-
公开(公告)号:WO2022203829A1
公开(公告)日:2022-09-29
申请号:PCT/US2022/018593
申请日:2022-03-03
摘要: An automated system for translating source code written in one programming language into a different programming language utilizes a neural transformer with attention trained on semi-supervised data. The model is jointly pre-trained with a masked language model objective and an autoregressive objective on a large unsupervised source code corpus to learn to comprehend the syntactic structure and semantics of source code. The pre-trained model is then fine-tuned with a token-type prediction objective and an autoregressive objective on supervised translation tasks and data augmented tasks to learn to translate source code from one programming language into a different programming language.
-
公开(公告)号:WO2023086158A1
公开(公告)日:2023-05-19
申请号:PCT/US2022/043561
申请日:2022-09-15
发明人: GARG, Spandan , ZILOUCHIAN MOGHADDAM, Roshanak , HARRINGTON, Paul Sean , WU, Chen , SUNDARESAN, Neelakantan
摘要: A computer implemented method includes accessing performance trace data for executed code of multiple services. Symbols corresponding to functions of the executed code are identified. First sequences of functions from the identified symbols are identified and a first performance threshold for each identified first sequence of functions is computed. The method includes receiving an incoming performance trace, detecting second sequences of functions from the incoming performance trace, identifying second sequences equivalent to the first sequences, and comparing performance of the identified second sequences to the first performance threshold for each of the equivalent first sequences to identify second sequences as comprising a performance bottleneck.
-
公开(公告)号:WO2022265737A1
公开(公告)日:2022-12-22
申请号:PCT/US2022/028660
申请日:2022-05-11
发明人: CLEMENT, Colin Bruce , DENG, Shao Kun , DRAIN, Dawn , SUNDARESAN, Neelakantan , SVYATKOVSKIY, Alexey , TIAN, Yiding , TUFANO, Michele , WANG, Paul An-Chieh , WU, Chen , YOU, Dongjiang
摘要: A cloud platform includes several web services that facilitate the automated tuning and deployment of pre-trained deep learning models configured for software engineering tasks. The automated tuning and deployment allow a developer to fine-tune a pre-existing model without having access to the parameters of the pre-existing and the fine-tuned model in a manner that does not require user management input. The cloud platform provides a set of files for each pre-trained models used to automatically build a fine-tuning infrastructure to fine-tune a model and a deployment infrastructure that deploys the fine-tuned model without requiring user input.
-
公开(公告)号:WO2022154872A1
公开(公告)日:2022-07-21
申请号:PCT/US2021/061054
申请日:2021-11-30
IPC分类号: G06F8/33
摘要: An automated system for detecting performance bugs in a program and for providing code recommendations to improve the performance of the program generates a code recommendation table from performance-related pull requests. The performance-related pull requests are identified in part from a classifier trained on semi-supervised data. A code recommendation table is generated from performance-related pull requests and is searched for similarly-improved code based on a set of difference features that includes structural and performance features of the before-code of a pull request that is not in the after-code.
-
公开(公告)号:WO2022164668A1
公开(公告)日:2022-08-04
申请号:PCT/US2022/012694
申请日:2022-01-18
发明人: BRESLAV, Mikhail , CLEMENT, Colin Bruce , DRAIN, Dawn , HU, Changran , SUNDARESAN, Neelakantan , WU, Chen
摘要: A source code generation system uses a neural transformer model with attention to predict candidate method bodies given a method docstring, method signature, and one or more method templates. The method templates are derived from intent-snippet pairs from StackOverflow question/answer pairs or template methods from GitHub. Joint embeddings are generated for the method bodies of the method templates and associated method docstrings for quick retrieval. A code completion system uses the source code generation system to generate candidate method bodies to complete a method signature and/or method docstring using the method templates.
-
公开(公告)号:WO2023003636A1
公开(公告)日:2023-01-26
申请号:PCT/US2022/031701
申请日:2022-06-01
摘要: A distillation system extracts knowledge from a large pre-trained sequence-to-sequence neural transformer model into a smaller bi-encoder. The pre-trained sequence-to-sequence neural transformer model is trained to translate data from a first domain into a second domain on a large corpus. A teacher model is generated from the pre-trained model by fine-tuning the pre-trained neural transformer model on a smaller translation task with true translation pairs. The fine-tuned model is then used to generate augmented data values which are used with the true translation pairs to train the bi-encoder. The bi-encoder is used for perform cross-domain searches.
-
-
-
-
-