11:45am–1:15pm (T4.2)
Mohammed Fahad, Principal Application Engineer
In this session we will present a recommended use model in that power is addressed early. With the available provisions in the tool like early power checking using EDCs and vectorless power clean-up, one must start addressing the power early during the design phase to achieve significant impact. With each revision of the RTL, as we move on during the development phase, the tool should help incrementally reduce the power eventually providing the most power-savvy design. This approach yields better results in terms of power saving impact and time-to-power.
2:15pm–3:45pm (T2.3)
Russel Klein, Program Director
Petri Solanti, Application Engineer
This tutorial will show how to verify a machine learning algorithm from Python code in a machine learning framework, like TensorFlow or Caffe, to RTL. As the algorithm is successively refined, at each stage it is necessary to show that both the refinement goals have been achieved, and that the implementation has not deviated from the prior design stage. The algorithm will be migrated from Python, to C++, and finally to RTL using High-Level Synthesis (HLS).
9:15am – 10:30am
Moderator
Gabriele Pulini, Product Marketing and Market Development, Siemens EDA
Panelists
Ashish Darbari, founder and CEO, Axiomise
Oren Katzir, vice president of applications engineering, Real Intent
Herbert Taucher, head of research group, Siemens AG
Anil Deshpande, associate director, Samsung Semiconductor India
Axel Jahnke, SoC R&D manager, Nokia
10:45am – 12:15pm
Rich Edelman, Siemens
3:15pm – 4:45pm
Philippe Luc, Codasip
Salahhedin Hetalani, Siemens
Nicolae Tusinschi, Siemens
12:15pm-12:45pm
Mark Handover, Siemens
Mohamed Badawy, Siemens