WO2022245390A1 - Logic cell for programmable gate array - Google Patents

Logic cell for programmable gate array Download PDF

Info

Publication number
WO2022245390A1
WO2022245390A1 PCT/US2021/060229 US2021060229W WO2022245390A1 WO 2022245390 A1 WO2022245390 A1 WO 2022245390A1 US 2021060229 W US2021060229 W US 2021060229W WO 2022245390 A1 WO2022245390 A1 WO 2022245390A1
Authority
WO
WIPO (PCT)
Prior art keywords
input
output
carry
logic cell
multiplexer
Prior art date
Application number
PCT/US2021/060229
Other languages
English (en)
French (fr)
Inventor
Jonathan W. Greene
Marcel Derevlean
Original Assignee
Microchip Technology Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US17/529,522 external-priority patent/US11671099B2/en
Application filed by Microchip Technology Inc. filed Critical Microchip Technology Inc.
Priority to DE112021007047.9T priority Critical patent/DE112021007047T5/de
Priority to CN202180096762.4A priority patent/CN117157880A/zh
Publication of WO2022245390A1 publication Critical patent/WO2022245390A1/en

Links

Classifications

    • HELECTRICITY
    • H03ELECTRONIC CIRCUITRY
    • H03KPULSE TECHNIQUE
    • H03K19/00Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
    • H03K19/02Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components
    • H03K19/173Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components using elementary logic circuits as components
    • H03K19/177Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components using elementary logic circuits as components arranged in matrix form
    • H03K19/17724Structural details of logic blocks
    • H03K19/17728Reconfigurable logic blocks, e.g. lookup tables
    • HELECTRICITY
    • H03ELECTRONIC CIRCUITRY
    • H03KPULSE TECHNIQUE
    • H03K19/00Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
    • H03K19/02Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components
    • H03K19/173Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components using elementary logic circuits as components
    • H03K19/177Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components using elementary logic circuits as components arranged in matrix form
    • H03K19/17724Structural details of logic blocks
    • H03K19/17732Macroblocks

