PXIe-GPU Compute & Graphics
Trifecta-GPU
PXI GPU | PXIe GPU | CPCI GPU | CPCIe GPU: NVIDIA RTX A2000
The Trifecta-GPU™ Family of COTS PXIe/CPCIe GPU Modules are the first COTS products that bring the extreme compute acceleration and ease-of-programming of NVIDIA RTX A2000 Embedded GPUs to PXIe/CPCIe platforms for modular Test & Measurement (T&M) and Electronic Warfare (EW) applications.
Extreme Compute Performance for PXIe
With peak performance of 8.3 FP32 TFLOPS, the Trifecta A2000 GPU delivers compute acceleration that is almost 5x that of the Catalyst T600 GPU and over 20x that of a Xilinx Kintex Ultrascale KU060 FPGA. With Trifecta PXIe-GPUs, users can now conduct fast and accurate signal analysis and machine and deep learning on acquired data, directly in the PXIe/CPCIe systems where the data is acquired.
PXIe Compute Accelerator Peak Performance Comparison
Mfg. Published FP32 GFLOPS, Q4'22 MSRPs
Flexible and Scalable: Single and Dual-Slot Configurations
Many PXIe and CPCIe chassis are limited to 38W/Slot for input power and thermal dissipation. To address this, Trifecta-GPUs are available in both single and dual-slot configurations. Dual-slot configurations (29W/Slot TGP) are suitable for all NI and 3rd-party PXIe chassis. Single-slot configurations are ideal for NI PXIe-1092 or PXIe-1095 chassis, which support 58W/Slot or 82W/Slot.
Best-in-Class Price/Performance
With peak FP32 performance of 8.3 TFLOPS and a list price of $6,999, the Trifecta-A2000 delivers almost 2 orders of magnitude better price performance than the most popular PXIe FPGA module. Trifecta-GPUs also support arbitrary length FFTs and other signal processing primitives to provide unmatched signal resolution for Low Probability of Intercept (LPI) signal detection.
PXIe Compute Accelerator Value Comparison
(FP32 GFLOPS / $k MSRP)
Mfg. Published FP32 GFLOPS, Q4'22 MSRPs
Easy-to-Program via MATLAB, Python, C/C++ and LabVIEW
Trifecta-GPUs support programming via MATLAB™, Python, C/C++, and LabVIEW™ with NVIDIA CUDA and OpenCL acceleration. They support both Windows and Linux operating environments, as well as popular AI frameworks including TensorFlow, PyTorch, RAPIDS AI, and RAPIDS cuSignal.
Supported Software Frameworks & Programming Environments
About Trifecta-GPUs
Trifecta-GPU models are based on the NVIDIA Embedded RTX A2000 GPU. They support PCIe Gen 4 x8 interfaces for optimal, future-proof performance and 4× miniDP outputs for multi-monitor applications with resolutions up to 4K. The A2000 GPU supports 8 GB GDDR6 memory, up to 8.3 FP32 TFLOPs, and a Total Graphics Power (TGP) of 58W.
- Trifecta A2000 Single-Slot and Dual-Slot GPUs have list prices of $6,999 and $7,499, respectively. Lead time for single units is typically 30 days. BAA & TAA Compliant and available on GSA via GSAMart by TestMart.
Compliance & Standards
Ready to learn more?
Contact RADX sales or download the datasheet for full specifications.