RADX Technologies, a high-tech small business that develops COTS, High Performance Computing (HPC) hardware and software products, has introduced the Catalyst-GPU™ Family of COTS, low-cost, PXIe/CPCIe GPU Modules at the IEEE AUTOTESTON 2022. Catalyst-GPUs are the first COTS products that bring the cost-effective, easy-to-program, high-performance compute acceleration and advanced graphics capabilities of NVIDIA® Quadro® T600 and T1000 GPUs to the PXIe/CPCIe platform - the fastest growing platform for Modular Test & Measurement (T&M) and Electronic Warfare (EW) applications.
Based on RADX’ patent-pending Catalyst-X™ design, Catalyst-GPU models available today include NVIDIA Quadro T600 and T1000 GPUs; and RADX plans to offer tech insertion options in the future, based on COTS GPU availability. Catalyst-GPUs support PCIe Gen 3 x 8 interfaces for optimal performance and 4 x miniDP outputs for multi-monitor applications with resolutions up to 4k. The Catalyst-GPU T600 supports 4GB of GDDR6 memory, up to 1.7 FP32 TFLOPs and a Total Graphics Power (TGP) of 38 W – suitable for operation in all NI and 3rd-party PXIe chassis. The Catalyst-GPU T1000 supports 8GB of GDDR6 memory, up to 2.5 FP32 TFLOPs and a TGP of 50W, which is optimized for deployment in NI PXIe-1092 and NI PXIe-1095 Chassis, both of which support 58 W/Slot or 82 W/Slot and PCIe G3 x8 interfaces, which are ideal for optimum GPU performance.
With comprehensive support for MATLAB™, Python, and C/C++, combined with support for virtually all popular computing frameworks, Catalyst-GPUs are easy-to-program for both Windows and Linux operating environments. Catalyst-GPUs feature multi-teraflop (TFLOP) level performance, which is ideal for accelerating signal processing applications. In addition, Catalyst-GPUs are ideal for Machine Learning (ML) and Deep Learning (DL) applications, which are becoming increasingly important for AI-based signal classification and geolocation, semiconductor and PCB testing, failure prediction, failure analysis, and other important missions.
Industry Leading Performance - Where data is acquired
The Catalyst-GPU T1000 model supports up to 2.5 FP32 TFLOPs. Until now, this level of compute acceleration has not been available in PXIe/CPCIe systems. With Catalyst-GPUs, users can now conduct fast and accurate analysis of acquired data directly in the PXIe/CPCIe systems where the data is acquired.
For example, in an NI PXIe-1092 Chassis with an NI PXIe-8881 Embedded Controller (Intel Xeon W-2245 8C/16T 3.9 GHz), running Windows 10 and MATLAB, the Catalyst-GPU T1000 delivers an average performance gain of 7.1x over the Embedded Controller on FP32 Fast Fourier Transforms (FFTs) ranging from 1k to 32M samples in length. Under Python, the Catalyst-GPU T1000 delivers an average performance gain of 19.2x.
On ML and DL AI Applications, the performance gains achievable by Catalyst-GPUs are also quite substantial. On the MATLAB FP32 Deep Learning Inference Benchmarks, the Catalyst-GPU T1000 delivers an average 18.4x performance gain over an Intel Xeon W-2245 8C/16T 3.9 GHz PXIe Embedded Controller.
“A key use case for Catalyst-GPUs is accelerating MATLAB applications in a convenient and cost-effective manner,” said Ross Q. Smith, RADX Co-founder and CEO. “MATLAB is extremely popular with T&M and EW R&D users and MATLAB’s intrinsic support for NVIDIA GPU acceleration means users can now speed up their signal processing and AI applications directly in their PXIe/CPCIe data acquisition systems - without having to transport gigabytes or terabytes of sensitive data to other analysis systems via ethernet or sneakernet, and without having to spend months porting their applications to other platforms.”
Improved Accuracy and Real-Time Bandwidth for Enhanced LPI Signal Processing
For signal processing applications, Catalyst-GPU supports arbitrary length FFT, PSD, Correlation, and other DSP algorithms. This capability enables accuracy and Resolution Bandwidths (RBWs) that are not practicable in non-GPU based systems. For example, in most FPGAs, the longest practical lengths for FFTs are typically 8k points (samples). However, in Catalyst-GPUs, 1M point and longer FFTs are practical, and, because of the GPU’s TFLOP performance capabilities, 1M FFTs may be executed in real-time or near-real-time, depending on the application. With longer FFTs, a signal’s true spectral composition becomes more apparent and actionable, and Low Probability of Intercept (LPI) signals can be easily detected and characterized.
Easy-to-Program via MATLAB, Python and C/C++
One of the most important aspects of Catalyst-GPUs is their ease-of-programming, which stems from their underlying NVIDIA GPUs that support programming via MATLAB™, Python and C/C++, which enables compute acceleration available via NVIDIA CUDA® and OpenCL®. This ease-of-programming has resulted in NVIDIA GPUs becoming the most popular compute accelerators in the world today - with literally millions of engineers, application developers and computer scientists using NVIDIA GPUs to accelerate their applications. Catalyst-GPUs support both Windows and Linux operating environments. In addition, Catalyst-GPUs support popular AI and other frameworks, including MATLAB™, TensorFlow, PyTorch, RAPIDS AI and RAPIDS cuSignal, to name a few.
“NI LabVIEW has efficient methods for calling Python, C/C++ and MATLAB libraries, including RADX’ own Transform-DSP libraries. This makes adding Catalyst-GPU acceleration to LabVIEW-based PXIe applications a snap,” said Matt Dennie, Director of Engineering and Certified LabVIEW Architect at Acquired Data Solutions (ADS). “Using this approach, we were able to greatly improve the performance and accuracy of one of our LabVIEW signal processing apps in days, versus the weeks or months it would take with other methods.”
Pricing and Availability
Catalyst-GPU T600 and T1000 models have list prices of $2,999 and $3,499, respectively. Lead time for single unit orders is typically 30 days, starting in Q422. Catalyst-GPUs are BAA and TAA Compliant, manufactured in the USA, and are available on GSA via TestMart.
Click here to learn more about the Catalyst-GPU models.
Click here to view the pricing and availability of these modules.