Automating CUDA Synchronization via Program Transformation

Wu, Mingyuan; Zhang, Lingming; Liu, Cong; Tan, Shin Hwei; Zhang, Yuqun

doi:10.1109/ase.2019.00075

Cited by 15 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Towards identifying faults commonly found in CUDA programs, a comprehensive search of related work focused on testing GPU programs [9][10][11][12][13][14][17][18][19][20][21][22]36,37 was conducted. CUDA programming books and Nvidia reference guide 6,7,38,39 were consulted.…”

Section: Cuda Program Faultsmentioning

confidence: 99%

“…It generates test data for a memory access model, simulating the execution environment for detecting race conditions. 18 MutGPU, the only tool developed for CUDA programs for fault-based testing, applies mutation testing and proposes nine mutation operators for CUDA to help improve the quality of the test cases. 37 Such operators were used in the present study to insert faults into the benchmarks.…”

Section: Related Workmentioning

confidence: 99%

“…Alur, Devietti, and Singhania 20 analyzed faults related to the configuration size of thread blocks. GPURepair, 50 AutoSync, 51 and auCS 52 use GPUVerify tool as an oracle to identify possible race conditions and automatically implement barrier synchronization to resolve them.…”

Section: Related Workmentioning

confidence: 99%

“…The literature has progressed regarding the identification of specific faults that may occur in CUDA programs (e.g., race conditions, [9][10][11][12][13][14][15][16][17][18] deadlocks, 17,19 and incorrect size configuration of thread blocks 20 )-several of those studies have employed formal verification or concolic execution techniques to detect them. 16,19,[21][22][23] However, some techniques have been criticized for producing false positives and supporting only small kernels due to the large number of threads expected to run on GPUs.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Structural testing for CUDA programming model

Luz,

Souza,

Souza

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryGraphic processors offer an accessible solution for high‐performance computing, addressing challenges across various fields. The Compute Unified Device Architecture (CUDA) programming model has emerged to enhance the performance of general‐purpose applications on graphic processors. However, developing CUDA programs is far from straightforward, and developers' lack of experience in parallel programming has led to numerous issues. This article presents a structural testing model and criteria to improve the quality of CUDA programs. These criteria facilitate the selection of test cases and aid in identifying faults. The ValiCUDA tool was developed to implement and validate this testing model and criteria. This tool instruments and analyzes programs, generating the necessary elements for each testing criterion. It also facilitates program execution and evaluation of criterion coverage. A statistical validation experiment assessed these criteria' effectiveness, cost, and strength metrics. The results demonstrate that the criteria can identify nontrivial faults in CUDA programs and assist testers in their testing endeavors for such applications.

show abstract

Section: Cuda Program Faultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Structural testing for CUDA programming model

Luz,

Souza,

Souza

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…On the other hand, over years various open-source and industrial so ware systems have been rapidly developed where the source code of these systems is typically stored in source code repositories. Such source code can be treated as important reusable assets for developers because they can help developers understand how others addressed similar problems for completing their program tasks, e.g., testing [9][10][11][12][13][14][15], fault localization [16][17][18], program repair and synthesis [19][20][21][22], in multiple so ware development domains [23][24][25]. Correspondingly, there also raises a strong demand for an e cient search process through a large codebase to nd relevant code for helping programming tasks.…”

Section: Introductionmentioning

confidence: 99%

TranS^3: A Transformer-based Framework for Unifying Code Summarization and Code Search

Wang¹,

Zhang²,

Zeng³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Code summarization and code search have been widely adopted in so ware development and maintenance. However, few studies have explored the e cacy of unifying them. In this paper, we propose TranS 3 , a transformer-based framework to integrate code summarization with code search. Speci cally, for code summarization, TranS 3 enables an actor-critic network, where in the actor network, we encode the collected code snippets via transformer-and tree-transformer-based encoder and decode the given code snippet to generate its comment. Meanwhile, we iteratively tune the actor network via the feedback from the critic network for enhancing the quality of the generated comments. Furthermore, we import the generated comments to code search for enhancing its accuracy. To evaluate the e ectiveness of TranS 3 , we conduct a set of experimental studies and case studies where the experimental results suggest that T ranS 3 can signi cantly outperform multiple state-of-the-art approaches in both code summarization and code search and the study results further strengthen the e cacy of TranS 3 from the developers' points of view.

show abstract