FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2117444998> ?p ?o ?g. }

• W2117444998 abstract "In recent years, GPUs have emerged as an extremely cost-effective means for achieving high performance. Many application developers, including those with no prior parallel programming experience, are now trying to scale their applications using GPUs. While languages like CUDA and OpenCL have eased GPU programming for non-graphical applications, they are still explicitly parallel languages. All parallel programmers, particularly the novices, need tools that can help ensuring the correctness of their programs. Like any multithreaded environment, data races on GPUs can severely affect the program reliability. Thus, tool support for detecting race conditions can significantly benefit GPU application developers. Existing approaches for detecting data races on CPUs or GPUs have one or more of the following limitations: 1) being illsuited for handling non-lock synchronization primitives on GPUs; 2) lacking of scalability due to the state explosion problem; 3) reporting many false positives because of simplified modeling; and/or 4) incurring prohibitive runtime and space overhead. In this paper, we propose GRace, a new mechanism for detecting races in GPU programs that combines static analysis with a carefully designed dynamic checker for logging and analyzing information at runtime. Our design utilizes GPUs memory hierarchy to log runtime data accesses efficiently. To improve the performance, GRace leverages static analysis to reduce the number of statements that need to be instrumented. Additionally, by exploiting the knowledge of thread scheduling and the execution model in the underlying GPUs, GRace can accurately detect data races with no false positives reported. Based on the above idea, we have built a prototype of GRace with two schemes, i.e., GRace-stmt and GRace-addr, for NVIDIA GPUs. Both schemes are integrated with the same static analysis. We have evaluated GRace-stmt and GRace-addr with three data race bugs in three GPU kernel functions and also have compared them with the existing approach, referred to as B-tool. Our experimental results show that both schemes of GRace are effective in detecting all evaluated cases with no false positives, whereas Btool reports many false positives for one evaluated case. On the one hand, GRace-addr incurs low runtime overhead, i.e., 22-116%, and low space overhead, i.e., 9-18MB, for the evaluated kernels. On the other hand, GRace-stmt offers more help in diagnosing data races with larger overhead." @default.
• W2117444998 created "2016-06-24" @default.
• W2117444998 creator A5004195454 @default.
• W2117444998 creator A5025342178 @default.
• W2117444998 creator A5028781688 @default.
• W2117444998 creator A5086667064 @default.
• W2117444998 date "2011-02-12" @default.
• W2117444998 modified "2023-10-12" @default.
• W2117444998 title "GRace" @default.
• W2117444998 cites W1521862884 @default.
• W2117444998 cites W1964232008 @default.
• W2117444998 cites W196542726 @default.
• W2117444998 cites W1969399184 @default.
• W2117444998 cites W1972544179 @default.
• W2117444998 cites W1994941228 @default.
• W2117444998 cites W2013247896 @default.
• W2117444998 cites W2019611783 @default.
• W2117444998 cites W2036048726 @default.
• W2117444998 cites W2039781906 @default.
• W2117444998 cites W2047830525 @default.
• W2117444998 cites W2072419942 @default.
• W2117444998 cites W2088139180 @default.
• W2117444998 cites W2088270410 @default.
• W2117444998 cites W2101161997 @default.
• W2117444998 cites W2106913893 @default.
• W2117444998 cites W2109516916 @default.
• W2117444998 cites W2109875364 @default.
• W2117444998 cites W2127989655 @default.
• W2117444998 cites W2132148774 @default.
• W2117444998 cites W2139712615 @default.
• W2117444998 cites W2144749751 @default.
• W2117444998 cites W2146606012 @default.
• W2117444998 cites W2149897682 @default.
• W2117444998 cites W2156428492 @default.
• W2117444998 cites W2160097679 @default.
• W2117444998 cites W2161600851 @default.
• W2117444998 cites W2161957670 @default.
• W2117444998 cites W2162446957 @default.
• W2117444998 cites W2168272209 @default.
• W2117444998 cites W2170634604 @default.
• W2117444998 cites W2340604309 @default.
• W2117444998 cites W3137220996 @default.
• W2117444998 cites W4248655060 @default.
• W2117444998 cites W4251803824 @default.
• W2117444998 doi "https://doi.org/10.1145/1941553.1941574" @default.
• W2117444998 hasPublicationYear "2011" @default.
• W2117444998 type Work @default.
• W2117444998 sameAs 2117444998 @default.
• W2117444998 citedByCount "47" @default.
• W2117444998 countsByYear W21174449982012 @default.
• W2117444998 countsByYear W21174449982013 @default.
• W2117444998 countsByYear W21174449982014 @default.
• W2117444998 countsByYear W21174449982015 @default.
• W2117444998 countsByYear W21174449982016 @default.
• W2117444998 countsByYear W21174449982017 @default.
• W2117444998 countsByYear W21174449982018 @default.
• W2117444998 countsByYear W21174449982019 @default.
• W2117444998 countsByYear W21174449982020 @default.
• W2117444998 countsByYear W21174449982021 @default.
• W2117444998 countsByYear W21174449982022 @default.
• W2117444998 countsByYear W21174449982023 @default.
• W2117444998 crossrefType "proceedings-article" @default.
• W2117444998 hasAuthorship W2117444998A5004195454 @default.
• W2117444998 hasAuthorship W2117444998A5025342178 @default.
• W2117444998 hasAuthorship W2117444998A5028781688 @default.
• W2117444998 hasAuthorship W2117444998A5086667064 @default.
• W2117444998 hasConcept C111919701 @default.
• W2117444998 hasConcept C119857082 @default.
• W2117444998 hasConcept C138101251 @default.
• W2117444998 hasConcept C162324750 @default.
• W2117444998 hasConcept C173608175 @default.
• W2117444998 hasConcept C199360897 @default.
• W2117444998 hasConcept C206729178 @default.
• W2117444998 hasConcept C21547014 @default.
• W2117444998 hasConcept C2778119891 @default.
• W2117444998 hasConcept C34165917 @default.
• W2117444998 hasConcept C41008148 @default.
• W2117444998 hasConcept C48044578 @default.
• W2117444998 hasConcept C55439883 @default.
• W2117444998 hasConcept C64869954 @default.
• W2117444998 hasConcept C97686452 @default.
• W2117444998 hasConceptScore W2117444998C111919701 @default.
• W2117444998 hasConceptScore W2117444998C119857082 @default.
• W2117444998 hasConceptScore W2117444998C138101251 @default.
• W2117444998 hasConceptScore W2117444998C162324750 @default.
• W2117444998 hasConceptScore W2117444998C173608175 @default.
• W2117444998 hasConceptScore W2117444998C199360897 @default.
• W2117444998 hasConceptScore W2117444998C206729178 @default.
• W2117444998 hasConceptScore W2117444998C21547014 @default.
• W2117444998 hasConceptScore W2117444998C2778119891 @default.
• W2117444998 hasConceptScore W2117444998C34165917 @default.
• W2117444998 hasConceptScore W2117444998C41008148 @default.
• W2117444998 hasConceptScore W2117444998C48044578 @default.
• W2117444998 hasConceptScore W2117444998C55439883 @default.
• W2117444998 hasConceptScore W2117444998C64869954 @default.
• W2117444998 hasConceptScore W2117444998C97686452 @default.
• W2117444998 hasLocation W21174449981 @default.
• W2117444998 hasOpenAccess W2117444998 @default.
• W2117444998 hasPrimaryLocation W21174449981 @default.
• W2117444998 hasRelatedWork W164750744 @default.

• next