US20010001860A1 - Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith - Google Patents
Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith Download PDFInfo
- Publication number
- US20010001860A1 US20010001860A1 US09/758,080 US75808001A US2001001860A1 US 20010001860 A1 US20010001860 A1 US 20010001860A1 US 75808001 A US75808001 A US 75808001A US 2001001860 A1 US2001001860 A1 US 2001001860A1
- Authority
- US
- United States
- Prior art keywords
- recited
- bits
- bit
- generates
- carry
- Prior art date
- Legal status (The legal status 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 status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
- G06F7/38—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
- G06F7/48—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
- G06F7/50—Adding; Subtracting
- G06F7/501—Half or full adders, i.e. basic adder cells for one denomination
- G06F7/5013—Half or full adders, i.e. basic adder cells for one denomination using algebraic addition of the input signals, e.g. Kirchhoff adders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
- G06F7/38—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
- G06F7/48—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
- G06F7/52—Multiplying; Dividing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2207/00—Indexing scheme relating to methods or arrangements for processing data by operating upon the order or content of the data handled
- G06F2207/38—Indexing scheme relating to groups G06F7/38 - G06F7/575
- G06F2207/48—Indexing scheme relating to groups G06F7/48 - G06F7/575
- G06F2207/4802—Special implementations
- G06F2207/4818—Threshold devices
Definitions
- the present invention is directed, in general, to adder and multiplier circuits and, more specifically, to adder and multiplier circuits employing logic gates having discrete, weighted inputs, combinations of the same, methods of performing combinatorial operations with such logic gates and combinations thereof.
- Digital systems are used extensively in computation and data processing, controls, communications and measurement. Digital systems use digital signals that may only assume discrete values. Typically, digital systems use binary signals that employ only two values. Since such systems only use two distinct values, errors caused by component variations are minimized. As a result, a digital system may be designed such that, for a given input, an output thereof is exactly correct and repeatable. This gives rise to the extreme accuracy for which digital systems are well known.
- Analog systems use analog signals that vary continuously over a specified range. Analog systems are thus particularly vulnerable to error, depending on the accuracy of the components used therein. Since digital systems are generally capable of greater accuracy and reliability than analog systems, many tasks formerly performed by analog systems are now performed exclusively by digital systems.
- a digital system such as a computer, typically includes an input device, an output device, a processor or central processing unit (CPU) and a data storage device (e.g., random access memory or hard disk).
- CPU typically contains an arithmetic/logic unit (ALU) that performs arithmetic functions (e.g., add, subtract, multiply and divide) and logic functions (e.g., AND, OR and NOT).
- ALU arithmetic/logic unit
- a CPU may also contain a floating point unit (FPU) that performs floating point operations (e.g., add, subtract, multiply and divide).
- One basic building block of digital systems is a logic gate.
- Conventional logic gates have one output and one or more inputs. The number of inputs is called the “fan-in” of the gate. The state of the output is completely determined by the state(s) of the input(s).
- Logical and arithmetic functions are typically performed by a number of logic gates coupled together to form a multi-layer network.
- the maximum number of gates cascaded in series between the input and the output of such a network is typically referred to as the number of layers of gates.
- Designers are concerned with the number of layers in a network for several reasons. In some applications, increasing the number of layers may reduce the required number of gates and gate inputs (i.e., fan-in), thus reducing the cost (which may be expressed in terms of integrated circuit area) of building the network. Of course, cascading a large number of gates together may result in unacceptable input-output delays and data dependency conditions. When the input of a gate is switched, a finite time elapses before the output of the gate changes. If a large number of gates are cascaded together to form a network, the time between an input change and a corresponding change in the network output may become excessive, thereby slowing down the operation of the network.
- Arithmetic functions are particularly susceptible to the effects of cascaded gates.
