A Bayesian network approach for compiler auto-tuning for embedded processors

Ashouri, Amir H.; Mariani, Giovanni; Palermo, Gianluca; Silvano, Cristina

doi:10.1109/estimedia.2014.6962349

Cited by 27 publications

(27 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For application a i being optimized, n shows the number of optimizations under analysis [15]. The selection problem's optimization space has an exponential space as its upper-bound.…”

Section: 31mentioning

confidence: 99%

“…where n shows the number of optimizations under analysis [15,18]. However, the mentioned bound is a simpli ed phase-ordering problem having a xed length optimization sequence length and no repetitive application of optimizations.…”

Section: 31mentioning

confidence: 99%

“…Principal Component Analysis (PCA) [3,15,18,19,21,28,29,61,78,142,198,199,202,248] Factor Analysis (FA) [21] 3.2.2 Architecture Independent Characterization. The information collected from a dynamic characterization, referred to as feature vector, is a compact summary of an application's dynamic behavior at run-time.…”

Section: Classi Cation Referencesmentioning

confidence: 99%

“…Reducing the input feature space for a machine learning algorithm may yield better learning results; however, the type of feature reduction used can be an important factor itself [3,21]. For instance, PCA was used in the original work proposed by Ashouri et al [15], but later the authors revised the model by exploiting EFA and observed clear bene ts [21]. We elaborate more on these methods in latter sections of the survey.…”

Section: Dimension Reduction Techniquesmentioning

confidence: 99%

“…Bayesian Net [15,21] Linear Models / SVMs [18,19,21,71,199,201,217,237] Decision Trees / Random Forests [41,77,92,99,99,101,105,152,162,166,178,200,253] Graph Kernels [138,170,171,198] Others [3, 11, 16, 19, 21, 21, 28, 28, 50-52, 52, 69, 70, 72, 78, 79, 83, 91, 92, 96, 96, 98, 100, 101, 105, 107, 108, 116, 132, 136, 151, 152, 155, 162, 163, 183, 183, 197, 199, 201, 202, 206, 217, 221, 235, 235, 236, 236, 240, 248, 250, 253, 253, 259, 259] Unsupervised Clustering [19,29,170,171,212,248] Evolutionary Algorithms (GAs,NEAT,NN) [3, 6, 50, 54, 66, 67, 69, 70, 73, 78, 82, 110, 110, 122, 123, 142, 146-148, 151, 151, 152, 152, 153, 155, 157, 162, 171, 184, 186, 198, 202, 205, 209, 212, 235, 235, 236, 238, 244, 259] Reinforcement Learning [66,172,173]…”

Section: Classi Cation Referencesmentioning

confidence: 99%

See 4 more Smart Citations

A Survey on Compiler Autotuning using Machine Learning

et al. 2018

Self Cite

View full text Add to dashboard Cite

Since the mid-1990s, researchers have been trying to use machine-learning based approaches to solve a number of di erent compiler optimization problems. These techniques primarily enhance the quality of the obtained results and, more importantly, make it feasible to tackle two main compiler optimization problems: optimization selection (choosing which optimizations to apply) and phase-ordering (choosing the order of applying optimizations). The compiler optimization space continues to grow due to the advancement of applications, increasing number of compiler optimizations, and new target architectures. Generic optimization passes in compilers cannot fully leverage newly introduced optimizations and, therefore, cannot keep up with the pace of increasing options. This survey summarizes and classi es the recent advances in using machine learning for the compiler optimization eld, particularly on the two major problems of (1) selecting the best optimizations, and (2) the phase-ordering of optimizations. The survey highlights the approaches taken so far, the obtained results, the ne-grain classi cation among di erent approaches and nally, the in uential papers of the eld. A. H. Ashouri et al.unrolling, register allocation, etc.) could substantially bene t several performance metrics. Depending on the objectives, these metrics could be execution time, code size, or power consumption. A holistic exploration approach to trade-o these metrics also represents a challenging problem [193].Autotuning [35,256] addresses automatic code-generation and optimization by using di erent scenarios and architectures. It constructs techniques for automatic optimization of di erent parameters to maximize or minimize the satis ability of an objective function. Historically, several optimizations were done in the backend where scheduling, resource-allocation and code-generation are done [56,93]. The constraints and resources form a linear system (ILP) which needs to be solved. Recently, researchers have shown increased e ort in introducing front-end and IR-optimizations. Two observations support this claim: (1) the complexity of a backend compiler requires exclusive knowledge strictly by the compiler designers, and (2) lower overheads with external compiler modi cation compared with back-end modi cations. The IR-optimization process normally involves ne-tuning compiler optimization parameters by a multi-objective optimization formulation which can be harder to explore. Nonetheless, each approach has its bene ts and drawbacks and are subject to analysis under their scope.A major challenge in choosing the right set of compiler optimizations is the fact that these code optimizations are programming language, application, and architecture dependent. Additionally, the word optimization is a misnomer -there is no guarantee the transformed code will perform better than the original version. In fact, aggressive optimizations can even degrade the performance of the code to which they are applied [251]. Understanding the behavior of the optimization...

