Abstract
From OpenMP 4.0 onwards, programmers can offload code regions to accelerators by using the target offloading feature. However, incorrect usage of target offloading constructs may incur data mapping issues. A data mapping issue occurs when the host fails to observe updates on the accelerator or vice versa. It may further lead to multiple memory issues such as use of uninitialized memory, use of stale data, and data race. To the best of our knowledge, currently there is no prior work on dynamic detection of data mapping issues in heterogeneous OpenMP applications.In this paper, we identify possible root causes of data mapping issues in OpenMP's standard memory model and the unified memory model. We find that data mapping issues primarily result from incorrect settings of map and nowait clauses in target offloading constructs. Further, the novel unified memory model introduced in OpenMP 5.0 cannot avoid the occurrence of data mapping issues. To mitigate the difficulty of detecting data mapping issues, we propose ARBALEST, an on-the-fly data mapping issue detector for OpenMP applications. For each variable mapped to the accelerator, ARBALEST's detection algorithm leverages a state machine to track the last write's visibility. ARBALEST requires constant storage space for each memory location and takes amortized constant time per memory access. To demonstrate ARBALEST's effectiveness, an experimental comparison with four other dynamic analysis tools (Valgrind, Archer, AddressSanitizer, MemorySanitizer) has been carried out on a number of open-source benchmark suites. The evaluation results show that ARBALEST delivers demonstrably better precision than the other four tools, and its execution time overhead is comparable to that of state-of-the-art dynamic analysis tools.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2021 IEEE 35th International Parallel and Distributed Processing Symposium, IPDPS 2021 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 464-474 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781665440660 |
| DOIs | |
| State | Published - May 2021 |
| Event | 35th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2021 - Virtual, Online Duration: May 17 2021 → May 21 2021 |
Publication series
| Name | Proceedings - 2021 IEEE 35th International Parallel and Distributed Processing Symposium, IPDPS 2021 |
|---|
Conference
| Conference | 35th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2021 |
|---|---|
| City | Virtual, Online |
| Period | 05/17/21 → 05/21/21 |
Funding
This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the U.S. Department of Energy Office of Science and the National Nuclear Security Administration, in particular its subproject on Scaling OpenMP with LLVM for Exascale performance and portability (SOLLVE). Part of this work was possible under funding by the German Research Foundation (DFG) through the German Priority Programme 1648 Software for Exascale Computing (SPPEXA). This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).
Keywords
- Accelerator
- Concurrency Bug Detection
- Data Mapping Issue
- Dynamic Analysis
- OpenMP