Definitions

  • the present invention relates to logic circuits in user-programmable integrated circuits such as a field programmable gate array (FPGA). More particularly, the present invention relates to logic cell architecture for such programmable integrated circuits to provide improved support for compressors.
  • FPGA field programmable gate array
  • FPGAs are integrated circuits composed of logic cells connected by a programmable routing network.
  • any logic cell output provided to the programmable routing network can be transmitted through the network to any logic cell input connected to the network.
  • a common type of logic cell includes a K-input look-up table (LUT), multiplexers, and carry chain logic. Such a logic cell would have at least K inputs coming from the programmable routing network and a carry input coming from the carry output of a previous cell in a chain of logic cells.
  • LUT K-input look-up table
  • One important property of an FPGA logic cell is how many of its inputs and outputs are provided by or to the programmable routing network.
  • the versatility of a logic cell may increase as the number of inputs and outputs available from or to the programmable routing network increases but so does the complexity and cost of the FPGA. From a cost metric consideration, a logic cell architecture achieving desired functionality with fewer inputs and outputs required to be connected to the programmable routing network may be preferable to a different architecture that achieves the same functionality but requires more inputs and outputs to be connected to the programmable routing network.
  • Another important property of an FPGA logic cell is the number K of inputs to the LUT.
  • K may range from 2 to 10 or more, but the most common values in practice are 3, 4 and 6.
  • a more general way of defining K applicable to any logic cell is as the largest number such that for every function of K inputs, the logic cell can be configured to compute it.
  • FPGA logic cells may be used to form compressors.
  • Compressors are a family of logic circuits that take multiple binary numerical values as inputs and produce their sum represented in fewer bits.
  • the well-known full adder can also be referred to as a 3:2 compressor because it takes three one-bit inputs and produces a single bit sum and single bit carry-out output. (Collectively the two bits corresponding to the sum and carry out indicate a count of the number of ones among the inputs).
  • compressors may be organized in a chain similar to a carry chain, with each compressor receiving one or more additional inputs from the previous compressor in the chain and generating the same number of additional outputs to the next compressor in the chain.
  • An example is a 4:2 compressor.
  • Some prior art logic cell architectures require two logic cells to implement each 3 :2 compressor: one to produce each of the two outputs.
  • Other prior art logic cell architectures can implement a 3:2 compressor with a single logic cell at the cost of more required connections with the programmable routing network.
  • a single logic cell architecture capable of implementing a 3:2 compressor with fewer required connections with the programmable routing network for power efficiency would be beneficial.
  • binary neural networks are networks that quantize weights and activations with binary values instead of full precision values.
  • Binary neural networks often require implementation of a function called “population count” or “pop count”. This function represents the number of ones among a set of M Boolean inputs as a log2(M)-bit binary output value.
  • Pop counters are typically implemented using many compressors.
  • a logic cell for a programmable logic integrated circuit apparatus includes K-input lookup table (LUT) circuitry including: i) a first (K-l)-input LUT and a second (K-l)-input LUT both sharing in common second through Kth inputs to the K-input LUT, each of the first and second (K-l)-input LUTs having an output; and ii) a first multiplexer having a first input coupled to the output of the first (K-l)-input LUT, a second input coupled to the output of the second (K-l)-input LUT, and a select input coupled to a first input of the K-input LUT circuitry.
  • LUT K-input lookup table
  • the first multiplexer provides a primary output Y of the logic cell, wherein Y is any independent function of the K inputs.
