Ultra Low Power Graphics February News

Latest with the release of the iPhone X bringing deep learning and its application to solve computer vision problems to mobile (edge) devices, object detection and the state-of-the-art in-face detection-accuracy took an enormous leap forward.

The challenge we face now is that the learned models ported to the edge device require an order of magnitudes more memory, more disk storage and more computational resources.

To address those resource problems, we unveil the first prototype of NEMA®|xNN, a power efficient inference-accelerator, to solve computer-vision tasks in edge-computing applications for convolutional network (CNN) tasks.

Developing power-optimized graphics software is inherently complex; therefore, smart analysis and programming 

 

tools become crucial instruments for the programmer.

Think Silicon® is adding two new members to its SDK, making programmers’ life easier. NEMA®|Power-Model enables programmers to identify and optimize the most energy consuming parts in their graphics software application. NEMA®|SHADER-Edit is a vertex and fragment shading editor with an integrated compiler, allowing programmers to rapidly create and compile optimal GLSL shaders offline without the need for a deeper knowledge of   the    internal    3D    GPU  operations.

Come and visit us at “Embedded World” in Nuremberg/Germany (Feb 27 - Mar 1st, Hall 4 Booth 4-673) so that you can see NEMA®|xNN, NEMA®|Power-Model and NEMA®|SHADER-Edit live on our booth. 

Think Silicon has answers! 

Ulli Mueller, VP Marketing & Business Development, Think Silicon

TSi_AI_NEMA_xNN-01

Read more button-01

NEMA_Power_Model_snapshot  nema_shader_edit

NEMA®|xNN – Low-power "Vision-Inference-Accelerator"

A power efficient inference accelerator to solve computer-vision tasks in edge-computing applications using optimized convolutional neural networks.

NEMA®|Power Model - "Visualize System Power consumption"

A tool which enables programmers to identify and optimize the most energy consuming parts in their graphics software application.

NEMA®|SHADER-Edit "Generate optimal vertex and fragment shaders"

A tool which allows the smooth and fast generation of NEMA®|t – 3D GPU executables.

Read more button-01 Read more button-01 Read more button-01

  News

 

 

First Low-Power AI-Inference Accelerator Vision Processing Unit From Think Silicon To Debut at Embedded World 2018

Embedded World 2018 - Building the solutions for tomorrow

Mobile World Congress 2018 - The NEMA®|Technology at your hands

DATE 2018 in Dresden: Highlighting Future and Emerging Technologies and Designing Autonomous Systems

 

 

 

Follow us

Twitter    Linkedin    Facebook    Youtube

© 2018 THINK SILICON is a registered trademark of THINK SILICON S.A. (or its subsidiaries) in the EU and/or elsewhere. All rights reserved.