More Like this

1. Phase-Aware CPU Workload Forecasting

   Alcorta, Erika S. ; Rama, Pranav ; Aswin, Ramachandran ; Gerstlauer, Andreas ( January 2021 , International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS))

   null (Ed.)

   Predicting workload behavior during execution is essential for dynamic resource optimization of processor systems. Early studies used simple prediction algorithms such as a history tables. More recently, researchers have applied advanced machine learning regression techniques. Workload prediction can be cast as a time series forecasting problem. Time series forecasting is an active research area with recent advances that have not been studied in the context of workload prediction. In this paper, we first perform a comparative study of representative time series forecasting techniques to predict the dynamic workload of applications running on a CPU. We adapt state-of-the-art matrix profile and dynamic linear models (DLMs) not previously applied to workload prediction and compare them against traditional SVM and LSTM models that have been popular for handling non-stationary data. We find that all time series forecasting models struggle to predict abrupt workload changes. These changes occur because workloads go through phases, where prior work has studied workload phase detection, classification and prediction. We propose a novel approach that combines time series forecasting with phase prediction. We process each phase as a separate time series and train one forecasting model per phase. At runtime, forecasts from phase-specific models are selected and combined based on the predicted phase behavior. We apply our approach to forecasting of SPEC workloads running on a state-of-the-art Intel machine. Our results show that an LSTM-based phase-aware predictor can forecast workload CPI with less than 8% mean absolute error while reducing CPI error by more than 12% on average compared to a non-phase-aware approach. 

   more » « less
2. Learning-Based Workload Phase Classification and Prediction Using Performance Monitoring Counters

   https://doi.org/10.1109/MLCAD52597.2021.9531161  

   Alcorta, Erika S. ; Gerstlauer, Andreas ( August 2021 , ACM/IEEE Workshop on Machine Learning for CAD (MLCAD))

   null (Ed.)

   Predicting coarse-grain variations in workload behavior during execution is essential for dynamic resource optimization of processor systems. Researchers have proposed various methods to first classify workloads into phases and then learn their long-term phase behavior to predict and anticipate phase changes. Early studies on phase prediction proposed table-based phase predictors. More recently, simple learning-based techniques such as decision trees have been explored. However, more recent advances in machine learning have not been applied to phase prediction so far. Furthermore, existing phase predictors have been studied only in connection with specific phase classifiers even though there is a wide range of classification methods. Early work in phase classification proposed various clustering methods that required access to source code. Some later studies used performance monitoring counters, but they only evaluated classifiers for specific contexts such as thermal modeling. In this work, we perform a comprehensive study of source-oblivious phase classification and prediction methods using hardware counters. We adapt classification techniques that were used with different inputs in the past and compare them to state-of-the-art hardware counter based classifiers. We further evaluate the accuracy of various phase predictors when coupled with different phase classifiers and evaluate a range of advanced machine learning techniques, including SVMs and LSTMs for workload phase prediction. We apply classification and prediction approaches to SPEC workloads running on an Intel Core-i9 platform. Results show that a two-level kmeans clustering combined with SVM-based phase change prediction provides the best tradeoff between accuracy and long-term stability. Additionally, the SVM predictor reduces the average prediction error by 80% when compared to a table-based predictor. 

   more » « less
3. Wasserstein Adversarial Transformer for Cloud Workload Prediction

   https://doi.org/10.1609/aaai.v36i11.21509  

   Arbat, Shivani ; Jayakumar, Vinodh Kumaran ; Lee, Jaewoo ; Wang, Wei ; Kim, In Kee ( June 2022 , Proceedings of the AAAI Conference on Artificial Intelligence)