- the serial solution for binary addition is given here as an example. Initially, a first augend bit and a first addend bit are added together, to produce a first sum bit and a first carry bit. The first carry bit is then added to the second augend and addend bits to produce the second sum and carry bits. Since the second sum bit is dependent on the value of the first carry bit, the second sum bit cannot be computed before the first carry bit is computed. While each input-output delay is small, the cumulative input-output delay perceived when adding large numbers, due to the propagation of the carry bit, is proportional to the number of bits added, and may be prohibitive.
- Boolean gates e.g., AND, OR or NOT
- n is the number of bits to be added and the logarithms are base two.
- Increasing processing power is a continuing goal in the development of microprocessors.
- Microprocessor designers are generally familiar with three ways to increase the processing power of a CPU.
- the CPU's clock frequency may be increased so that the CPU can perform a greater number of operations in a given time period.
- Microprocessors are designed to operate at increasingly high clock frequencies. For instance, the 8080 (introduced in 1974 by the Intel Corporation) was designed to operate at about 2 to 3 MHZ.
- Today, Intel's Pentium II line of processors are designed to operate with clock frequencies over 300 MHZ. While a higher clock frequency generally results in increased processing power, the higher clock frequency also increases power dissipation, resulting in higher device operating temperatures. Microprocessor designers, therefore, must address these additional problems to avoid catastrophic device failures.
- Another way to increase processing power is to increase input and output data bus width, thereby allowing the CPU to process a greater amount of code and data.
- Early microprocessors were packaged using dual in-line packaging (DIP) technology. Increasing the width of the data buses was both expensive and unrealistic, often resulting in extremely large device packages.
- DIP dual in-line packaging
- PGA pin grid array
- the present invention provides a circuit and method for deriving an adder output bit (such as a carry out bit, a carry-generate bit or a carry-propagate bit) from adder input bits (such as a carry in bit, (at least) first and second addend and augend bits, (at least) first and second carry-generate bits or (at least) first and second carry-propagate bits.
- the present invention further provides a multiplier circuit, a method of multiplying, a microprocessor and digital signal processor (DSP) employing the circuit or the method and a method of generating weights for logic gates.
- DSP digital signal processor
- the circuit includes: (1) first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial logic that generates the adder output bit from the intermediate bits. Circuits may be coupled to one another in layers to yield a wider adder. In such configuration, addend and augend bits are transformed into carry-generate and carry-propagate bits, which are ultimately transformed into a carry out bit.
- the present invention introduces novel digital addition and multiplication circuits that take advantage of multiple discrete logic levels to perform respective addition and multiplication operations significantly faster than prior art adders and multipliers.
- the principles of the present invention extend to cover logic gates that process more than two adder input bits concurrently.
- the first logic gate generates a first intermediate bit based on a comparison between a concatenation of ones of the adder input bits and zero.
- the second logic gate generates a second intermediate bit based on a comparison between a concatenation of ones of the adder input bits and two.
- the third logic gate generates a third intermediate bit based on a comparison between a concatenation of ones of the adder input bits and four.
- the first, second and third logic gates cooperate to provide the correct intermediate bits to the combinatorial circuitry based on the values of the various adder input bits.
- the combinatorial logic comprises first, second and third AND gates and first and second OR gates coupled to outputs thereof.
- the combinatorial logic generates the adder output bit by additionally employing the ones of the adder input bits.
- each of the first, second and third logic gates includes: (1) a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at the at least two binary inputs and (2) a quantizer, coupled to the summer, that generates an output binary digit at a binary output thereof that is a function of the weighted sum.
- the logic gates employ an internal representation having more than two logic levels to perform combinatorial operations, but nonetheless have purely binary inputs and outputs.
- the binary inputs and outputs ensure that the logic gates can be employed in an otherwise conventional binary digital architecture without requiring the architecture to be modified apart from insertion of the logic gates or circuits that employ the logic gates in combination with more conventional gates, e.g., Boolean gates.
- the discrete weights are integer multiples of a predetermined number.
- the predetermined number may be “1,” allowing the discrete weights to assume integer values.
- the predetermined number may be any suitable number.
- each of the at least two binary inputs includes: (1) a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight and (2) a switch, coupled to the current source, that switches the electrical current as a function of a corresponding particular input binary digit.
- the current source may be derived from a voltage source by way of a resistance.
- the voltage source may be provided by a power supply that provides power to other logic circuitry (such as other microprocessor circuitry) that may surround, and interact with, the logic gate.
- substantially constant electrical current is defined to be sufficiently constant such that the accuracy of the logic gate is not adversely affected.
- the level of precision required of the current is or can be a function of the range of discrete integer weights employed in the logic gate.
- the circuit further includes a threshold input that provides a threshold number to the quantizer, the output binary digit being a function of a relationship between the weighted sum and the threshold number.
- the threshold number provides a bias to the quantizer, allowing a threshold between the binary output states to assume a value other than zero.
- the discrete weights are advantageously selected to minimize (ideally to zero) the threshold number. This has the advantage of minimizing the number or size of current sources or sinks and thus potentially reducing the area (and therefore the cost) of the logic gate.
- the corresponding discrete weights are provided by a selected one of: (1) current sources and (2) current sinks.
- the current sources may be made to correspond to positive discrete weights and the current sinks may be made to correspond to negative discrete weights, such that currents are added and subtracted in the summer to obtain the desired weighted sum.
- the logic gates of the present invention can be adapted to operate with respect to discrete weights of either positive or negative sign or a combination thereof.
- the minimum integer weights and thresholds determining the threshold gates of arbitrary fan-ins able to compute the group carry-generate bit from multiple carry-generate and carry-propagate bits are also presented together with the method of determining them for gates of arbitrary fan-ins (larger than two).
- the circuit further includes a plurality of other of the circuits coupled together to form a multiplier circuit.
- the present invention further provides a multiplier circuit, including a summer having at least two inputs with corresponding weights, the inputs corresponding to bits of a multiplicand, the weights based on a multiplier, the summer generating a weighted sum of the multiplicand.
- the weighted sum represents the result of a multiplication of the multiplier and the multiplicand and is analog in nature.
- a digital equivalent of the weighted sum may be derived by either successive comparisons with known analog levels (thereby producing a succession of result bits) or by converting the analog weighted sum to a digital number in an analog-to-digital (A/D) converter.
- the weights are preferably created by bit-shifting the multiplier.
- a bias may also be applied to the multiplier circuit to accommodate equations of the type: AxB+C; called inner product or multiply accumulate.
- FIG. 1 illustrates an embodiment of a logic gate constructed according to the principles of the present invention
- FIG. 2 illustrates an embodiment of a carry bit generating circuit constructed according to the present invention
- FIGS. 3A, 3B and 3 C illustrate schematic representations of weights and varying threshold values for the logic gate of FIG. 1 with fan-ins of three, five and seven, respectively;
- FIGS. 4A, 4B and 4 C illustrate schematic representations of weights and fixed threshold values for the logic gate of FIG. 1 with fan-ins of three, five and seven, respectively;
- FIG. 5 illustrates an embodiment of a portion of a multiplier circuit constructed according to the present invention
- FIG. 6 illustrates a microprocessor employing the gate of FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B or 4 C or the circuits of FIGS. 2 or 5 ;
- FIG. 7 illustrates a digital signal processor (DSP) employing the gate of FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B or 4 C or the circuits of FIGS. 2 or 5 .
- DSP digital signal processor
- the logic gate 100 includes a summer 140 , having first and second binary inputs 110 , 120 with corresponding first and second discrete weights 112 , 122 .
- the summer 140 generates a weighted sum of first and second input binary digits at the first and second binary inputs 110 , 120 , respectively.
- the logic gate 100 further includes a quantizer 150 , coupled to the summer 140 .
- the quantizer 150 generates an output binary digit at a binary output 130 thereof that is a function of the weighted sum.
- the logic gate 100 still further includes a threshold input 160 that provides a threshold number to the quantizer 150 , which is subtracted from the weighted sum.
- the output binary digit is, therefore, a function of a relationship between the weighted sum and the threshold number.
- the logic gate 100 may thus be reconfigured to provide different logic functions by changing the values of the first and second discrete weights 112 , 122 , the value of the threshold input 160 or both.
