Up By Their Bootstraps: Online Learning in Artificial Neural Networks for CMP Uncore Power Management

by Jae-Yeon Won, Xi Chen, Paul Gratz and Jiang Hu, from Texas A&M University and Vassos Soteriou from Cyprus University of Technology

This paper is focusing on the power management of un-core structure: Last-Level Cache (LLC) and Network-on-Chip (NoC). The method is using online learning ANN and assisted by PI control. They compare the offline/online ANN and many combination of different optimization method. Overall, they reduce the energy-delay product of uncore system by 27% versus state-of-the-art methodologies.

Motivation of this paper: 
1. The non-core (uncore) structure also consume lot of energy in modern CMP since the number and communication between cores increasing.
2. Most of previous core power management focused on either core DVFS or DVFS domain partitioning around cores and merely including a slice of the uncore.
3. In reality, the applications often have abrupt changes, which cannot be captured by rule-based controller like PI (Proportional Integral).

Major points in this paper: 
1. An ANN-based, PI-assisted online uncore power management is proposed. It can achieve 27% energy-delay product reduction for uncore system, and the performance degradation is less than 3%.
2. A offline ANN is also designed and analyzed, which is less effective than the online ANN (with PI-assisted).
3. the overhead of online ANN is demonstrated insignificant and incremental power is 0.32% of total CMP power.

Strength: 
1. This paper focus on another power consumption domain in SoC, which is un-core structure (shared cache, NoC and etc. ). The proposed online ANN is demonstrated effective and cheap.

2. They overcome the weakness of ANN "online training to different applications" by feedback adaptation and self-sharpening. Both method increases the speed of ANN adapting to the current application requirement.

Weakness: 
1. 2 key background is missing: a) why uncore power consumption is predictable, b) for abrupt change application, why PID control doesn't work (D for derivative, which is exactly handling the abrupt change).

2. The paper gives conclusion of uncore system energy-delay consumption is reduced by 27%. However, the paper doesn't mention the proportion of uncore power consumption and entire chip power consumption.

3. The model of ANN is chosen by experience (mentioned in paper), which can be demonstrated by comparing other configuration. The ANN also take past m intervals (then m*n inputs), which can be improved by RNN with m length memory.

4. Figure 7 shows the effect of different gain to the ANN learning comparing with PI controller. However, for the purpose of this paper, the ANN should provide better prediction rather than close to PI result.

Overall, this paper provides a effective method for ANN-PI online uncore PM method, but details requires more demonstration.


Minjun Wu
02/28/2019


Comments

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