A Thread Partitioning Method for Speculative Multithreading

2009 ◽  
Author(s):  
Xiaoyu Pan ◽  
Yinliang Zhao ◽  
Zheng Chen ◽  
Xuhao Wang ◽  
Yuanke Wei ◽  
...  
Keyword(s):  
Speculative Multithreading ◽  
Thread Partitioning

Thread Partitioning Algorithm for Speculative Multithreading Based on Path Optimization

2012 ◽  
Vol 23 (8) ◽  
pp. 1950-1964 ◽  
Author(s):  
Yuan-Cheng LI ◽  
Yin-Liang ZHAO ◽  
Mei-Rong LI ◽  
Yan-Ning DU
Keyword(s):  
Path Optimization ◽  
Speculative Multithreading ◽  
Partitioning Algorithm ◽  
Thread Partitioning

A thread partitioning approach for speculative multithreading

2013 ◽  
Vol 67 (3) ◽  
pp. 778-805 ◽  
Author(s):  
Bin Liu ◽  
Yinliang Zhao ◽  
Yuxiang Li ◽  
Yanjun Sun ◽  
Boqin Feng
Keyword(s):  
Speculative Multithreading ◽  
Thread Partitioning

Exploiting Thread-Level Parallelism Based on Balancing Load for Speculative Multithreading

2014 ◽  
Vol 678 ◽  
pp. 8-11 ◽  
Author(s):  
Yuan Cheng Li
Keyword(s):  
Optimal Solution ◽  
Solution Space ◽  
Automatic Parallelization ◽  
Cluster Method ◽  
Heuristic Rules ◽  
Speculative Multithreading ◽  
Speculative Parallelization ◽  
Load Imbalance ◽  
Thread Partitioning ◽  
Level Parallelism

Speculative Multithreading (SpMT) technology is an effective mechanism for automatic parallelization of irregular programs. While speculative parallelization can potentially deliver significant speedup for irregular applications, several speculative parallelization overheads resulting from the factors, especially inter-thread load imbalance, limit these speedups in practice. Most existing thread partitioning methods are mainly based on heuristic rules strategies to generate speculative threads. However, these heuristic rules extracted from people’s experiences cannot estimate quantitatively but qualitatively the overhead. Based on the thorough analysis of the speculative parallelization overhead resulting from inter-thread load imbalance, we propose a novel method to balance the inter-thread load. In this method, we firstly determine a method by which to unroll the loops. Then, we introduce cluster method to search the solution space of speculative threads and finally get the optimal solution. The experimental results show that, the proposed method can effectively reduce the inter-thread load imbalance; and the load imbalance overhead can be effectively reduced by 43.7%. And we can gain 8.8% performance improvement on Olden benchmark suits.

Data Structure Directed Thread Partitioning Method and Execution Model

2014 ◽  
Vol 24 (10) ◽  
pp. 2432-2459
Author(s):  
Yan-Ning DU ◽  
Yin-Liang ZHAO ◽  
Bo HAN ◽  
Yuan-Cheng LI
Keyword(s):  
Data Structure ◽  
Execution Model ◽  
Thread Partitioning
Sign in / Sign up

Export Citation Format

Share Document