- NVIDIA RTX GA107, 2560 CUDA cores, 80 Tensor cores, 20 RT cores
- Up to 4x SDI inputs and outputs
- Up to 2x CVBS/RGB inputs + audio inputs
- Up to 2x DP/HDMI/DVI outputs
- Configurable operating power, 25W to 90W
Overview
This versatile module includes both an advanced NVIDIA Ampere architecture GPU and WOLF’s Frame Grabber eXtreme (FGX2). This board accepts multiple simultaneous inputs, including SDI, CVBS, RGsB, and stereo audio. The captured inputs can be routed to the high-performance NVIDIA RTX™ A2000 for processing and be output in several formats, including SDI, DisplayPort, HDMI, and others on request.
The NVIDIA Ampere architecture has introduced many significant improvements to the performance and efficiency of the GPU, with more flexible CUDA FP32/INT core use, more efficient third generation Tensor cores, and second generation RT cores. The Ampere GPU fabrication uses an 8nm manufacturing processing providing significant power improvements which, along with other Ampere architecture improvements, can provide up to 144 GFLOPS/W, providing almost three times the performance per slot compared to the Pascal generation’s 51 GFLOPS/W.
The WOLF Frame Grabber eXtreme (FGX2) provides the board with data conversion from one standard to another, with a wide array of video input and output options for both cutting-edge digital I/O and legacy analog I/O. The FGX2 supports NVIDIA GPUDirect which allows direct access to the GPU memory for processing and analysis.
WOLF’s advanced cooling technology is designed to move heat using a low weight, high efficiency path to move heat away from the GPU.
Additional Features
- DisplayPort 1.4 digital video outputs
- support for High Dynamic Range (HDR) video
- 4K at 120Hz/5K at 60Hz, with 10-bit color depth
- Flexible WOLF IP – other display interfaces available upon request, such as ARINC-818, CoaxPress, STANAG 3350
- WOLF FGX2 supports NVIDIA GPUDirect, providing an efficient CPU offload
- Ampere GPGPU parallel processing support:
- CUDA Toolkit 11, CUDA Compute capability 8.6
- OpenCL™ 3.0, DirectX® 12 Ultimate, OpenGL 4.6, OpenGL ES 3.2, Vulkan™ 1.2
- 80 Tensor Cores (3rd Gen), 34/66 TOPS
- 20 Ray Tracing cores (2nd Gen)
- NVENC (7th Gen) and NVDEC (5th Gen) with up to 8K video encoding and hardware decoding support
- 8 GB GDDR6 memory, 128 Bit, 192 GB/s max
Connectivity/System Management
- PCIe switch with x8 to the XMC connector
- PCIe Gen3 support requires min. TBP of 35W
- Linux and Windows drivers are available
Mechanical/Architecture
- Designed for Harsh Environments:
- Rugged conduction cooled or air cooled
- Operating temperature: conduction cooled -40° to +85°C, air cooled -40° to +71°C
- Vibration (sine wave): 10G peak, 5 - 2000Hz
- Shock: 40G peak conduction cooled, 30G peak air cooled
- Dimensions: TBD
- Weight (approximately): TBD
- VITA 46.9 I/O mapping for VPX rear I/O
Datasheet
Open the product datasheet - includes block diagram, order codes, etc.
