At TechnoLynx, we specialise in developing custom GPU software and optimising AI models for IoT devices, including virtual assistants, edge devices, and industrial IoT applications. For instance, we leverage NVIDIA Jetson and Tesla T4 GPUs with CUDA, Arc and HD GPUs from our partner Intel with OpenCL and Apple devices via CoreML. Additionally, we collaborate with AWS Greengrass to run on edge servers, targeting GPUs available on EC2 instances in containerised environments.
But what exactly is edge computing? It's a novel approach to computing that brings data processing closer to where it's needed, benefiting from AI technology and machine learning. By processing data closer to where it's generated, edge computing can deliver quicker and more accurate results, which is particularly advantageous for real-time applications and IoT sensors.
For those curious about why edge computing matters, consider this: it can accelerate your software by up to an order of magnitude using GPUs. We accomplish this by developing custom GPU software and optimising AI models’ inference time, leveraging AI accelerators like NVIDIA Tensor Cores via TensorRT or Scalable Intel Xeon processors via Intel DL Boost. Our techniques include pruning, quantisation, and mixed precision, allowing for higher performance while using less memory and power.

Our IoT edge computing solutions have many applications, from accelerating classical computer vision algorithms to improving image processing on IoT devices. We've achieved significant performance improvements for our clients in various sectors, harnessing the benefits of edge computing for smarter retail, Industry 4.0, healthcare, and smart cities.
However, edge computing is just one aspect of AI technology. There are various types of artificial intelligence, each with its own strengths and weaknesses. The Turing Test, for example, evaluates a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human. Furthermore, computing is a distributed endeavour, especially in edge computing scenarios where processing happens closer to the data source. This distributed nature allows for efficient utilisation of training data, which is crucial given the massive amounts of data generated in IoT applications. While edge computing offers localised processing power, cloud computing provides scalable resources for handling large-scale data processing tasks. Together, these technologies form a robust ecosystem for AI-driven applications in various industries.
At our consultancy, we are committed to staying up to date with the latest developments in IoT Edge computing. Our team includes AWS-certified engineers who are experts in working with GPUs in containerised environments like AWS Greengrass.
If you are interested in learning more about how we can help accelerate your IoT software, please don't hesitate to contact us!

Our Founder’s passion for GPUs and accelerated computing

Our Founder, Balázs Keszthelyi, started his career as a real-time graphics programmer and has retained his enthusiasm for GPUs ever since. Having worked on multiple complex GPU projects like SPH fluid simulation, AES acceleration, and path tracing, he ended up helping Broadcom in Cambridge develop their own GPU IP, the VideoCore V, which is now in use in Raspberry PI. During that tenure, he represented Broadcom at the Khronos standard body on matters concerning OpenCL and became named contributor to the SYCL standard. He later leads his V-Nova team to the delivery of the first GPU-compute-friendly video codec, now known as the SMPTE ST 2117-1 VC-6 standard.

Smart Retail

In smart retail, our camera systems expertise enables us to track buyer behaviour, analyse actions, and monitor share-of-shelf, enhancing the overall retail experience.

Industry 4.0

In Industry 4.0, our solutions aim to reduce downtime, minimise maintenance costs, and improve productivity by leveraging predictive maintenance analysis, power outage prediction, defect detection, and robotics.

Healthcare

In healthcare, we utilise our experience with CT scans, MRI, fNIRS processing, and biosignal analytics to create tailored solutions that improve patient outcomes and enhance the healthcare experience, demonstrating the potential benefits of edge computing in the healthcare sector.

Smart Cities

In smart cities, we focus on developing innovative solutions to optimise processes, reduce costs, and improve efficiency, such as optimising public transport, traffic lights, and real-time tracking, showcasing the versatility and benefits of edge computing in urban environments.