New graphics XMC delivers flexibility and minimises latency

Abaco Systems has expanded its growing range of video/graphics solutions with the launch of the rugged, high bandwidth NVP2102A XMC Graphics and GPGPU Card. Created to complement the NVP2102, the new device provides further support for legacy interfaces and peripherals.

Based on the NVIDIA Quadro Pascal (GP107) P2000 GPU architecture and producing up to 2.3 TeraFLOPS of peak performance, target applications for the new board cover those that demand very high-end graphics abilities or CUDA support when executing general-purpose processing, and that need raw video capture and display. The product is competitively advantaged by its provision of four 3G-SDI inputs – double the number generally found. It also offers two NTSC/PAL video inputs as well as supporting two audio inputs. Video output is through two 3G-SDI and two DVI or DisplayPort interfaces.

Of note is the product’s support for direct video capture to GPU memory. This significantly reduces latency, minimising glass-to-glass time – enabling the delivery of actionable information in closer to real-time. The input resolution of incoming video is automatically identified, and raw video frames are carried directly to GPU memory (or host memory). In GPU memory, processing including image analysis, image enhancement, sensor fusion, 360-degree video stitching, target detection and so on takes advantage of the extraordinary abilities of NVIDIA GPGPU (CUDA/OpenCL) technology to achieve output to the user far faster than would otherwise be possible. The captured data can additionally be encoded employing the GPU-native H.265 (HEVC) or H.264 encoders directly in GPU memory. Windows or Linux drivers and API are offered for x86 systems.

“With the NVP2102A, we’re delivering the kind of performance and functionality on an XMC card that, until recently, would have required a full-size card – occupying a valuable chassis slot,” said Peter Thompson, vice president, Product Management at Abaco Systems. “Not only does the NVP2102A minimise SWaP, but it also features the advanced capabilities of the latest NVIDIA GPU and no fewer than four video inputs. Also, its architecture enables it to deliver reduced latency – addressing a significant challenge for developers of advanced video and graphics processing applications.”