3U VPX GPGPU Processing Module VPX3U-A4500E-VO

WOLF’s Model VPX3U-A4500E-VO is a Graphics and Video Card that includes a NVIDIA RTX™ A4500 embedded CPU in a rugged 3U VPX Module.   Built on NVIDIA Ampere architecture this GPU includes: CUDA Cores for parallel processing, Tensor Cores for AI accelerated compute and Ray Tracing Cores for high rendering speeds.  As well as a configurable PCIe Gen4 switch.

With its impressive processing power, it is the perfect choice for rugged Aerospace and Defence Applications covering High Performance tasks.

The WOLF Model VPX3U-A4500-VO is a 3U VPX GPGPU Processing Module.  Firstly, since it is based on the NVIDIA Ampere architecture, many improvements to the performance and efficiency of the GPU have occurred.  Such as a flexible CUDA FP32/INT core use, more efficient Tensor Cores and 2nd gen. RT Cores.

Secondly, due to an improvement in the manufacturing process of the GPU, there have been significant power improvements.  Leading to 154GFLOPS/W, which is twice the performance per slot compared to previous generations.

Finally, WOLF implemented it’s advanced cooling technology on this module.  Moving heat using a low weight, high efficiency path from the SoC die to the wedgelocks.

Features of the 3U VPX GPGPU Processing Module VPX3U-A4500E-VO include:

  • NVIDIA RTX™ GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores, 4 DP outputs
  • 16 GB GDDR6 256-bit memory with up to 512 GB/s
  • PCIe x16 Gen4 with a configurable PCIe switch
  • Module power: TBD-180W, configurable
  • *Peak performance requires the highest power configuration mode.
  • Four simultaneous DisplayPort 1.4 outputs:
  • 4K at 120Hz or 8K at 60Hz with 10-bit colour depth
  • Support for High Dynamic Range (HDR) video
  • HDMI and DVI options
  • Ampere GPGPU parallel processing:
  • CUDA Toolkit 11, CUDA Compute capability 8.6
  • OpenCL™ 3.0, DirectX® 12 Ultimate, OpenGL 4.6, OpenGL ES 3.2, Vulkan™ 1.2
  • 184 Tensor Cores (3rd Gen), 68 (dense) / 136 (sparse) Tensor TFLOPS
  • 46 Ray Tracing cores (2nd Gen)
  • Error Correcting Code (ECC) memory
  • NVENC (7th Gen) and NVDEC (5th Gen) with up to 8K video encoding and hardware decoding support


Therefore, for more information, contact us.


There are no reviews yet.

Only logged in customers who have purchased this product may leave a review.