Improving AI performance with hardware acceleration

Hardware Acceleration - boosting AI performance with GPUs (NVIDIA, MALI), ARM Neon, and other accelerators
Algorithm Implementation - optimising computer vision and AI algorithms using compute APIs such as OpenCL, CUDA, ArmNN
Edge AI Solutions - AI application design for System-on-Chip (SoC) and Microcontroller Unit (MCU) based devices: ST Microelectronics, NXP and NVIDIA-powered edge computing
Computer Vision - seamless integration of computer vision algorithms for industry-specific applications
AI-Enhanced Performance - leveraging cutting-edge hardware accelerators to enhance processing speed and efficiency
Customizable Solutions - tailored AI and hardware acceleration strategies for unique semiconductor challenges

Let’s meet

If you wish to discuss potential cooperation please leave your email address and we will get back to you with a meeting set up at your convenience.

Digica Solutions would like to keep you up-to-date with information on Digica services. For information on how we will use your data, international transfers of data and your rights, please see Full Privacy Policy details.

Project descriptions

LiDAR point cloud processing algorithms

LiDAR data is critical in sensor fusion algorithms for autonomous driving. Algorithms operating on LiDAR point clouds are a crucial part of the processing performed by the vehicle's on-board computer. Parallelization and optimization of these algorithms in order to meet latency requirements are of prime importance for real-time systems.

Our objectives in this project were the implementation of point cloud pre-processing “kernels” running on Imagination’s GPU platform using OpenCL, comparison against a reference CUDA implementation, visualisation of the processed point cloud and optimisation and testing on the target hardware platform.

Edge AI supports people with impaired vision

Support of people with impaired vision by detecting nearby obstructions has been achieved by applying computer vision with a depth camera integrated into a walking stick.

Our AI-based object detection system recognises surfaces and moving objects based on proximity and the potential hazard and communicates this using a haptic controller and a Bluetooth earpiece.

The first prototype implementation is being trialled with Blackworld, a blind and partially sighted organisation in Poland.

Edge AI supports people with impaired vision

Edge AI supports people with impaired vision 1

Edge AI supports people with impaired vision 2

Knowledge Distillation KD for image reconstruction

Knowledge Distillation (KD) for image reconstruction

Ray tracing is computationally intensive: ML techniques can be used to improve performance significantly. Our SoC customer’s initial implementation operated on an entire HD image. Division into tiles, which can be processed in parallel, improves performance on existing hardware, allowing lower quality ray tracing images to be enhanced using neural networks.

Identifying structural defects in silicon production

A leading producer of medical imaging silicon wanted to reduce the number of defective wafers reaching the assembly stage.

Our objectives were to reduce the volume of faulty silicon assembled into equipment and reaching end customers by predicting which regions were defective after manufacture. The model pipeline was deployed into the client’s production process.

Identifying structural defects in silicon production

Identifying structural defects in silicon production 1

Identifying structural defects in silicon production 2

Implementation of image processing algorithms

Implementation of image processing algorithms

A leading producer of computer vision systems was looking into the possibility of porting their image processing software on to a new heavily parallelized processor architecture. This could offer a more configurable alternative to their existing FPGA implementation, without compromising performance; ultimately this provides a more open, customisable solution for their end-customers.

Improving AI performance with hardware acceleration

Let’s meet

Project descriptions

LiDAR point cloud processing algorithms

Edge AI supports people with impaired vision

Knowledge Distillation (KD) for image reconstruction

Identifying structural defects in silicon production

Implementation of image processing algorithms

How we work

LET'S GET STARTED!

We divide the inclusion of AI into our client’s system into a series of features which are comprised as follows:

Unlock the full potential of AI through Semiconductor hardware acceleration