industry news
Subscribe Now

Ambient Scientific Announces Beta Release of Software Compilers for its Programmable AI Processor GPX-10

Ambient Scientific is excited to announce the release of Beta versions of its compilers for GPX-10 AI processor using general purpose programmable MX8 cores, designed for enabling OnDevice AI in endpoint and edge devices. 

Ambient is releasing two types of compilers(i) Vertical Compilers that  enable fast development of AI applications and (ii) A Generic compiler that provides programming flexibility to application developers for  implementing AI models of their choice. 

Using Vertical compilers, developers can create applications for range of applications for voice, computer vision and sensor fusion using pre-determined neural networks. Vertical Compiler for Voice enables voice-based AI applications such as creation of custom wake words, Menu of command phrases and Voice-IDs. End users will be able to create or change their wake-words, phrases and voice-IDs as many times as they choose over the life of the product. This is particularly important in situations where the device use-conditions are changed, or the user decides to repurpose an already deployed device. Vertical Compiler for Vision enables creation of various computer vision applications with up to twenty-one classes of vision-objects as defined by OEM. The Vertical Compiler for Sensor fusion enables developers to implement multi-parameter-based sensor fusion AI inferencing – a first of its kind in endpoint devices. 

Developers will be able to download these compliers along with the development environments for training, validation, and deployment to GPX-10 AI Processor. Sample voice, vision and sensor-fusion applications are also provided for quick proof of concept tests. 

Ambient Scientific’s Generic Compiler enables developers to  implement computer vision applications for recognition of up to 100  object classes. It supports most of the pretrained and prebuilt  computer vision models (based on Mobilenet v1/v2, Resnet, VGG etc.)  that are commonly used in industry for commercial or benchmarking  purposes. Developers can also use Ambient Scientific Generic  Compiler to develop and implement CNN based custom applications  for computer vision such as object recognition and classification,  presence and occupancy detection. These applications can be built  with transfer learning from pretrained models or developed from  scratch. The Generic Compiler is framework agnostic. It allows   developers to create neural network models using their own choice of  AI frameworks such as TensorFlow, PyTorch, caffe, paddle-paddle,  CNTK, C++ etc. and deploy their models on GPX-10 AI Processor. 

Ambient Scientific’s Vertical and Generic compilers are built to scale user applications across all Ten programmable AI cores of GPX-10 to maximize the performance while optimizing power consumption. The compilers are available to developers under NDA.

About Ambient Scientific 

Ambient Scientific is a leading developer of industry’s lowest power programmable AI processors designed to address the explosive demand for Inference and Training in endpoint, edge and Battery-operated AI devices giving both connected and unconnected devices and appliances their own personalities. Ambient’s AI processor and microcontroller products and software libraries are designed to bring a plethora of exciting new innovative products to the market quickly. 

By enabling AI at the edge, Ambient’stechnology plays a key role in sustainable computing by alleviating data traffic across networks and reducing the demand on the cloud datacenters which today power most of the AI inference and training resources. 

Learn more at https://ambientscientific.ai/

Leave a Reply

featured blogs
Nov 23, 2022
The current challenge in custom/mixed-signal design is to have a fast and silicon-accurate methodology. In this blog series, we are exploring the Custom IC Design Flow and Methodology stages. This methodology directly addresses the primary challenge of predictability in creat...
Nov 22, 2022
Learn how analog and mixed-signal (AMS) verification technology, which we developed as part of DARPA's POSH and ERI programs, emulates analog designs. The post What's Driving the World's First Analog and Mixed-Signal Emulation Technology? appeared first on From Silicon To So...
Nov 21, 2022
By Hossam Sarhan With the growing complexity of system-on-chip designs and technology scaling, multiple power domains are needed to optimize… ...
Nov 18, 2022
This bodacious beauty is better equipped than my car, with 360-degree collision avoidance sensors, party lights, and a backup camera, to name but a few....

featured video

Unique AMS Emulation Technology

Sponsored by Synopsys

Learn about Synopsys' collaboration with DARPA and other partners to develop a one-of-a-kind, high-performance AMS silicon verification capability. Please watch the video interview or read it online.

Read the interview online:

featured paper

Algorithm Verification with FPGAs and ASICs

Sponsored by MathWorks

Developing new FPGA and ASIC designs involves implementing new algorithms, which presents challenges for verification for algorithm developers, hardware designers, and verification engineers. This eBook explores different aspects of hardware design verification and how you can use MATLAB and Simulink to reduce development effort and improve the quality of end products.

Click here to read more

featured chalk talk

56 Gbps PAM4 Performance in FPGA Applications

Sponsored by Mouser Electronics and Samtec

If you are working on an FPGA design, the choice of a connector solution can be a crucial element in your system design. Your FPGA connector solution needs to support the highest of speeds, small form factors, and emerging architectures. In this episode of Chalk Talk, Amelia Dalton joins Matthew Burns to chat about you can get 56 Gbps PAM4 performance in your next FPGA application. We take a closer look at Samtec’s AcceleRate® HD High-Density Arrays, the details of Samtec’s Flyover Technology, and why Samtec’s complete portfolio of high-performance interconnects are a perfect fit for 56 Gbps PAM4 FPGA Applications.

Click here for more information about Samtec AcceleRate® Slim Body Direct Attach Cable Assembly