tinyML Talks on May 21, 2024 “Making ML Tiny with High-Level Synthesis” by Russell Klein from Siemens

We held our next tinyML Talks webcast. Russell Klein from Siemens EDA presented Making ML Tiny with High-Level Synthesis on May 21, 2024.

Crafting an optimal bespoke machine learning accelerator for an ASIC or FPGA implementation means balancing communication, computation, and data movement. Trading off the conflicting goals of performance, accuracy, and efficiency means building and evaluating multiple accelerator architectures, often in the context of a larger system. This talk will show how High-Level Synthesis can be used to quickly create and assess multiple RTL implementations for an AI accelerator from a single algorithmic description. We will explain how HLS can be used to find the optimal quantization for features and weights, layer-by-layer or globally for an entire network. And we will show how HLS can be used to investigate caching strategies and their impact on power and performance. High-Level Synthesis can be the key to deploying ML into the most constrained and challenging Edge and IoT systems.

Russell Klein is a technical director with Siemens EDA working in the High-Level Synthesis group. His work focuses on optimizing hardware/software systems’ performance and efficiency through repartitioning with HLS. He also is an adjunct professor in the master’s program at Portland State University, teaching in the college of electrical and computer engineering. He has been awarded 6 patents in the area of hardware/software systems design and verification.

=========================
Download presentation slides:
Russell Klein

Watch on YouTube:
Russell Klein

Feel free to ask your questions on this thread and keep the conversation going!