With the rapid growth of the machine learning applications, the workloads of future HPC systems are anticipated to be a mix of scientific simulation, big data analytics, and machine learning applications. Simulation is a great research vehicle to understand the performance implications of co-running scientific applications with big data and machine learning workloads on large-scale systems. In this paper, we present Union, a workload manager that provides an automatic framework to facilitate hybrid workload simulation in CODES. Furthermore, we use Union, along with CODES, to investigate various hybrid workloads composed of traditional simulation applications and emerging learning applications on two dragonfly systems. The experiment results show that both message latency and communication time are important performance metrics to evaluate network interference. Network interference on HPC applications is more reflected by the message latency variation, whereas ML application performance depends more on the communication time.
more »
« less
Learning based Memory Interference Prediction for Co-running Applications on Multi-Cores
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
- Award ID(s):
- 1763848
- NSF-PAR ID:
- 10299963
- Date Published:
- Journal Name:
- ACM/IEEE Workshop on Machine Learning for CAD (MLCAD)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This article investigates the application of machine learning-based probabilistic prediction methodologies to estimate the performance of silicon-based solar cells. The concept of confidence-bound regions is introduced and the advantages of this concept are discussed in detail. The results show that the optical and electrical performance of a photovoltaic device can be accurately estimated using Gaussian processes with accurate knowledge of the uncertainty in the prediction values. It is also shown that cell design parameters can be estimated for a desired performance metric and trained machine learning models can be deployed as a standalone application.more » « less
-
Loosely-coupled and lightweight microservices running in containers are likely to form complex execution dependencies inside the system. The execution dependency arises when two execution paths partially share component microservices, resulting in potential runtime performance interference. In this paper, we present a blackbox approach that utilizes legitimate HTTP requests to accurately profile the internal pairwise dependencies of all supported execution paths in the target microservices application. Concretely, we profile the pairwise dependency of two execution paths through performance interference analysis by sending bursts of two types of requests simultaneously. By characterizing and grouping all the execution paths based on their pairwise dependencies, the blackbox approach can derive a clear dependency graph(s) of the entire backend of the microservices application. We validate the effectiveness of the blackbox approach through experiments of open-source microservices benchmark applications running on real clouds (e.g., EC2, Azure).more » « less
-
Approximation is a technique that optimizes the balance between application outcome quality and its resource usage. Trading quality for performance has been investigated for single application scenarios, but not for environments where multiple approximate applications may run concurrently on the same machine, interfering with each other by sharing machine resources. Applying existing, single application techniques to this multi-programming environment may lead to configuration space size explosion, or result in poor overall application quality outcomes. Our new RAPID-M system is the first cross-application con-figuration management framework. It reduces the problem size by clustering configurations of individual applications into local"similarity buckets". The global cross-applications configuration selection is based on these local bucket spaces. RAPID-M dynamically assigns buckets to applications such that overall quality is maximized while respecting individual application cost budgets. Once assigned a bucket, reconfigurations within buckets may be performed locally with minimal impact on global selections. Experimental results using six configurable applications show that even large configuration spaces of complex applications can be clustered into a small number of buckets, resulting in search space size reductions of up to 9 orders of magnitude for our six applications. RAPID-M constructs performance cost models with an average prediction error of ≤3%. For our application execution traces, RAPID-M dynamically selects configurations that lower the budget violation rate by 33.9% with an average budget exceeding rate of 6.6% as compared to other possible approaches. RAPID-M successfully finishes 22.75% more executions which translates to a 1.52X global output quality increase under high system loads. The overhead of RAPID-M is within ≤1% of application execution times.more » « less
-
As more apps embrace AI, it is becoming increasingly common that multiple Deep Neural Networks (DNN)-powered apps may run at the same time on a mobile device. This paper explores scheduling in such multi-instance DNN scenarios, on general open mobile systems (e.g., common smartphones and tablets). Unlike closed systems (e.g., autonomous driving systems) where the set of co-run apps is known beforehand, the user of an open mobile system may install or uninstall arbitrary apps at any time, and a centralized solution is subject to adoption barriers. This work proposes the first-known decentralized application-level scheduling mechanism to address the problem. By leveraging the adaptivity of Deep Reinforcement Learning, the solution is shown to make the scheduling of co-run apps converge to a Nash equilibrium point, yielding a good balance of gains among the apps. The solution moreover automatically adapts to the running environment and the underlying OS and hardware. Experiments show that the solution consistently produces significant speedups and energy savings across DNN workloads, hardware configurations, and running scenarios.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/MLCAD52597.2021.9531245
