2007 IFIP International Conference on Very Large Scale Integration 2007
DOI: 10.1109/vlsisoc.2007.4402472
|View full text |Cite
|
Sign up to set email alerts
|

A software-supported methodology for designing high-performance 3D FPGA architectures

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2008
2008
2013
2013

Publication Types

Select...
5
2

Relationship

2
5

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 8 publications
0
7
0
Order By: Relevance
“…Table II clearly indicates that the proposed 3D FPGA design can provide significant advantages over the corresponding 2D architecture by reducing the performance in DPP on average 26.32% (non-interlaced) 20.91% (h = 2), and 13.16% (h = 4), respectively. Also, Table III shows that on average 34.72% (noninterlaced), 44.56% (h = 2), and 50.78% (h = 4) ADP reductions can be obtained from the proposed 3D FPGA design comparing with the 2D FPGA architecture.…”
Section: Comparisonsmentioning
confidence: 99%
See 1 more Smart Citation
“…Table II clearly indicates that the proposed 3D FPGA design can provide significant advantages over the corresponding 2D architecture by reducing the performance in DPP on average 26.32% (non-interlaced) 20.91% (h = 2), and 13.16% (h = 4), respectively. Also, Table III shows that on average 34.72% (noninterlaced), 44.56% (h = 2), and 50.78% (h = 4) ADP reductions can be obtained from the proposed 3D FPGA design comparing with the 2D FPGA architecture.…”
Section: Comparisonsmentioning
confidence: 99%
“…In other words, one of the drawbacks in designing a 3D FPGA is that it would require more silicon area for implementation. Thus, the selection of appropriate connectivity across the different layers of the 3D FPGA architecture is essential to ensure the high performance design [20]. This paper proposes an interlaced S 2D -boxes and S 3D -boxes placement approach to reach the high performance in DPP and ADP for 3D FPGA design applications.…”
Section: Interlaced S-boxes Placementmentioning
confidence: 99%
“…The first of them affects devices, where each layer can be thought as a "functional layer" [11,12], while in the latter approach each of the layers is specialized (i.e. memory, switches, logic, etc) [13]. Even thought the proposed architecture affects a 3D FPGA, where all the layers have identical hardware resources (i.e.…”
Section: Introductionmentioning
confidence: 99%
“…The interconnection network of largescale reconfigurable architectures exhibits increased resistance (R) and capacitance (C) values. However, in the 3D approach, the circuits are split up into smaller parts and stacked appropriately alleviating such problems [1,4,5].…”
Section: Introductionmentioning
confidence: 99%
“…More specifically, the first one is responsible for the application partitioning to device layers, the second one deals with the placement of each layer and the routing procedure on the 3D-reconfigurable architectures (with full-custom interconnection fabric), while the last one performs the power/energy estimations of these devices. All of them are part of the new Design Framework, named 3D MEANDER [5,15].…”
Section: Introductionmentioning
confidence: 99%