A Machine Learning Approach to Mapping Streaming Workloads to Dynamic Multicore Processors

Authors:

Paul-Jules Micolet, Aaron Smith, Christophe Dubach


Motivation:

To determine how to partition and group the cores in a Dynamic Multicore Processors (DMPs) among application threads, this paper first studies the effect of thread partitioning and hardware resource allocation and then introduces a machine-learning methodology. The experiments are operated on StreamIt applications due to its parallelism feature.


Main points:

1. The best performance this paper talks about is a statistical result.
2. This paper analyses the effect of thread partitioning, core composition and the combination of both optimizations. The results show that thread partition and core composition are almost independent and the combination of these two optimizations has a better performance in the 15 benchmarks test.
3. The paper also studies the effect of loop transformation. The experiment results show that loop unrolling can help to speed up the performance but limited by the trade-off between ILT and TLP.
4. The paper uses KNN model to determine the number of threads for the application and linear regression model to determine the number of cores. The features are extracted from the static StreamIt code. Averagely, this machine learning approach is 16% less than the best in performance.


Trade-offs:

1. The features are extracted from the SteamIt built-in function which may miss some other impactful features.
2. That the StreamIt programs don’t have much conditional statements is a shortage.
3. The KNN method needs to find the best K. The result shows its accuracy is not as good as the combination. Will another method be more effective than KNN? Or determining the number of threads is not as important as the number of cores?

Besides, I don’t understand Table 2:

The paper says each column of this table presents the thread and the number in each cell presents the number of cores in this thread. However, according to the text, the best performance has 13 threads but the maximum number of the thread is 10. The machine learning approach has 8 threads while 7 in the table.


Simin Wang

Comments

  1. UnknownFebruary 19, 2019 at 6:50 AM

    It is true that there was some notable inaccuracy though the final result looked good. For point #2, conditional dataflow would be interesting though static pipelines are fairly common. I agree that Table 2 is very confusing!

    ReplyDelete

Post a Comment

Popular posts from this blog

A Machine Learning Approach to Live Migration Modeling

Dynamic management of resources in data centers improves data center utilization in terms of energy consumption and device utilization. Virtual machines are among techniques to achieve this goal. To enable the VM to adapt to dynamic fluctuations of workloads, Live Migrated virtual machines are introduced, which stands for moving a VM from one physical host to another while the VM keeps running. Live migration enables load balancing, fault tolerance, ease maintenance, etc. However, live migration is costly in terms of data traffic. Having an understanding of performance metrics of different live migration algorithms is important so that one can rely on an efficient algrothm to migrate a running VM is important. Therefore, this work uses a Machine Learning (ML) approach to predict key metrics of different live migration algorithms, and then find the best suitable choice for live migration. Indeed, given resource usage as well as the characteristics of VM work load, this paper predict...
Read more

StormDroid: A Streaminglized Machine Learning-Based System for Detecting Android Malware

Introduction: The paper approaches the problem of Malware Detection using machine learning approach. In this paper, the authors propose considering new type of features along with two traditionally used set of features for developing techniques for malware detection. Along with this proposal, the paper makes other contributions as well. The authors provide a new framework which is able to process information from large data sets as streams, and efficiently perform malware detection. Motivation: Android is an open platform for development. It has certainly made easy for everyone to develop and publish apps.  The number of apps published on Google store is in millions. However, it has also made easier for hackers to reach out to a larger population for malicious attacks. Additionally, with surge in the number of attacks on devices, more data is available for analysis which can be used by the machine learning models to identify malicious apps. This is motivation to use machine ...
Read more

CrystalBall: Statically Analyzing Runtime Behavior via Deep Sequence Learning

Image
Author:  Stephen Zekany, Daniel Rings, Nathan Harada, Michael A. Laurenzano, Lingjia Tang, Jason Mars Intro: Understanding the runtime behavior of the software is critical in many aspects of program development. A conventional approach to this problem is using dynamic profiling, meaning we have to run the program multiple times with environments that representative enough for the actual working situation. Besides that, a dynamic profiling approach has other weakness such as cannot profiling a subset of functions or paths very economically and requires re-profiling each time any changes is applied to the code. This paper presents a statically profiling method, harnessing the ability of RNN to discover the hidden information of hot path in the code. Also, since the training process uses intermediate representation as input, the result will have better generalization power. Methodology: The dataset is in the form of a basic block feature; each sequence of basic blocks repr...
Read more