Fatigue at High Temperature

Modern embedded systems execute applications, which interacts with the operating system and hardware differently depending on type of workload. These cross-layer interactions result in wide variations of chipwide thermal profile. In this paper, a reinforcement learning-based run-time manager is proposed that guarantees application-specific performance requirements and controls the POSIX thread allocation and voltage/frequency scaling for energy-efficient thermal management. This controls three thermal aspectspeak temperature, average temperature and thermal cycling. Contrary to existing learning-based run-time approaches that optimize energy and temperature individually, the proposed run-time manager is the first approach to combine the two objectives, simultaneously addressing all three thermal aspects. However, determining thread allocation and core frequencies to optimize energy and temperature is an NP-hard problem. This leads to an exponential growth in the learning table (significant memory overhead) and a corresponding increase in the exploration time to learn the most appropriate thread allocation and core frequency for a particular application workload. To confine the learning space and to minimize the learning cost, the proposed run-time manager is implemented in a two-stage hierarchy: a heuristic-based thread allocation at a longer time interval to improve thermal cycling, followed by a learning-based hardware frequency selection at a much finer interval to improve average temperature, peak temperature and energy consumption. This enables finer control on temperature in an energy-efficient manner, while simultaneously addressing scalability, which is a crucial aspect for multi-/many-core embedded systems. The proposed hierarchical run-time manager is implemented for Linux running on nVidia's Tegra SoC, featuring four ARM Cortex-A15 cores. Experiments conducted with a range of embedded and cpu intensive applications demonstrate that the proposed run-time manager not only reduces energy consumption by an average 15% with respect to Linux, but also improves all the thermal aspects -average temperature by 14 • C, peak temperature by 16 • C and thermal cycling by 54%.

show abstract

“…Calculating, from each thermal cycle, the number of cycles to failure using CoffinManson's rule [Manson 1972;Coffin Jr 1973].…”

Section: Lifetime Reliabilitymentioning

confidence: 99%

Adaptive and Hierarchical Runtime Manager for Energy-Aware Thermal Management of Embedded Systems

Das

Al-Hashimi

Merrett

2016

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…Crack closure i s m o r e a t h i g h t e m p e r a t u r e t h a t i n f l uences crack growth rates. Therefore, C. Life prediction methods: Life prediction in high temperature fatigue can be grouped into five categories namely i) Linear summation of time and cycle [42,43] ii) Modifications of low-temperature fatigue relationships [44] iii) Ductility exhaustion [45] iv) Strain range partitioning [46] and v) Continuous damage parameter [47][48][49]. For example, the model …”

Section: B Crack Growthmentioning

confidence: 99%

Metal Fatigue and Basic Theoretical Models: A Review

Bhat¹,

Patibandla²

2011

Alloy Steel - Properties and Use

View full text Add to dashboard Cite

“…, [42] in electronic packaging industry on an average the typical fatigue life of solder materials ranges from 500 cycles to 3500 cycles depending on the type of loading, type of material and the experimental conditions. Hence in the field of electronic packaging most use of strain based models is almost unanimously accepted.…”

Section: Stress Based Modelsmentioning

confidence: 99%

Effect of Structural Design Parameters on Wafer Level CSP Ball Shear Strength and Their Influence on Accelerated Thermal Cycling Reliability

Lakhkar

Viswanadham

Agonafer

2009

Volume 5: Electronics and Photonics

View full text Add to dashboard Cite

Ball shear testing is typically conducted in Wafer level chip scale package (WLCSP) fabrication to estimate the strength of the solder ball attachment. Generally, the solder ball shear strength is dependent on the solder ball size, pad size, solder/pad interface treatment, reflow temperature and time. Solder ball strength is also a function of ram speed and height at which the ball is sheared with respect to the wafer. Recent investigations suggest that ball shear test is being used as an indicator for board level reliability of assemblies. In current market lead time for launching a new product is very short. Unfortunately, it takes several weeks to qualify a new product by board level qualification process. If there is a methodology through which one can predict the board level performance by extrapolating the wafer level test, it will save great amount of resources in testing and millions of dollars worth of testing time. In the first part of this study, we conducted a wafer level ball shear test. A DOE was created for varying wafer level structural parameters like solder ball size and type. Ball shear tests and Accelerated thermal cycling have similar failure signatures of compression on inner side and tension on outer side. Thus, for specific cases there is a possibility of correlating the two failure methodologies based on their failure signatures. Strain rate for ball shear test was determined based on shear speed and solder pad diameter. Strain rate for accelerated thermal cycling was determined based on difference in CTE between board and package. In this paper, results from ball shear test and accelerated thermal cycling are compared to find correlations for specific cases. The correlations derived from this study are statistical and empirical.

show abstract

Fatigue at High Temperature

Cited by 132 publications

References 12 publications

Adaptive and Hierarchical Runtime Manager for Energy-Aware Thermal Management of Embedded Systems

Adaptive and Hierarchical Runtime Manager for Energy-Aware Thermal Management of Embedded Systems

Metal Fatigue and Basic Theoretical Models: A Review

Effect of Structural Design Parameters on Wafer Level CSP Ball Shear Strength and Their Influence on Accelerated Thermal Cycling Reliability

Contact Info

Product

Resources

About