Proceedings of the IEEE Custom Integrated Circuits Conference
DOI: 10.1109/cicc.1992.591107
|View full text |Cite
|
Sign up to set email alerts
|

An MPGA Compatible FPGA Architecture

Abstract: A bs t r ac t This paper describes a new FPGA architecture which relies on a proprietary antifuse technology coupled with 0.8 micron CMOS technology. In this architecture, individual CMOS transistors, not just logic blocks, can be configured to match MPGA macrocells transistor for transistor. Small mux like blocks are also available for logic or latch functions or collectively as configurable static RAMS. The architecture supports macrocell libraries with delay and resource usages similar to commercial 1.5 mic… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 21 publications
(10 citation statements)
references
References 7 publications
(5 reference statements)
0
10
0
Order By: Relevance
“…Although we expect these blocks to be used infrequently, the roles they serve in asynchronous circuits are essential, and are not implementable in standard digital logic. Thus, they must appear as special, built-in blocks in any FPGA which hopes to implement asynchronous circuits, but which does not allow mappings to program circuits at the transistor level (for an example of an EPGA which might allow sufficient transistor-level programming to implement an arbiter, see [Marple 1992]). For examples of how both types of blocks are used, please see figure 4.…”
Section: Fumentioning
confidence: 99%
“…Although we expect these blocks to be used infrequently, the roles they serve in asynchronous circuits are essential, and are not implementable in standard digital logic. Thus, they must appear as special, built-in blocks in any FPGA which hopes to implement asynchronous circuits, but which does not allow mappings to program circuits at the transistor level (for an example of an EPGA which might allow sufficient transistor-level programming to implement an arbiter, see [Marple 1992]). For examples of how both types of blocks are used, please see figure 4.…”
Section: Fumentioning
confidence: 99%
“…As used in the original gate arrays, the most simple and un-specific way of providing this capability is to use a transistor as the basic logic element, and build gates and storage elements from it. This approach was indeed attempted in a commercial FPGA from the now-defunct company Crosspoint [144]. This kind of very fine-grained logic block, however, requires the use of large amounts of programmable interconnect to create any typical logic function.…”
Section: Fpga Logic Block Fundamentals and Trade-offsmentioning
confidence: 99%
“…FPGA architects over the last two decades have selected basic logic blocks made of transistors (noted above) [144], NAND gates [160], an interconnection of multiplexers [79], lookup tables [49], and PAL-style wide-input gates [217]. These choices were originally driven by intuitive insights on the part of architects, typically with very little data or analysis, with a few exceptions [79].…”
Section: Fpga Logic Block Fundamentals and Trade-offsmentioning
confidence: 99%
See 1 more Smart Citation
“…Base logic units are most typically implemented as LUTs [9], but NAND gates [10], transistors [11], and multiplexers [12] have also been used. A homogeneous FPGA is an FPGA that consists of only base logic units and programmable routing.…”
Section: Definitions For Modern Fpgasmentioning
confidence: 99%