Filters








158,055 Hits in 5.0 sec

Dynamic feature selection for hardware prediction

Alan Fern, Robert Givan, Babak Falsafi, T.N. Vijaykumar
2006 Journal of systems architecture  
To avoid exponential growth we introduce the idea of "dynamic feature selection" for building hardware predictors that can use a large amount of predictive information.  ...  Based on this idea, we design the dynamic decision tree (DDT) predictor, which exhibits only linear size growth in the number of features.  ...  In this paper we presented a novel framework, dynamic feature selection, for hardware prediction.  ... 
doi:10.1016/j.sysarc.2004.12.007 fatcat:7omfb7tlijcudg7g7lcqzemvay

Low-Overhead Compressibility Prediction for High-Performance Lossless Data Compression

Youngil Kim, Jinwoo Jeong, Wang Kexin, Yong Ho Song, Seungdo Choi, Daeyong Lee, Joonyong Jeong, Jaewook Kwak, Jungkeol Lee, Gyeongyong Lee, Sangjin Lee, Kibin Park
2020 IEEE Access  
ACKNOWLEDGEMENT We are grateful to the anonymous reviewers for their valuable feedback and comments.  ...  Additionally, Table 3 also shows the amount of hardware resources consumed by each hardware module for feature-extraction and compressibility prediction, respectively.  ...  The dynamic Huffman area is the remaining area excluding the other two areas. 2) Feature extraction The DEFLATE compression system extracts the features that are necessary for compressibility prediction  ... 
doi:10.1109/access.2020.2975929 fatcat:skznkvmg4jgnpnd2gvwgq2sp4q

Celebrating diversity: a mixture of experts approach for runtime mapping in dynamic environments

Murali Krishna Emani, Michael O'Boyle
2015 Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation - PLDI 2015  
This paper focuses on selecting the best number of threads for a parallel application in dynamic environments. It develops a new scheme based on a mixture of experts approach.  ...  Matching program parallelism to platform parallelism using thread selection is difficult when the environment and available resources dynamically change.  ...  Features While predictive modeling is relatively automated, it critically relies on good feature selection.  ... 
doi:10.1145/2737924.2737999 dblp:conf/pldi/EmaniO15 fatcat:fjy27us6xfey5jjozwlofmiwc4

Using Grammatical Evolution Techniques to Model the Dynamic Power Consumption of Enterprise Servers

Juan C. Salinas Hilburg, Marina Zapater, Jose L. Risco Martin, Jose M. Moya, Jose L. Rodrigo
2015 2015 Ninth International Conference on Complex, Intelligent, and Software Intensive Systems  
This paper proposes the use of Evolutionary Computation to obtain a model for server dynamic power consumption.  ...  With our generated models, we are able to predict the overall server power consumption for arbitrary workloads, outperforming previous approaches in the state-of-the-art.  ...  for power prediction.  ... 
doi:10.1109/cisis.2015.16 dblp:conf/cisis/HilburgZRMR15 fatcat:i3sar3myyfb7dgox6zenumlw2y

A Study on the Influence of Software and Hardware Features on Program Energy

Ajitha Rajan, Adel Noureddine, Panagiotis Stratis
2016 Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement - ESEM '16  
We then performed statistical feature selection to extract the features relevant to energy consumption. We discuss potential optimisations for the selected features.  ...  We collected over 100 hardware and software metrics, statically and dynamically, using existing tools for program analysis, instrumentation and run time monitoring.  ...  Dynamic Program Features We use the Pin tool [28] (version 2.14) to collect 42 dynamic program features.  ... 
doi:10.1145/2961111.2962593 dblp:conf/esem/RajanNS16 fatcat:gyslcrv4tjeklbxtucmxfl5kcu

Evaluation of the Gini-index for Studying Branch Prediction Features

Veerle Desmet
2004 AIP Conference Proceedings  
In this paper we evaluate the predictive power of different branch prediction features using the metric Gini-index, which is used as feature selection measure in the construction of decision trees.  ...  We show that the Gini-index is a good metric for comparing branch prediction features.  ...  Fern et al. propose in [10] a prediction mechanism that dynamically selects the most predictive features from a large feature set.  ... 
doi:10.1063/1.1787340 fatcat:4t7zgd2mn5cc5iy5omu4s2qaqa

Identifying SDC-Causing Instructions Based on Random Forests Algorithm

2019 KSII Transactions on Internet and Information Systems  
SDCPredictor identifies SDC-causing Instructions depending on analyzing the static and dynamic features of instructions rather than fault injections.  ...  The experimental results demonstrate that SDCPredictor is highly accurate in predicting the SDCs proneness.  ...  For SCDPredictor and SDCAuto, most of the times are spent on the feature extraction, SDC proneness prediction and selection algorithm.  ... 
doi:10.3837/tiis.2019.03.025 fatcat:pa4r62bwaze4nj2ygl3ujgz5fe

A Study of the Performance Potential for Dynamic Instruction Hints Selection [chapter]

Rao Fu, Jiwei Lu, Antonia Zhai, Wei-Chung Hsu
2006 Lecture Notes in Computer Science  
instruction hints dynamically.  ...  Instruction hints have become an important way to communicate compile-time information to the hardware.  ...  The authors want to thank Abhinav Das and Jinpyo Kim for their suggestions and help. We also thank all of the anonymous reviewers for their valuable comments.  ... 
doi:10.1007/11859802_7 fatcat:tkw4ji4j5zca3j2otayn4ueugm

