B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zoren. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188--222, January 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....The prediction can be derived from the structure of the branch itself, e.g. the backwards taken forwards not taken approach of the Alpha AXP 21064, or encoded into the branch instruction itself as a bias bit, as in the IA 64 instruction set. The compiler, through profiling or static heuristics [6, 11], can provide hints to 17 the microarchitecture about the likely direction of the branch. Given enough state, dynamic branch predictors are more accurate than static branch predictors, since dynamic predictors take into account changing conditions at run time. 2.3.6 Branch Predictors in Current ....

....decision trees. In this section, we review other work related to branch prediction and machine learning. 8.3.1 Neural Networks Neural networks have been used for doing branch prediction before, but in a quite different context. Neural networks have been used to perform static branch prediction [11]. The likely branch direction of a static branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [6, 11] Our ....

[Article contains additional citation context not shown here]

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....several computer architecture applications. which allows us to get simulated IPC results from SimpleScalar [3] We discuss the impact of this methodological change in Section 6.1. Static branch prediction with neural networks. Neural networks have been used to perform static branch prediction [4], where the likely direction of a branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 4] Static branch ....

....branch prediction [4] where the likely direction of a branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 4]. Static branch prediction performs worse than existing dynamic techniques, but can be useful for performing static compiler optimizations and providing extra information to dynamic branch predictors such as the agree predictor [28] Branch prediction and genetic algorithms. Neural networks are ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....The prediction can be derived from the structure of the branch itself, e.g. the backwards taken forwards not taken approach of the Alpha AXP 21064, or encoded into the branch instruction itself as a bias bit, as in the IA 64 instruction set. The compiler, through profiling or static heuristics [6, 11], can provide hints to 17 the microarchitecture about the likely direction of the branch. Given enough state, dynamic branch predictors are more accurate than static branch predictors, since dynamic predictors take into account changing conditions at run time. 2.3.6 Branch Predictors in Current ....

....decision trees. In this section, we review other work related to branch prediction and machine learning. 8.3.1 Neural Networks Neural networks have been used for doing branch prediction before, but in a quite different context. Neural networks have been used to perform static branch prediction [11]. The likely branch direction of a static branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [6, 11] Our ....

[Article contains additional citation context not shown here]

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....several computer architecture applications. which allows us to get simulated IPC results from SimpleScalar [3] We discuss the impact of this methodological change in Section 6.1. Static branch prediction with neural networks. Neural networks have been used to perform static branch prediction [4], where the likely direction of a branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 4] Static branch ....

....branch prediction [4] where the likely direction of a branch is predicted at compile time by supplying program features, such as control flow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 4]. Static branch prediction performs worse than existing dynamic techniques, but can be useful for performing static compiler optimizations and providing extra information to dynamic branch predictors such as the agree predictor [28] Branch prediction and genetic algorithms. Neural networks are ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....in poor performance. Many techniques have been proposed to reduce aliasing [1, 5, 6] these techniques work well in practice. Neural Networks in Compilers. Static branch prediction uses program features, such as control flow and opcode information, to predict branch behavior at compile time [7, 8]. Calder, et al. have shown how static prediction can achieve misprediction rates of 20 by supplying program information as input to a feed forward neural network trained with back propagation [8] In general, static branch prediction performs worse than dynamic techniques, but can be useful for ....

.... features, such as control flow and opcode information, to predict branch behavior at compile time [7, 8] Calder, et al. have shown how static prediction can achieve misprediction rates of 20 by supplying program information as input to a feed forward neural network trained with back propagation [8]. In general, static branch prediction performs worse than dynamic techniques, but can be useful for performing static compiler optimizations. Neural networks have also been used to schedule straight line machine code in a compiler [9] to increase ILP. Characteristics of Branch Prediction. ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....can be derived from the structure of the branch, e.g. the backwards taken forwards not taken approach of the Alpha AXP 21064, or it can be encoded into the branch instruction as a bias bit, as in the IA 64 and HP PA RISC instruction sets. The compiler, through profiling or static heuristics [5, 7], can provide hints to the microarchitecture about the likely direction of the branch. Static branch predictors are usually less accurate than dynamic branch predictors because they cannot respond to dynamic changes in program behavior. Lindsay explores the use of decision trees to encode ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Trans. on Programming Languages and Systems, 19(1), 1997.

