RidgeRun NVIDIA PVA Development Algorithms
PVA Algorithms from LibPVA
RidgeRun has implemented the following image processing algorithms on the PVA. These are foundational for image signal processing (ISP) pipelines and optimized for high efficiency.
All the measurements were taken using the following characteristics:
- Platform: Jetson AGX Orin 32GB
- OS: Jetpack 6.2
- Power Profile: MAXN power mode + Jetson Clocks
- CPU: All measurements use aggressive compiler optimization flags and OpenMP. Introducing NEON might halve the execution times.
- PVA: all measurements use a single VPS (half of the PVA)
- Power Measurements: using jetson-stats (a tool based on tegrastats) with a VDD_CPU_CV power meter probe.
The profiling details are:
- Execution time CPU (ms): using dual ARM core execution
- Execution time PVA (ms): using dual VPU PVA execution
- Power Consumption CPU only (W): using a number of cores such that the execution time of the CPU is nearly the same as the PVA.
- Power Consumption PVA only (W): using dual VPU PVA execution
Bit Shifting (Debayering Resolution Downscaling)
This technique allows for resolution reduction through controlled bit manipulation during debayering. It’s useful in optimizing bandwidth or matching downstream resolution requirements.
Average performance measurements are shown in the following table for the most common resolutions. Measurements are shown for an optimized implementation of the algorithm, and all results are in milliseconds. Additionally, power consumption measurements are shown in watts. A shift of 10 bits was used for the benchmarks. Performance measurements can also be observed in the attached graph.
| Resolution | Execution time CPU (ms) | Execution time PVA (ms) | Power consumption CPU only (W) | Power consumption PVA (W) |
|---|---|---|---|---|
| 1280x720 | 0.309 | 0.04865 | 8.75 | 3.21 |
| 1920x1080 | 0.675 | 0.10678 | 9.14 | 3.27 |
| 3840x2160 | 2.51 | 0.4061 | 9.54 | 3.24 |
This downscales a single-channel image from 16-bit to 8-bit. To match the latency of the PVA, it is required to use six ARM cores.
Radial Lens Shading Correction
Corrects vignetting or intensity falloff from the center to the edges of an image caused by lens characteristics. It’s implemented using radial correction maps that are efficiently processed on the PVA.
Average performance measurements are shown in the following table for the most common resolutions. Measurements are shown for an optimized implementation of the algorithm, and all results are in milliseconds. Additionally, power consumption measurements are shown in watts. Performance measurements can also be observed in the attached graph.
| Resolution | Execution time CPU (ms) | Execution time PVA (ms) | Power consumption CPU only (W) | Power consumption CPU and PVA (W) |
|---|---|---|---|---|
| 1280x720 | 1.56 | 0.145 | 8.4 | 3.69 |
| 1920x1080 | 3.5 | 0.330 | 7.6 | 3.61 |
| 3840x2160 | 13.8 | 1.402 | 7.2 | 3.57 |
The measurements were done with:
- 8-bit Fixed-point correction maps (including channels)
- RGB images (RGB24) - 8-bit per channel
- ARM CPU requires four ARM cores to match the PVA latency.
Colour Space Conversion (RGBA-Gray)
Transforms image data from one color space to another (e.g., RGB to YUV). It’s essential for encoding, display pipelines, and transmission where non-RGB formats are used.
These implementations showcase how RidgeRun leverages the PVA to create real-time, power-efficient vision pipelines suitable for embedded systems under tight performance constraints.
Average performance measurements are shown in the following table for the most common resolutions. Measurements are shown for an optimized version of the algorithm, and all results are in milliseconds. Additionally, power consumption measurements are shown in watts. In the example measurements, an RGBA to Grayscale conversion was performed. Performance measurements can also be observed in the attached graph.
| Resolution | Execution time CPU (ms) | Execution time PVA (ms) | Power consumption CPU only (W) | Power consumption PVA (W) |
|---|---|---|---|---|
| 1280x720 | 1.36 | 0.085 | 10.35 | 3.97 |
| 1920x1080 | 3.05 | 0.195 | 10.74 | 3.84 |
| 3840x2160 | 12.1 | 0.746 | 10.74 | 3.61 |
The images involved:
- Input: RGBA32 (8-bit per channel, four channels)
- Output: Gray8 (8-bit single channel)
- The CPU requires six cores to match the PVA's latency.
2D Filtering (Convolution)
Applies a 2D filter using a 5x5 kernel, it can be used for general image filtering as well as showcasing general 2D convolution performance.
Average performance measurements are shown in the following table for the most common resolutions. Measurements are shown for an optimized version of the algorithm, and all results are in milliseconds. Additionally, better performance can be achieved with further optimization as shown in NVIDIA's PVA Solutions implementation of the convolution. Performance measurements can also be observed in the attached graph.
| Resolution | Execution time CPU (ms) | Execution time PVA (ms) | Power consumption CPU only (W) | Power consumption PVA (W) |
|---|---|---|---|---|
| 1280x720 | 52.445 | 1.237 | TBD | TBD |
| 1920x1080 | 115.724 | 2.528 | TBD | TBD |
| 3840x2160 | 456.973 | 9.975 | TBD | TBD |
The images involved:
- Input: Gray8 (8-bit single channel)
- Output: Gray8 (8-bit single channel)
Final Remarks
From the energy perspective, it is possible to notice that the power consumption may increase. Nevertheless, since the PVA is faster in most cases, the energy consumption and the execution time are lower overall.
The power consumption has been acquired at the entire platform level using the jetson-stats Python library.