Value speculation scheduling for high performance processors

Chao-Ying Fu, Matthew D. Jennings, Sergei Y. Larin, Thomas M. Conte
1998 SIGPLAN notices  
Prediction hardware is used to provide value predictions for allowing the execution of speculated instructions to continue.  ...  Several hardware based value predictor designs have been proposed to exploit this predictability by eliminating flow dependencies for highly predictable values.  ...  We also thank the anonymous reviewers for their valuable comments.  ... 
doi:10.1145/291006.291058 fatcat:lwcnt6i2j5apndnuy3tk74nypi

Value speculation scheduling for high performance processors

Chao-Ying Fu, Matthew D. Jennings, Sergei Y. Larin, Thomas M. Conte
1998 Proceedings of the eighth international conference on Architectural support for programming languages and operating systems - ASPLOS-VIII  
Prediction hardware is used to provide value predictions for allowing the execution of speculated instructions to continue.  ...  Several hardware based value predictor designs have been proposed to exploit this predictability by eliminating flow dependencies for highly predictable values.  ...  We also thank the anonymous reviewers for their valuable comments.  ... 
doi:10.1145/291069.291058 dblp:conf/asplos/FuJLC98 fatcat:eccvkufeuff2zcbtvtyu3e5anm

Accurate phase-level cross-platform power and performance estimation

Xinnian Zheng, Lizy K. John, Andreas Gerstlauer
2016 Proceedings of the 53rd Annual Design Automation Conference on - DAC '16  
Results show on average over 97% prediction accuracy for predicting both fine-grain performance and power traces at speeds of over 500 MIPS.  ...  Fast and accurate performance and power prediction is a key challenge in co-development of hardware and software.  ...  We would also like to thank the anonymous reviewers for their helpful suggestions to improve the paper. References  ... 
doi:10.1145/2897937.2897977 dblp:conf/dac/ZhengJG16 fatcat:op7l44p7prardjw3cxkwmmo4em

Smart, adaptive mapping of parallelism in the presence of external workload

M. K. Emani, Zheng Wang, M. F. P. O'Boyle
2013 Proceedings of the 2013 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)  
It shows how static code features can be used along with dynamic runtime features for optimal thread number prediction.  ...  Figure 5 . 5 : 55 Impact of selected features on the predictive models.  ... 
doi:10.1109/cgo.2013.6495010 dblp:conf/cgo/EmaniWO13 fatcat:ebxa4mr5qzcp5ifbiix23eyc4u

Guest Editors' Introduction to the Special Issue on Hardware Security

Amro Awad, Rujia Wang
2020 IEEE transactions on computers  
The first paper, titled OPTIMUS: A Security-Centric Dynamic Hardware Partitioning Scheme for Processors that Prevent Microarchitecture State Attacks, proposes a novel architecture that allows dynamic partitioning  ...  One of the accepted papers, titled Understanding Selective Delay as a Method for Efficient Secure Speculative Execution, explores using selective delays as a way to defend against speculative execution  ...  The first paper, titled OPTIMUS: A Security-Centric Dynamic Hardware Partitioning Scheme for Processors that Prevent Microarchitecture State Attacks, proposes a novel architecture that allows dynamic partitioning  ... 
doi:10.1109/tc.2020.3021223 fatcat:nz37oxlhovahlbggly7iwpl22i

Improving the performance of object-oriented languages with dynamic predication of indirect jumps

Jose A. Joao, Onur Mutlu, Hyesoon Kim, Rishi Agarwal, Yale N. Patt
2008 Proceedings of the 13th international conference on Architectural support for programming languages and operating systems - ASPLOS XIII  
by 24.8% Provides better performance and energy-efficiency than three indirect jump predictors Incurs low hardware cost (3.6KB) if dynamic predication is already used for conditional branches 18 Sensitivity  ...  Harmful (Correct Prediction, Correct DIP Target) Useful (Mispredicted, Correct DIP Target) Correctly predicted BTB correct Additional Evaluation (in paper) Static vs. dynamic target selection policies  ... 
doi:10.1145/1346281.1346293 dblp:conf/asplos/JoaoMKAP08 fatcat:y55ufotd5naklbkhck66p7aici

Malware-aware processors: A framework for efficient online malware detection

Meltem Ozsoy, Caleb Donovick, Iakov Gorelik, Nael Abu-Ghazaleh, Dmitry Ponomarev
2015 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)  
Our work improves on the state of the art in the following ways: (1) We define and explore the use of sub-semantic features for online detection of malware. (2) We explore hardware implementations and  ...  Therefore, software detectors are applied selectively and at a low frequency, creating opportunities for malware to remain undetected.  ...  Logistic Regression Prediction Unit We implemented the logistic regression prediction unit using INS2 feature. The feature vector has 50 elements to represent selected opcodes.  ... 
doi:10.1109/hpca.2015.7056070 dblp:conf/hpca/OzsoyDGAP15 fatcat:h3sbyp2uvrcaphrkiwcpdh6xlu
« Previous Showing results 1 — 15 out of 158,055 results