From 97a529b0e6fd4d9ca2c35a2ecbeb0db37c3b4dfe Mon Sep 17 00:00:00 2001 From: Ryan Syracuse Date: Wed, 12 Jun 2019 14:58:16 -0400 Subject: [PATCH 1/9] why-choose-gpu --- docs/platform/why-linode-gpu/index.md | 71 +++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 docs/platform/why-linode-gpu/index.md diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/why-linode-gpu/index.md new file mode 100644 index 00000000000..791887ea4db --- /dev/null +++ b/docs/platform/why-linode-gpu/index.md @@ -0,0 +1,71 @@ +--- +author: + name: Linode + email: docs@linode.com +description: 'Why use GPU Instances' +keywords: ["", "grub"] +license: '[CC BY-ND 4.0](http://creativecommons.org/licenses/by-nd/4.0/)' +aliases: [] +published: 2019-06-12 +title: Why use GPU Instances? +modified_by: + name: Linode +--- + +## Why Choose a Linode GPU Instance? + +When considering the benefits of a GPU, a good analogy to keep in mind is the difference between a speedboat and a cargo ship. Though a speedboat will always be the fastest option when traveling between point A and B (and the better option for most people), the cargo ship is still needed whenever massive quantities of “cargo” or "simple data" need to be moved. Although a cargo ship is slower than a speedboat overall, it can transport data significantly faster when compared to the round trips a speedboat would need to make to transport the same data. In this sense, your GPU can be thought of as a cargo ship, while your CPU is a speedboat. + +GPU’s (Graphical Processing Units) are generally needed in situations where the few cores and threads provided by a CPU alone wouldn’t be enough to handle the large scale tasks that require the use of thousands of threads at a single given point in time. A GPU has significantly more logical cores than a standard CPU, and although they work similarly, this makes a GPU significantly better for performing any task that would benefit from many simple long-term computations performed in tandem with each other. In othe words, this means that GPUs are the perfect fit for the large scale monotonous calculations that are required to perform many of the tasks required for big data, video encoding, AI, Machine Learning, and more. + +## Machine Learning and AI + +Machine Learning is a powerful, modern approach to data science, where a machine is given a set of data to parse that it then uses to learn through experience without being explicitly told to do so. You can see this most often in your day to day through the “recommendation” features on many popular music and video applications, online shops, search engines, and more. In these cases where you are intelligently being recommended something specifically for your own tastes, machine learning is often responsible. This isn’t the only place where machine learning can be applied however. Self-driving cars, process automation, Security, Marketing Analytics, and even the field of Medicine are just a few additional areas where machine learning can now be seen applied in various ways. + +AI, or Artificial Intelligence, is a more broad concept, applying to any application of technology which is designed to act intelligently and mimic the cognitive functions of human or animal brains. It’s important to consider that Machine Learning is a subset of AI but is not it’s only application. + +Machine Learning and AI are generally designed and configured using the same tools. Below are a few recommendations: + +- [tensorflow](https://www.tensorflow.org) - A free, open-source, machine learning framework and deep learning library. Originally developed by [Google](google.com) for internal use before being fully released to the public under the Apache License, Tensorflow is a powerful open source machine learning platform. + +- [pytorch](https://pytorch.org/) - Tailored for GPU functionality in Python, Pytorch is a deep learning research platform designed for maximum flexibility and speed. + +- [Apache Mahout](https://mahout.apache.org/) - Apache Mahout is a scalable library of machine learning algorithms, and a distributed linear algebra framework designed to let mathematicians, statisticians, and data scientists quickly implement their own algorithms. + +## Big Data + +Big data is a term used to refer to data sets so large and complex that they require their own set of software and hardware tools to interact with them. When thinking of big data and whether or not the term applies to you, it often helps to visualize the “three Vs”: + +- **Volume:** “Big Data” is just another way to say “Large Quantities of Data." + + Generally when you consider multiple Terabytes, Exabytes, Petabytes, or more, you're talking about the quantity of information that is found in Big Data. + + +- **Velocity:** With Big Data, you’re dealing with data that is being created, called, moved,and interacted with quickly, or with high velocity. This is something especially true on social media platforms, where large amounts of data are designed to be interacted with in as close to real time as possible. + +- **Variety:** Variety refers to the many different types of data you may need to be able to interact with. Photos, video, audio, documents, and more can all be written