   Predictive VM (Virtual Machine) auto-scaling is a promising technique to optimize cloud applications’ operating costs and performance. Understanding the job arrival rate is crucial for accurately predicting future changes in cloud workloads and proactively provisioning and de-provisioning VMs for hosting the applications. However, developing a model that accurately predicts cloud workload changes is extremely challenging due to the dynamic nature of cloud workloads. Long- Short-Term-Memory (LSTM) models have been developed for cloud workload prediction. Unfortunately, the state-of-the-art LSTM model leverages recurrences to predict, which naturally adds complexity and increases the inference overhead as input sequences grow longer. To develop a cloud workload prediction model with high accuracy and low inference overhead, this work presents a novel time-series forecasting model called WGAN-gp Transformer, inspired by the Transformer network and improved Wasserstein-GANs. The proposed method adopts a Transformer network as a generator and a multi-layer perceptron as a critic. The extensive evaluations with real-world workload traces show WGAN- gp Transformer achieves 5× faster inference time with up to 5.1% higher prediction accuracy against the state-of-the-art. We also apply WGAN-gp Transformer to auto-scaling mechanisms on Google cloud platforms, and the WGAN-gp Transformer-based auto-scaling mechanism outperforms the LSTM-based mechanism by significantly reducing VM over-provisioning and under-provisioning rates. 

   more » « less
4. Indexer++: workload-aware online index tuning with transformers and reinforcement learning

   https://doi.org/10.1145/3477314.3507691  

   Sharma, Vishal ; Dyreson, Curtis ( April 2022 , SAC '22: Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing)

   With the increasing workload complexity in modern databases, the manual process of index selection is a challenging task. There is a growing need for a database with an ability to learn and adapt to evolving workloads. This paper proposes Indexer++, an autonomous, workload-aware, online index tuner. Unlike existing approaches, Indexer++ imposes low overhead on the DBMS, is responsive to changes in query workloads and swiftly selects indexes. Our approach uses a combination of text analytic techniques and reinforcement learning. Indexer++ consist of two phases: Phase (i) learns workload trends using a novel trend detection technique based on a pre-trained transformer model. Phase (ii) performs online, i.e., continuous or while the DBMS is processing workloads, index selection using a novel online deep reinforcement learning technique using our proposed priority experience sweeping. This paper provides an experimental evaluation of Indexer++ in multiple scenarios using benchmark (TPC-H) and real-world datasets (IMDB). In our experiments, Indexer++ effectively identifies changes in workload trends and selects the set of optimal indexes. 

   more » « less
5. Learning based Memory Interference Prediction for Co-running Applications on Multi-Cores

   https://doi.org/10.1109/MLCAD52597.2021.9531245  

   Saeed, Ahsan ; Mueller-Gritschneder, Daniel ; Rehm, Falk ; Hamann, Arne ; Ziegenbein, Dirk ; Schlichtmann, Ulf ; Gerstlauer, Andreas ( August 2021 , ACM/IEEE Workshop on Machine Learning for CAD (MLCAD))

   null (Ed.)

   Early run-time prediction of co-running independent applications prior to application integration becomes challenging in multi-core processors. One of the most notable causes is the interference at the main memory subsystem, which results in significant degradation in application performance and response time in comparison to standalone execution. Currently available techniques for run-time prediction like traditional cycle-accurate simulations are slow, and analytical models are not accurate and time-consuming to build. By contrast, existing machine-learning-based approaches for run-time prediction simply do not account for interference. In this paper, we use a machine learning- based approach to train a model to correlate performance data (instructions and hardware performance counters) for a set of benchmark applications between the standalone and interference scenarios. After that, the trained model is used to predict the run-time of co-running applications in interference scenarios. In general, there is no straightforward one-to-one correspondence between samples obtained from the standalone and interference scenarios due to the different run-times, i.e. execution speeds. To address this, we developed a simple yet effective sample alignment algorithm, which is a key component in transforming interference prediction into a machine learning problem. In addition, we systematically identify the subset of features that have the highest positive impact on the model performance. Our approach is demonstrated to be effective and shows an average run-time prediction error, which is as low as 0.3% and 0.1% for two co-running applications. 

   more » « less