- Featured Products
- Request a Quote
- Product Support
The VPX3-4935 3U VPX GPU processor card delivers incredible processing power from its NVIDIA Quadro Turing TU104 GPU, providing an impressive 3072 CUDA cores for parallel processing and a 50% improvement in performance per CUDA core compared to the previous Pascal generation. The VPX3-4935 is one of a family of GPU modules available from Curtiss-Wright to enable the development of High-Performance Embedded Computing (HPEC) systems. What’s more, the Turing architecture’s Tensor Cores accelerate the tensor/matrix computation used for deep learning neural network training and inference operations, answering the growing demand for artificial intelligence and high-performance processing in deployed EW and ISR applications.
- Aligned with SOSA™ Technical Standard
- Cutting-edge Turing GPU architecture
- Support for artificial intelligence and machine learning
- Lightning-speed data processing
Bring new levels of performance to your ISR and EW applications with the VPX3-4935:
Aligned with the SOSA™ Technical Standard
Designed to eliminate interoperability challenges between COTS modules, the VPX3-4935 offers a variant developed in alignment with The Open Group Sensor Open Systems Architecture™ (SOSA) Technical Standard.
Cutting-edge Turing GPU architecture
The NVIDIA Turing architecture provides a 50% improvement in performance per CUDA core compared to the previous Pascal generation. Its redesigned memory path combines shared memory, texture caching, and memory load caching into one unit, resulting in twice the bandwidth and over twice the capacity for L1 cache and common workloads than the previous Pascal generation.
Support for artificial intelligence and machine learning
The VPX3-4935’s TU104 GPU features 384 Tensor Cores, designed to speed up the tensor/matrix computation used for deep learning neural network training, for dedicated AI inference.
Lightning-speed data processing
Moving data quickly and efficiently is paramount for high-speed GPUs. The VPX3-4935 uses GDDR6 memory, which provides twice the bandwidth of the GDDR5 memory used in previous generations. Incorporating a PCIe switch, this module is configurable for compatibility with various OpenVPX slot profiles.
- Variant developed in alignment with the SOSA Technical Standard available
- NVIDIA Quadro Turing TU104 (RTX5000E) with 11.2 TFLOPS & 11.2 TIPS
- 3072 CUDA Cores, 384 Tensor Cores, 48 RT Cores
- 16 GB GDDR6 256-bit memory
- Max memory bandwidth: 448 GB/s
- PCIe Gen 3 x16 switch
- Operating power configurable hard cap: 50-150W
- 4 simultaneous video outputs
- 3 Display Port ++
- 1 DVI
- ISR and EW applications that require the highest performing GPU processing
- SWaP-constrained deep learning inference that can benefit from the largest number of Tensor Cores in 3U
- High-performance radar, SIGINT, EO/IR, sensor fusion, processing and display, and autonomous vehicles