and saved in a number of different formats. Variety is worth being mindful of in order to ensure that all of your different data is classified into appropriate categories. + +If these definitions seem to describe your environment, or your use case, then a Big Data Solution may be right for you. + +In the modern Big Data world, GPUs can help to give Big Data systems the additional computational capabilities they often need for ideal performance. Below are a few examples of tools which you can use for your own Big Data solutions: + +- [Hadoop](https://hadoop.apache.org/) - Hadoop is an Apache project that allows creation of parallel processing applications on large data sets, distributed across networked nodes. It is designed specifically for large data sets, and would be considere + +- [Apache Spark](https://spark.apache.org/) - Apache Spark is a unified analytics engine for large-scale data processing. Designed with speed and ease of use in mind. + +- [Apache Storm](https://storm.apache.org/) - Apache Storm is a distributed computation system that processes streaming data at real time. + +### Video Encoding + +Video Encoding is the process of taking the original source format of a video file, and converting it to another which can be viewable on a different device or using a different tool. Though this process has been around for a good long while and is normally resource intensive, having a good GPU can give you more speed and mobility when completing these tasks: + + - [FFmpeg](https://developer.nvidia.com/ffmpeg) - FFmpeg is an extremely popular multimedia framework able that supports a massive number of video formats, making it the top choice for video encoding by a number of Linux users and professionals. + + +## Cuda + +Cuda Is a parallel computing platform and programming model that allows you to interact more directly with your GPU for general purpose computing. In practice, this would mean that a developer could write code in C, C++, or many other supported languages to utilize their GPU to create their own tools and programs. You can see an example of code written with Cuda below: + +Cuda is the technology that powers some other well known tools like [Tensorflow](#machine-learning-and-ai). + +If you're interested in using CUDA on your GPU Linode, we can recommend referencing NVIDIA's [Library of Documentation](https://docs.nvidia.com/cuda/) or this [Introduction to Cuda](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) for more information. From 7db8d6396a8192dbbc3c4f93e8df74ce9ee3fd86 Mon Sep 17 00:00:00 2001 From: leslitagordita Date: Wed, 12 Jun 2019 19:28:40 -0400 Subject: [PATCH 2/9] Fist pass copy edits --- docs/platform/why-linode-gpu/index.md | 59 ++++++++++++--------------- 1 file changed, 26 insertions(+), 33 deletions(-) diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/why-linode-gpu/index.md index 791887ea4db..f08669c5a6a 100644 --- a/docs/platform/why-linode-gpu/index.md +++ b/docs/platform/why-linode-gpu/index.md @@ -2,70 +2,63 @@ author: name: Linode email: docs@linode.com -description: 'Why use GPU Instances' +description: 'Use Cases for Linode GPU Instances' keywords: ["", "grub"] license: '[CC BY-ND 4.0](http://creativecommons.org/licenses/by-nd/4.0/)' aliases: [] published: 2019-06-12 -title: Why use GPU Instances? +title: Linode GPU Use Cases modified_by: name: Linode --- -## Why Choose a Linode GPU Instance? +## What are GPUs? -When considering the benefits of a GPU, a good analogy to keep in mind is the difference between a speedboat and a cargo ship. Though a speedboat will always be the fastest option when traveling between point A and B (and the better option for most people), the cargo ship is still needed whenever massive quantities of “cargo” or "simple data" need to be moved. Although a cargo ship is slower than a speedboat overall, it can transport data significantly faster when compared to the round trips a speedboat would need to make to transport the same data. In this sense, your GPU can be thought of as a cargo ship, while your CPU is a speedboat. +GPUs (Graphical Processing Units) are specialized hardware originally created to manipulate computer graphics and image processing. GPUs are designed to process large blocks of data in parallel making them excellent for compute intensive tasks that require thousands of simultaneous threads. Because a GPU has significantly more logical cores than a standard CPU, it can perform computations that process large amounts of data in parallel, more efficiently. This means GPUs accelerate the large calculations that are required by big data, video encoding, AI, and machine learning. -GPU’s (Graphical Processing Units) are generally needed in situations where the few cores and threads provided by a CPU alone wouldn’t be enough to handle the large scale tasks that require the use of thousands of threads at a single given point in time. A GPU has significantly more logical cores than a standard CPU, and although they work similarly, this makes a GPU significantly better for performing any task that would benefit from many simple long-term computations performed in tandem with each other. In othe words, this means that GPUs are the perfect fit for