IR2V EC

Abstract

We propose IR2V EC , a Concise and Scalable encoding infrastructure to represent programs as a distributed embedding in continuous space. This distributed embedding is obtained by combining representation learning methods with flow information to capture the syntax as well as the semantics of the input programs. As our infrastructure is based on the Intermediate Representation (IR) of the source code, obtained embeddings are both language and machine independent. The entities of the IR are modeled as relationships, and their representations are learned to form a seed embedding vocabulary . Using this infrastructure, we propose two incremental encodings: Symbolic and Flow-Aware . Symbolic encodings are obtained from the seed embedding vocabulary , and Flow-Aware encodings are obtained by augmenting the Symbolic encodings with the flow information. We show the effectiveness of our methodology on two optimization tasks (Heterogeneous device mapping and Thread coarsening). Our way of representing the programs enables us to use non-sequential models resulting in orders of magnitude of faster training time. Both the encodings generated by IR2V EC outperform the existing methods in both the tasks, even while using simple machine learning models. In particular, our results improve or match the state-of-the-art speedup in 11/14 benchmark-suites in the device mapping task across two platforms and 53/68 benchmarks in the thread coarsening task across four different platforms. When compared to the other methods, our embeddings are more scalable , is non-data-hungry , and has better Out-Of-Vocabulary (OOV) characteristics .

Optimizing performance and energy across problem sizes through a search space exploration and machine learning

“…Machine Learning models. We also note that more or less computation-intensive ML models are used for prediction, ranging from simple decision trees or support vector machine [39], [48], [49], to complex deep learning methods [41], [45]. Multiple models can also be considered as illustrated by Roy et al [38].…”

DFSGraph: Data Flow Semantic Model for Intermediate Representation Programs Based on Graph Network

“…They can match or even surpass advanced methods using only simple LSTM [21] and pre-trained embeddings. Venkatakeerthy et al [22] provided IR2Vec, a concise and scalable encoding infrastructure to represent programs as distributed embeddings in continuous space. This method takes symbolic and flow-aware embeddings to construct LLVM Entities and map them to real-valued distributed embeddings.…”

AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection

“…One solution is representing code in different languages with a uniform compiler-generated intermediate representation (IR). The model could be trained on IR (Ben-Nun, Jakobovits, and Hoefler 2018;VenkataKeerthy et al 2020) rather than on the source code, allowing it to learn common patterns across different languages. However, obtaining IR for different programming languages requires intensive domain expertise and engineering efforts to fix compilation errors, making it infeasible for language extension.…”