Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.09337 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910743765450752 |
|---|---|
| author | Shi, Xuri Zhang, Kai Wang, X. Sean Zhang, Xiaodong Lee, Rubao |
| author_facet | Shi, Xuri Zhang, Kai Wang, X. Sean Zhang, Xiaodong Lee, Rubao |
| contents | A spectrum of new hardware has been studied to accelerate database systems in the past decade. Specifically, CUDA cores are known to benefit from the fast development of GPUs and make notable performance improvements. The state-of-the-art GPU-based implementation, i.e., Crystal, can achieve up to 61 times higher performance than CPU-based implementations. However, experiments show that the approach has already saturated almost all GPU memory bandwidth, which means there is little room left for further performance improvements. We introduce RTCUDB, the first query engine that leverages ray tracing (RT) cores in GPUs to accelerate database query processing. RTCUDB efficiently transforms the evaluation of a query into a ray-tracing job in a three-dimensional space. By dramatically reducing the amount of accessed data and optimizing the data access pattern with the ray tracing mechanism, the performance of RTCUDB is no longer limited by the memory bandwidth as in CUDA-based implementations. Experimental results show that RTCUDB outperforms the state-of-the-art GPU-based query engine by up to 18.3 times while the memory bandwidth usage drops to only 36.7% on average. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09337 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RTCUDB: Building Databases with RT Processors Shi, Xuri Zhang, Kai Wang, X. Sean Zhang, Xiaodong Lee, Rubao Databases A spectrum of new hardware has been studied to accelerate database systems in the past decade. Specifically, CUDA cores are known to benefit from the fast development of GPUs and make notable performance improvements. The state-of-the-art GPU-based implementation, i.e., Crystal, can achieve up to 61 times higher performance than CPU-based implementations. However, experiments show that the approach has already saturated almost all GPU memory bandwidth, which means there is little room left for further performance improvements. We introduce RTCUDB, the first query engine that leverages ray tracing (RT) cores in GPUs to accelerate database query processing. RTCUDB efficiently transforms the evaluation of a query into a ray-tracing job in a three-dimensional space. By dramatically reducing the amount of accessed data and optimizing the data access pattern with the ray tracing mechanism, the performance of RTCUDB is no longer limited by the memory bandwidth as in CUDA-based implementations. Experimental results show that RTCUDB outperforms the state-of-the-art GPU-based query engine by up to 18.3 times while the memory bandwidth usage drops to only 36.7% on average. |
| title | RTCUDB: Building Databases with RT Processors |
| topic | Databases |
| url | https://arxiv.org/abs/2412.09337 |