
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
Chaoying Fu, Jill T. Bodine, Thomas M. Conte, "Modeling Value Speculation: An Optimal Edge Selection Problem," IEEE Transactions on Computers, vol. 52, no. 3, pp. 277292, March, 2003.  
BibTex  x  
@article{ 10.1109/TC.2003.1183944, author = {Chaoying Fu and Jill T. Bodine and Thomas M. Conte}, title = {Modeling Value Speculation: An Optimal Edge Selection Problem}, journal ={IEEE Transactions on Computers}, volume = {52}, number = {3}, issn = {00189340}, year = {2003}, pages = {277292}, doi = {http://doi.ieeecomputersociety.org/10.1109/TC.2003.1183944}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  Modeling Value Speculation: An Optimal Edge Selection Problem IS  3 SN  00189340 SP277 EP292 EPD  277292 A1  Chaoying Fu, A1  Jill T. Bodine, A1  Thomas M. Conte, PY  2003 KW  Value prediction KW  value speculation KW  optimal edge selection KW  data dependence graph KW  critical path reduction. VL  52 JA  IEEE Transactions on Computers ER   
Abstract—Techniques for value speculation have been proposed for dynamically scheduled and statically scheduled machines to increase instructionlevel parallelism (ILP) by breaking flow (true) dependences and allowing valuedependent operations to be executed speculatively. The effectiveness of value speculation depends upon the ability to select and break dependences to shorten overall execution time, while encountering penalties for value misprediction. To understand and improve the techniques for value speculation, we model value speculation as an optimal edge selection problem. The optimal edge selection problem involves finding a minimal set of edges (dependences) to break in a data dependence graph that achieves maximal benefits from value speculation, while taking the penalties for value misprediction into account. Based on three properties observed from the optimal edge selection problem, an efficient optimal edge selection algorithm is designed. From the experimental results of running the optimal edge selection algorithm for the 20 most heavily executed paths selected from each SPECint95 benchmark, several insights are shown. The average critical path reduction is 9.61 percent on an average and 25.57 percent at its maximum. Surprisingly, 66 percent of the edges selected by the optimal algorithm have value prediction accuracies over 99 percent. Moreover, most of the selected edges cross the middle of the data dependence graph. The selected producer operations thereby tend to reside in the upper portion of the data dependence graph, while the selected consumer operations appear toward the lower portion.
[1] M.H. Lipasti, C.B. Wilkerson, and J.P. Shen, "Value Locality and Load Value Prediction," Proc. Seventh Int'l Conf. on Architectural Support for Programming Languages and Operating Systems, ACM Press, New York, 1996, pp. 138147.
[2] M.H. Lipasti and J.P. Shen, "Exceeding the DataFlow Limit Via Value Prediction," Proc. 29th Ann. ACM/IEEE Int'l Symp. on Microarchitecture, IEEE CS Press, Los Alamitos, Calif., 1996, pp. 226237.
[3] F. Gabbay and A. Mendelson, Can Program Profiling Support Value Prediction? Proc. 30th Int'l Symp. Microarchitecture, pp. 270280, Dec. 1997.
[4] F. Gabbay and A. Mendelson, The Effect of Instruction Fetch Bandwidth on Value Prediction Proc. 25th Int'l Symp. Computer Architecture, pp. 272281, 1998.
[5] F. Gabbay, “Speculative Execution based on Value Prediction,” TR #1080, Electrical Eng. Dept., Technion, Nov. 1996.
[6] B. Calder, G. Reinman, and D. Tullsen, Selective Value Prediction Proc. 26th Int'l Symp. Computer Architecture, 1999.
[7] E. Tune, D. Liang, D. Tullsen, and B. Calder, “Dynamic Prediction of Critical Path Instructions,” Proc. Seventh Int'l Symp. HighPerformance Computer Architecture, Jan. 2001.
[8] Y. Sazeides and J. Smith, “The Predictability of Data Values,” Proc. 30th Ann. Int'l Symp. Microarchitecture (MICRO '30), pp. 248258, Dec. 1997.
[9] Y. Sazeides and J.E. Smith, “Implementation of Context Based Value Predictors,” Technical Report ECE978, Univ. of WisconsinMadison, Dec. 1997.
[10] R. Sathe and M. Franklin, “Available Parallelism with Data Value Prediction,” Proc. Fifth Int'l Conf. High Performance Computing (HiPC98), pp. 194201, Apr. 1998.
[11] W.A. Havanki, S. Banerjia, and T.M. Conte, “Treegion Scheduling for WideIssue Processors,” Proc. Fourth Int'l Symp. HighPerformance Computer Architecture, Feb. 1998.
[12] W.W. Hwu, S.A. Mahlke, W.Y. Chen, P.P. Chang, N.J. Warter, R.A. Bringmann, R.G. Ouellette, R.E. Hank, T. Kiyohara, G.E. Haab, J.G. Holm,, and D.M. Lavery, ``The Superblock: An Effective Technique for VLIW and Superscalar Compilation,'' J. Supercomputing, vol. 7, pp. 950, 1993.
[13] S. Aditya, V. Kathail, and B.R. Rau, “Elcor's Machine Description System: Version 3.0,” HewlettPackard Laboratories Technical Report HPL98128, Oct. 1998.
[14] V. Kathail, M. Schlansker, and B.R. Rau, “HPLPD Architecture Specification: Version 1.1,” HewlettPackard Laboratories Technical Report HPL9380(R.1), Feb. 2000.
[15] T.H. Cormen,C.E. Leiserson, and R.L. Rivest,Introduction to Algorithms.Cambridge, Mass.: MIT Press/McGrawHill, 1990.
[16] C. Fu, M.D. Jennings, S.Y. Larin, and T.M. Conte, “Value Speculation Scheduling for High Performance Processors,” Proc. Eighth Int'l Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOSVIII), Oct. 1998.
[17] C. Fu, M.D. Jennings, S.Y. Larin, and T.M. Conte, “SoftwareOnly Value Speculation Scheduling,” technical report, Dept. of Electrical and Computer Eng., North Carolina State Univ., June 1998.
[18] C. Fu and T.M. Conte, “Value Speculation Mechanisms for EPIC Architectures,” technical report, Dept. of Electrical and Computer Eng., North Carolina State Univ., Oct. 1998.
[19] T. Nakra, R. Gupta, and M. Soffa, “Value Prediction in VLIW Machine,” Proc. 26th Int'l Symp. Computer Architecture, May 1999.
[20] E. Larson and T. Austin, Compiler Controlled Value Prediction Using Branch Predictor Based Confidence Proc. 33rd Ann. ACM/IEEE Int'l Symp. Microarchitecture, Dec. 2000.
[21] K. Wang and M. Franklin, Highly Accurate Data Value Prediction Using Hybrid Predictors Proc. 30th Int'l Symp. Microarchitecture, 1997.
[22] B. Calder, P. Feller, and A. Eustace, “Value Profiling,” Proc. 30th Ann. ACM/IEEE Int'l Symp. Microarchitecture, Dec. 1997.
[23] C. Fu, “CompilerDriven Value Speculation Scheduling,” PhD thesis, Dept. of Electrical and Computer Eng., North Carolina State Univ., 2000.
[24] B. Fields, S. Rubin, and R. Bodik, “Focusing Processor Policies via CriticalPath Prediction,” Proc. 28th Int'l Symp. Computer Architecture, June 2001.
[25] E. Tune, D. Liang, D. Tullsen, and B. Calder, “Dynamic Prediction of Critical Path Instructions,” Proc. Seventh Int'l Symp. HighPerformance Computer Architecture, Jan. 2001.