Cookie Einstellungen
Diese Webseite verwendet ausschließlich notwendige Cookies, die für das Funktionieren von Login und Cookie-Hinweis unbedingt erforderlich sind. Statistik- und Werbe-Cookies kommen nicht zum Einsatz. Weitere Informationen finden Sie in unserer Datenschutzerklärung.
OK
GR2

3U VPX High Performance Dual Channel Graphics Output Board

The Abaco GR2 is a 3U VPX graphics output card based on the NVIDIA Pascal ™ Quadro P5000/P3000 GPUs. The GR2 offers very high performance graphics and GPGPU capability - up to 6.4 TFLOPS floating-point - with CUDA® and OpenCL™ support.

For both runtime performance and ease of programming, the NVIDIA ® Pascal ™ Quadro ® P5000/P3000 GPUs enable significant gains in SIGINT, radar and video or graphics processing applications. Their high degree of parallelism (2,048/1,280 CUDA cores) also makes them an optimum fit for GPGPU applications including AI, machine learning and autonomy.

The GR2 - which meets the MIL-STD-810G standard - is available in both air- and conduction cooled formats and supports PCI Express ™ 3.0 (16, 8 or 4 lanes) when configured with compatible single board computers.

Two DisplayPort ™ 1.4 outputs are avaiilable from the rear P2 VPX connector. The board can consume up to 100W dependent on the choice of GPU and the application. Maximum power consumption of the board can be temporarily reduces by adjusting the graphics clock speed with a software utility after boot.

Windows ® and Linux® drivers are provided for x86-based platforms.

AXIS Software Toolkit
AXIS ImageFlex is an image processing and visualization toolkit enabling rapid development of high performance image processing, visualization and autonomy applications aimed at size, weight and power (SWaP) sensitive platforms. It is focused on high performance GPU processing and graphics with inter-operability with other programing paradigms such as OpenGL® 4.6, OpenCL™ 1.2, CUDA and OpenCV.

Features
  • HPC graphics output board
  • 3U VPX form factor, 1” pitch
  • NVIDIA Pascal GPU Quadro P5000 MXM
    - 6.4 TFLOPS peak FP32 performance
    - 2,048 CUDA cores, 16GB GDDR5
  • or NVIDIA Pascal GPU Quadro P3000 MXM
    - 3.9 TFLOPs peak FP32 performance
    - 1,280 CUDA cores, 6GB GDDR5
  • 2x DisplayPort 1.4 outputs - 4K @ 60Hz
  • PCI Gen 3 - x16, x8, x4 lanes
  • Windows and Linux drivers on x86
  • NVIDIA CUDA 6.1, OpenCL™ 1.2 and NVIDIA software suite
  • Air-cooled and conduction cooled
  • Standards
    - Meets MIL-STD-810G
please contact systerra for ordering options. Minimum order quantity: 10
Return to last Page ...