  • the logic cell includes a carry circuit with an X multiplexer coupled to provide an output selected from one of a constant logic reference and the primary output Y; and an exclusive-OR gate providing a sum output S, wherein the exclusive-OR gate is coupled to receive the output of the X multiplexer as a first input and a carry -input as a second input.
  • the logic cell for a programmable logic integrated circuit includes a programmable routing network, wherein the K-input lookup table circuitry receives the K inputs from the programmable routing network, and wherein the programmable routing network receives the primary output and the sum output.
  • the logic cell includes K-input lookup table circuitry for providing the primary output and a carry circuit coupled to receive one or more signals from the lookout table and a carry -in input and which provides a carry-out output and sum output.
  • the carry-in input is not received from the programmable routing network and the carry-out output is not provided to the programmable routing network.
  • the carry-in input is received from a previous logic cell in a chain of logic cells, and the carry-out output is provided to a subsequent logic cell in the chain.
  • the logic cell can be selectively configured to provide the value of the carry-in input at the carry-out output while also providing any function of the K inputs at the primary output.
  • the logic cell can be selectively configured to provide the value of the carry-in input at the sum output while also providing any function of the K inputs at the primary output.
  • the logic cell can be selectively configured to provide one bit of an adder with the sum appearing at the sum output and a carry appearing at the carry out output. In one embodiment, the logic cell can be selectively configured to implement the final bit of a multi-bit adder with the sum appearing at the sum output and the carry out output selectively driven to a pre-determined value (e.g., 0 or 1).
  • K>4 such as 4 or 6.
  • K is not limited to these values and may be any non-negative integer value.
  • a method includes the step of a) providing K-input lookup table (LUT) circuitry comprising: i) a first (K-l)-input LUT and a second (K-l)-input LUT both sharing in common second through Kth inputs to the K-input LUT, each of the first and second (K-l)- input LUTs having an output, and ii) a first multiplexer having a first input coupled to the output of the first (K-l)-input LUT, a second input coupled to the output of the second (K-l)-input LUT, and a select input coupled to a first input of the K-input LUT circuitry, the first multiplexer providing a primary output Y of the logic cell.
  • LUT K-input lookup table
  • the method includes the step of b) providing a carry circuit coupled to receive a carry-in input (Cl) and to generate a carry-out output (CO) and a sum output (S), wherein the carry-out output is selectively independent of Y, wherein the carry circuit comprises: i) an X multiplexer coupled to provide an output selected from one of a constant logic reference and the primary output; and ii) an exclusive-OR gate providing the sum output, wherein the exclusive-OR gate is coupled to receive the output of the X multiplexer as a first input and the carry -input as a second input.
  • the method includes the step of c) generating the carry- out output selectively independent of Y, and d) propagating the carry -in input to a selected one of the carry-out output and the sum output of the logic cell.
  • FIG. l is a block diagram of a logic cell in accordance with an aspect of the present invention.
  • FIG. 2 illustrates two adders implemented using a chain of logic cells
  • FIG. 3 illustrates one embodiment of the logic cell’s P and X multiplexers and associated configuration circuitry in accordance with an aspect of the present invention
  • FIG. 4 illustrates configuration settings for configuring the logic cell of FIG. 1 to accomplish stated functions
  • FIG. 5 A is a block diagram of a 3:2 compressor implemented in accordance with an aspect of the present invention using the logic cell of FIG. 1;
  • FIG. 5B is a detailed view of a 3:2 compressor implemented in accordance with an aspect of the present invention using the logic cell of FIG. 1;
  • FIG. 6A is a functional block diagram of a 4:2 compressor
  • FIG. 6B is a block diagram of a 4:2 compressor implemented in accordance with an aspect of the present invention using the logic cell of FIG. 1;
  • FIG. 7 is a block diagram of a 2-input adder implemented in accordance with an aspect of the present invention using the logic cell of FIG. 1;
  • FIG. 8 illustrates one embodiment of a method of configuring the logic cell illustrated in FIG. 1.
