.png){kind=icon}
Return
Multi-objective voltage island floorplanning using sequence pair representation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.suscom.2012.01.004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the nanometer era of VLSI design, high power consumption is considered to be a show-stopper for many applications. Voltage island design has emerged as a popular method for addressing this issue. This technique requires multiple supply voltages on the same chip with blocks assigned to different supply voltages. Implementation challenges force blocks with similar supply voltages to be placed contiguous to one another, thereby creating islands. Classical floorplanners assume a single supply voltage in the entire chip and thus require additional design steps to realize voltage islands. In this paper we present a new multi-objective floorplanning algorithm based on the sequence pair representation that can floorplan blocks in the form of islands. Given the possible supply voltage choices for each block, the floorplanner simultaneously attempts to reduce power and area of the chip. Our floorplanner integrates the tasks of assigning blocks to different supply voltages and the placing of the blocks in the chip. Compared to previous work, the proposed floorplanner on average reduces the area overhead of the chip by 13.5% with 34% runtime improvement. As power and area are jointly optimized, we also explore the trade-off between these cost functions. Experimental results show that equal weight to area and power cost function do not provide the best floorplan solution. (C) 2012 Elsevier Inc. All rights reserved.
Keywords:
Voltage island
Floorplanning
Sequence pair
Pareto front
Optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
S
IF:
5.7
Papers:
966
Citations:
2.9K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveFloquet Majorana Fermions for Topological Qubits in Superconducting Devices and Cold-Atom Systems
OAAI
OAAIShareSaveShareSaveShareSave
View more