- the first and second binary inputs 110 , 120 contain first and second current sources 114 , 124 , respectively.
- the first and second binary inputs 110 , 120 further contain first and second switches 116 , 126 , respectively, coupled to the first and second current sources 114 , 124 .
- the first and second current sources 114 , 124 produce substantially constant first and second electrical currents, respectively, corresponding to the first and second discrete weights 112 , 122 .
- the first and second switches 116 , 126 then switch the first and second electrical currents as a function of the first and second input binary digits 110 , 120 , respectively.
- the logic gate 100 functions as a conventional OR gate.
- the logic gate 100 operates as follows. If the first and second input binary digits are both zero, the first and second switches 116 , 126 are off and a current in the summer 140 is substantially zero. Since the threshold number is set at “0.5,” the quantizer 150 provides a zero to the binary output 130 . If, however, either the first or second input binary digit is one, one of the first or second switches 116 , 126 turns on, providing the summer 140 with a current substantially corresponding to the number “1.” Since the one unit of current is greater than the threshold of “0.5,” the quantizer 150 provides a one to the binary output 130 .
- both the first and second input binary digits are one, then both the first and second switches 116 , 126 turn on, providing the summer 140 with a current substantially corresponding to the number “2.”
- the quantizer 150 also provide a one to the binary output 130 , the logic gate 100 thus functioning as an OR gate.
- the threshold number may be modified as required by changing the threshold input.
- the threshold number may be set at “1.5” to enable the logic gate 100 to perform an AND function.
- the quantizer 150 then provides a one to the binary output 130 only when a current corresponding to more than “1.5” appears at the summer 140 .
- FIG. 2 illustrated is an embodiment of a carry bit generating circuit, generally designated 200 , constructed according to the present invention.
- the carry bit generating circuit 200 may be employed as part of a half or full adder and takes advantage of the logic gates of the type illustrated in FIG. 1 and is illustrated as one type of a circuit for generating an adder output bit from adder input bits.
- the carry bit generating circuit 200 derives a carry out bit (one type of adder output bit) from a carry in bit and first and second addend and augend bits (types of adder input bits). If the carry bit generating circuit 200 is employed as part of a larger logic circuit (such as may occur in a multiplier circuit), the addend or augend bits may represent sums generated by logic circuits located upstream of the carry bit generating circuit 200 .
- the illustrated embodiment of the carry bit generating circuit 200 includes a first logic gate 210 that generates a first intermediate bit based on a comparison between a concatenation of the second addend and augend bits a 2 , b 2 and zero.
- the second addend and augend bits a 2 , b 2 are concatenated into a string.
- the second addend and augend bits a 2 , b 2 are illustrated as being provided as a single input to the first logic gate 210 .
- the second addend and augend bits a 2 , b 2 are provided at separate inputs (as is illustrated with respect to the logic gate 100 of FIG. 1).
- the concatenation of the second addend and augend bits a 2 , b 2 is compared with zero in the first logic gate 210 to determine whether or not the concatenation exceeds zero. If so, the first logic gate 210 generates a one as a first intermediate bit. If not, the first logic gate 210 generates a zero as a first intermediate bit.
- the carry bit generating circuit further includes a second logic gate 220 that generates a second intermediate bit based on a comparison between the concatenation of the second addend and augend bits a 2 , b 2 and two (as with the logic gate 210 , the second addend and augend bits a 2 , b 2 are illustrated as being provided as a single input for simplicity's sake) .
- the concatenation that was employed in a comparison with zero in the first logic gate 210 is likewise compared with two in the second logic gate 220 to determine whether or not the concatenation exceeds two. If so, the second logic gate 220 generates a one as a second intermediate bit. If not, the second logic gate 210 generates a zero as a second intermediate bit.
- the carry bit generating circuit 200 further includes a third logic gate 230 that generates a third intermediate bit based on a comparison between a concatenation of the first addend and augend bits a 1 , b 1 and the carry in bit and four (again, as with the logic gate 210 , the second addend and augend bits a 2 , b 2 and the carry in bit are illustrated as being provided as a single input for simplicity's sake).