  • the present invention improves the efficiency of existing LUT -based FPGA logic cells at implementing accumulators and counters in conjunction in parallel with producing primary outputs which are a function of the LUT inputs.
  • FIG. 1 an illustrative LUT -based logic cell 190 that allows improved efficiency for counters and accumulators is shown in FIG. 1.
  • the logic cell 190 of FIG. 1 includes K-input LUT circuitry shown within dashed lines 120 formed from a first (K-l)-input LUT 124a and a second (K-l)-input LUT 124b.
  • the small squares 126 and 128 represent configuration inputs used to define the functions of LUTs 124a and 124b respectively.
  • Both LUTs 124a and 124b share in common the K-l function inputs Im, Im, . . . Ihk shown at reference numerals 132, 134, and 136, respectively.
  • a first (2-input) multiplexer 122 (“Y multiplexer”) has a first data input coupled to the output F0 of the first (K-l)-input LUT 124a, a second data input coupled to the output FI of the second (K-l)-input LUT 124b, and a select input coupled to a function input Ini at reference numeral 130 of the LUT 120.
  • the data output of the Y multiplexer 122 serves as the output of the K-input LUT circuitry 120 and the primary output (Y) of the logic cell 190 as shown at reference numeral 48.
  • K 4.
  • the logic cell 190 of FIG. 1 also includes a carry-in input Cl 42, a carry-out output CO 44, and a sum output S 50.
  • a carry circuit 160 in the logic cell 190 of FIG. 1 includes a second multiplexer (“G multiplexer”) shown in FIG. 1 as a 4-input multiplexer 32 having a first data input coupled to the F0 output of the first K-l -input LUT 124a, a second data input coupled to the FI output of the second K-l -input LUT 124b, a third data input coupled to a logic-high reference, a fourth data input coupled to a logic-low reference, and a data output denoted G.
  • Select inputs shown as small square 34 coupled to configuration circuitry for the multiplexer 32 determine which one of the inputs of the G multiplexer 32 will be passed to its data output.
  • a third multiplexer (“P multiplexer”) is shown in FIG. 1 as a 3-input multiplexer 36 in the carry circuit 160 of the logic cell 190.
  • the P multiplexer 36 has a first data input coupled to the primary output, Y 48, of the K-input LUT circuitry 120 from the Y multiplexer 122, a second data input coupled to a logic-high reference, and a third data input coupled to a logic-low reference.
  • Configuration circuitry 38 selects which one of the inputs of the P multiplexer 36 will be passed to its data output denoted P 39.
  • a fourth multiplexer i.e. a carry-out multiplexer (“CO multiplexer”)
  • CO multiplexer a carry-out multiplexer
  • FIG. 1 A fourth multiplexer, i.e. a carry-out multiplexer (“CO multiplexer”), is shown in FIG. 1 as a 2-input multiplexer 40 in the carry circuit 160 of the logic cell 190.
  • the CO multiplexer 40 has a first data input coupled to the data output G 35 of the G multiplexer 32, a second data input coupled to the carry -in input Cl 42 of the logic cell 190, a select input coupled to the output P 39 of the P multiplexer 36, and a data output coupled to provide the carry-out output CO 44 of the logic cell 190.
  • a fifth multiplexer 86 (“X multiplexer”) in the carry circuit of the logic cell 190 has a first data input receiving the primary output, Y 48, of the first multiplexer 122 and a second data input coupled to a logic-low reference.
  • Configuration circuitry 88 selects which one of the inputs of the X multiplexer will be passed to its data output denoted X 89.
  • An exclusive-OR gate 46 in the carry circuit 160 of the logic cell 190 has a first input coupled to receive the carry-in input Cl 42, and a second input coupled to the data output X 89 of the X multiplexer 86.
  • the output of the exclusive-OR gate is the sum output, S 50, of the logic cell 190.
  • either of the F0 or FI inputs from LUTs 124a and 124b, and one of the logic reference inputs can be omitted from the G or P multiplexers (i.e., the second multiplexer 32 or third multiplexer 36).
  • the carry circuitry of one or more consecutive logic cells may use a carry-lookahead, carry-select, or similar logic functionally equivalent to the carry function as illustrated in FIG. 1 but able to operate at increased speed.
  • the logic cell 190 of FIG. 1 has K function inputs and a carry -in input.
  • the particular example shown in FIG. 1 includes K function inputs Ini 130, Im 132, Im 134, through Ihk 136.
  • additional function inputs driving both of LUTs 124a and 124b can be added.
