Predicting Cross-Core Performance Interference on Multicore Processors with Regression Analysis

Zhao, Jiacheng; Cui, Huimin; Xue, Jingling; Feng, Xiaobing

doi:10.1109/tpds.2015.2442983

Cited by 23 publications

(17 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive Modeling. Recent studies have shown that machine learning based predictive modeling is effective in code optimization [43], [44], performance predicting [45], [46], parallelism mapping [20], [47], [48], [49], [50], and task scheduling [51], [52], [53], [54], [55], [56]. Its great advantage is its ability to adapt to the ever-changing platforms as it has no prior assumption about their behavior.…”

Section: Domain-specific Optimizationsmentioning

confidence: 99%

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Zhang

Fang

Yang

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

As many-core accelerators keep integrating more processing units, it becomes increasingly more difficult for a parallel application to make effective use of all available resources. An effective way for improving hardware utilization is to exploit spatial and temporal sharing of the heterogeneous processing units by multiplexing computation and communication tasks -a strategy known as heterogeneous streaming. Achieving effective heterogeneous streaming requires carefully partitioning hardware among tasks, and matching the granularity of task parallelism to the resource partition. However, finding the right resource partitioning and task granularity is extremely challenging, because there is a large number of possible solutions and the optimal solution varies across programs and datasets. This article presents an automatic approach to quickly derive a good solution for hardware resource partition and task granularity for task-based parallel applications on heterogeneous many-core architectures. Our approach employs a performance model to estimate the resulting performance of the target application under a given resource partition and task granularity configuration. The model is used as a utility to quickly search for a good configuration at runtime. Instead of hand-crafting an analytical model that requires expert insights into low-level hardware details, we employ machine learning techniques to automatically learn it. We achieve this by first learning a predictive model offline using training programs. The learnt model can then be used to predict the performance of any unseen program at runtime. We apply our approach to 39 representative parallel applications and evaluate it on two representative heterogeneous many-core platforms: a CPU-XeonPhi platform and a CPU-GPU platform. Compared to the single-stream version, our approach achieves, on average, a 1.6x and 1.1x speedup on the XeonPhi and the GPU platform, respectively. These results translate to over 93% of the performance delivered by a theoretically perfect predictor.

show abstract

Section: Domain-specific Optimizationsmentioning

confidence: 99%

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Zhang

Fang

Yang

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…For instance, given the performance of a task on an idle node, the performance on a loaded node can be predicted using time series forecasting methods [66]. Another approach to predict performance degradation due to resource sharing is based on the current load on shared CPU resources, as revealed by hardware performance counters [67,68].…”

Section: Principal Performance Factorsmentioning

confidence: 99%

“…Zhao et al [68] predict the execution duration of a task in relationship to the number of threads by applying a thread resource contention model (Section 4.4). Each thread is treated like an independent single-threaded instance of the task, contending for CPU resources.…”

Section: Scale Modeling At the Task Levelmentioning

confidence: 99%

Predictive performance modeling for distributed batch processing using black box monitoring and machine learning

Witt

Bux

Gusew

et al. 2019

Information Systems

View full text Add to dashboard Cite

In many domains, the previous decade was characterized by increasing data volumes and growing complexity of computational workloads, creating new demands for highly data-parallel computing in distributed systems. Effective operation of these systems is challenging when facing uncertainties about the performance of jobs and tasks under varying resource configurations, e. g., for scheduling and resource allocation. We survey predictive performance modeling (PPM) approaches to estimate performance metrics such as execution duration, required memory or wait times of future jobs and tasks based on past performance observations. We focus on non-intrusive methods, i. e., methods that can be applied to any workload without modification, since the workload is usually a black-box from the perspective of the systems managing the computational infrastructure. We classify and compare sources of performance variation, predicted performance metrics, required training data, use cases, and the underlying prediction techniques. We conclude by identifying several open problems and pressing research needs in the field.

show abstract

“…For multi-threaded CPU tasks, we assume the performance would be perfectly scaled up with the number of threads. The assumption is reasonable since MapReduce applications are data parallel and do not include synchronization inside a task, and the performance interference across multiple threads caused by shared cache and bandwidth contentions can be predicted using the approach in [39], which is ignored in this paper. So the data processing time under a given configuration k can be computed using Equation 5, and the data reading time will be discussed in Section 4.4.…”

Section: Modeling Data Processing Speedmentioning

confidence: 99%

“…There has been a lot of work addressing contentions on shared cache [10,23,38], memory bandwidth [15,37,36], memory subsystem [26,27,40,17,33,34,39], and I/O resource [6,35,24]. Meanwhile, GPUPerf [31] has been developed to predict the performance and understand bottlenecks of GPGPU applications.…”

Section: Related Workmentioning

confidence: 99%

Hadoop+

Cui

Lü

et al. 2015

Proceedings of the 29th ACM on International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

Despite the widespread adoption of heterogeneous clusters in modern data centers, modeling heterogeneity is still a big challenge, especially for large-scale MapReduce applications. In a CPU/GPU hybrid heterogeneous cluster, allocating more computing resources to a MapReduce application does not always mean better performance, since simultaneously running CPU and GPU tasks will contend for shared resources.This paper proposes a heterogeneity model to predict the shared resource contention between the simultaneously running tasks of a MapReduce application when heterogeneous computing resources (e.g. CPUs and GPUs) are allocated. To support the approach, we present a heterogeneous MapReduce framework, Hadoop+, which enables CPUs and GPUs to process big data coordinately, and leverages the heterogeneity model to assist users in selecting the computing resources for different purposes.Our experimental results show three benefits. First, Hadoop+ exploits GPU capability, and achieves 1.4x to 16.1x speedups over Hadoop for 5 real applications when running individually. Second, the heterogeneity model can be used to allocate GPUs among multiple simultaneously running MapReduce applications, bringing up to 36.9% (17.6% in average) speedup when multiple applications are running simultaneously. Third, the model is verified to be able to select the optimal or most cost-effective resource consumption.

show abstract

Predicting Cross-Core Performance Interference on Multicore Processors with Regression Analysis

Cited by 23 publications

References 45 publications

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures

Predictive performance modeling for distributed batch processing using black box monitoring and machine learning

Hadoop+

Contact Info

Product

Resources

About