the large scale monotonous calculations that are required to perform many of the tasks required for big data, video encoding, AI, Machine Learning, and more. +## Use Cases +### Machine Learning and AI -## Machine Learning and AI +Machine learning is a powerful approach to data science that uses large sets of data to build prediction algorithms. These prediction algorithms are commonly used in “recommendation” features on many popular music and video applications, online shops, and search engines. When you receive intelligent recommendations tailored to your own tastes, machine learning is often responsible. Other areas where you might find machine learning being used is in self-driving cars, process automation, security, marketing analytics, and health care. -Machine Learning is a powerful, modern approach to data science, where a machine is given a set of data to parse that it then uses to learn through experience without being explicitly told to do so. You can see this most often in your day to day through the “recommendation” features on many popular music and video applications, online shops, search engines, and more. In these cases where you are intelligently being recommended something specifically for your own tastes, machine learning is often responsible. This isn’t the only place where machine learning can be applied however. Self-driving cars, process automation, Security, Marketing Analytics, and even the field of Medicine are just a few additional areas where machine learning can now be seen applied in various ways. +AI (Artificial Intelligence) is a broad concept that describes technology designed to behave intelligently and mimic the cognitive functions of humans, like learning, decision making, and speech recognition. AI uses large sets of data to learn and adapt in order to achieve a specific goal. GPUs provide the processing power needed for common AI and machine learning tasks like input data preprocessing and model building. -AI, or Artificial Intelligence, is a more broad concept, applying to any application of technology which is designed to act intelligently and mimic the cognitive functions of human or animal brains. It’s important to consider that Machine Learning is a subset of AI but is not it’s only application. +Below is a list of common tools used for machine learning and AI that can be installed on a Linode GPU instance: -Machine Learning and AI are generally designed and configured using the same tools. Below are a few recommendations: +- [tensorflow](https://www.tensorflow.org) - a free, open-source, machine learning framework and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. -- [tensorflow](https://www.tensorflow.org) - A free, open-source, machine learning framework and deep learning library. Originally developed by [Google](google.com) for internal use before being fully released to the public under the Apache License, Tensorflow is a powerful open source machine learning platform. +- [pytorch](https://pytorch.org/) - a machine learning library for Python that uses the popular GPU optimized [Torch](https://en.wikipedia.org/wiki/Torch_(machine_learning)) framework. -- [pytorch](https://pytorch.org/) - Tailored for GPU functionality in Python, Pytorch is a deep learning research platform designed for maximum flexibility and speed. +- [Apache Mahout](https://mahout.apache.org/) - a scalable library of machine learning algorithms, and a distributed linear algebra framework designed to let mathematicians, statisticians, and data scientists quickly implement their own algorithms. -- [Apache Mahout](https://mahout.apache.org/) - Apache Mahout is a scalable library of machine learning algorithms, and a distributed linear algebra framework designed to let mathematicians, statisticians, and data scientists quickly implement their own algorithms. +### Big Data -## Big Data +Big data is a discipline that analyzes and extracts meaningful insights from large and complex data sets. These sets are so large and complex that they require specialized software and hardware to appropriately capture, manage, and process the data. When thinking of big data and whether or not the term applies to you, it often helps to visualize the “three Vs”: -Big data is a term used to refer to data sets so large and complex that they require their own set of software and hardware tools to interact with them. When thinking of big data and whether or not the term applies to you, it often helps to visualize the “three Vs”: +- **Volume:** Generally, if you are working with terabytes, exabytes, petabytes, or more amounts of information you are in the realm of big data. -- **Volume:** “Big Data” is just another way to say “Large Quantities of Data." - Generally when you consider multiple Terabytes, Exabytes, Petabytes, or more, you're talking about the quantity of information that is found in Big Data. +- **Velocity:** With Big Data, you’re using data that is being created, called, moved, and interacted with at a high velocity. One example is the real time data generated on social media platforms by its users. +- **Variety:** Variety refers to the many different types of data formats with which you may need to interact. Photos, video, audio, and