  • the primary output Y 48 of the logic cell 190 presents a value that is any function of the K-l function inputs.
  • a second output (the carry-out output CO 44) presents a value present on the carry -in input Cl 42 or an output sourced by the second multiplexer 32 as selected by the output of the third multiplexer 36.
  • the inputs Ini, Im, Im, . . . Ihk, and outputs S and Y are connected to the programmable routing network 52.
  • FIG. 2 illustrates a chain of logic cells such as logic cell 190 within an FPGA.
  • the carry-out output (CO) of one logic cell directly drives the carry-in input (Cl) of the next cell in the chain and neither Cl nor CO needs to be connected to the programmable routing network.
  • FIG. 2 also illustrates the use of a chain of logic cells to implement a pair of adders 200 including ADDER1 210 and ADDER2 220.
  • the programmable routing network of FIG. 1 can be configured to place a plurality of logic cells such as logic cell 190 in a carry chain.
  • Each adder is comprised of a plurality of consecutively-coupled logic cells in the carry chain.
  • Each logic cell generates a corresponding sum bit S and a carry out (CO) output signal to provide to the carry -in input (Cl) of the next cell.
  • logic cell 212 includes a carry -in input Cl, a sum output S, and a carry-out output CO coupled to the carry-in input Cl of logic cell 214.
  • the logic cell 216 associated with the most significant bit of ADDER1 210 produces an output S representing the most significant bit of ADDER1.
  • Logic cell 216 also provides the proper CO signal 218 to the carry -in input of the logic cell corresponding to the least significant bit of ADDER2 220.
  • the configurations of the P, G, and X multiplexers may vary between the logic cell 212 associated with the least significant bit, the logic cell 216 associated with the most significant bit, and the logic cells such as 214 associated with the intermediate bits of ADDER1 210.
  • the P, G, and X multiplexers are configured by the respective configuration circuitry 38, 34, 88, to ensure the proper signals are output by each logic cell within the adders.
  • the P multiplexer is configured to prevent the carry from propagating into the first logic cell of the next adder (such as logic cell 222 of ADDER2).
  • FIG. 3 illustrates a combined implementation 300 of the, the P multiplexer (36) and its configuration circuitry (38) as circuitry 310 as well as the X multiplexer (86) and its configuration circuitry (88) as circuitry 320. Because the P multiplexer has three inputs and the X multiplexer has two inputs, there are six possible combinations of P and X multiplexer selections. However, only four out of the six possible combinations are of interest. These are listed in truth table 330 in FIG. 3. As a result the configuration circuitry for the P and X multiplexers can be implemented in as few as two configuration bits (CFG0 and CFG1) with the appropriate logic.
  • CFG0 and CFG1 configuration bits
  • the P multiplexer and configuration circuitry 310 includes NOR gate 312 receiving the primary output Y and a first configuration bit, CFG0. NOR gate 312 is coupled to NOR gate 314. The output of NOR gate 312 is provided as one of the inputs to NOR gate 314. NOR gate 314 also receives a second configuration bit, CFG1. The output of NOR gate 314 is output P 39.
  • the X multiplexer and configuration circuitry 320 includes NAND gate 322 which receives the two configuration bits, CFG0 and CFG1.
  • NAND gate 322 is coupled to NAND gate 324.
  • NAND gate 324 receives the output of NAND gate 322 and the primary output Y as inputs.
  • NAND gate 324 is coupled to inverter gate 326 such that the output of NAND gate 324 is provided to inverter gate 326.
  • the output of inverter gate 326 is output X 89.
  • NAND gate 324 is followed by inverter gate 326 to achieve an AND function.
  • gate 324 is replaced with an AND gate to dispense with the need for the inverter gate 326.
  • Truth table 330 illustrates the P 39 and X 89 outputs of the P multiplexer 36 and the X multiplexer 88, respectively of FIG. 1 based on the values of configuration bits CFGO and CFG1 provided to the P multiplexer and configuration circuitry 310 and the X multiplexer and configuration circuitry 320.
  • FIG. 4 illustrates configuration settings for configuring the logic cell of FIG. 1 to accomplish the various modes illustrated in the first column of table 400.
  • the logic cell 190 of the present invention as illustrated in FIG. 1 can be configured to provide any function of K inputs as Y and to propagate Cl unchanged through to CO (and leaving the S output unused), by setting the P multiplexer 36 so select 1 and the X multiplexer 86 to select Y.