- the first addend and augend bits a 1 , b 1 and the carry in bit are concatenated into a string. This concatenation is then compared with four in the third logic gate 230 to determine whether or not the concatenation exceeds four. If so, the third logic gate 230 generates a one as a third intermediate bit. If not, the third logic gate 230 generates a zero as a third intermediate bit.
- the carry bit generating circuit 200 further includes a first OR gate 240 that generates a fourth intermediate bit from the first addend and augend bits a 1 , b 1 . If either or both of the first addend and augend bits a 1 , b 1 is one, the first OR gate 240 generates a one as a fourth intermediate bit; otherwise, the first OR gate 240 generates a zero as a fourth intermediate bit.
- the carry bit generating circuit 200 further includes a first AND gate 250 that generates a fifth intermediate bit from the first addend and augend bits a 1 , b 1 . If both of the first addend and augend bits a 1 , b 1 , are one, the first AND gate 250 generates a one as a fifth intermediate bit; otherwise, the first AND gate 250 generates a zero as a fifth intermediate bit.
- the carry bit generating circuit 200 further includes a second AND gate 260 .
- the second AND gate 260 is coupled to the first and third logic gates 210 , 230 and generates a sixth intermediate bit based on the first and third intermediate bits. If the first and third intermediate bits are both one, the second AND gate 260 generates a one as a sixth intermediate bit. Otherwise, the second AND gate 260 generates a zero as a sixth intermediate bit.
- the carry bit generating circuit 200 further includes a third AND gate 270 .
- the third AND gate 270 is coupled to the second logic gate 220 and the first OR gate 240 .
- the third AND gate 270 generates a seventh intermediate bit based on the first intermediate bit and the fourth intermediate bit. If the first intermediate bit and the fourth intermediate bit are one, the third AND gate 270 generates a one as a seventh intermediate bit. Otherwise, the third AND gate 270 generates a zero as a seventh intermediate bit.
- the carry bit generating circuit 200 includes a second OR gate 280 that is coupled to the second AND gate 260 , the third AND gate 270 and the first AND gate 250 .
- the second OR gate 280 generates the carry out bit based on the sixth, seventh and fifth intermediate bits. If any one of the sixth, seventh and fifth intermediate bits is one, the second OR gate 280 generates a one as a carry out bit. Otherwise, the second OR gate 280 generates a zero as a carry out bit.
- the carry bit generating circuit 200 produces a carry out bit that is appropriate to the values of the incoming addend, augend and carry in bits.
- the carry bit generating circuit 200 involves only three layers of logic. The unique architecture and characteristics of the first, second and third logic gates 210 , 220 , 230 , not only can possibly accommodate greater numbers of incoming addend and augend bits into larger logic gates without increasing the number of layers of logic, but also can yield a reduction in logic layers over the prior art.
- Equations (1), (2) and (3) may be employed to choose weights corresponding to incoming carry-generate (v ⁇ /2 for g 1 ) and carry-propagate (w ⁇ /2 for p i ) bits, respectively, and threshold values (t ⁇ +2 ) for a logic gate having a given fan-in:
- FIGS. 3A, 3B and 3 C illustrated are schematic representations of weights and varying threshold values for the logic gate 100 of FIG. 1 with fan-ins of three, five and seven, respectively.
- the gate 100 has three inputs 320 , 310 , 300 , corresponding to carry-generate bit g 1 , carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weight v 0 associated with the carry-propagate bit p 0 always equals 0, so the gate 100 does not need to provide an input for it.
- the weights corresponding to these inputs 320 , 310 , 300 are “2,” “1” and “1,” respectively.
- the carry bit generating circuit 200 is illustrated as having a threshold input 390 having a corresponding weight of “-2.”.
- the gate 100 has five inputs 340 , 330 , 320 , 310 , 300 corresponding to carry-generate bit g 2 , carry-propagate bit p 2 , carry-generate bit g 1 , carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weights corresponding to these inputs 340 , 330 , 320 , 310 , 300 are “5,” “3,” “2,”“1” and “1,” respectively.
