In modern SRAM based Field Programmable Gate Arrays, a Look-Up Table (LUT) is the principal constituent logic element which can realize every possible Boolean function. However, this flexibility of LUTs comes with a heavy area penalty. A part of this area overhead comes from the increased amount of configuration memory which rises exponentially as the LUT size increases. In this paper, we first present a detailed analysis of a previously proposed FPGA architecture which allows sharing of LUTs memory (SRAM) tables among NPN-equivalent functions, to reduce the area as well as the number of configuration bits. We then propose several methods to improve the existing architecture. A new clustering technique has been proposed which packs NPN-equivalent functions together inside a Configurable Logic Block (CLB). We also make use of a recently proposed high performance Boolean matching algorithm to perform NPN classification. To enhance area savings further, we evaluate the feasibility of more than two LUTs sharing the same SRAM table. Consequently, this work explores the SRAM table sharing approach for a range of LUT sizes (4-7), while varying the cluster sizes (4-16). Experimental results on MCNC benchmark circuits set show an overall area reduction of ∼7% while maintaining the same critical path delay.
An Application Specific Inflexible FPGA (ASIF) is a tailored design, for a given group of known circuits, which is generated by extensively reducing the routing resources of an FPGA. In an ASIF, different dynamically reconfigurable application circuits are initially mapped and tested on an FPGA fabric. Subsequently, the FPGA fabric is reduced to achieve an efficient architecture for known application circuits. However, a large portion of ASIF is still occupied by fully flexible logic blocks, containing the same amount of area and SRAM memory cells, as found in a traditional FPGA. Thus, here lies a potential to further optimize the logic blocks of an ASIF at the expense of removing or reducing their reconfigurability. This work optimizes the logic blocks of an ASIF through the SRAM-Table sharing technique, without compromising their reconfigurability. Moreover, the routing channels of ASIF are further optimized by applying the Boolean functions (Gates) insertion technique. The applied techniques (SRAM-Table sharing and Boolean functions insertion) not only reduce the area, delay and power, but also minimize the reconfiguration time, bitstream size and the size of external memory required to store the bitstream of circuits. This optimized version of ASIF is termed as ASIF[Formula: see text]. Furthermore, an embedded FPGA in a System-on-Chip that requires the partial dynamic reconfiguration for known circuits, can be automatically reduced to an ASIF[Formula: see text]. It is found through experimental results that an ASIF[Formula: see text] is 4–9[Formula: see text] area-efficient and requires [Formula: see text] lesser number of SRAM cells, as compared to the previously proposed ASIF for a group of 2–5 circuits. It also achieves 34–53[Formula: see text] area saving as compared to a traditional FPGA.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.