GigaMACS™ Technology
The Only Solution with High Speed, Near-Zero Latency, Real-time Performance
GigaMACS™ ResNet-34 Results
Compare GigaMACS™ real-time ResNet34 results to nVidia’s self-reported data. Real-time high-speed frames in high resolutions are not a problem for models using GigaMACS™!
We compared GigaMACS™ to nVidia’a V100 and A100 GPUs
The goal is to accept live HD images at 240 FPS and identify all the objects in real-time.
The Demo Videos
GigaMACS™ Demo on Xilinx VU9P FPGA
- Constant performance
- Near-zero Latency
- Accepts & Processes 240 FPS
- No Dropped Frames
nVidia’s Tesla V100 and A100 demo
- Erratic Performance
- High Latency
- Dropped over 212 FPS
- Lost 88% to 90% of Data
Clock Speeds
GigaMACS™ hardware runs significantly slower and cooler while generating higher FPS with near-zero latency. All the nVidia hardware boards are running over a billion cycles to achieve fewer frames per second. GigaMACS™ runs at a sedate 125 MHz, yet still outperforms GPUs running over 1 GHz using 10 times the power and heat.
Stop sacrificing model size, speed, and performance. Design larger and more complex models using GigaMACS™.
Request More Information