@article{Ren2021, author = {Zhixiang Ren and Yongheng Liu and Tianhui Shi and Lei Xie and Yue Zhou and Jidong Zhai and Youhui Zhang and Yunquan Zhang and Wenguang Chen}, title = {AIPerf: Automated Machine Learning as an AI-HPC Benchmark}, year = {2021}, journal = {Big Data Mining and Analytics}, volume = {4}, number = {3}, pages = {208-220}, keywords = {Artificial Intelligence (AI), High-Performance Computing (HPC), automated machine learning}, url = {https://www.sciopen.com/article/10.26599/BDMA.2021.9020004}, doi = {10.26599/BDMA.2021.9020004}, abstract = {The plethora of complex Artificial Intelligence (AI) algorithms and available High-Performance Computing (HPC) power stimulates the expeditious development of AI components with heterogeneous designs. Consequently, the need for cross-stack performance benchmarking of AI-HPC systems has rapidly emerged. In particular, the de facto HPC benchmark, LINPACK, cannot reflect the AI computing power and input/output performance without a representative workload. Current popular AI benchmarks, such as MLPerf, have a fixed problem size and therefore limited scalability. To address these issues, we propose an end-to-end benchmark suite utilizing automated machine learning, which not only represents real AI scenarios, but also is auto-adaptively scalable to various scales of machines. We implement the algorithms in a highly parallel and flexible way to ensure the efficiency and optimization potential on diverse systems with customizable configurations. We utilize Operations Per Second (OPS), which is measured in an analytical and systematic approach, as a major metric to quantify the AI performance. We perform evaluations on various systems to ensure the benchmark’s stability and scalability, from 4 nodes with 32 NVIDIA Tesla T4 (56.1 Tera-OPS measured) up to 512 nodes with 4096 Huawei Ascend 910 (194.53 Peta-OPS measured), and the results show near-linear weak scalability. With a flexible workload and single metric, AIPerf can easily scale on and rank AI-HPC, providing a powerful benchmark suite for the coming supercomputing era.} }