Runtime power monitoring in high-end processors: methodology and empirical data

By Canturk Isci, Margaret Martonosi. Proceedings. 36th Annual IEEE/ACM International Symposium on Microarchitecture, 2003. MICRO-36., 2003

662 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/4681e5c81986033c4ed551937791f5189bf3f2e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Hardware and Architecture

Citations in the corpus

RAPL: Memory power estimation and capping (2010, background): “Prior work has looked extensively at using activity based modeling for processor power estimation, with its benefits and shortcomings well studied and documented [19, 20].”
Dynamo: Facebook's Data Center-Wide Power Management System (2016, background): “This is because the network hardware in our data centers does not yet support RAPL-like power capping.”
Data Center Energy Consumption Modeling: A Survey (2016, methodology): “[69][85] [156][158] single core Performance counter based Choosing the proper performance counter(s) is a challenge, while certain performance counters may not be available across different processors.”
Energy characterization and instruction-level energy model of Intel's Xeon Phi processor (2013, methodology): “use performance counters to estimate activity factors for Pentium 4’s architecture-level energy model [5].”
Informed Microarchitecture Design Space Exploration Using Workload Dynamics (2007, neutral): “[5] C. Isci and M. Martonosi, Runtime Power Monitoring in High-End Processors: Methodology and Empirical Data, MICRO, 2003.”
Accurate online power estimation and automatic battery behavior based power model generation for smartphones (2010, background): “We then explain the development of training software to exercise the relevant power management and activity states of hardware components with signiﬁcant power consumptions.”
SimPoint 3.0: Faster and More Flexible Program Phase Analysis (2005, background): “Isci and Martonosi [13, 14] have shown the ability to dynamically identify the power phase behavior using power vectors.”
PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications (2010, methodology): “The approaches used include simulation [6], [11], [21], [29], [35], [36], [37], performance-profile-based estimation [27], [30], and direct measurement [5], [13], [27], [30].”