High-level synthesis for AI: Part One
The computational and algorithmic demands made by computer vision systems highlight HLS' value for AI system development.
IP Topics
Using advanced IP to build SoCs for hyperscale data centres
SoC suppliers building the key components for hyperscale data centres need access to the latest IP to handle functions such as PCIe, DDR5, cache coherency, NVMe SSDs, and the highest-bandwidth Ethernet implementations.
Enabling the move to a system-centric view
Bob Smith of the ESD Alliance describes how we can promote the ongoing evolution of the design ecosystem.
Accelerating the implementation of application-specific processors
Application-specific processors can provide high performance for specialised tasks at low energy cost.
Optimizing the hardware implementation of machine learning algorithms
Optimizing the way in which machine learning algorithms are implemented in hardware will be a major differentiator for SoCs, especially for edge devices.
The antifuse advantage for one-time programmable non-volatile memory
Antifuse-based OTP NVM is highly scalable, has the area efficiency to enable macros of megabit capacities, and offers low read power.
Understanding USB 3.2 and Type-C
The basics of USB 3.2, how to implement it in an SoC, and how USB Type-C connectors and cables are used in USB 3.2 systems.
Reliability verification: It’s all about the baseline
How you can use the dedicated rule decks now being provided by foundries as the foundation for a reliability verification flow.
Why AI needs security
As AI becomes pervasive in computing applications, so too does the need for high-grade security in all levels of the system.
Using threat models and risk assessments to define device security requirements
The proliferation of attacks against embedded systems is making designers realize that they need to do more to secure their products and ecosystems.
PLATINUM SPONSORS
View All Sponsors