  • the logic cell 190 of the present invention as illustrated in FIG. 1 can be configured to provide any function of K inputs at Y and to propagate Cl to the S output.
  • the output of the G multiplexer is propagated to the CO output. This is accomplished by setting the P multiplexer 36 so select 0 and the X multiplexer 86 to select 0. This mode is useful if the next logic cell in the chain starts an adder (such as logic cell 222 in FIG. 2).
  • the logic cell 190 of the present invention as illustrated in FIG. 1 can be configured to implement one bit of an adder with S reflecting the sum and CO as the carry-out to the next more significant bit of the adder, by setting the P multiplexer 36 so select Y and the X multiplexer 86 to select Y.
  • logic cell 190 of FIG. 1 can be configured to implement the most significant bit of an adder with S reflecting the sum.
  • the output of the G multiplexer is propagated to the CO output. This is accomplished by setting the P multiplexer 36 so select 0 and the X multiplexer 86 to select Y. This is useful if the next logic cell in the chain starts another adder (such as logic cell 222 in FIG. 2).
  • FIG. 5 A illustrates one embodiment of a 3:2 compressor 500 implemented using the logic cell 190 of FIG. 1.
  • a properly implemented 3:2 compressor 500 receives three signals (U, V, W) from the programmable routing network, computes two new signals, EXOR(U, V,W) and MAJ(U, V,W), and sends them back out to the programmable routing network.
  • the logic cells designated as “190-n” refer to instances of logic cell 190 of FIG. 1 where the value of “n” is used to distinguish between instances.
  • logic cell 190-0 is coupled to logic cell 190-1, with carry-out output CO of logic cell 190-0 coupled to the carry -in input Cl of logic cell 190-1.
  • “MAJ” is the majority function. The majority function produces a single output from multiple inputs. The majority function produces a “1” when more than 1 ⁇ 2 of its inputs are “1” and otherwise produces a “0”.
  • XOR refers to the Boolean exclusive or function which produces a “1” if and only if there are an odd number of inputs that are a “1” and otherwise produces a “0”.
  • the G multiplexer 32 of logic cell 190-0 provides the F0 input at its respective data output G 35;
  • the P multiplexer 36 of each of the logic cells 190-0 and 190-1 provides a logic low (i.e., 0) at its respective data output P 39;
  • the X multiplexer 86 of each of the logic cells 190-0 and 190-1 provides a logic low (i.e. 0) at its respective data output X 89.
  • the LUTs 124a, 124b and the G multiplexer 32 of logic cell 190-1 are free for other uses, or may be configured as described in relation to logic cell 190-0 to implement the first cell of another independent 3:2 compressor, as next described in relation to FIG. 5B.
  • FIG. 5B shows the internal details of how a single logic cell 190 can simultaneously implement the second stage (logic cell 190-1 in FIG. 5 A) of one compressor and the first stage (logic cell 190-0 in FIG. 5 A) of a second, independent compressor.
  • the X multiplexer 86 is configured as described in relation to logic cell 190-1 of FIG. 5A to provide the value at the S output that is required for the second stage of the first compressor.
  • the LUTs 124a and 124b, the P multiplexer 36, and the G multiplexer 32 are configured as described in relation to logic cell 190-0 of FIG. 5 A to provide the values at the Y and CO outputs that are required for the first stage of the second compressor.
  • M compressors can be implemented in M+l logic cells. The incremental cost of a 3:2 compressor is thus only one logic cell 190.
  • FIG. 6A illustrates a block diagram of one embodiment of a 4:2 compressor 600 formed from full adders 612, 614 coupled together as shown, i.e., the S output 50 of full adder 614 is fed to one of the inputs of full adder 612.
  • the W, V, and U inputs are fed to respective inputs of full adder 614, and the Z and T inputs are fed to respective input of full adder 612.
  • the N output is provided from the CO output of full adder 614
  • the M output is provided from the CO output of full adder 612
  • the L output is provided from the S output of full adder 612.
  • Each full adder 612, 614 has three equivalent inputs and a sum and carry output.
  • the compressor 600 is fed from inputs arbitrarily designated as inputs T, U, V, W, and Z. In practice, multiple instances of this compressor would be used, connected in a chain similar to a carry chain with the input T of one compressor driven by the output N of the previous compressor in the chain.
