Fine-grained synchronizations and dataflow programming on GPUs
Research output: Contribution to book/conference proceedings/anthology/report › Conference contribution › Contributed › peer-review
Contributors
Abstract
The last decade has witnessed the blooming emergence of many-core platforms, especially the graphic processing units (GPUs). With the exponential growth of cores in GPUs, utilizing them efficiently becomes a challenge. The data-parallel programming model assumes a single instruction stream for multiple concurrent threads (SIMT); therefore little support is offered to enforce thread ordering and finegrained synchronizations. This becomes an obstacle when migrating algorithms which exploit fine-grained parallelism, to GPUs, such as the dataow algorithms. In this paper, we propose a novel approach for fine-grained inter-thread synchronizations on the shared memory of modern GPUs. We demonstrate its performance and compare it with other fine-grained and medium-grained synchronization approaches. Our method achieves 1.5x speedup over the warp-barrier based approach and 4.0x speedup over the atomic spin-lock based approach on average. To further explore the possibility of realizing fine-grained dataow algorithms on GPUs, we apply the proposed synchronization scheme to Needleman-Wunsch-a 2D wavefront application involving massive cross-loop data dependencies. Our implementation achieves 3.56x speedup over the atomic spin-lock implementation and 1.15x speedup over the conventional data-parallel implementation for a basic sub-grid, which implies that the fine-grained, lock-based programming pattern could be an alternative choice for designing general-purpose GPU applications (GPGPU).
Details
Original language | English |
---|---|
Title of host publication | ICS '15: Proceedings of the 29th ACM on International Conference on Supercomputing |
Publisher | Association for Computing Machinery (ACM), New York |
Pages | 109-118 |
Number of pages | 10 |
ISBN (electronic) | 978-1-4503-3559-1 |
Publication status | Published - 8 Jun 2015 |
Peer-reviewed | Yes |
Externally published | Yes |
Publication series
Series | ICS: International Conference on Supercomputing |
---|
Conference
Title | 29th ACM International Conference on Supercomputing, ICS 2015 |
---|---|
Duration | 8 - 11 June 2015 |
City | Newport Beach |
Country | United States of America |
Keywords
Research priority areas of TU Dresden
ASJC Scopus subject areas
Keywords
- Dataow, Fine-grained synchronization, GPU, Spin-lock