ISMM 2022
as the organisers put it
Welcome to the 2022 ACM SIGPLAN International Symposium on Memory Management (ISMM). ISMM is a premier forum for research in memory management and solicits papers from areas including but not limited to: Memory system design and analysis Hardware support for memory management Memory management for large-scale data-intensive systems Novel memory architectures Memory management at datacenter and cloud scales Garbage Collection algorithms and implementations Formal analysis and verification of memory management algorithms Compiler analyses to aid memory management Tools to analyze memory usa ...
who it's for
memory management researchers, runtime engineers, garbage collector implementers, systems software engineers, os developers, cloud infrastructure engineers, data center operators
topics
disaggregated memory management; HotBox hybrid access model; huge-page-aware allocator Temeraire; per-CPU allocator caches; virtualized cluster memory management; reuse-distance AVL tree; marginal utility per-page; memory coloring for CHERI; pointer authentication PAC-Man attack; distillation methodology for GC overhead; TLB locality improvements from allocators; compacting versus non-compacting GC
| title | author | length |
|---|---|---|
| Welcome from the Chairs and Conference Report | David Chisnall, Michael Lippautz | 17m |
Conference sees 7 submissions after a one‑week extension, a 50% drop from the prior year, with 4 accepted papers and no shepherding; one PC paper is decided by… | ||
| Industry panel: Memory management priorities for the next few years | Nathaniel Wesley Filardo, Chris Kennelly, Christine H. Flood | 01h 06m |
Claims: garbage-collected runtimes face hundreds-of-gigabyte heaps so non-compacting mark‑and‑sweep hits scalability limits while Julia moves toward mostly… | ||
| Reconsidering OS Memory Optimizations in the Presence of Disaggregated Memory | Shai Aviram Bergman, Priyank Faldu, Boris Grot, Lluís Vilanova, Mark Silberstein | 30m |
Claim: disaggregated memory with 750 ns–1.5 µs remote latency flips usual OS choices, so the authors build HotBox, a base-page-only memory manager that uses a… | ||
| MemSweeper: Virtualizing Cluster Memory Management for High Memory Utilization | AmirHossein Seyri, Abhisek Pan, Balajee Vamanan | 37m |
MemSweeper virtualizes a shared memcached heap so pages move across tenants and slab classes based on measured reuse rather than static partitions, implemented… | ||
| We Live in Interesting Times | Steve Blackburn | 01h 04m |
Argues memory management is more relevant than ever and gives concrete findings: a fleet study shows allocator changes cut TLB stalls by about 20% stalled… | ||
| nothing matches | ||