documents can all be written and saved in a number of different formats. It is important to consider the variety of data that you will collect in order to appropriately categorize your it. -- **Velocity:** With Big Data, you’re dealing with data that is being created, called, moved,and interacted with quickly, or with high velocity. This is something especially true on social media platforms, where large amounts of data are designed to be interacted with in as close to real time as possible. +GPUs can help give Big Data systems the additional computational capabilities they need for ideal performance. Below are a few examples of tools which you can use for your own big data solutions: -- **Variety:** Variety refers to the many different types of data you may need to be able to interact with. Photos, video, audio, documents, and more can all be written and saved in a number of different formats. Variety is worth being mindful of in order to ensure that all of your different data is classified into appropriate categories. +- [Hadoop](https://hadoop.apache.org/) - an Apache project that allows the creation of parallel processing applications on large data sets, distributed across networked nodes. -If these definitions seem to describe your environment, or your use case, then a Big Data Solution may be right for you. +- [Apache Spark](https://spark.apache.org/) - a unified analytics engine for large-scale data processing designed with speed and ease of use in mind. -In the modern Big Data world, GPUs can help to give Big Data systems the additional computational capabilities they often need for ideal performance. Below are a few examples of tools which you can use for your own Big Data solutions: - -- [Hadoop](https://hadoop.apache.org/) - Hadoop is an Apache project that allows creation of parallel processing applications on large data sets, distributed across networked nodes. It is designed specifically for large data sets, and would be considere - -- [Apache Spark](https://spark.apache.org/) - Apache Spark is a unified analytics engine for large-scale data processing. Designed with speed and ease of use in mind. - -- [Apache Storm](https://storm.apache.org/) - Apache Storm is a distributed computation system that processes streaming data at real time. +- [Apache Storm](https://storm.apache.org/) - a distributed computation system that processes streaming data in real time. ### Video Encoding -Video Encoding is the process of taking the original source format of a video file, and converting it to another which can be viewable on a different device or using a different tool. Though this process has been around for a good long while and is normally resource intensive, having a good GPU can give you more speed and mobility when completing these tasks: - - - [FFmpeg](https://developer.nvidia.com/ffmpeg) - FFmpeg is an extremely popular multimedia framework able that supports a massive number of video formats, making it the top choice for video encoding by a number of Linux users and professionals. +Video Encoding is the process of taking a video file's original source format and converting it to another format that is viewable on a different device or using a different tool. This resource intensive task can be greatly accelerated using the power of GPUs. + - [FFmpeg](https://developer.nvidia.com/ffmpeg) - a popular open-source multimedia manipulation framework that supports a large number of video formats. -## Cuda -Cuda Is a parallel computing platform and programming model that allows you to interact more directly with your GPU for general purpose computing. In practice, this would mean that a developer could write code in C, C++, or many other supported languages to utilize their GPU to create their own tools and programs. You can see an example of code written with Cuda below: +### General Purpose Computing using CUDA -Cuda is the technology that powers some other well known tools like [Tensorflow](#machine-learning-and-ai). +CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface that allows you to interact more directly with your GPU for general purpose computing. In practice, this means that a developer can write code in C, C++, or many other supported languages to utilize their GPU to create their own tools and programs. -If you're interested in using CUDA on your GPU Linode, we can recommend referencing NVIDIA's [Library of Documentation](https://docs.nvidia.com/cuda/) or this [Introduction to Cuda](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) for more information. +If you're interested in using CUDA on your GPU Linode, see NVIDIA's [Library of Documentation](https://docs.nvidia.com/cuda/) or an [Introduction to Cuda](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) for more information. From 70b264c4492ce8ee2ffcd07cd750de1ed516711b Mon Sep 17 00:00:00 2001 From: Angel Date: Thu, 13 Jun 2019 10:59:03 -0400 Subject: [PATCH 3/9] Added a section linking to the Getting started with GPU guide. --- docs/platform/why-linode-gpu/index.md | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/why-linode-gpu/index.md index f08669c5a6a..b08c09ffdb0 100644 --- a/docs/platform/why-linode-gpu/index.md +++ b/docs/platform/why-linode-gpu/index.md @@ -3,7 +3,7 @@ author: name: Linode email: docs@linode.com description: 'Use Cases for Linode GPU Instances' -keywords: ["", "grub"] +keywords: ["GPU","Linode GPU", "How to use GPU", "Machine Learning", "AI", "Deep Learning", "grub"] license: '[CC BY-ND 4.0](http://creativecommons.org/licenses/by-nd/4.0/)' aliases: [] published: 2019-06-12 @@ -25,9 +25,9 @@ AI (Artificial Intelligence) is a broad concept that describes technology design Below is a list of common tools used for machine learning and AI that can be installed on a Linode GPU instance: -- [tensorflow](https://www.tensorflow.org) - a free, open-source, machine learning framework and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. +- [TensorFlow](https://www.tensorflow.org) - a free, open-source, machine learning framework and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. -- [pytorch](https://pytorch.org/) - a machine learning library for Python that uses the popular GPU optimized [Torch](https://en.wikipedia.org/wiki/Torch_(machine_learning)) framework. +- [PyTorch](https://pytorch.org/) - a machine learning library for Python that uses the popular GPU optimized [Torch](https://en.wikipedia.org/wiki/Torch_(machine_learning)) framework. - [Apache Mahout](https://mahout.apache.org/) - a scalable library of machine learning algorithms, and a distributed linear algebra framework designed to let mathematicians, statisticians, and data scientists quickly implement their own algorithms. @@ -56,9 +56,12 @@ Video Encoding is the process of taking a video file's original source format an - [FFmpeg](https://developer.nvidia.com/ffmpeg) - a popular open-source multimedia manipulation framework that supports a large number of video formats. - ### General Purpose Computing using CUDA -CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface that allows you to interact more directly with your GPU for general purpose computing. In practice, this means that a developer can write code in C, C++, or many other supported languages to utilize their GPU to create their own tools and programs. +CUDA (Compute Unified Device Architecture) is a parallel computing platform and API that allows you to interact more directly with the GPU for general purpose computing. In practice, this means that a developer can write code in C, C++, or many other supported languages utilizing their GPU to create their own tools and programs. If you're interested in using CUDA on your GPU Linode, see NVIDIA's [Library of Documentation](https://docs.nvidia.com/cuda/) or an [Introduction to Cuda](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) for more information. + +### Getting Started with Linode GPU + +If you are ready to get started with Linode GPU we wrote a guide that walks you through deploying a Linode GPU instance, and installing the GPU drivers so that you can best utilize the machine for the use cases you've read in this guide. Read it [here](/docs/platform/why-linode-gpu/docs/platform/linode-gpu/getting-started-with-gpu/). From 9ddc351491b1e5ce134612c3a75aeabae84e7b8d Mon Sep 17 00:00:00 2001 From: hzoppetti Date: Thu, 13 Jun 2019 13:15:21 -0400 Subject: [PATCH 4/9] added section on graphics, links to nvidia, removed link to other guide until feature branch merge --- docs/platform/why-linode-gpu/index.md | 28 +++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/why-linode-gpu/index.md index b08c09ffdb0..683e6c5c280 100644 --- a/docs/platform/why-linode-gpu/index.md +++ b/docs/platform/why-linode-gpu/index.md @@ -16,6 +16,18 @@ modified_by: GPUs (Graphical Processing Units) are specialized hardware originally created to manipulate computer graphics and image processing. GPUs are designed to process large blocks of data in parallel making them excellent for compute intensive tasks that require thousands of simultaneous threads. Because a GPU has significantly more logical cores than a standard CPU, it can perform computations that process large amounts of data in parallel, more efficiently. This means GPUs accelerate the large calculations that are required by big data, video encoding, AI, and machine learning. +### The Linode GPU Instance +Linode GPU Instances are NVIDIA Quadro RTX 6000 GPU cards with Tensor, ray tracing (RT), and CUDA cores. + +### The Most Common Use Case on Linode GPU +The most common use case for a GPU is for graphics processing. Transforming the large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. The NVIDIA RTX 6000 of the Linode GPU Instance makes light work of both of these jobs. + +New shading enhancements include mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline; Variable Rate Shading to dynamically control shading rate; Texture-Space Shading which utilizes a private memory held texture space; and Multi-View Rendering allowing for rendering multiple views in a single pass. + +Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offer you real-time ray tracing capabilities using a single GPU. + +Read more about the NVIDIA RTX 6000 [here](https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf). + ## Use Cases ### Machine Learning and AI @@ -25,7 +37,7 @@ AI (Artificial Intelligence) is a broad concept that describes