LACross: Learning-Based Analytical Cross-Platform Performance and Power Prediction

Zheng, Xinnian; John, Lizy K.; Gerstlauer, Andreas

doi:10.1007/s10766-017-0487-0

Cited by 17 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross platform prediction is used by Zheng et al 8 to show that the performance of a target ARM‐based system can be predicted from a source x86‐based system. They collect performance counters from x86‐based host systems to be used as input features in the training phase.…”

Section: Related Workmentioning

confidence: 99%

“…A LASSO machine learning model was recently proposed to predict the ARM-based target system's performance by collecting performance counters on x86-based systems 7,8 for several MiBench and SD-VBS benchmarks. Similarly, the P4 framework has been proposed 9 for ARM-based systems prediction using a neural network trained using performance counters that identify application phases on the x86-based system for heterogeneous systems.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling

Mankodi

Bhatt

Chaudhury

2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary Selection from several computer systems with different hardware features resulting in different software performance is a critical problem to solve. The problem becomes even more challenging when access to computer systems with different features is difficult. We had proposed a novel solution, “cross performance prediction with scaling,” in our previous work. In the scaling model, we predicted the physical system's runtime using a machine learning model trained only on a performance dataset of simulation‐based systems applying a scaling factor to the predicted runtime. In this article, we propose another novel idea, “cross performance prediction with transfer learning,” that uses transfer learning to solve the same problem. This model predicts the target physical system's performance using a machine learning model trained on a combined performance dataset from simulation‐based systems and an accessible source physical system. We evaluate both the models using several benchmark algorithms from SD‐VBS and MiBench suites. Our scaling model results have achieved a prediction error of 10%–25% for general‐purpose systems, whereas the transfer learning model has higher errors in the range of 50%. We have also developed a method to extract the rules built during the decision tree model's training to predict the runtime.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling

Mankodi

Bhatt

Chaudhury

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Much of the previous work on power modeling and estimation is based on performance counters 1‐3,6‐19 . These counters are used to monitor system components such as CPUs, GPUs, memory, disk, and I/O.…”

Section: Introductionmentioning

confidence: 99%

“…Much of the previous work on power modeling and estimation is based on performance counters. [1][2][3][6][7][8][9][10][11][12][13][14][15][16][17][18][19] These counters are used to monitor system components such as CPUs, GPUs, memory, disk, and I/O. The values of these performance counters are then correlated with the power consumed by each system component to derive a power model for each system component.…”

mentioning

confidence: 99%

Utilizing ensemble learning for performance and power modeling and improvement of parallel cancer deep learning CANDLE benchmarks

Taylor

2021

Concurrency and Computation

View full text Add to dashboard Cite

Machine learning (ML) continues to grow in importance across nearly all domains in modeling to learn from data. Often a tradeoff exists between a model's ability to minimize bias and variance. In this article, we utilize ensemble learning to combine linear, nonlinear, and tree-/rule-based ML methods to cope with the bias-variance tradeoff and result in more accurate models. We use the datasets collected for two parallel cancer deep learning CANDLE benchmarks, NT3 and P1B2, to build performance and power models based on hardware performance counters using single-object and multiple-objects ensemble learning to identify the most important counters for improvement on the Cray XC40 Theta at Argonne National Laboratory. Based on the insights from these models, we improve the performance and energy of P1B2 and NT3 by optimizing the deep learning environments TensorFlow, Keras, Horovod, and Python under the huge page size of 8 MB. Experimental results show that ensemble learning not only produces more accurate models but also provides more robust performance counter ranking. We achieve up to 61.15% performance improvement and up to 62.58% energy saving for P1B2 and up to 55.81% performance improvement and up to 52.60% energy saving for NT3 on up to 24,576 cores.

show abstract

“…Much of the previous work on power modeling and estimation is based on performance counters [7], [9], [17], [25], [45], [1], [5], [15], [28], [29], [35], [42], [46], [51], [53], [54], [57]. These counters are used to monitor system components such as CPU, GPU, memory, disk, and I/O.…”

Section: Introductionmentioning

confidence: 99%

Performance, Energy, and Scalability Analysis and Improvement of Parallel Cancer Deep Learning CANDLE Benchmarks

Taylor

Wozniak

et al. 2019

Proceedings of the 48th International Conference on Parallel Processing

View full text Add to dashboard Cite

Machine learning (ML) continues to grow in importance across nearly all domains and is a natural tool in modeling to learn from data. Often a tradeoff exists between a model's ability to minimize bias and variance. In this paper, we utilize ensemble learning to combine linear, nonlinear, and tree-/rule-based ML methods to cope with the bias-variance tradeoff and result in more accurate models. Hardware performance counter values are correlated with properties of applications that impact performance and power on the underlying system. We use the datasets collected for two parallel cancer deep learning CANDLE benchmarks, NT3 (weak scaling) and P1B2 (strong scaling), to build performance and power models based on hardware performance counters using single-object and multiple-objects ensemble learning to identify the most important counters for improvement. Based on the insights from these models, we improve the performance and energy of P1B2 and NT3 by optimizing the deep learning environments TensorFlow, Keras, Horovod, and Python under the huge page size of 8 MB on the Cray XC40 Theta at Argonne National Laboratory. Experimental results show that ensemble learning not only produces more accurate models but also provides more robust performance counter ranking. We achieve up to 61.15% performance improvement and up to 62.58% energy saving for P1B2 and up to 55.81% performance improvement and up to 52.60% energy saving for NT3 on up to 24,576 cores.

show abstract

LACross: Learning-Based Analytical Cross-Platform Performance and Power Prediction

Cited by 17 publications

References 31 publications

Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling

Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling

Utilizing ensemble learning for performance and power modeling and improvement of parallel cancer deep learning CANDLE benchmarks

Performance, Energy, and Scalability Analysis and Improvement of Parallel Cancer Deep Learning CANDLE Benchmarks

Contact Info

Product

Resources

About