....of heuristics based on studying a corpus of existing programs was described by Calder et al. 4] where neural networks were employed. The work of Ball and Larus was also extended in Wu and Larus [21]by the use of the Dempster Shafer theory of evidence. However, it was shown by Calder et al. in [5] that this method is susceptible to differences in compilers and architectures as it was based on a prior prediction of object code. Recentworks such as that of Grunwald, Lindsay, and Zorn [11] propose the use of static predictors to aid dynamic predictors. This paper proposes a set of ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. (1997) Evidence-Based Static Branch Prediction using Machine Learning. ACM Trans. on Prog. Lang. and Systems. 19-1. 188-222. 18

....The prediction can be derived from the structure of the branch, e.g. the backwards taken forwards not taken approach of the Alpha AXP21064, or encoded into the branch instruction as a bias bit, as in the IA 64 and HP PA RISC instruction sets. The compiler, through profiling or static heuristics [4, 7], can provide hints to the microarchitecture about the likely direction of the branch. Static branch predictors are usually less accurate than dynamic branch predictors because they cannot consider changing conditions at run time. Lindsay explores the use of decision trees to encode ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....using example inputs and outputs. Neural networks have been used for a variety of applications, including pattern recognition, classification [8] and image understanding [15, 13] Static branch prediction with neural networks. Neural networks have been used to perform static branch prediction [3], where the likely direction of a branch is predicted at compile time by supplying program features, such as controlflow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 3] Static branch ....

....branch prediction [3] where the likely direction of a branch is predicted at compile time by supplying program features, such as controlflow and opcode information, as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [1, 3]. Static branch prediction performs worse than existing dynamic techniques, but is useful for performing static compiler optimizations. Branch prediction and genetic algorithms. Neural networks are part of the field of machine learning, which also includes genetic algorithms. Emer and Gloy use ....

Brad Calder, Dirk Grunwald, Michael Jones, Donald Lindsay, James Martin, Michael Mozer, and Benjamin Zorn. Evidencebased static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....in poor performance. Many techniques have been proposed to reduce aliasing [1, 5, 6] these techniques work well in practice. Neural Networks in Compilers. Static branch prediction uses program features, such as control ow and opcode information, to predict branch behavior at compile time [7, 8]. Calder, et al. have shown how static prediction can achieve misprediction rates of 20 by supplying program information as input to a feedforward neural network trained with back propagation [8] In general, static branch prediction performs worse than dynamic techniques, but can be useful for ....

.... features, such as control ow and opcode information, to predict branch behavior at compile time [7, 8] Calder, et al. have shown how static prediction can achieve misprediction rates of 20 by supplying program information as input to a feedforward neural network trained with back propagation [8]. In general, static branch prediction performs worse than dynamic techniques, but can be useful for performing static compiler optimizations. Neural networks have also been used to schedule straight line machine code in a compiler [9] to increase ILP. Characteristics of Branch Prediction. ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

....and outputs. Neural networks have been used for a variety of applications, including pattern recognition, classification [10] image processing, and image understanding [16, 14] Static branch prediction with neural networks. Neural networks have been used to perform static branch prediction [4], where the likely direction of a branch is predicted at compile time by extracting program features such as controlflow and opcode information and supplying these features as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static ....

....the likely direction of a branch is predicted at compile time by extracting program features such as controlflow and opcode information and supplying these features as input to a trained neural network. This approach achieves an 80 correct prediction rate, compared to 75 for static heuristics [2, 4]. Static branch prediction performs worse than existing dynamic techniques, but is useful for performing static compiler optimizations. Branch prediction and genetic algorithms. Neural networks are part of the field of machine learning, which also includes genetic algorithms. Emer and Gloy use ....

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

No context found.

