Bang Di
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Bang Di has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Dong Li
University of California, Merced, Merced, CA, USA
2 shared publications - Chen Liang
Alibaba Group, Hangzhou, China
1 shared publication - Dongdong Huang
Alibaba Group, Hangzhou, China
1 shared publication - Fudong Qiu
Alibaba Cloud Computing, Hangzhou, China
1 shared publication - Hang Yang
Alibaba Cloud, Hangzhou, China
1 shared publication - Hao Chen
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China
1 shared publication
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 892-906
Tai Chi: A General High-Efficiency Scheduling Framework for SmartNICs in Hyperscale Clouds
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 892-906
Open AccessTai Chi: A General High-Efficiency Scheduling Framework for SmartNICs in Hyperscale Clouds
- 8 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (5) , 1161-1177
Efficient Buffer Overflow Detection on GPU
Rich thread-level parallelism of GPU has motivated co-running GPU kernels on a single GPU. However, when GPU kernels co-run, it is possible that one kernel can leverage buffer overflow to attack another kernel running on the same GPU. Existing work has either large performance overhead or limited capability in detecting buffer overflow. In this paper, we introduce GMODx, a runtime software system that can detect GPU buffer overflow. GMODx performs always-on monitoring on allocated memory based on canary-based design. First, for fine-grained memory management, GMODx introduces a set of byte arrays to store buffer information for overflow detection. Techniques, including lock-free accesses to the byte arrays, delayed memory free, efficient memory reallocation, and garbage collection for the byte arrays, are proposed to achieve high performance. Second, for coarse-grained memory management, GMODx utilizes unified memory to delegate the always-on monitoring to the CPU. To reduce performance overhead, we propose several techniques, including customized list data structure and specific optimizations against the unified memory. Our experiments show that GMODx is capable of detecting buffer overflow for the fine-grained memory management without performance loss, and that it incurs small runtime overhead (4.2% on average and up to 9.7%) for the coarse-grained memory management.
- 8 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (5) , 1161-1177
Efficient Buffer Overflow Detection on GPU
Rich thread-level parallelism of GPU has motivated co-running GPU kernels on a single GPU. However, when GPU kernels co-run, it is possible that one kernel can leverage buffer overflow to attack another kernel running on the same GPU. Existing work has either large performance overhead or limited capability in detecting buffer overflow. In this paper, we introduce GMODx, a runtime software system that can detect GPU buffer overflow. GMODx performs always-on monitoring on allocated memory based on canary-based design. First, for fine-grained memory management, GMODx introduces a set of byte arrays to store buffer information for overflow detection. Techniques, including lock-free accesses to the byte arrays, delayed memory free, efficient memory reallocation, and garbage collection for the byte arrays, are proposed to achieve high performance. Second, for coarse-grained memory management, GMODx utilizes unified memory to delegate the always-on monitoring to the CPU. To reduce performance overhead, we propose several techniques, including customized list data structure and specific optimizations against the unified memory. Our experiments show that GMODx is capable of detecting buffer overflow for the fine-grained memory management without performance loss, and that it incurs small runtime overhead (4.2% on average and up to 9.7%) for the coarse-grained memory management.