Multi-Objective Optimization to Improve Both Thermal and Device Performance of a Nonuniformly Powered Micro-Architecture

2010 ◽  
Vol 132 (2) ◽  
Author(s):  
Saket Karajgikar ◽  
Dereje Agonafer ◽  
Kanad Ghose ◽  
Bahgat Sammakia ◽  
Cristina Amon ◽  
...  

Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, and memory controller has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional units dissipate little or no power. This highly nonuniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effects on computer performance, product reliability, and yield. Moving the functional units may reduce the junction temperature but can affect performance by a factor as much as 30%. In this paper, a multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. The analysis was performed for 90 nm Pentium IV Northwood architecture operating at 3 GHz clock speed. Each functional unit on the die has a specific role, so functional units with similar roles were grouped together. Thus, the actual Pentium IV die was divided into four groups (front end, execution cores, bus and L2, and out-of-order engine). Repositioning constraints were determined using circuit delay models of major functional units in a micro-architectural simulator. Thus, depending on the scenario, relocating functional units can result in virtually no performance loss (less than 2% is assumed to be minimal and is reported as 0%) to as much as 30% performance loss. From the results, the minimum and the maximum temperatures were 56.6°C and 62.2°C. This ΔT corresponds to thermal design power of 60.2 W. For microprocessors with higher thermal design power (115 W) and operating at higher clock speed, higher ΔT can be realized. Based on this paper’s analysis, the optimized scenario resulted in a junction temperature of 56.6°C at the cost of a 14% performance loss.

Author(s):  
Saket Karajgikar ◽  
Dereje Agonafer ◽  
Kanad Ghose ◽  
Bahgat Sammakia ◽  
Cristina Amon ◽  
...  

Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, memory controller, etc. has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional blocks dissipate little or no power. This highly non-uniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effect on computer performance and product reliability as well as yield. Moving the functional blocks may reduce the junction temperature but can also affect the performance by a factor as high as 35%. In this paper, multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. From the results, the minimum and the maximum temperature was 82.4°C and 94.5°C with a corresponding penalty on the performance of 35% and 0% respectively. The optimized location of the functional blocks resulted in a temperature of 83.2°C for a performance loss of 5%.


Author(s):  
Saket Karajgikar ◽  
Dereje Agonafer ◽  
Kanad Ghose ◽  
Bahgat Sammakia ◽  
Cristina Amon ◽  
...  

Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, memory controller, etc. has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional units dissipate little or no power. This highly non-uniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effects on computer performance, product reliability, and yield. Moving the functional units may reduce the junction temperature but can also affect performance by as much as 30%. In this paper, multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. From the results, the minimum and the maximum temperature was 56.6°C and 62.2°C with a corresponding penalty on the performance of 14% and 0% respectively. The numerical analysis was performed for 90 nm Pentium® IV Northwood architecture at 3 GHz clock speed.


Power loss is the most significant parameter in power system analysis and its adequate calculation directly effects the economic and technical evaluation. This paper aims to propose a multi-objective optimization algorithm which optimizes dc source magnitudes and switching angles to yield minimum THD in cascaded multilevel inverters. The optimization algorithm uses metaheuristic approach, namely Harmony Search algorithm. The effectiveness of the multi-objective algorithm has been tested with 11-level Cascaded H-Bridge Inverter with optimized DC voltage sources using MATLAB/Simulink. As the main objective of this research paper is to analyze total power loss, calculations of power loss are simplified using approximation of curves from datasheet values and experimental measurements. The simulation results, obtained using multi-objective optimization method, have been compared with basic SPWM, optimal minimization of THD, and it is confirmed that the multilevel inverter fired using multi- objective optimization technique has reduced power loss and minimum THD for a wide operating range of multilevel inverter.


Author(s):  
Hongtao Li ◽  
Meinrad Burer ◽  
Franc¸ois Marechal ◽  
Daniel Favrat ◽  
Guolian Hou ◽  
...  

With a given power demand pattern supplied by a set of pulverized fuel coal-fired (PC) power generation units at various locations, different power dispatching solutions will result in different fuel consumptions, CO2 emissions, and power generation costs. This is due to the performance differences of their shut-down and start-up processes as well as those under the operational conditions, and to fuel prices differences between different power stations. In this paper, a methodology characterized with a multi-objective optimization approach based on a fast evolutionary algorithm is employed to optimize the daily total power generation operating cost and the daily total CO2 emissions. The shut down and start-up processes are divided into 7 sub-operations: load-decreasing, shutdown, boiler ignition preparation, ignition-warming up, connecting to grid, load-increasing and stabilization process, according to their characteristics in order to calculate the fuel consumptions, the CO2 emissions and the cost. Available data have been used to derive the models that characterize the emission and cost performances of typical PC units as well as their rating and partial load performances [1]. From the results of the multi-objective optimization, the so called Pareto Optimal Frontiers (POFs) are used to evaluate the effect of CO2 tax on the optimal power dispatching solutions. The influence of SO2 tax on the CO2 abatement marginal cost is also analyzed.


Sign in / Sign up

Export Citation Format

Share Document