MathWorks MATLAB with NVIDIA TensorRT integration

Wednesday, 04 April, 2018 | Supplied by: MathWorks Australia


MathWorks has announced that MATLAB now offers NVIDIA TensorRT integration through GPU Coder. This helps engineers and scientists develop AI and deep learning models in MATLAB with the performance and efficiency needed to meet the growing demands of data centres, as well as embedded and automotive applications.

MATLAB provides a complete workflow to rapidly train, validate and deploy deep learning models. Engineers can use GPU resources without additional programming so they can focus on their applications rather than performance tuning.

The integration of NVIDIA TensorRT with GPU Coder enables deep learning models developed in MATLAB to run on NVIDIA GPUs with high throughput and low latency. MathWorks’ internal benchmarks show that MATLAB-generated CUDA code combined with TensorRT can deploy Alexnet with 5x better performance than TensorFlow and can deploy VGG-16 with 1.25x better performance than TensorFlow for deep learning inference.

Online: au.mathworks.com
Phone: 02 8669 4700
Related Products

STMicroelectronics ST60A3H0 transceiver IC

The STMicroelectronics ST60A3H0 transceiver IC is designed to remove the need for cables and...

SCHURTER MSM II metal line indicator

The SCHURTER MSM II metal line indicator is available in a range of illumination variants: point,...

Vishay EFUSE-48V100A eFuse reference design

The Vishay EFUSE-48V100A eFuse reference design features TrenchFET MOSFETs and is designed to...


  • All content Copyright © 2024 Westwick-Farrow Pty Ltd