Search For:

Displaying 1-4 out of 4 total
Characterization and analysis of HMMER and SVM-RFE parallel bioinformatics applications
Found in: IEEE Workload Characterization Symposium
By U. Srinivasan, Peng-Sheng Chen, Qian Diao, Chu-Cheow Lim, E. Li, Yongjian Chen, R. Ju, Yimin Zhang
Issue Date:October 2005
pp. 87-98
Bioinformatics applications constitute an emerging data-intensive, high-performance computing (HPC) domain. While there is much research on algorithmic improvements, (2004), the actual performance of an application also depends on how well the program maps...
 
Support of Probabilistic Pointer Analysis in the SSA Form
Found in: IEEE Transactions on Parallel and Distributed Systems
By Ming-Yu Hung,Peng-Sheng Chen,Yuan-Shin Hwang,Roy Dz-Ching Ju,Jenq-Kuen Lee
Issue Date:December 2012
pp. 2366-2379
Probabilistic pointer analysis (PPA) is a compile-time analysis method that estimates the probability that a points-to relationship will hold at a particular program point. The results are useful for optimizing and parallelizing compilers, which need to qu...
 
Interprocedural Probabilistic Pointer Analysis
Found in: IEEE Transactions on Parallel and Distributed Systems
By Peng-Sheng Chen, Yuan-Shin Hwang, Roy Dz-Ching Ju, Jenq Kuen Lee
Issue Date:October 2004
pp. 893-907
<p><b>Abstract</b>—When performing aggressive optimizations and parallelization to exploit features of advanced architectures, optimizing and parallelizing compilers need to quantitatively assess the profitability of any transformations i...
 
Compiler support for speculative multithreading architecture with probabilistic points-to analysis
Found in: Proceedings of the ninth ACM SIGPLAN symposium on Principles and practice of parallel programming (PPoPP '03)
By Jenq Kuen Lee, Ming-Yu Hung, Peng-Sheng Chen, Roy Dz-Ching Ju, Yuan-Shin Hwang
Issue Date:June 2003
pp. 25-36
Speculative multithreading (SpMT) architecture can exploit thread-level parallelism that cannot be identified statically. Speedup can be obtained by speculatively executing threads in parallel that are extracted from a sequential program. However, performa...
     
 1