Technology Collaboration
GPU-Accelerated Computing for PXIe Systems.
RADX Technologies and G²CPU are collaborating to bring high-performance GPU computing, real-time signal processing, and high-speed data movement to PXIe-based test and measurement systems — all within the NI LabVIEW ecosystem, using COTS products available today.
Combine RADX PXIe-GPU, PXIe-SSD, and PXIe-GbE hardware with G²CPU's GPU acceleration toolkit to build powerful, software-defined applications without the complexity traditionally associated with GPU programming.
Better Together: High-Performance Hardware and Software
Today's demanding test and measurement applications require more than high-speed data acquisition. Engineers must also process, analyze, store, and distribute enormous volumes of data in real time.
RADX and G²CPU address these challenges by combining high-performance, commercially available PXIe hardware with advanced GPU acceleration software that integrates directly into the NI LabVIEW environment.
The result is a powerful foundation for next-generation signal processing, automated test, RF analysis, and AI-enabled measurement systems.
RADX Technologies: The Hardware Foundation
RADX develops high-performance COTS PXIe modules that bring advanced computing, storage, and networking capabilities directly into modular test systems.
- Catalyst PXIe-GPU modules featuring NVIDIA-based GPU acceleration
- Venturi and Trifecta PXIe-SSD solutions for high-speed recording and storage
- Catalyst PXIe-GbE modules for high-bandwidth networking and RDMA
- Orca-C2X expansion technology for additional PCIe computing capabilities
The GPU Toolkit for LabVIEW
GPU acceleration, native to LabVIEW and the NI ecosystem. Your code, your LabVIEW, now at GPU speed.
Batch your operations, saturate your GPU, and do over a billion FFTs per second. Any N-dimensional operation batches across any array of N dimensions or more.
Zero-copy streaming from instrument to GPU to disk at full PCIe bandwidth. Asynchronous I/O for raw throughput, low-latency synchronous I/O where determinism matters.
GPU-accelerated compression built for test and measurement data. Compress inside the pipeline so your storage and network carry more of what you actually captured.
LabVIEW probes work on data that lives on the GPU, on any device, from any vendor. Because debugging shouldn't stop where acceleration starts.
Share a live GPU buffer with any CUDA-capable environment through standard CUDA IPC. Prototype and train in Python, deploy in LabVIEW — data stays exactly where it is.
Decide at runtime whether code executes on CPU, CUDA, OpenCL, or Intel oneAPI. No recompiling, no retooling. Multiple GPUs, mixed vendors, same application.
From Acquisition to Analysis: A Complete PXIe Computing Workflow
Together, RADX and G²CPU enable high-bandwidth data acquisition, GPU-accelerated processing, and high-speed storage within a unified PXIe environment.
Acquire
Capture high-bandwidth measurement data from PXIe instruments and RF acquisition systems.
Process
Move data efficiently to RADX GPU hardware using G²CPU zero-copy technology for accelerated signal processing.
Analyze
Execute advanced DSP, FFT, AI, and other computationally intensive operations through LabVIEW and compatible frameworks.
Store & Stream
Record and transfer large data volumes using RADX high-speed PXIe-SSD storage and GbE networking hardware.
Real-Time Performance in Action
Ultra-Wideband RF Recording, Playback, and GPU-Accelerated Analysis
The G²CPU RTSA demonstration showcases an integrated real-time spectrum analysis workflow combining RADX PXIe GPU and SSD hardware with G²CPU's software for wideband acquisition, GPU-based signal analysis, and high-speed recording.
Specifications below reflect commercially available RADX product capabilities and published G²CPU demonstration results. Individual system performance depends on configuration.
Designed for Demanding Computing and Measurement Applications
GPU Acceleration in LabVIEW
Bring GPU-based parallel computing directly into familiar LabVIEW development environments — without writing a line of CUDA.
Real-Time Signal Processing
Accelerate computationally intensive DSP operations for demanding measurement and analysis workloads with up to 250× performance gains.
High-Bandwidth Data Movement
Zero-copy streaming from instrument to GPU to disk at full PCIe bandwidth. Asynchronous I/O for raw throughput, synchronous where determinism matters.
High-Speed Data Recording
Capture and store large volumes of measurement data using RADX high-capacity NVMe PXIe-SSD solutions at up to 7.1 GB/s.
AI and Advanced Analytics
Share live GPU buffers with Python, MATLAB, PyTorch, TensorFlow, and other AI frameworks via standard CUDA IPC — prototype and deploy in LabVIEW.
COTS-Based System Integration
Build high-performance PXIe solutions using commercially available RADX hardware and G²CPU software — orderable today with ~45-day lead times.
Enabling the Next Generation of Test and Measurement
RF and Spectrum Analysis
High-throughput processing of wideband RF signals for spectrum monitoring and signal characterization.
Aerospace and Defense
GPU-accelerated processing and high-speed recording for demanding aerospace, defense, and electronic warfare applications.
Automated Test and Measurement
Accelerated measurement processing for complex automated testing and validation workflows.
Software-Defined Radio
Advanced signal processing and high-throughput data handling for software-defined radio applications.
AI-Enabled Signal Analysis
GPU computing resources for machine learning, classification, and other AI-assisted analysis workflows.
High-Speed Data Acquisition
Efficient acquisition, processing, recording, and playback of large measurement datasets.
A Powerful Combination for PXIe System Developers
Accelerated Development
Leverage familiar LabVIEW workflows and commercially available PXIe hardware to simplify development of GPU-enabled applications.
Reduced Integration Complexity
Bring compute, data storage, and networking capabilities into a unified PXIe-based system architecture using COTS products.
Exceptional Computing Performance
Apply GPU acceleration and massively parallel processing — including 1M+ point FFT and 100×–500× performance gains — to computationally demanding applications.
Flexible, Scalable Architecture
Configure solutions using appropriate hardware, software, and processing resources to meet different application requirements and budgets.
Accelerate Your Next PXIe Application
Discover how RADX high-performance PXIe hardware and G²CPU's GPU acceleration technologies can help address your most demanding real-time processing, data acquisition, and test and measurement challenges.
Whether you're developing advanced RF systems, accelerating existing LabVIEW applications, or integrating high-performance computing into your PXIe architecture, RADX can help you explore the right hardware foundation.
Related RADX Products