MemLiner - Lining up Tracing and Application for a Far-Memory-Friendly Runtime

This course aims to teach learners about far-memory techniques that enable applications to use remote memory in modern datacenters. The learning outcomes include understanding the challenges of far-memory systems, the impact of garbage collection on memory access patterns, and the development of MemLiner to improve far-memory system performance. The course covers skills such as object classification, identifying memory access patterns, and implementing runtime techniques. The teaching method involves presenting research findings, discussing key design ideas, and evaluating the performance of MemLiner in cloud systems. The intended audience for this course includes software developers, system architects, and researchers interested in optimizing memory usage in datacenter applications.