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




Authors: Paul-Jules Micolet, Aaron Smith, Christophe Dubach      

Motivation:
There exists no accurate as well as automated solution for optimizing the performance of streaming applications at both hardware level and software level. This paper presents a machine learning technique to get near optimal performance using software level threads and hardware level cores. It analyzes the effect of number of threads and number of cores on an application’s performance and attempts to get optimal performance by determining appropriate number of threads and number of cores of a Dynamic Multicore Processor using static code features of the application.

Positive Points:

[1] Paper analyzes the impact of thread partitioning on performance of various StreamIt applications for individual cores and composed cores. It concludes that the performance of an application follows the same trend and does not depend on the composition of cores. Hence, it reduces the problem of finding set of threads and core composition to two separate problems that can be modeled individually.

[2] It uses KNN model to get optimum number of threads and uses linear regression to get optimal core composition for a thread. It extracts over 50 features from StreamIt applications and only uses features which are highly correlated to optimal number of threads making the model simple. It also synthesizes benchmarks to get sufficient amount of data points for training.

[3] It unrolls loops in the program code which facilitates Thread Level Parallelism (TLP) and Instruction Level Parallelism (ILP) to estimate the optimum partitioning of the program by statically analyzing the code.

Negative Points:

[1] Paper considers variables which are highly correlated with the optimal number of threads but only considers the positive correlation and doesn’t consider negative correlation for KNN model. It also assumes that the features have similar range and hence it uses Euclidean distance for KNN without normalizing features.

[2] Model determines optimal thread number with 33% accuracy which improves to 67% for two threads away from optimal solution which is 10-20% below optimum performance.

[3] As a future work, these methods could be enhanced to take into account running multiple applications and optimizing overall number of threads and core composition using preemptive scheduling.

[4] It uses default partitioning scheme of StreamIt compiler. This partitioning could be improved using [1] which could lead to better overall performance.

[5] Will the method work if the rates of the pipes in programs are dynamic? Do we need runtime analysis of the program?

- Saurabh Gupta

Comments

  1. UnknownFebruary 19, 2019 at 6:44 AM

    Good analysis. Your correct that the paper doesn't consider dynamic stream rates; actually very little analysis of the applications themselves is presented. A question is for what type of streaming applications is this methodology likely to be effective. Also, it seemed that feature extraction was a manual process. Would the same features be predictive for other applications? How general is the StreamIt application suite.

    ReplyDelete

Post a Comment

Popular posts from this blog

A Machine Learning Approach to Live Migration Modeling

Authors:  Changyeon Jo, Youngsu Cho, Bernhard Egger Seoul National University Summary:  This paper proposed a machine learning approach to predict the system metrics for different VM migration algorithms. These system metrics are affected by migration algorithm, host machine status and user applications and feasible for machine learning approach. The prediction model takes 21 system/application input features (including which algorithm), and generates 6 metrics as the output. As a result, it can accurately estimate each metrics under different application, VM and algorithms. One of the application, the paper provide a semi-automated algorithm selection based on this machine learning model and user-provided SLA (service level agreements) constraints. Questions about Machine Learning:  Why machine learning is applied: The combination of algorithm, VM status and current running applications status, is a huge searching space. Machine learning features: which algor...
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

Coordinated Management of Multiple Interacting Resources in Chip Multiprocessors: A Machine Learning Approach

Authors: Ramazan Bitirgen, Engin Ipek, Jose F. Martinez Motivation: Sharing system resources efficiently on chip multiprocessors (CMPs) platforms is the key to obtain high utilization and enforce system-level performance objectives. Unrestricted sharing of microarchitectural resources will result in destructive interference and unacceptable performance. However, the works focus on coordinated management of multiple interacting resources on CMPs are very scarce , even though several proposals focusing on addressing the management of a single microarchitectural resource exist. Aiming to fill this gap, this paper proposes a framework with the machine learning technology to manage multiple shared CMP resources in a coordinated fashion to enforce higher-level performance objectives. This novel mechanism consists of per-application hardware performance models and a global resource manager. Positive Points: 1. The global resource manager is able to aggregate each app...
Read more