├── .DS_Store ├── .gitignore ├── LICENSE.txt ├── README.md ├── analysis.ipynb ├── data ├── .DS_Store ├── cluster_summary.csv ├── generate_utilization_pkl.ipynb ├── job_trace │ ├── trace_kalos.csv │ └── trace_seren.csv ├── utilization │ ├── .DS_Store │ └── util_pkl │ │ ├── gpu_power_kalos.pkl │ │ ├── gpu_power_seren.pkl │ │ ├── gpu_temp_kalos.pkl │ │ ├── gpu_temp_seren.pkl │ │ ├── ib_seren.pkl │ │ ├── server_power.pkl │ │ ├── util_cpu_mem_kalos.pkl │ │ ├── util_cpu_mem_seren.pkl │ │ ├── util_gpu_kalos.pkl │ │ ├── util_gpu_kalos_full.pkl │ │ ├── util_gpu_pai.pkl │ │ ├── util_gpu_philly.pkl │ │ └── util_gpu_seren.pkl └── utils.py └── figure ├── bar_job_state.pdf ├── box_gpu_num.pdf ├── cdf_job_duration_queue.pdf ├── cdf_job_duration_util.pdf ├── cdf_job_gpunum.pdf ├── cdf_job_jobtime.pdf ├── cdf_power.pdf ├── cdf_resource_util.pdf ├── cdf_temperature.pdf └── treemap_job_dist.pdf /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/README.md -------------------------------------------------------------------------------- /analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/analysis.ipynb -------------------------------------------------------------------------------- /data/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/.DS_Store -------------------------------------------------------------------------------- /data/cluster_summary.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/cluster_summary.csv -------------------------------------------------------------------------------- /data/generate_utilization_pkl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/generate_utilization_pkl.ipynb -------------------------------------------------------------------------------- /data/job_trace/trace_kalos.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/job_trace/trace_kalos.csv -------------------------------------------------------------------------------- /data/job_trace/trace_seren.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/job_trace/trace_seren.csv -------------------------------------------------------------------------------- /data/utilization/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/.DS_Store -------------------------------------------------------------------------------- /data/utilization/util_pkl/gpu_power_kalos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/gpu_power_kalos.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/gpu_power_seren.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/gpu_power_seren.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/gpu_temp_kalos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/gpu_temp_kalos.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/gpu_temp_seren.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/gpu_temp_seren.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/ib_seren.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/ib_seren.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/server_power.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/server_power.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_cpu_mem_kalos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_cpu_mem_kalos.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_cpu_mem_seren.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_cpu_mem_seren.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_gpu_kalos.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_gpu_kalos.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_gpu_kalos_full.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_gpu_kalos_full.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_gpu_pai.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_gpu_pai.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_gpu_philly.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_gpu_philly.pkl -------------------------------------------------------------------------------- /data/utilization/util_pkl/util_gpu_seren.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utilization/util_pkl/util_gpu_seren.pkl -------------------------------------------------------------------------------- /data/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/data/utils.py -------------------------------------------------------------------------------- /figure/bar_job_state.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/bar_job_state.pdf -------------------------------------------------------------------------------- /figure/box_gpu_num.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/box_gpu_num.pdf -------------------------------------------------------------------------------- /figure/cdf_job_duration_queue.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_job_duration_queue.pdf -------------------------------------------------------------------------------- /figure/cdf_job_duration_util.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_job_duration_util.pdf -------------------------------------------------------------------------------- /figure/cdf_job_gpunum.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_job_gpunum.pdf -------------------------------------------------------------------------------- /figure/cdf_job_jobtime.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_job_jobtime.pdf -------------------------------------------------------------------------------- /figure/cdf_power.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_power.pdf -------------------------------------------------------------------------------- /figure/cdf_resource_util.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_resource_util.pdf -------------------------------------------------------------------------------- /figure/cdf_temperature.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/cdf_temperature.pdf -------------------------------------------------------------------------------- /figure/treemap_job_dist.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/InternLM/AcmeTrace/HEAD/figure/treemap_job_dist.pdf --------------------------------------------------------------------------------