Dead timestamp identification in Stampede

Harel, Nissim; Mandviwala, Hasnain A.; Knobe, Kathleen; Ramachandran, Umakishore

doi:10.1109/icpp.2002.1040864

Cited by 5 publications

(17 citation statements)

References 11 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The less restrictive nature of the Stampede programming model allows conception of different types of algorithms for GVT calculation like the one described in [8]. In [5] we have proposed yet another algorithm that uses application-level knowledge enabling garbage collection based entirely on local events with no reliance on any global mechanism.…”

Section: Related Workmentioning

confidence: 99%

“…In the case of DGC, the forward and backward propagation of timestamp guarantees are instigated by put/get operations on channels. In a companion paper [5], we experimentally compared the performance of these three GC algorithms in the context of a real-time color-based people tracker application that was developed at Compaq CRL [11]. We use memory footprint -the amount of memory used for buffering timestamped items in the Stampede channels by the application as a function of real time -as the metric for performance evaluation.…”

Section: Enhancements To the Dgc Algorithmmentioning

confidence: 99%

“…There are three competing mechanisms for GC in Stampede: a REFerence count based garbage collector (REF), a Transparent Garbage Collector (TGC) [8], and a Dead timestamp based Garbage Collector (DGC) [5]. Each algorithm represents a specific point in the tradeoff between information needed to be provided to the runtime system and the corresponding aggressiveness for eliminating garbage.…”

Section: Algorithms For Garbage Collection In Stampedementioning

confidence: 99%

“…The DGC algorithm [5] is inspired by the observation that even in dynamic applications, it may be possible to discern all the potential channel, thread, and connection creations by analyzing the application code. Under such circumstances, it is possible for the application programmer to supply the runtime system with a task graph that is a maximal representation of the application dynamism.…”

Section: Dead Timestamps Based Garbage Collectormentioning

confidence: 99%

“…In a more recent paper [5], we have introduced a new algorithm, called dead-timestamp based garbage collection (DGC), that uses an application-level task graph to make runtime decisions on the interest set for timestamps. We show that using such application-level knowledge can result in a significant space advantage (up to 40%) compared to the earlier algorithm that does not use such knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Comparative Study of Stampede Garbage Collection Algorithms

Mandviwala

Harel

Knobe

et al. 2005

Languages and Compilers for Parallel Computing

View full text Add to dashboard Cite

Stampede is a parallel programming system to support interactive multimedia applications. The system maintains temporal causality in such streaming real-time applications via channels that buffer timestamped items. A Stampede application is a coarse-grain dataflow pipeline of these timestamped items. Not all timestamps are relevant for an application output due to the differential processing rates of pipeline stages. Therefore, garbage collection (GC) is crucial for Stampede runtime performance. Three GC algorithms are currently available in Stampede. In this paper, we ask the question how far off these algorithms are from an ideal garbage collector, one in which the memory usage is exactly equal to that which is required for buffering only the relevant timestamped items in channels. This oracle, while unimplementable, serves as an empirical lower-bound for memory usage. We then propose optimizations that will help us get closer to this lower-bound. Using an elaborate measurement and post-mortem analysis infrastructure in Stampede, we evaluate the performance potential for these optimizations. A color-based people tracking application is used for the performance evaluation. Our results show that these optimizations reduce the memory usage by over 60% for this application over the best GC algorithm available in Stampede.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Enhancements To the Dgc Algorithmmentioning

confidence: 99%