期刊
出版社
IEEE
DOI: 10.1109/LLVMHPC54804.2021.00011
关键词
Hardware Specialization; LLVM IR; Code Similarity Learning; Workload Analysis
资金
- Advanced Scientific Computing Research Program in the U.S. Department of Energy, Office of Science [DE-AC0205CH11231]
- Office of Science of the U.S. Department of Energy [DE-AC02-05CH11231]
Automating the workload characterization process in hardware design is crucial, especially with the increasing complexity of applications and input problems. A new approach based on code similarity learning is proposed, decomposing applications into small kernels mapped to known patterns for reusing behavior on hardware. This approach involves a new code representation and similarity metric, automated detection using compiler and machine learning methods, and distinguishing kernels in benchmarks for suggesting optimal configurations for hardware accelerators.
Automating the workload characterization process is increasingly important in hardware design. Although compiler tools can automatically collect profiling data and predict performance behaviors, the process has to be repeated for each potential design. Such challenge is exacerbated by the fast growing body of applications and input problems. We propose an alternative approach based on code similarity learning. The application is decomposed into small kernels that can be mapped to known patterns. The behaviors of a pattern on a hardware setup can be reused. To enable this technology, we propose a new code representation and similarity metric. We automate the detection process using compiler and ML methods. Specifically, we reformulate application's dataflow graphs so that they can be compared based on both compute and data movement. We show this representation can distinguish kernels in the HPCG benchmark and help suggest optimal configurations for SpMV and GEMM hardware accelerators.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据