UKM-AUT23-PG24new_Layout 1 09/08/2023 09:12 Page 24
SMART MANUFACTURING
HOW TO LEVERAGE A GPU SERVER FOR AI AND AUTOMATION WORKLOADS
WHAT IS A GPU SERVER?
A GPU server taps into the processing power of a dedicated GPU (Graphics Processing Unit) to process large datasets quickly and efficiently. GPUs were designed for parallel processing and were originally created to accelerate the rendering of 3D graphics for immersive gaming and other video capabilities. This parallel computing lends itself well to graphics heavy workloads like image recognition, as well as accelerating the training and inference of neural networks for deep learning algorithms.
VISUAL INSPECTION AI
Visual inspection is an important part of the manufacturing process that helps to ensure product quality. AI is often used in visual inspection to help catch defects the human eye may miss. So how exactly is AI used for quality control in manufacturing?
Imagine you have a line of bottles moving along the production line. Data (such as images of the print on the label and exact position of the label on the bottles) can be collected, then used to create a model. After this model is tested for accuracy, it can be used to help identify faulty labels.
Using machine vision, smart cameras on the manufacturing line can inspect each bottle and compare it to the pre-generated model. Computer vision can then be used to interpret the images and detect defects. When a defect is identified, an event can be triggered, such as an alert notification to a device or operator, or the automated or manual removal of the bottle from the manufacturing line.
GPU SERVERS FOR MACHINE VISION Machine vision computers are an integral part of a quality inspection solution. Whether they are part of a standalone device or integrated into an OEM appliance, machine vision computers need to be powerful, fast, and reliable to help to catch easy-to-miss details. When choosing a computer to support a machine vision solution near the production line, it is important to consider the environment it will be used in.
Manufacturing environments are often dirty, feature extreme temperatures, and can even be dangerous to humans, so having a computer that can stand up to these environments is essential. Built to handle the challenges of many industrial environments, a rugged machine vision computer from OnLogic, such as the Karbon 803 or Karbon 804, is a great platform for a machine vision solution for quality control in manufacturing.
RACKMOUNT EDGE SERVER WITH GPU For larger production needs with multiple lines that each require inspection, you could have a rugged machine vision computer installed with each
24
production line. Alternatively, all lines could be monitored and controlled by a single high performance rackmount edge server. The high performance computing of the edge server can support multiple production lines with a single piece of hardware.
GPU EDGE SERVER REQUIREMENTS A server deployment at the edge introduces some new requirements not as common in traditional server deployments.
CPU performance at the edge: CPU performance is one of the first considerations most people make when looking at a server. Some applications will require Intel Xeon scalable CPUs. For other applications, modern Intel Core CPUs, which integrate many of the features of previous generation Xeon scalable processors, offer a more affordable, but still extremely powerful, alternative. The Axial AC101 Edge Server offers the latest Intel 13th Gen Hybrid Architecture processors with up to 24 cores and 32 threads.
GPU compute and space limitations: For AI workload acceleration, a PCIe GPU is usually a primary requirement for performance. The AC101 is a short-depth edge server that is capable of supporting a full height, full length GPU.
Baseboard Management Controller (BMC): A BMC allows you to control the server while out of band, which can be key in a distributed architecture at the edge. At scale, effective device management becomes critical. The AC101 does not require users to pay any additional licensing fees to utilize the full capabilities of the BMC unlike many other servers on the market.
Tamper protection: At the edge, systems can’t always be deployed in areas with access control. To address this, the AC101 comes with a locking security bezel and limited front facing I/O. This helps prevent access to the 4x internal U.3 (NVMe) or SATA SSDs and 2x M.2 SSDs.
Ready to learn how you can leverage a GPU server for your AI and automation workloads? You can find out more on the OnLogic blog:
www.onlogic.com/company/io- hub/how-to-leverage-a-gpu-server-for-ai-and- automation-workloads/. Alternatively, explore OnLogic’s entire selection of computers available with GPU and reach out to the company’s team today!
OnLogic
www.onlogic.com/uk-en/
Autumn 2023 UKManufacturing
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48
