Hardware Multithreaded Transactions

Fix, Jordan; Nagendra, Nayana Prasad; Apostolakis, Sotiris; Zhang, Hansen; Qiu, Sophie; August, David I.

doi:10.1145/3173162.3173172

Cited by 5 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite increased applicability, evaluation results of automatic speculative-DOALL systems on real hardware are still underwhelming due to overheads that often negate the benefits of parallelization [5,14]. This paper first identifies core inefficiencies of the state-of-the-art parallelizing compilers and subsequently describes how Perspective mitigates them.…”

Section: Background and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Perspective

Apostolakis

Chan

et al. 2020

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Syste

Self Cite

View full text Add to dashboard Cite

The promise of automatic parallelization, freeing programmers from the error-prone and time-consuming process of making efficient use of parallel processing resources, remains unrealized. For decades, the imprecision of memory analysis limited the applicability of non-speculative automatic parallelization. The introduction of speculative automatic parallelization overcame these applicability limitations, but, even in the case of no misspeculation, these speculative techniques exhibit high communication and bookkeeping costs for validation and commit. This paper presents Perspective, a speculative-DOALL parallelization framework that maintains the applicability of speculative techniques while approaching the efficiency of non-speculative ones. Unlike current approaches which subsequently apply speculative techniques to overcome the imprecision of memory analysis, Perspective combines a novel speculation-aware memory analyzer, new efficient speculative privatization methods, and a planning phase to select a minimal-cost set of parallelizationenabling transforms. By reducing speculative parallelization overheads in ways not possible with prior parallelization systems, Perspective obtains higher overall program speedup (23.0× for 12 general-purpose C/C++ programs running on a 28-core shared-memory commodity machine) than Privateer (11.5×), the prior automatic DOALL parallelization system with the highest applicability.CCS Concepts • Software and its engineering → Compilers; Multithreading.

show abstract

Section: Background and Motivationmentioning

confidence: 99%

“…Despite the dramatic advance that speculation for automatic parallelization represents, challenges remain that prevent its widespread adoption [5,14,22,33]. While memory flow speculation is popular, its relaxed program dependence structure comes with a high cost.…”

Section: Introductionmentioning

confidence: 99%