  • FIG. 6B is a block diagram illustrating how only two logic cells 190-0 and 190-1 are required to implement adders 612, 614 to form the 4:2 compressor 600 of FIG. 6A. Table 602 shows the configuration of logic cells 190-0 and 190-1 to implement this function.
  • the top full adder 614 of FIG. 6A is implemented as logic cell 190-1 of FIG. 6B, with an additional pass-through function to be described below so as to be available to the programmable routing network.
  • the lower full adder 612 is implemented in logic cell 190- 0, including generation of the signal M which then passes through logic cell 190-1 from the Cl input to the S output.
  • the N output of one 4:2 compressor implemented using logic cells 190-0 and 190-1 can be used to drive the T input of another 4:2 compressor implemented using the next two logic cells in the carry chain.
  • FIG. 7 is a block diagram of a 2-input, N-bit adder 700 implemented in accordance with an aspect of the present invention using logic cells 190.
  • the N-bit adder 700 employs N+l logic cells shown as 190-0 through 190-N connected as shown.
  • the Cl input of the logic cell 190-0 is coupled to a constant logic low “0” level.
  • the CO output of each logic cell 190-0 through 190-(N-1) is coupled to the Cl input of the next logic cell 190 in the adder 700.
  • the Ini and Im inputs of logic cells 190-0 through 190-(N-1) are coupled to the N operand inputs U[0] through U[N-1] and V[0] through V[N-1] , respectively, for the adder 700.
  • the S outputs of each logic cell 190-0 through 190-N form the sum outputs Z[0] through Z[N] for each of the N+l output bits of the adder.
  • the logic cell 190-N need only pass its carry-in (Cl) input to its sum (S) output and on to the programmable routing network.
  • the table 702 in FIG. 7 shows the configuration of each of the logic cells in the adder 700.
  • FIG. 8 illustrates a method for implementing modes from the function table 400 of FIG. 4.
  • the method includes the step 810 of providing K-input lookup table (LUT) circuitry comprising: i) a first (K-l)-input LUT and a second (K-l)-input LUT both sharing in common second through Kth inputs to the K-input LUT, each of the first and second (K-l)-input LUTs having an output, and ii) a first multiplexer having a first input coupled to the output of the first (K-l)-input LUT, a second input coupled to the output of the second (K-l)-input LUT, and a select input coupled to a first input of the K-input LUT circuitry, the first multiplexer providing a primary output Y of the logic cell.
  • K ⁇ 4 such as 3 or 4.
  • K is any non-negative integer.
  • the method of FIG. 8 includes the step 820 of providing a carry circuit coupled to receive a carry-in input Cl and to generate a carry-out output CO and a sum output S, wherein the carry-out output is selectively independent of Y, wherein the carry circuit comprises: i) an X multiplexer coupled to provide an output selected from one of a constant logic reference and the primary output Y; and ii) an exclusive-OR gate providing the sum output S, wherein the exclusive-OR gate is coupled to receive the output of the X multiplexer as a first input and the carry -in input as a second input.
  • Step 830 includes generating the carry-out output CO selectively independent of Y, i.e., by setting P multiplexer 36 to 0, so as to have the CO output 44 reflect the data output G 35 irrespective of the value of Y, or to 1, so as to have the CO output 44 reflect the Cl input 42, irrespective of the value of Y.
  • the carry-out output CO is also selectively independent of Cl, i.e., by setting P multiplexer 36 to 0, so as to have the CO output 44 reflect the data output G 35 irrespective of the value of CL
  • Step 840 includes configuring the X multiplexer to propagate the carry -in input as a selected one of the carry-out output and the sum output of the logic cell.
  • a logic cell for a programmable logic integrated circuit apparatus includes i) a K-input lookup table (LUT) circuit having a primary output Y and at least one additional output (F), such as F0 or FI in FIG. 1; and ii) a carry circuit coupled to receive the outputs of the LUT and a carry-in input Cl of the logic cell, wherein the carry circuit generates a sum output S and a carry-out output CO of the logic cell, and wherein the carry circuit can be configured in various ways.
  • LUT K-input lookup table
  • F additional output
  • CO carry-out output