Calder, B., Grunwald, D., Jones, M., Lindsay, D., Martin, J., Mozer, M., Zorn, B.: Evidence-Based Static Branch Prediction Using Machine Learning. In: ACM Transactions on Programming Languages and Systems (ToPLaS-19). Volume 19. (1997)

....themselves, we need only apply our process once. This contrasts with Cooper et al. who use genetic algorithms (GA) to solve compilation phase ordering problems [7] and the COGEN(t) 10] compiler. Calder et al. use supervised learning techniques to fine tune static branch prediction heuris tics [4]. Since our performance criteria is based on execution time it requires an unsupervised technique such as the one we present in this paper. 3 Compilation, Heuristics and Priority Functions Compiler writers have a difficult task. They are expected to create effective and inexpensive solutions to ....

B. Calder, D. G. ad Michael Jones, D. Lindsey, J. Martin, M. Mozer, and B. Zorn. Evidence-Based Static Branch Prediction Using Machine Learning. In A CM Transactions on Programming Languages and Systems (ToPLaS-19), volume 19, 1997.

....themselves, we need only apply our process once. This contrasts with Cooper et al. who use genetic algorithms (GA) to solve compilation phase ordering problems [7] and the COGEN(t) 10] compiler. Calder et al. use supervised learning techniques to ne tune static branch prediction heuristics [4]. Since our performance criteria is based on execution time it requires an unsupervised technique such as the one we present in this paper. 3 Compilation, Heuristics and Priority Functions Compiler writers have a dicult task. They are expected to create e ective and inexpensive solutions to ....

B. Calder, D. G. ad Michael Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-Based Static Branch Prediction Using Machine Learning. In ACM Transactions on Programming Languages and Systems (ToPLaS-19), volume 19, 1997.

....strategies on a daily basis. This makes this approach highly adaptable to Web traffic changes. The prefetching strategies perform with high accuracy and medium coverage. Machine learning has been successfully applied in other research areas such as branch prediction in computer architecture [21]. After providing the background for this work in Chapter 2 we study the resource utilization of Web proxy servers under real workloads (Chapter 3) In Chapter 4 we evaluate approaches to reduce disk I O by adjusting Web proxy server interaction with a standard Unix file system. In Chapter 5 we ....

Brad Calder, Dirk Grunwald, Michael Jones, Donald Lindsay, James Martin, Michael Mozer, and Benjamin Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems , 19(1):188--223, January 1997.

No context found.

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zoren. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188--222, January 1997.

No context found.

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zoren. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188--222, January 1997.

No context found.

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. In ACM Transactions on Programming Languages and Systems, 19(1), 1997.

No context found.

CALDER, B., GRUNWALD, D., JONES, M., LINDSAY, D., MARTIN, J., MOZER, M., AND ZORN, B. 1997. Evidence-based static branch prediction using machine learning. ACM Trans. Program. Lang. Syst. 19, 1, 188--222.

No context found.

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188--222, 1997.

No context found.

Brad Calder, Dirk Grunwald, Michael Jones, Donald Lindsay, James Martin, Michael Mozer, and Benjamin Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188-222, January 1997.

No context found.

B. Calder, D. Grunwald, M. Jones, D. Lindsay, J. Martin, M. Mozer, and B. Zorn. Evidence-based static branch prediction using machine learning. ACM Trans. on Programming Languages and Systems, 19(1), 1997.

No context found.

Calder, B., et al., Evidence-based Static Branch Prediction using Machine Learning. ACM Transactions on Programming Languages and Systems, 19(1), 1997.

No context found.

Brad Calder, Dirk Grunwald, Michael Jones, Donald Lindsay, James Martin, Michael Mozer, and Benjamin Zorn. Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19(1):188-222, January 1997.

No context found.

Calder, Brad, Grunwald, Dirk, Jones, Michael, Lindsay, Donald, Martin, James, Mozer, Michael, and Zorn, Benjamin. Evidence-Based Static Branch Prediction Using Machine Learning. ACM Transactions on Programming Languages and Systems (1997), 188-222.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC