Wed 19 Jan 2022 13:55 - 14:20 at Salon III - Weak Memory Models Chair(s): Mae Milano

Existing semantic formalisations of the Intel-x86 architecture cover only a small fragment of its available features that are relevant for the consistency semantics of multi-threaded programs as well as the persistency semantics of programs interfacing with non-volatile memory.

We extend these formalisations to cover: (1) non-temporal writes, which provide higher performance and are used to ensure that updates are flushed to memory; (2) reads and writes to other Intel-x86 memory types, namely uncacheable, write-combined, and write-through; as well as (3) the interaction between these features. We develop our formal model in both operational and declarative styles, and prove that the two characterisations are equivalent. We have empirically validated our formalisation of the consistency semantics of these additional features and their subtle interactions by extensive testing on different Intel-x86 implementations.

Wed 19 Jan

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

13:30 - 14:45
Weak Memory ModelsPOPL at Salon III
Chair(s): Mae Milano University of California, Berkeley
13:30
25m
Research paper
The Leaky Semicolon: Compositional Semantic Dependencies for Relaxed-Memory ConcurrencyInPerson
POPL
Alan Jeffrey Roblox, James Riely DePaul University, Mark Batty University of Kent, Simon Cooksey University of Kent, Ilya Kaysin JetBrains Research; University of Cambridge, Anton Podkopaev HSE University
DOI Media Attached
13:55
25m
Research paper
Extending Intel-x86 Consistency and Persistency: Formalising the Semantics of Intel-x86 Memory Types and Non-temporal StoresRemote
POPL
Azalea Raad Imperial College London, Luc Maranget Inria, Viktor Vafeiadis MPI-SWS
DOI Media Attached
14:20
25m
Research paper
Truly Stateless, Optimal Dynamic Partial Order ReductionRemote
POPL
Michalis Kokologiannakis MPI-SWS, Iason Marmanis MPI-SWS, Vladimir Gladstein MPI-SWS; St. Petersburg University; JetBrains Research, Viktor Vafeiadis MPI-SWS
DOI Media Attached