Landscapes

  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Logic Circuits (AREA)
PCT/US2021/060229 2021-05-21 2021-11-20 Logic cell for programmable gate array WO2022245390A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
DE112021007047.9T DE112021007047T5 (de) 2021-05-21 2021-11-20 Logikzelle für programmierbares gate-array
CN202180096762.4A CN117157880A (zh) 2021-05-21 2021-11-20 用于可编程门阵列的逻辑单元

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202163191774P 2021-05-21 2021-05-21
US63/191,774 2021-05-21
US17/529,522 2021-11-18
US17/529,522 US11671099B2 (en) 2021-05-21 2021-11-18 Logic cell for programmable gate array

Publications (1)

Publication Number Publication Date
WO2022245390A1 true WO2022245390A1 (en) 2022-11-24

Family

ID=78957526

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/060229 WO2022245390A1 (en) 2021-05-21 2021-11-20 Logic cell for programmable gate array

Country Status (2)

Country Link
DE (1) DE112021007047T5 (de)
WO (1) WO2022245390A1 (de)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200150925A1 (en) * 2018-11-13 2020-05-14 Microsemi Soc Corp. Fpga logic cell with improved support for counters

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200150925A1 (en) * 2018-11-13 2020-05-14 Microsemi Soc Corp. Fpga logic cell with improved support for counters

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MICHAEL T FREDERICK ET AL: "Beyond the arithmetic constraint", FPGA 2008 : SIXTEENTH ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS ; MONTEREY BEACH RESORT, MONTEREY, CALIFORNIA, USA, FEBRUARY 24 - 26, 2008, NEW YORK, NY : ASSOCIATION FOR COMPUTING MACHINERY, US, 24 February 2008 (2008-02-24), pages 37 - 46, XP058166147, ISBN: 978-1-59593-934-0, DOI: 10.1145/1344671.1344679 *
THOMAS B PREUSSER ET AL: "Enhancing FPGA Device Capabilities by the Automatic Logic Mapping to Additive Carry Chains", FIELD PROGRAMMABLE LOGIC AND APPLICATIONS (FPL), 2010 INTERNATIONAL CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 31 August 2010 (2010-08-31), pages 318 - 325, XP031854525, ISBN: 978-1-4244-7842-2 *

Also Published As

Publication number Publication date
DE112021007047T5 (de) 2023-12-28

Similar Documents

Publication Publication Date Title
US6066960A (en) Programmable logic device having combinational logic at inputs to logic elements within logic array blocks
US10936286B2 (en) FPGA logic cell with improved support for counters
US5724276A (en) Logic block structure optimized for sum generation
US6356112B1 (en) Exclusive or/nor circuit
US7372297B1 (en) Hybrid interconnect/logic circuits enabling efficient replication of a function in several sub-cycles to save logic and routing resources
US5898602A (en) Carry chain circuit with flexible carry function for implementing arithmetic and logical functions
EP2306331B1 (de) Integrierte schaltung mit kaskadierungs-dsp-slices
EP1397863B1 (de) Rekonfigurierbare logik-vorrichtung
US8085064B2 (en) Logic module including versatile adder for FPGA
US20040070422A1 (en) Programmable logic devices having enhanced cascade functions to provide increased flexibility
US7164290B2 (en) Field programmable gate array logic unit and its cluster
US7185035B1 (en) Arithmetic structures for programmable logic devices
US8667046B2 (en) Generalized programmable counter arrays
JP4328487B2 (ja) 組合せ回路、暗号回路、その生成方法及びプログラム
US6154052A (en) Combined tristate/carry logic mechanism
US7372296B2 (en) Configurable logic device providing enhanced flexibility, scalability and providing area efficient implementation of arithmetic operation on n-bit variables
US11671099B2 (en) Logic cell for programmable gate array
US6990508B1 (en) High performance carry chain with reduced macrocell logic and fast carry lookahead
US7818361B1 (en) Method and apparatus for performing two's complement multiplication
US7003545B1 (en) High performance carry chain with reduced macrocell logic and fast carry lookahead
WO2022245390A1 (en) Logic cell for programmable gate array
JPH04233629A (ja) 先取り加算器
US20030120694A1 (en) Method and apparatus for use in booth-encoded multiplication
US7765249B1 (en) Use of hybrid interconnect/logic circuits for multiplication
JP2018538704A (ja) プログラマブルゲートアレイの論理ブロックアーキテクチャ

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21827719

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 112021007047

Country of ref document: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21827719

Country of ref document: EP

Kind code of ref document: A1