This website uses cookies. By using this site, you consent to the use of cookies. For more information, please take a look at our Privacy Policy.
Home > FPGA Technical Tutorials > FPGAs: World Class Designs > FPGA Architectures > FINE-, MEDIUM-, AND COARSE-GRAINED ARCHITECTURES

TABLE OF CONTENTS

Xilinx FPGA FPGA Forum

FINE-, MEDIUM-, AND COARSE-GRAINED ARCHITECTURES

FONT SIZE : AAA

 It is common to categorize FPGA offerings as being either fine grained or  coarse grained. In order to understand what this means, we first need to remind  ourselves that the main feature that distinguishes FPGAs from other devices is  that their underlying fabric predominantly consists of large numbers of relatively simple programmable logic block “ islands ” embedded in a “ sea ” of programmable interconnect ( Figure 2-1 ).   

In the case of a fine-grained architecture , each logic block can be used to  implement only a very simple function. For example, it might be possible to configure the block to act as any 3-input function, such as a primitive logic gate (AND,  OR, NAND, etc.) or a storage element (D-type flip-flop, D-type latch, etc.).

In the case of a coarse-grained architecture , each logic block contains a  relatively large amount of logic compared to their fine-grained counterparts.  For example, a logic block might contain four 4-input LUTs, four multiplexers, four D-type flip-flops, and some fast carry logic (see the following topics  in this chapter for more details).

Underlying FPGA fabric.png

An important consideration with regard to architectural granularity is that  fine-grained implementations require a relatively large number of co nnections  into and out of each block compared to the amount of functionality that can be  supported by those blocks. As the granularity of the blocks increases to mediumgrained and higher, the amount of connections into the blocks decreases compared to the amount of functionality they can support. This is important because  the programmable interblock interconnect accounts for the vast majority of the  delays associated with signals as they propagate through an FPGA.

Insider Info  

In addition to implementing glue logic and irregular structures like state machines,  fine-grained architectures are said to be particularly efficient when executing systolic algorithms (functions that benefit from massively parallel implementations).  These architectures are also said to offer some advantages with regard to traditional  logic synthesis technology, which is geared toward fine-grained ASIC architectures.

  • XC18V02PC44BRT

    Manufacturer:Xilinx

  • Xilinx PLCC44
  • Product Categories:

    Lifecycle:Active Active

    RoHS: -

  • XC4VLX60-10FF1148I

    Manufacturer:Xilinx

  • FPGA Virtex-4 LX Family 59904 Cells 90nm Technology 1.2V 1148-Pin FCBGA
  • Product Categories: FPGAs (Field Programmable Gate Array)

    Lifecycle:Active Active

    RoHS: No RoHS

  • XC4VLX60-10FFG668C

    Manufacturer:Xilinx

  • FPGA Virtex-4 LX Family 59904 Cells 90nm Technology 1.2V 668-Pin FCBGA
  • Product Categories: FPGAs

    Lifecycle:Active Active

    RoHS:

  • XC18V02VQ44AEN

    Manufacturer:Xilinx

  • EEPROM
  • Product Categories:

    Lifecycle:Active Active

    RoHS: -

  • XC2S30-5TQ144C

    Manufacturer:Xilinx

  • FPGA Spartan-II Family 30K Gates 972 Cells 263MHz 0.18um Technology 2.5V 144-Pin TQFP
  • Product Categories: FPGAs

    Lifecycle:Active Active

    RoHS: No RoHS

Need Help?

Support

If you have any questions about the product and related issues, Please contact us.