AIScale Deep Learning Processor

AI deployment made easy

With our AIScale Deep Learning Processor Engine we are committed to provide our clients and partners universal, easy-to-use, efficient, scalable, flexible and lowest power FPGA and SoC based machine learning inference platforms. Our AIScale Deep Learning Processor with it´s unique architecture in combination with our DeepCompressor and our All-Zero-Skipping technology serves clients in the fields of computer vision, robotics, speech recognition, surveillance systems.

Kortiq's All-Zero-Skipping technology, a novel, unmatched way of network pruning and highly advanced compression methods offer a significant reduction in required external memory transfer size and power. Skipping unnecessary calculations enables unprecedented compute power. In combination with our novel way of mapping calculations to hardware resources and our easy-to-use tool package we enable our clients in the above industries to achieve fast turnaround from idea to product, with having an efficient and economic solution in mind.

The AIScale Processor with it´s radically new architecture provides magnitude higher processing power for edge devices over existing solutions with the further advantage of ease-of-use and easy integration. It drastically reduces size, power and cost for local processing in embedded devices at the edge.

AIScale in a nutshell

Apples or Pears?

SOLVE THIS CLASSIFICATION CHALLENGE WITH KORTIQ AISCALE

The Challenge

Detecting and recognizing objects might be a simple task for a human, but when it comes to automatic detection and recognition by a high-end embedded vision system it might become very challenging to solve this problem efficiently.

Capturing

Razor-sharp images delivered by high-end cameras are the solid basis to master the challenge. But traditional image processing algorithms and pattern recognition might not be up to solving that task. It becomes very complicated.

Classification

What makes the pear different from the apple. To train a Convolutional Neural Network with a lot of different pictures from apples and pears makes it much easier to classify the pear and can increase the accuracy in detection. TensorFlow and CPU clusters or GPUs will help speed up the training phase.

Apples or Pears?

CONVOLUTIONAL NEURAL NETWORK CAN HELP TO MASTER THE CHALLENGE

FEATURE MAPS

= "PEAR"

CONVOLUTION LAYERS

FULLY-CONNECTED
LAYERS

POOLING LAYERS

INPUT IMAGE

Integrate KORTIQ AIScale

With KORTIQ AIScale CNN Hardware Accelerator IP we can help you to recognize WHAT you see

Integration of AIScale CNN with ZYNQ SOC

Integrate KORTIQ

KORTIQ AIScale Deep Compressor will massively shrink your selected network

Trained Network

Compression of trained network
with KORTIQ AIScale DeepCompressor

Compressed Network

Integrate KORTIQ

With KORTIQ AIScale we help you to recognize WHAT you see

Compressed Network

Translate to FPGA with
TensorFlow2AIScale translator

= "PEAR"

Apples or Pears or even Persons ?

MEET THE CHALLENGE AND SOLVE IT WITH KORTIQ

AGAIN

AIScale Advantages

APPLICATIONS

EMBEDDED VISION AND ROBOTICS IN INDUSTRIAL AND AUTOMOTIVE MARKETS

We are focusing on embedded- and computer vision and robotics in the industrial (Industry 4.0, IoT) and automotive markets to support new features such as Image Classification, Object Recognition, Object Tracking, Face Recognition and others that deep learning neural networks can bring to many of manufacturing, automation control and robotics applications. Using e.g. a cost optimized Xilinx Zynq device and a pre-trained CNN running on our implemented AIScale Neural Network Engine IP, all integretad in a high quality Smart Camera, can help improve reliability, lead to higher quality and yield.

OUR CUSTOMERS

KNOW CAMERA SYSTEMS AND IMAGE PROCESSING OR SIMPLY LOOK FOR AN OPTIMIZED ENGINE FOR THEIR NEURAL NETWORKS

Our clients know how to build a machine- or computer vision system. They are in image processing algorithms, video analytics and know how to create a high-end camera system choosing the right software and components such as lenses, image sensors, housing, semiconductor components and more. Now they are looking for a technology enabler to add machine learning tasks, a partner who focuses exactly on this piece of CNN hardware IP that enables them to get started with e.g. a Image Recognition feature immediately by integrating one true re-configurable, easy-to-use hardware with small footprint.

AISCALE DEEP LEARNING ACCELERATOR

SMART AND EASY TECHNOLOGY ENABLER USING ALL-ZERO-SKIPPING TECHNOLOGY

Designed by our team with 10+ years experience in Machine Learning Algorithms, FPGA- and SoC design, our hard-wired, easy-to-use and very small AIScale CNN Accelerator is designed to support all different types of CNN with only one underlaying architecture. Prune, compress and process the CNN with our All-Zero-Skipping Technology. Then simply initialize and run your pre-trained network with two functions. No need to generate different hardware architectures or special SW programming. AIScale Deep Learning Accelerator has a very small footprint based on coarse-grained, re-configurable computing principle for cost optimized, highly efficient, flexible and scalable FPGA, eFPGA and SoC based solutions.

Video - AI deployment made easy - our implementation flow

Hardware Integration made easy using Vivado IP Integrator

Video - People Detection with Zynq 7020

VIDEO – Kortiq Small and Efficient CNN Accelerator: Powered by Xilinx

Kortiq provides an easy to use, scalable and small form factor CNN accelerator. The device supports all types of CNN and dynamically accelerates different layer types found in the network. The Xilinx Zynq family of SoCs and MPSoCs help Kortiq devices achieve targeted performance levels and flexibility, while being cost-effective.

All Programmable @AIScale V1.0 (May 2018)

The AIScale Compute Core (MAC)

AIScale CC (MAC)

FIRST: INITIALIZE RECONFIGURABLE STRUCTURE

The Re-configurable Compute Core is the heart of our AI Scale accelerator and provides exceeding flexibility and scalability. The small footprint is based on coarse-grained true re-configurable computing principle and architecture.

AIScale CC supports and processes Convolutional-, Pooling-, Adding- and Fully-Connected layers. Based on your needs in size, frames per second or accuracy the accelerator can be parameterized from very few CC to several 100 CC.

Make advantage of a hardwired, optimized network with opportunity to switch between different CNN solutions based on customers needs using pre-trained network parameters. It can be structured for low latency and custom memory allocations.