Sciweavers

114 search results - page 1 / 23
» Speculative Parallelization - Eliminating the Overhead of Fa...
Sort
View
IPPS
2000
IEEE
13 years 9 months ago
A Mechanism for Speculative Memory Accesses Following Synchronizing Operations
In order to reduce the overhead of synchronizing operations of shared memory multiprocessors, this paper proposes a mechanism, named specMEM, to execute memory accesses following ...
Takayuki Sato, Kazuhiko Ohno, Hiroshi Nakashima
PPAM
2005
Springer
13 years 10 months ago
Checkpointing Speculative Distributed Shared Memory
This paper describes a checkpointing mechanism destined for Distributed Shared Memory (DSM) systems with speculative prefetching. Speculation is a general technique involving predi...
Arkadiusz Danilecki, Anna Kobusinska, Michal Szych...
IPPS
2003
IEEE
13 years 10 months ago
Improving Speculative Thread-Level Parallelism Through Module Run-Length Prediction
Exploiting speculative thread-level parallelism across modules, e.g., methods, procedures, or functions, have shown promise. However, misspeculations and task creation overhead ar...
Fredrik Warg, Per Stenström
ICS
1999
Tsinghua U.
13 years 9 months ago
Improving the performance of speculatively parallel applications on the Hydra CMP
Hydra is a chip multiprocessor (CMP) with integrated support for thread-level speculation. Thread-level speculation provides a way to parallelize sequential programs without the n...
Kunle Olukotun, Lance Hammond, Mark Willey
ASPLOS
1998
ACM
13 years 9 months ago
Data Speculation Support for a Chip Multiprocessor
Thread-level speculation is a technique that enables parallel execution of sequential applications on a multiprocessor. This paper describes the complete implementation of the sup...
Lance Hammond, Mark Willey, Kunle Olukotun