• Publications
  • Influence
Incoop: MapReduce for incremental computations
TLDR
This paper describes the architecture, implementation, and evaluation of Incoop, a generic MapReduce framework for incremental computations that detects changes to the input and automatically updates the output by employing an efficient, fine-grained result reuse mechanism. Expand
The data locality of work stealing
TLDR
The initial experiments on iterative data-parallel applications show that the work-stealing scheduling algorithm matches the performance of static-partitioning under traditional work loads but improves the performance up to 50% over static partitioning under multiprogrammed work loads and a locality-guided work stealing algorithm that improves the data locality of multi-threaded computations by allowing a thread to have an affinity for a processor. Expand
The Data Locality of Work Stealing
TLDR
A locality-guided work-stealing algorithm that improves the data locality of multithreaded computations by allowing a thread to have an affinity for a processor and improves the performance of work stealing up to 80%. Expand
Scheduling parallel programs by work stealing with private deques
TLDR
Two work-stealing algorithms with private deques are proposed and it is proved that the algorithms guarantee similar theoretical bounds as work stealing with concurrent deques, which enables implementing flexible task creation and distribution strategies. Expand
Adaptive functional programming
TLDR
A general mechanism for adaptive computing that enables one to make any purely-functional program adaptive is proposed and it is shown that the mechanism is practical by giving an efficient implementation as a small ML library. Expand
Self-adjusting computation: (an overview)
TLDR
This invited talk presents an overview of self-adjusting computation and briefly discusses the progress in developing the approach and present some recent advances. Expand
Adaptive functional programming
CEAL: a C-based language for self-adjusting computation
TLDR
The design and implementation of CEAL are described and it is shown that CEAL is effective in practice: compiled self-adjusting programs respond to small modifications to their data by orders of magnitude faster than recomputing from scratch while slowing down a from-scratch run by a moderate constant factor. Expand
A Core Calculus for Provenance
TLDR
This article considers a higher-order, functional language with sums, products, and recursive types and functions, and equip it with a tracing semantics in which traces themselves can be replayed as computations, including standard forms of provenance studied previously. Expand
Provenance as dependency analysis†
TLDR
It is argued that dependency analysis techniques familiar from program analysis and program slicing provide a formal foundation for forms of provenance that are intended to show how (part of) the output of a query depends on (parts of) its input. Expand
...
1
2
3
4
5
...