5/30/2023 0 Comments Iguard pur surface![]() IEEE Computer Society, Washington, DC, USA, 44-54. In Proceedings of the 2009 IEEE International Symposium on Workload Characterization (IISWC) (IISWC '09). Rodinia: A Benchmark Suite for Heterogeneous Computing. Sheaffer, Sang-Ha Lee, and Kevin Skadron. Shuai Che, Michael Boyer, Jiayuan Meng, David Tarjan, Jeremy W.Martin Burtscher, Rupesh Nasre, and Keshav Pingali.IEEE Computer Society, Washington, DC, USA, 141-151. In Proceedings of the 2012 IEEE International Symposium on Workload Characterization (IISWC) (IISWC '12). A Quantitative Study of Irregular Programs on GPUs. In 2008 Workshop on Software Tools for MultiCore Systems. Automated Dynamic Analysis of CUDA Programs. Michael Boyer, Kevin Skadron, and Westley Weimer.In Proceedings of the 31st ACM SIGPLAN Conference on Programming Language Design and Implementation (Toronto, Ontario, Canada) (PLDI '10). PACER: Proportional Detection of Data Races. The Design and Implementation of a Verification Technique for GPU Kernels. Donaldson, Jeroen Ketema, Shaz Qadeer, Paul Thomson, and John Wickerson. In Proceedings of the ACM International Conference on Object Oriented Programming Systems Languages and Applications (Tucson, Arizona, USA) (OOPSLA '12). Adam Betts, Nathan Chong, Alastair Donaldson, Shaz Qadeer, and Paul Thomson.In Proceedings of the Sixteenth Annual ACM Symposium on Parallelism in Algorithms and Architectures (Barcelona, Spain) (SPAA '04). On-the-fly Maintenance of Series-parallel Relationships in Fork-join Multithreaded Programs. Springer-Verlag New York, Inc., New York, NY, USA, 230-245. In Proceedings of the 6th International Symposium on NASA Formal Methods - Volume 8430. Warps and Atomics: Beyond Barrier Synchronization in the Verification of GPU Kernels. Springer-Verlag, Berlin, Heidelberg, 226-242. In Proceedings of the 16th International Conference on Computer Aided Verification - Volume 8559. Engineering a Static Verification Tool for GPU Kernels. Donaldson, Jeroen Ketema, Daniel Liew, and Shaz Qadeer. Ethel Bardsley, Adam Betts, Nathan Chong, Peter Collingbourne, Pantazis Deligiannis, Alastair F.In 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). Saman Ashkiani, Martin Farach-Colton, and John D.In Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (Istanbul, Turkey) (ASPLOS '15). GPU Concurrency: Weak Behaviours and Programming Assumptions. Donaldson, Ganesh Gopalakrishnan, Jeroen Ketema, Daniel Poetzl, Tyler Sorensen, and John Wickerson. In total, iGUARD detected 57 races in 21 GPU programs, without false positives. It detected previously unknown subtle bugs in popular GPU programs, including three in NVIDIA supported commercial libraries. Importantly, iGUARD detects newer types of races that were hitherto not possible for any known tool. The GPU's parallelism helps speed up race detection by 15x over a closely related prior work. We thus perform the race detection on the GPU itself without relying on the CPU. ![]() A key need for a race detector to be practical is to accurately detect races at reasonable overheads. We present iGUARD, a runtime software tool to detect races in GPU programs due to incorrect use of such advanced features. While these features can speed up many applications and enable newer use cases, they can also introduce subtle synchronization errors if used incorrectly. To cater to the needs of emerging applications with semantically richer and finer grain sharing patterns, GPU vendors have been introducing advanced programming features, e.g., scoped synchronization and independent thread scheduling. Newer use cases of GPU (Graphics Processing Unit) computing, e.g., graph analytics, look less like traditional bulk-synchronous GPU programs. ![]()
0 Comments
Leave a Reply. |