technology design Below is a list of common tools used for machine learning and AI that can be installed on a Linode GPU instance: -- [TensorFlow](https://www.tensorflow.org) - a free, open-source, machine learning framework and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. +- [TensorFlow](https://www.tensorflow.org) - a free, open-source, machine learning framework, and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. - [PyTorch](https://pytorch.org/) - a machine learning library for Python that uses the popular GPU optimized [Torch](https://en.wikipedia.org/wiki/Torch_(machine_learning)) framework. @@ -60,8 +72,16 @@ Video Encoding is the process of taking a video file's original source format an CUDA (Compute Unified Device Architecture) is a parallel computing platform and API that allows you to interact more directly with the GPU for general purpose computing. In practice, this means that a developer can write code in C, C++, or many other supported languages utilizing their GPU to create their own tools and programs. -If you're interested in using CUDA on your GPU Linode, see NVIDIA's [Library of Documentation](https://docs.nvidia.com/cuda/) or an [Introduction to Cuda](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) for more information. +If you're interested in using CUDA on your GPU Linode, see the following resources: + + - [NVIDIA's Library of Documentation](https://docs.nvidia.com/cuda/) + + - [Introduction to CUDA](https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/) + + - [NVIDIA's CUDA exercise repository](https://github.com/csc-training/CUDA/tree/master/exercises) + +### Where to Go from Here -### Getting Started with Linode GPU +If you are ready to get started with Linode GPU, we wrote a guide that walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. Read it [here](). -If you are ready to get started with Linode GPU we wrote a guide that walks you through deploying a Linode GPU instance, and installing the GPU drivers so that you can best utilize the machine for the use cases you've read in this guide. Read it [here](/docs/platform/why-linode-gpu/docs/platform/linode-gpu/getting-started-with-gpu/). +To see the extensive array of available Docker container apps available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account. \ No newline at end of file From ac2d9d86cdce4d9af33bc2129cf763ee37a1d60f Mon Sep 17 00:00:00 2001 From: hzoppetti Date: Thu, 13 Jun 2019 13:49:38 -0400 Subject: [PATCH 5/9] added shader to the dictionary --- ci/vale/dictionary.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/ci/vale/dictionary.txt b/ci/vale/dictionary.txt index 53855802a5c..03265dc1bf9 100644 --- a/ci/vale/dictionary.txt +++ b/ci/vale/dictionary.txt @@ -1202,6 +1202,7 @@ sfproject sfroot sftp sha256 +shader shadowsocks sharded sharding From 76fa8495b3da4aa30ed3274c823233a76040c6d9 Mon Sep 17 00:00:00 2001 From: Andy Stevens Date: Thu, 13 Jun 2019 15:57:17 -0400 Subject: [PATCH 6/9] Second pass copy edit --- docs/platform/why-linode-gpu/index.md | 30 ++++++++++++++------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/why-linode-gpu/index.md index 683e6c5c280..7cb463eb71e 100644 --- a/docs/platform/why-linode-gpu/index.md +++ b/docs/platform/why-linode-gpu/index.md @@ -17,16 +17,7 @@ modified_by: GPUs (Graphical Processing Units) are specialized hardware originally created to manipulate computer graphics and image processing. GPUs are designed to process large blocks of data in parallel making them excellent for compute intensive tasks that require thousands of simultaneous threads. Because a GPU has significantly more logical cores than a standard CPU, it can perform computations that process large amounts of data in parallel, more efficiently. This means GPUs accelerate the large calculations that are required by big data, video encoding, AI, and machine learning. ### The Linode GPU Instance -Linode GPU Instances are NVIDIA Quadro RTX 6000 GPU cards with Tensor, ray tracing (RT), and CUDA cores. - -### The Most Common Use Case on Linode GPU -The most common use case for a GPU is for graphics processing. Transforming the large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. The NVIDIA RTX 6000 of the Linode GPU Instance makes light work of both of these jobs. - -New shading enhancements include mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline; Variable Rate Shading to dynamically control shading rate; Texture-Space Shading which utilizes a private memory held texture space; and Multi-View Rendering allowing for rendering multiple views in a single pass. - -Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offer you real-time ray tracing capabilities using a single GPU. - -Read more about the NVIDIA RTX 6000 [here](https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf). +Linode GPU Instances include NVIDIA Quadro RTX 6000 GPU cards with Tensor, ray tracing (RT), and CUDA cores. Read more about the NVIDIA RTX 6000 [here](https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf). ## Use Cases ### Machine Learning and AI @@ -37,7 +28,7 @@ AI (Artificial Intelligence) is a broad concept that describes technology design Below is a list of common tools used for