show abstract

“…For application a i being optimized, n shows the number of optimizations under analysis [15]. The selection problem's optimization space has an exponential space as its upper-bound.…”

Section: 31mentioning

confidence: 99%

Section: 31mentioning

confidence: 99%

Section: Classi Cation Referencesmentioning

confidence: 99%

Section: Dimension Reduction Techniquesmentioning

confidence: 99%

Section: Classi Cation Referencesmentioning

confidence: 99%

See 3 more Smart Citations

A Survey on Compiler Autotuning using Machine Learning

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

Smart selection of optimizations in dynamic compilers

Rosário

Silva

Camacho

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary Dynamic compilers perform compilation and generation of target code during runtime, implying that the compilation time is added into the program runtime. Thus, to build a high‐performing dynamic compilation system, it is crucial to be able to generate high‐quality code and, at the same time, have a small compilation cost. In this article, we present an approach that uses machine learning to select sequences of optimization for dynamic compilation that considers both code quality and compilation overhead. Our approach starts by training a model, offline, with a knowledge bank of those sequences with low overhead and high‐quality code generation capability using a genetic heuristic. Then, this bank is used to guide the smart selection of optimizations sequences for the compilation of code fragments during the emulation of an application. We evaluate the proposed strategy in two LLVM‐based dynamic binary translators, namely OI‐DBT and HQEMU, and show that these two translators can achieve average speedups of 1.26x and 1.15x in MiBench and Spec Cpu benchmarks, respectively.

show abstract

Fast selection of compiler optimizations using performance prediction with graph neural networks

Rosário

Silva

Zanella

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Tuning application performance on modern computing infrastructures involves choices in a vast design space as modern computing architectures can have several complex structures impacting performance. Moreover, different applications use these structures in different ways, leading to a challenging performance function. Consequently, it is hard for compilers or experts to find optimal compilation parameters for an application that maximizes such performance function. One approach to tackle this problem is to evaluate many possible optimization plans and select the best among them. However, executing an application to measure its performance for every plan can be very expensive. To tackle this problem, previous work has investigated the use of Machine Learning techniques to predict the performance of the applications without executing them quickly. In this work, we evaluate the use of graph neural networks (GNN) to make fast predictions without executing the application to guide the selection of good optimization sequences. We propose a GNN architecture to make such predictions. We train and test it using 30 thousand different compilation plans applied to 300 different applications, using ARM64 and LLVM IR code representations as input. Our results indicate that the control and data flow graph can then learn features from the control and data flow graph to outperform nongraph‐aware Machine Learning models. Our GNN architecture achieved 91% accuracy in our dataset compared to 79% when using a nongraph‐aware architecture–taking only 16ms to predict a given input. If the application been optimized took an average of 10 s to execute, and we evaluated 1000 optimization sequences, it would take almost 9 h to assess all pairs, but only 16 s with our GNN .

show abstract

A Bayesian network approach for compiler auto-tuning for embedded processors

Cited by 27 publications

References 19 publications

A Survey on Compiler Autotuning using Machine Learning

A Survey on Compiler Autotuning using Machine Learning

Smart selection of optimizations in dynamic compilers

Fast selection of compiler optimizations using performance prediction with graph neural networks

Contact Info

Product

Resources

About