Enable Simultaneous DNN Services Based on Deterministic Operator Overlap and Precise Latency Prediction
Machine Learning and Artificial Intelligence
Best Reproducibility Advancement Finalist
TimeTuesday, 16 November 202111:30am - 12pm CST
DescriptionWhile user-facing services experience diurnal load patterns, co-locating services improve the hardware utilization. Prior work on co-locating services on GPUs run queries sequentially, as the latencies of the queries are neither stable nor predictable when running simultaneously. The input sensitiveness and the non-deterministic operator overlap are two primary factors of the latency unpredictability. Hence, We propose Abacus, a runtime system that runs multiple services simultaneously. Abacus enables deterministic operator overlap to enforce latency predictability. Abacus consists of an overlap-aware latency predictor, a headroom-based query controller, and segmental model executors. The predictor predicts the latencies of the deterministic operator overlap. The controller determines the appropriate operator overlap for QoS guarantee of all the services. The executors run the operators as needed to support the deterministic operator overlap. Our evaluation shows that Abacus reduces 51.3% of the QoS violation and improves the throughput by 29.8% on average compared with state-of-the-art solutions.