Feature: System design
Active Silicon GPUs with and without GPUDirect for video for 700px frames Furthermore, AMD DirectGMA offers the following:
• It supports GPUs FirePro W5000 and above, FireProS series, and others;
• Operating system – Windows 8/10 64-bit or Linux 64-bit; • It supports the OpenCL, OpenGL and DirectX APIs; • AMD graphic cards support STREAM technology, which uses the OpenCL cross-platform programming standard.
Setup requirements include: • AMD GPU supporting DirectGMA; • Active Silicon’s SDK and AMD SDK; • Active Silicon’s FireBird or Phoenix frame grabber.
GPUDirect In comparison, Nvidia’s GPUDirect for video/RDMA offers: • Support for GPUs Quadro, GRID, Tesla, and others; • Operating system – Windows 7/8/10 64-bit or Linux 64-bit (RDMA: Linux only);
• It supports the CUDA, OpenCL, OpenGL, DirectX APIs; • Nvidia cards offer from eight to over 5000 CUDA cores, offering a range of processing power.
Setup requirements include: • Nvidia GPU supporting GPUDirect for video; • Active Silicon’s SDK and Nvidia SDK; • Active Silicon’s FireBird or Phoenix frame grabber.
Nvidia’s GPUDirect RDMA is the technology equivalent
under Linux and this API allows Active Silicon’s frame grabber to image data directly into the GPU’s memory, physically located on the graphics card memory, bypassing the system memory altogether. This is similar to AMD’s DirectGMA discussed earlier, also supported by Active Silicon acquisition cards and software libraries.
More in the pipeline All Active Silicon FireBird and Phoenix frame grabbers are compatible with GPUDirect for Video and DirectGMA. The well-documented API and SDK sample code allows
for easy integration of parallel computing techniques on standard PC hardware. Active Silicon’s SDK includes a comprehensive suite of C++ examples for GPUDirect for Video and DirectGMA with full source code. Nvidia’s and AMD’s APIs are just two examples of GPUs
and their APIs available today; there are several GPU manufacturers offering similar software. This means that enabling faster image processing via GPU is becoming a common and straightforward technique to relieve memory bottlenecks in vision systems.
Active Silicon GPU solutions with and without DirectGMA or RDMA for 700px frames 38 November 2022
www.electronicsworld.co.uk
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
