CODAI 2025 Workshop скачать в хорошем качестве

CODAI 2025 Workshop

Contents of this video ----------- 0:00:00 Welcome + Introduction - Dr. Michael J. Klaiber 0:10:47 Keynote: “MLIR-based programming for Spatial Architectures”, Dr. Stephen Neuendorffer, AMD Fellow 1:07:37 “Practical Discrepancies in AI Performance”, Sean Silva, Principal Engineer, EnChargeAI" 1:44:44 “Quidditch: An End-to-End Deep Learning Compiler for Occamy using IREE & xDSL”, Prof. Dr. Tobias Grosser, Associate Professor at The University of Cambridge" 2:13:31 “Insights into Interpreters, Compilers, and Optimizers for Neural Networks”, Shreya Alladi et al., University of Murcia 2:33:20 "Anatomy of an AI Compiler", Dr. Andreas Bytyn, Principal Engineer, Axelera AI 3:07:30 “Roofline’s Flexible Deployment Solution to Compile for GPUs, CPUs, and NPUs in Edge-AI Systems”, Dr. Jan Moritz Joseph, CEO, Roofline.ai 3:32:49 “Optimizing AI Performance: CuBLAS Tensor Core matmul in MLIR”, Alejandro Carmona Martínez et al., Universidad de Murcia 3:54:13 "A lightweight C Code Generator for Heterogeneous TinyML Systems”, Chen Liu et al., TU Dresden 4:25:15 “What happens in SRAM should stay in SRAM”, Alexander Belke & Shubham Rai, Robert Bosch GmbH 4:42:55 “PEAX - A Model Augmentation Framework for Adaptive Techniques and Embedded Applications”, Max Sponner et al., Infineon 5:04:30 "Co-optimizing algorithms, hardware and software for AI acceleration : IBM Perspective", Ananda Samajdar, Research Staff Member, IBM