Many cloud services have Quality-of-Service (QoS) requirements; most requests have to to complete within a given latency constraint. Recently, researchers have begun to investigate whether it is possible to meet QoS while attempting to save power on a per-request basis. Existing work shows that one can indeed hand-tune a request latency predictor offline for a particular cloud application, and consult it at runtime to modulate CPU voltage and frequency, resulting in substantial power savings. In this paper, we propose ReTail, an automated and general solution for request-level power management of latency-critical services with QoS constraints. We present a systematic process to select the features of any given application that best correlate with its request latency. ReTail uses these features to predict latency, and adjust CPU’s power consumption. ReTail’s predictor is trained fully at runtime. We show that unlike previous findings, simple techniques perform better than complex machine learning models, when using the right input features. For a web search engine, ReTail outperforms prior mechanisms based on complex hand-tuned predictors for that application domain. Furthermore, ReTail’s systematic approach also yields superior power savings across a diverse set of cloud applications.
more »
« less
Machine Learning-Based Microarchitecture- Level Power Modeling of CPUs
Energy efficiency has emerged as a key concern for modern processor design, especially when it comes to embedded and mobile devices. It is vital to accurately quantify the power consumption of different micro-architectural components in a CPU. Traditional RTL or gate-level power estimation is too slow for early design-space exploration studies. By contrast, existing architecture-level power models suffer from large inaccuracies. Recently, advanced machine learning techniques have been proposed for accurate power modeling. However, existing approaches still require slow RTL simulations, have large training overheads or have only been demonstrated for fixed-function accelerators and simple in-order cores with predictable behavior. In this work, we present a novel machine learning-based approach for microarchitecture-level power modeling of complex CPUs. Our approach requires only high-level activity traces obtained from microarchitecture simulations. We extract representative features and develop low-complexity learning formulations for different types of CPU-internal structures. Cycle-accurate models at the sub-component level are trained from a small number of gate-level simulations and hierarchically composed to build power models for complete CPUs. We apply our approach to both in-order and out-of-order RISC-V cores. Cross-validation results show that our models predict cycle-by-cycle power consumption to within 3% of a gate-level power estimation on average. In addition, our power model for the Berkeley Out-of-Order (BOOM) core trained on micro-benchmarks can predict the cycle-by-cycle power of real-world applications with less than 3.6% mean absolute error.
more »
« less
- Award ID(s):
- 1763848
- NSF-PAR ID:
- 10387264
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Computers
- Volume:
- 72
- Issue:
- 4
- ISSN:
- 0018-9340
- Page Range / eLocation ID:
- 1 to 14
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Summary Energy‐efficient scientific applications require insight into how high performance computing system features impact the applications' power and performance. This insight can result from the development of performance and power models. In this article, we use the modeling and prediction tool MuMMI (Multiple Metrics Modeling Infrastructure) and 10 machine learning methods to model and predict performance and power consumption and compare their prediction error rates. We use an algorithm‐based fault‐tolerant linear algebra code and a multilevel checkpointing fault‐tolerant heat distribution code to conduct our modeling and prediction study on the Cray XC40 Theta and IBM BG/Q Mira at Argonne National Laboratory and the Intel Haswell cluster Shepard at Sandia National Laboratories. Our experimental results show that the prediction error rates in performance and power using MuMMI are less than 10% for most cases. By utilizing the models for runtime, node power, CPU power, and memory power, we identify the most significant performance counters for potential application optimizations, and we predict theoretical outcomes of the optimizations. Based on two collected datasets, we analyze and compare the prediction accuracy in performance and power consumption using MuMMI and 10 machine learning methods.
-
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
-
The current trend of performance growth in HPC systems is accompanied by a massive increase in energy consumption. In this article, we introduce GreenMD, an energy-efficient framework for heterogeneous systems for LU factorization utilizing multi-GPUs. LU factorization is a crucial kernel from the MAGMA library, which is highly optimized. Our aim is to apply DVFS to this application by leveraging slacks intelligently on both CPUs and multiple GPUs. To predict the slack times, accurate performance models are developed separately for both CPUs and GPUs based on the algorithmic knowledge and manufacturer’s specifications. Since DVFS does not reduce static energy consumption, we also develop undervolting techniques for both CPUs and GPUs. Reducing voltage below threshold values may give rise to errors; hence, we extract the minimum safe voltages ( V safeMin ) for the CPUs and GPUs utilizing a low overhead profiling phase and apply them before execution. It is shown that GreenMD improves the CPU, GPU, and total energy about 59%, 21%, and 31%, respectively, while delivering similar performance to the state-of-the-art linear algebra MAGMA library.more » « less
-
The water content in the soil regulates exchanges between soil and atmosphere, impacts plant livelihood, and determines the antecedent condition for several natural hazards. Accurate soil moisture estimates are key to applications such as natural hazard prediction, agriculture, and water management. We explore how to best predict soil moisture at a high resolution in the context of a changing climate. Physics-based hydrological models are promising as they provide distributed soil moisture estimates and allow prediction outside the range of prior observations. This is particularly important considering that the climate is changing, and the available historical records are often too short to capture extreme events. Unfortunately, these models are extremely computationally expensive, which makes their use challenging, especially when dealing with strong uncertainties. These characteristics make them complementary to machine learning approaches, which rely on training data quality/quantity but are typically computationally efficient. We first demonstrate the ability of Convolutional Neural Networks (CNNs) to reproduce soil moisture fields simulated by the hydrological model ParFlow-CLM. Then, we show how these two approaches can be successfully combined to predict future droughts not seen in the historical timeseries. We do this by generating additional ParFlow-CLM simulations with altered forcing mimicking future drought scenarios. Comparing the performance of CNN models trained on historical forcing and CNN models trained also on simulations with altered forcing reveals the potential of combining these two approaches. The CNN can not only reproduce the moisture response to a given forcing but also learn and predict the impact of altered forcing. Given the uncertainties in projected climate change, we can create a limited number of representative ParFlow-CLM simulations (ca. 25 min/water year on 9 CPUs for our case study), train our CNNs, and use them to efficiently (seconds/water-year on 1 CPU) predict additional water years/scenarios and improve our understanding of future drought potential. This framework allows users to explore scenarios beyond past observation and tailor the training data to their application of interest (e.g., wet conditions for flooding, dry conditions for drought, etc…). With the trained ML model they can rely on high resolution soil moisture estimates and explore the impact of uncertainties.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TC.2022.3185572
