Optimistic parallelism requires abstractions

By Milind Kulkarni, Keshav Pingali, Bruce Walter, Ganesh Ramanarayanan, Kavita Bala, L. P. Chew. ACM-SIGPLAN Symposium on Programming Language Design and Implementation, 2007

401 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A quantitative study of irregular programs on GPUs (2012, methodology): “• Delaunay Mesh Refinement (DMR): This is a meshrefinement algorithm from computational geometry [11], [29].”
A type and effect system for deterministic parallel Java (2009, background): “Sometimes to express parallelism we need to look at interference in terms of higher-level operations than read and write [29].”
Transactional boosting: a methodology for highly-concurrent transactional objects (2008, background): “[19] describe Euclid, a system that exploits commutativity and inverses for efficient thread-level speculation.”
The tao of parallelism in algorithms (2011, methodology): “This can be implemented using a data structure similar to a reorder buffer in out-of-order processors [40].”
A lightweight infrastructure for graph analytics (2013, methodology): “To support this argument, this paper introduces several improvements to an existing system, Galois [15], that provide for a rich programming model with coordinated and autonomous scheduling, and with and without”
STAMP: Stanford Transactional Applications for Multi-Processing (2008, methodology): “A few larger workloads that target TM systems have been designed to address the disparity between microbenchmarks and full applications: Delaunay mesh generation [35], database management [14], BerkeleyDB [12], maze routing [40], and Delaunay mesh refinement and agglomerative clustering [24].”