What is the cost of weak determinism?

Segulja, Cedomir; Abdelrahman, Tarek S.

doi:10.1145/2628071.2628099

Cited by 11 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several of the benchmark programs contained unintentional data races which were identified and patched in the literature [38]. We applied this set of patches, which were kindly shared by the author of the aforementioned work.…”

Section: Correctness and Performance Evaluationmentioning

confidence: 99%

“…Software-based DMT systems come in many flavors but essentially, they all establish a deterministic schedule by passing a token. We refer to the literature for an excellent overview of the possible ways to implement the deterministic schedule, as well as their implications [38]. In the remainder of this discussion, we focus on the fundamental reason why DMT systems are incompatible with MVEEs that run diversified variants: the timing of and prerequisites for the deterministic token passing.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Taming Parallelism in a Multi-Variant Execution Environment

Volckaert

Coppens

Sutter

et al. 2017

Proceedings of the Twelfth European Conference on Computer Systems

View full text Add to dashboard Cite

Exploit mitigations, by themselves, do not stop determined and well-resourced adversaries from compromising vulnerable software through memory corruption. Multivariant execution environments (MVEEs) add additional assurance by executing multiple, diversified copies (variants) of the same program in lockstep while monitoring their behavior for signs of attacks (divergence). While executing multiple copies of the same program requires additional computational resources, modern MVEEs run many workloads at near-native speed and can detect adversaries before they leak secrets or achieve persistence on the host system.Multi-threaded programs are challenging to execute in lockstep by an MVEE. If the threads in a set of variants are not scheduled in the exact same order, the variants will diverge from each other in terms of the system calls they make. While benign, such divergence undermines the MVEEs ability detect divergence caused by malicious program inputs. To address this problem, we developed an MVEE-specific synchronization scheme that lets us execute a set of multithreaded variants in lockstep without causing benign divergence. Our fully-fledged MVEE runs the PARSEC 2.1 and SPLASH-2x parallel benchmarks (with four worker threads per variant) with a slowdown of less than 15% relative to unprotected execution. Addressing this longstanding compatibility issue makes MVEEs a viable defense for a far greater range of realistic workloads.

show abstract

Section: Correctness and Performance Evaluationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Taming Parallelism in a Multi-Variant Execution Environment

Volckaert

Coppens

Sutter

et al. 2017

Proceedings of the Twelfth European Conference on Computer Systems

View full text Add to dashboard Cite

show abstract

“…Follow-on work has shown a variety of ways to optimize the performance overheads of determinism, e.g., through compiler optimizations [5], relaxed memory consistency [2,11,12,14], existing hardware support for virtual memory [3,7,21,29], and eliminating the synchronous implementation of commits present in prior determinism systems [23]. Segulja and Abdelrahman [27] measure the performance cost of enforcing a deterministic logical clock and find it to be less than 2x across a range of benchmarks and runtime perturbations, showing that determinism needn't be fundamentally expensive. Recently, the RFDet system [19] demonstrated the performance benefits of memory consistency optimizations with its deterministic implementation of LRC [20].…”

Section: Related Workmentioning

confidence: 99%

High-performance determinism with total store order consistency

Merrifield

Devietti

Eriksson

2015

Proceedings of the Tenth European Conference on Computer Systems

View full text Add to dashboard Cite

We present CONSEQUENCE, a deterministic multi-threading library. CONSEQUENCE achieves deterministic execution via store buffering and strict ordering of synchronization operations. To ensure high performance under a wide variety of conditions, the ordering of synch operations is based on a deterministic clock [25], and store buffering is implemented using version-controlled memory [23].Recent work on deterministic concurrency [14,19] has proposed relaxing the consistency model beyond total store order (TSO). Through novel optimizations, CONSEQUENCE achieves the same or better performance on the Phoenix, PARSEC and SPLASH-2 benchmark suites, while retaining TSO memory consistency. Across 19 benchmark programs, CONSEQUENCE incurs a worst-case slowdown of 3.9× vs. pthreads, with 14 out of 19 programs at or below 2.5×. We believe this performance improvement takes parallel programming one step closer to "determinism by default."

show abstract

“…However, they are free of bugs caused by races, which are particularly difficult to reason about [2]. Further, data-race-free programs can be executed deterministically with very little added cost [53]. This makes race-freedom a desirable property.…”

Section: Introductionmentioning

confidence: 99%

“…There are sources of nondeterminism other than thread communication but their impact is smaller[53]; we do not address them in this paper.…”

mentioning

confidence: 99%

C lean

Segulja

Abdelrahman

2015

Proceedings of the 42nd Annual International Symposium on Computer Architecture

Self Cite

View full text Add to dashboard Cite

Data races make parallel programs hard to understand. Precise race detection that stops an execution on first occurrence of a race addresses this problem, but it comes with significant overhead. In this work, we exploit the insight that precisely detecting only write-after-write (WAW) and read-afterwrite (RAW) races suffices to provide cleaner semantics for racy programs. We demonstrate that stopping an execution only when these races occur ensures that synchronizationfree-regions appear to be executed in isolation and that their writes appear atomic. Additionally, the undetected racy executions can be given certain deterministic guarantees with efficient mechanisms.We present CLEAN, a system that precisely detects WAW and RAW races and deterministically orders synchronization. We demonstrate that the combination of these two relatively inexpensive mechanisms provides cleaner semantics for racy programs. We evaluate both software-only and hardware-supported CLEAN. The software-only CLEAN runs all Pthread benchmarks from the SPLASH-2 and PARSEC suites with an average 7.8x slowdown. The overhead of precise WAW and RAW detection (5.8x) constitutes the majority of this slowdown. Simple hardware extensions reduce the slowdown of CLEAN's race detection to on average 10.4% and never more than 46.7%.

show abstract

What is the cost of weak determinism?

Cited by 11 publications

References 42 publications

Taming Parallelism in a Multi-Variant Execution Environment

Taming Parallelism in a Multi-Variant Execution Environment

High-performance determinism with total store order consistency

C lean

Contact Info

Product

Resources

About