상세 보기
초록
GPUs, which are widely used high-performance hardware accelerators in heterogeneous computing, and programming models for architectures such as OpenCL and CUDA, have recently been developed to achieve high productivity. LLVM is an open-source compiler infrastructure that enables low-level optimization through LLVM intermediate representation (LLVM IR) in various programming language environments. In this paper, we propose a fully-automatic Dynamic Profiling framework which performs instruction-level analysis through IR-level code instrumentation for typical OpenCL workload kernels.
키워드
Dynamic Profiling; GPU; LLVM; OpenCL; Graphics processing unit; Program compilers; Code instrumentation; Dynamic Profiling; Heterogeneous computing; High-performance hardware; Intermediate representations; Language environment; LLVM; OpenCL; Open source software
- 제목
- Runtime Profiling of OpenCL Workloads Using LLVM-based Code Instrumentation
- 저자
- Yu, Yongseung.; Kang, Seokwon; Park, Yongjun
- 발행일
- 2019-10
- 유형
- Conference Paper
- 저널명
- IEEE Region 10 Annual International Conference, Proceedings/TENCON
- 권
- 2018-October
- 페이지
- 1520 ~ 1524