FLASH - Towards a High-performance Hardware Acceleration Architecture for Cross-silo Federated Learning
Offered By: USENIX via YouTube
Course Description
Overview
Explore a groundbreaking conference talk on FLASH, a high-performance hardware acceleration architecture designed for cross-silo federated learning systems. Delve into the innovative approach of extracting and implementing two basic operators—modular exponentiation and multiplication—as highly efficient engines to achieve adequate acceleration for nine widely-used cryptographic operations. Learn about the dataflow scheduling scheme that dynamically composes different cryptographic operations, maximizing resource utilization. Discover the impressive performance gains achieved by FLASH, including up to 14.0× and 3.4× acceleration over CPU and GPU respectively, and its integration with FATE, the most widely-adopted cross-silo FL framework. Gain insights into the potential of FLASH as an ASIC, offering a 23.6× performance improvement upon the FPGA prototype.
Syllabus
NSDI '23 - FLASH: Towards a High-performance Hardware Acceleration Architecture for Cross-silo...
Taught by
USENIX
Related Courses
FPGA computing systems: Partial Dynamic ReconfigurationPolitecnico di Milano via Polimi OPEN KNOWLEDGE Introduction to Amazon Elastic Inference
Pluralsight FPGA computing systems: Partial Dynamic Reconfiguration
Politecnico di Milano via Coursera Introduction to Amazon Elastic Inference (Traditional Chinese)
Amazon Web Services via AWS Skill Builder Introduction to Amazon Elastic Inference (Portuguese)
Amazon Web Services via AWS Skill Builder