- the gate 100 is illustrated as having a threshold input 390 having a corresponding weight of “-5.”
- the gate 100 has seven inputs 360 , 350 , 340 , 330 , 320 , 310 , 300 corresponding to carry-generate bit g 3 , carry-propagate bit p 3 , carry-generate bit g 2 , carry-propagate bit p 2 , carry-generate bit g 1 , carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weights corresponding to these inputs 360 , 350 , 340 , 330 , 320 , 310 , 300 are “13,”“8,” “5,” “3,” “2,” “1” and “1,” respectively.
- the gate 100 is illustrated as having a threshold input 390 having a corresponding weight of “-13.”
- FIGS. 4A, 4B and 4 C illustrate schematic representations of minimal weights and threshold values for the logic gate 100 of FIG. 1 with fan-ins of three, five and seven, respectively.
- the gate 100 has three inputs 420 , 410 , 400 , corresponding to carry-generate bit g 1 , carry carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weights corresponding to these inputs 420 , 410 , 400 are “2,”“-1” and “1,” respectively.
- the gate 100 is illustrated as having a threshold input 490 having a corresponding weight of “-1.”
- the gate 100 has five inputs 440 , 430 , 420 , 410 , 400 corresponding to carry-generate bit g 2 , carry-propagate bit p 2 , carry-generate bit g 1 , carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weights corresponding to these inputs 440 , 430 , 420 , 410 , 400 are “5,” “-3,”“2,” “-1” and “1, ” respectively.
- the gate 100 is illustrated as having a threshold input 490 having a corresponding weight of “-1.”
- the gate 100 has seven inputs 460 , 450 , 440 , 430 , 420 , 410 , 400 corresponding to carry-generate bit g 3 , carry-propagate bit p 3 , carry-generate bit g 2 , carry-propagate bit p 2 , carry-generate bit g 1 , carry-propagate bit p 1 and carry-generate bit g 0 , respectively.
- the weights corresponding to these inputs 460 , 450 , 440 , 430 , 420 , 410 , 400 are “13” “-8,” “5,” “-3” “2,” “-1” and “1,” respectively.
- the gate 100 is illustrated as having a threshold input 490 having a corresponding weight of “-1.”
- the multiplier 500 primarily includes a summer 510 (symbolized by a “ ⁇ ”) and may, in some embodiments, further include a quantizer 520 (a broken line signifies the optionality of the quantizer 520 ).
- the summer 510 has at least two inputs 511 , 512 ( 513 . . . 514 , 515 ) that correspond to bits b 0 , b 1 (b 2 . . . b n-1 , b n ) of a multiplier.
- the multiplier 500 may be of any width or may be packed (advantageously provided with interspersed zeros to separate individual multipliers packed therein).
- Each of the at least two inputs 511 , 512 ( 513 . . . 514 , 515 ) further has corresponding weights 521 , 522 ( 523 . . . 524 , 525 ).
- the weights correspond to bits a 0 , a 1 (a 2 . . . a n-1 , a n ) of a multiplicand.
- the multiplicand may be of any width or may be packed.
- the weights 521 , 522 ( 523 . . . 524 , 525 ) are bit-shifted versions of the full multiplicand (illustrated in FIG. 5 by appending a progressing number of zeros to the full multiplicand).
- the multiplier circuit 500 functions like the logic gate 100 of FIG. 1.
- the weights 521 , 522 ( 523 . . . 524 , 525 ) can be currents of appropriate magnitude, provided to the summer 510 as a function of the state of the corresponding at least two inputs 511 , 512 ( 513 . . . 514 , 515 ).
- the summer 510 generates a weighted sum of the bits b 0 , b 1 , b 2 . . . b n-1 , b n (which amounts to multiple addition of the bits b 0 , b 1 , b 2 . . .
- the summer 510 generates a current having a magnitude substantially equal to the weighted sum of the bits b 0 , b 1 , b 2 . . . b n-1 , b n .