machine learning and AI that can be installed on a Linode GPU instance: -- [TensorFlow](https://www.tensorflow.org) - a free, open-source, machine learning framework, and deep learning library. Tensorflow was originally developed by [Google](google.com) for internal use and later fully released to the public under the Apache License. +- [TensorFlow](https://www.tensorflow.org) - a free, open-source, machine learning framework, and deep learning library. Tensorflow was originally developed by [Google](http://google.com) for internal use and later fully released to the public under the Apache License. - [PyTorch](https://pytorch.org/) - a machine learning library for Python that uses the popular GPU optimized [Torch](https://en.wikipedia.org/wiki/Torch_(machine_learning)) framework. @@ -52,7 +43,7 @@ Big data is a discipline that analyzes and extracts meaningful insights from lar - **Velocity:** With Big Data, you’re using data that is being created, called, moved, and interacted with at a high velocity. One example is the real time data generated on social media platforms by its users. -- **Variety:** Variety refers to the many different types of data formats with which you may need to interact. Photos, video, audio, and documents can all be written and saved in a number of different formats. It is important to consider the variety of data that you will collect in order to appropriately categorize your it. +- **Variety:** Variety refers to the many different types of data formats with which you may need to interact. Photos, video, audio, and documents can all be written and saved in a number of different formats. It is important to consider the variety of data that you will collect in order to appropriately categorize it. GPUs can help give Big Data systems the additional computational capabilities they need for ideal performance. Below are a few examples of tools which you can use for your own big data solutions: @@ -62,6 +53,17 @@ GPUs can help give Big Data systems the additional computational capabilities th - [Apache Storm](https://storm.apache.org/) - a distributed computation system that processes streaming data in real time. +### Graphics Processing + +One of the most traditional use cases for a GPU is graphics processing. Transforming a large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offers real-time ray tracing capabilities using a single GPU. + +New to the NVIDIA RTX 600 are the following shading enhancements: + +- Mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline +- Variable Rate Shading to dynamically control shading rate +- Texture-Space Shading which utilizes a private memory held texture space +- Multi-View Rendering allowing for rendering multiple views in a single pass. + ### Video Encoding Video Encoding is the process of taking a video file's original source format and converting it to another format that is viewable on a different device or using a different tool. This resource intensive task can be greatly accelerated using the power of GPUs. @@ -80,8 +82,8 @@ If you're interested in using CUDA on your GPU Linode, see the following resourc - [NVIDIA's CUDA exercise repository](https://github.com/csc-training/CUDA/tree/master/exercises) -### Where to Go from Here +## Where to Go from Here -If you are ready to get started with Linode GPU, we wrote a guide that walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. Read it [here](). +If you are ready to get started with Linode GPU, our [Getting Started with Linode GPU Instances] guide walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. To see the extensive array of available Docker container apps available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account. \ No newline at end of file From d705a240114cb941633890a77891e984bf33bf96 Mon Sep 17 00:00:00 2001 From: hzoppetti Date: Thu, 13 Jun 2019 16:24:56 -0400 Subject: [PATCH 7/9] adding link to guide --- docs/platform/{ => linode-gpu}/why-linode-gpu/index.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) rename docs/platform/{ => linode-gpu}/why-linode-gpu/index.md (93%) diff --git a/docs/platform/why-linode-gpu/index.md b/docs/platform/linode-gpu/why-linode-gpu/index.md similarity index 93% rename from docs/platform/why-linode-gpu/index.md rename to docs/platform/linode-gpu/why-linode-gpu/index.md index 7cb463eb71e..47f5d809384 100644 --- a/docs/platform/why-linode-gpu/index.md +++ b/docs/platform/linode-gpu/why-linode-gpu/index.md @@ -7,7 +7,7 @@ keywords: ["GPU","Linode GPU", "How to use GPU", "Machine Learning", "AI", "Deep license: '[CC BY-ND 4.0](http://creativecommons.org/licenses/by-nd/4.0/)' aliases: [] published: 2019-06-12 -title: Linode GPU Use Cases +title: Use Cases for Linode GPU Instances modified_by: name: Linode --- @@ -84,6 +84,6 @@ If you're interested in using CUDA on your GPU Linode, see the following resourc ## Where to Go from Here -If you are ready to get started with Linode GPU, our [Getting Started with Linode GPU Instances] guide walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. +If you are ready to get started with Linode GPU, our [Getting Started with Linode GPU Instances](/docs/platform/linode-gpu/getting-started-with-gpu/) guide walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. -To see the extensive array of available Docker container apps available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account. \ No newline at end of file +To see the extensive array of Docker container applications available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account. \ No newline at end of file From 94763bb584fb370801263f1aacdf73aa87f44b18 Mon Sep 17 00:00:00 2001 From: hzoppetti Date: Thu, 13 Jun 2019 16:26:52 -0400 Subject: [PATCH 8/9] moved graphics processing section --- .../linode-gpu/why-linode-gpu/index.md | 22 +++++++++---------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/docs/platform/linode-gpu/why-linode-gpu/index.md b/docs/platform/linode-gpu/why-linode-gpu/index.md index 47f5d809384..002151c65c0 100644 --- a/docs/platform/linode-gpu/why-linode-gpu/index.md +++ b/docs/platform/linode-gpu/why-linode-gpu/index.md @@ -53,17 +53,6 @@ GPUs can help give Big Data systems the additional computational capabilities th - [Apache Storm](https://storm.apache.org/) - a distributed computation system that processes streaming data in real time. -### Graphics Processing - -One of the most traditional use cases for a GPU is graphics processing. Transforming a large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offers real-time ray tracing capabilities using a single GPU. - -New to the NVIDIA RTX 600 are the following shading enhancements: - -- Mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline -- Variable Rate Shading to dynamically control shading rate -- Texture-Space Shading which utilizes a private memory held texture space -- Multi-View Rendering allowing for rendering multiple views in a single pass. - ### Video Encoding Video Encoding is the process of taking a video file's original source format and converting it to another format that is viewable on a different device or using a different tool. This resource intensive task can be greatly accelerated using the power of GPUs. @@ -82,6 +71,17 @@ If you're interested in using CUDA on your GPU Linode, see the following resourc - [NVIDIA's CUDA exercise repository](https://github.com/csc-training/CUDA/tree/master/exercises) +### Graphics Processing + +One of the most traditional use cases for a GPU is graphics processing. Transforming a large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offers real-time ray tracing capabilities using a single GPU. + +New to the NVIDIA RTX 600 are the following shading enhancements: + +- Mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline +- Variable Rate Shading to dynamically control shading rate +- Texture-Space Shading which utilizes a private memory held texture space +- Multi-View Rendering allowing for rendering multiple views in a single pass. + ## Where to Go from Here If you are ready to get started with Linode GPU, our [Getting Started with Linode GPU Instances](/docs/platform/linode-gpu/getting-started-with-gpu/) guide walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. From 8fbf3e20673f4984e88d30d3d6e4d7a9beb1fde9 Mon Sep 17 00:00:00 2001 From: Angel Date: Fri, 14 Jun 2019 11:55:19 -0400 Subject: [PATCH 9/9] Update index.md --- docs/platform/linode-gpu/why-linode-gpu/index.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/platform/linode-gpu/why-linode-gpu/index.md b/docs/platform/linode-gpu/why-linode-gpu/index.md index 002151c65c0..85b62e31b29 100644 --- a/docs/platform/linode-gpu/why-linode-gpu/index.md +++ b/docs/platform/linode-gpu/why-linode-gpu/index.md @@ -75,7 +75,7 @@ If you're interested in using CUDA on your GPU Linode, see the following resourc One of the most traditional use cases for a GPU is graphics processing. Transforming a large set of pixels or vertices with a shader or simulating realistic lighting via ray tracing are massive parallel processing tasks. Ray tracing is a computationally intensive process that simulates lights in a scene and renders the reflections, refractions, shadows, and indirect lighting. It's impossible to do on GPUs in real-time without hardware-based ray tracing acceleration. The Linode GPU Instances offers real-time ray tracing capabilities using a single GPU. -New to the NVIDIA RTX 600 are the following shading enhancements: +New to the NVIDIA RTX 6000 are the following shading enhancements: - Mesh shading models for vertex, tessellation, and geometry stages in the graphics pipeline - Variable Rate Shading to dynamically control shading rate @@ -86,4 +86,4 @@ New to the NVIDIA RTX 600 are the following shading enhancements: If you are ready to get started with Linode GPU, our [Getting Started with Linode GPU Instances](/docs/platform/linode-gpu/getting-started-with-gpu/) guide walks you through deploying a Linode GPU Instance and installing the GPU drivers so that you can best utilize the use cases you've read in this guide. -To see the extensive array of Docker container applications available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account. \ No newline at end of file +To see the extensive array of Docker container applications available, check out [NVIDIA's site](https://ngc.nvidia.com/catalog/landing). Note: To access some of these projects you need an NGC account.