: 1                     
+        explanation: >
+            libvpx codec is fully supported on 64-bit Arm servers running Linux.
+    - questions:
+        question: >
+            Does varying the preset settings on the images impact the codec performance?
+        answers:
+            - "Yes"
+            - "No"
+        correct_answer: 1                   
+        explanation: >
+            You can vary the preset settings on the different resolution images and measure the impact on performance.
+               
+
+# ================================================================================
+#       FIXED, DO NOT MODIFY
+# ================================================================================
+title: "Review"                 # Always the same title
+weight: 20                      # Set to always be larger than the content in this path
+layout: "learningpathall"       # All files under learning paths have this same wrapper
+---

content/learning-paths/servers-and-cloud-computing/codec1/libaom.md

@@ -0,0 +1,172 @@
+---
+layout: learningpathall
+title: Build and Run the AV1 codec
+weight: 2
+---
+
+## What is the AV1 codec?
+
+AV1 is a free software video codec library from the [Alliance for Open Media (AOM)](https://aomedia.org/). 
+
+It serves as the reference software implementation for the AV1 video coding format. 
+
+Significant efforts to optimize the open-source implementation, known as `libxaom`, of the AV1 encoder are available for Arm Neoverse platforms with Neon and SVE2 instructions. The optimized code is available on [Google Git](https://aomedia.googlesource.com/aom/).
+
+## Install the necessary software packages
+
+You will need various development tools to build AV1 including CMake and the GNU compiler.
+
+The instructions assume you are running Ubuntu. 
+
+Install the required tools by running: 
+
+```bash
+sudo apt install gcc g++ wget cmake p7zip-full -y
+```
+
+## Download and build AV1 from source
+
+Download the AV1 source code:
+
+```bash
+git clone https://aomedia.googlesource.com/aom
+```
+
+Change directory to the repository, configure the build, and build the library:
+
+```bash
+mkdir -p aom/build_aom
+cd aom/build_aom
+cmake ..
+make -j$(nproc)
+```
+
+For additional details refer to the [README](https://aomedia.googlesource.com/aom/?pli=1#basic-build).
+
+## Run AV1 unit tests
+
+The AV1 library has a comprehensive suite of unit tests, written using the GTest framework.
+
+The build above includes the `test_libaom` executable. 
+
+You can run all unit tests by starting `test_libaom` with no arguments. However, the number of tests is huge, and it takes a long to run them all. Instead, you can constrain the number of tests by specifying a filter.
+
+There is a help argument you can try: 
+
+```bash
+./test_libaom --help
+```
+
+There is also an argument to list the tests:
+
+```bash
+./test_libaom --gtest_list_tests | less
+```
+
+To run a subset of tests, you can use a filter to run only the Neon Sum of Absolute Difference (SAD) tests.
+
+Here is an example with the filter:
+
+```bash
+./test_libaom --gtest_filter="*NEON*SAD*"
+```
+
+The output is:
+
+```output
+Note: Google Test filter = *NEON*SAD*-:NEON_I8MM.*:NEON_I8MM/*:NEON_I8MM_*:SVE.*:SVE/*:SVE_*:SVE2.*:SVE2/*:SVE2_*
+[==========] Running 3650 tests from 17 test suites.
+[----------] Global test environment set-up.
+[----------] 22 tests from NEON/MaskedSADTest
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/0
+[       OK ] NEON/MaskedSADTest.OperationCheck/0 (152 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/1
+[       OK ] NEON/MaskedSADTest.OperationCheck/1 (152 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/2
+[       OK ] NEON/MaskedSADTest.OperationCheck/2 (152 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/3
+[       OK ] NEON/MaskedSADTest.OperationCheck/3 (152 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/4
+[       OK ] NEON/MaskedSADTest.OperationCheck/4 (153 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/5
+[       OK ] NEON/MaskedSADTest.OperationCheck/5 (152 ms)
+[ RUN      ] NEON/MaskedSADTest.OperationCheck/6
+[       OK ] NEON/MaskedSADTest.OperationCheck/6 (152 ms)
+
+< output omitted>
+
+[----------] 90 tests from NEON_DOTPROD/SADSkipx4Test (1433 ms total)
+
+[----------] Global test environment tear-down
+[==========] 3650 tests from 17 test suites ran. (56720 ms total)
+[  PASSED  ] 3650 tests.
+
+  YOU HAVE 581 DISABLED TESTS
+```
+
+## Performance benchmarking
+
+You can benchmark video encoding either on-demand or live-stream.
+
+To start, download some example `8-bit FHD`, `8-bit 4K` and `10-bit 4K` video files:
+
+```bash
+wget https://ultravideo.fi/video/Bosphorus_1920x1080_120fps_420_8bit_YUV_Y4M.7z 
+wget https://ultravideo.fi/video/Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z 
+wget https://ultravideo.fi/video/Bosphorus_3840x2160_120fps_420_10bit_YUV_Y4M.7z 
+```
+
+Next, extract the contents of the 7z files: 
+
+```bash
+7za e Bosphorus_1920x1080_120fps_420_8bit_YUV_Y4M.7z
+7za e Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
+7za e Bosphorus_3840x2160_120fps_420_10bit_YUV_Y4M.7z 
+```
+
+### On-demand video encoding 
+
+For on-demand encoding you can experiment different number of processors and monitor performance. 
+
+For example, run with `--good` and use the `--cpu-used` argument to vary the number of processors from 2 to 6.
+
+Run standard bit depth and change the CPU count and see the results using:
+
+```bash
+./aomenc --good --cpu-used=4 --bit-depth=8 -o output.mkv Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m 
+```
+
+Try the above command with different `--cpu-used` values.
+
+You can do the same for high bit depth:
+
+```bash
+./aomenc --good --cpu-used=4 --bit-depth=10 -o output.mkv Bosphorus_3840x2160_120fps_420_10bit.y4m 
+```
+
+### Live-stream video encoding
+
+For live-stream encoding you can experiment different number of processors and monitor performance using the `--cpus-used` in the range from 5 to 9. 
+
+For standard bit depth with 8 CPUs run:
+
+```bash
+./aomenc --rt --cpu-used=8 --bit-depth=8 -o output.mkv Bosphorus_1920x1080_120fps_420_8bit_YUV.y4m
+```
+
+For high bit depth run:
+
+```bash
+./aomenc --rt --cpu-used=8 --bit-depth=10 -o output.mkv Bosphorus_3840x2160_120fps_420_10bit.y4m
+```
+
+## View Results
+
+The encoding frame rate (Frames per second) for the video files is output at the end of each run.
+
+Shown below is example output from running the AV1 codec on the 8-bit FHD sample video file:
+
+```output
+Pass 1/2 frame  600/601   139432B    1859b/f   55770b/s   62641 ms (9.58 fps)
+Pass 2/2 frame  600/600   638429B    8512b/f  255360b/s 1103538 ms (0.54 fps)
+```