Write a Blog >>
ISMM 2018
co-located with PLDI 2018
Mon 18 Jun 2018 16:30 - 17:00 at Discovery AB - Analyzing the Cache and Scheduling Chair(s): Michael D. Bond

Cache in multicore machines is often shared, and the cache performance depends on how memory accesses belonging to different programs interleave with one another. The full range of performance possibilities includes all possible interleavings, which are too numerous to be studied by experiments for any mix of non-trivial programs.

This paper presents a theory to characterize the effect of memory access interleaving due to parallel execution of non-data-sharing programs. The theory uses an established metric called the footprint (which can be used to calculate miss ratios in fully-associative LRU caches) to measure cache demand, and considers the full range of interleaving possibilities. The paper proves a lower bound for footprints of interleaved traces, and then formulates an upper bound in terms of the footprints of the constituent traces. It also shows the correctness of footprint composition used in a number of existing techniques, and places precise bounds on its accuracy.

Mon 18 Jun

Displayed time zone: Eastern Time (US & Canada) change

16:00 - 17:30
Analyzing the Cache and SchedulingISMM 2018 at Discovery AB
Chair(s): Michael D. Bond Ohio State University
16:00
30m
Talk
mPart: Miss-Ratio Curve Guided Partitioning in Key-Value Stores
ISMM 2018
Daniel Byrne Michigan Technological University, USA, Nilufer Onder Michigan Technological University, USA, Zhenlin Wang Michigan Technological University
16:30
30m
Talk
Prediction and Bounds on Shared Cache Demand from Memory Access Interleaving
ISMM 2018
Jacob Brock University of Rochester, Chen Ding University of Rochester, Rahman Lavaee , Fangzhou Liu , Liang Yuan Institute of Computing Technology at Chinese Academy of Sciences, China
17:00
30m
Talk
Balanced Double Queues for GC Work-Stealing on Weak Memory Models
ISMM 2018
Michihiro Horie IBM Research - Tokyo, Hiroshi Horii IBM Research, Japan, Kazunori Ogata IBM Research, Japan, Tamiya Onodera IBM, Japan