- a digital equivalent of the current may be derived by either successive comparisons with known analog levels, perhaps provided by way of a nonlinear function incorporated into the quantizer 520 (thereby producing a corresponding succession of result bits) or by converting the analog weighted sum to a digital number in an A/D converter (not shown).
- the quantizer 520 (which preferably embodies a nonlinear function) receives the weighted sum and provides a signal representing one bit of the result of a multiplication of the multiplicand and the multiplier.
- FIG. 5 further illustrates a further input 516 that allows a bias 526 to be provided to the multiplication.
- the bias 526 permits the multiplier circuit 500 to calculate functions of the type AxB+C, where C is the bias.
- C is the bias.
- a one is applied at the further input 516 , as shown.
- FIG. 6 illustrated is a microprocessor 600 employing the gates of FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B or 4 C (or gates of larger fan-in) or the circuits of FIGS. 2 or 5 .
- the microprocessor 600 is illustrated as comprising a cache memory 610 for containing data, instructions or a combination thereof.
- An execution core 620 interacts with the cache memory 610 to draw data or instructions therefrom and to execute the instructions with respect to the data.
- the execution core 620 comprises an arithmetic and logic unit (ALU) 630 that actually manipulates the data in accordance with the instructions.
- the ALU 630 may be pipelined and may be superscalar, allowing instructions to be executed faster or in parallel, as may be advantageous in some applications. Of course, such need not be the case.
- the ALU includes either or both of an adder 631 or a multiplier 632 designed to add or multiply incoming data. Both the adder 631 and the multiplier 632 contain one or more logic gates 100 as illustrated in FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B, 4 C or one or more circuits 200 , 500 as illustrated in FIGS. 2 and 5. Those skilled in the art will readily understand, however, that the logic gate 100 and circuits 200 , 500 of the present invention may be employed to advantage in other circuitry within a microprocessor. Further, the logic gate 100 and circuits 200 , 500 of the present invention may be employed in other processing units that are not microprocessors.
- FIG. 7 illustrated is a digital signal processor (DSP) 700 employing the gate 100 of FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B or 4 C (or gates of larger fan-in) or the circuits of FIGS. 2 or 5 .
- a DSP is, in essence, a microprocessor that is optimized to handle data that streams in real time (a signal).
- the signal may be a sound, a video or any other data stream.
- the DSP 700 is illustrated as comprising a signal input 710 and a signal output 720 .
- the signal input 710 receives either digital data representing a signal or, if equipped with an analog-to-digital converter, receives analog data representing the signal.
- the signal input 720 can produce either digital data representing a transformed version of the signal or, if equipped with a digital-to-analog converter, analog data representing the transformed version of the signal.
- the signal transformation unit 730 Interposed between the signal input 710 and the signal output 720 is a signal transformation unit 730 that transforms the signals passing therethrough. Transformations carried out in the signal transformation unit often involve addition or multiplication operations (in fact, one can think of a signal transformation unit as a microprocessor).
- the signal transformation unit 730 is provided with at least an adder 731 and/or a multiplier 732 designed to add or multiply portions of an incoming signal.
- Both the adder(s) and multiplier(s) 731 and the multiplier 732 contain one or more logic gates 100 as illustrated in FIGS. 1, 3A, 3 B, 3 C, 4 A, 4 B, 4 C or one or more circuits 200 , 500 as illustrated in FIGS. 2 and 5.
- logic gate 100 and circuits 200 , 500 of the present invention may be employed to advantage in other circuitry within a DSP. Further, the logic gate 100 and circuits 200 , 500 of the present invention may be employed in other DSP that are not microprocessor-based.
- the present invention provides a circuit and method for deriving an adder output bit from adder input bits, a multiplier circuit, a method of multiplying and a microprocessor and DSP employing the circuit or the method.
- the circuit includes: (1) first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial logic that generates the adder output bit from the intermediate bits.
- the multiplier includes a summer having at least two inputs with corresponding weights, the inputs corresponding to bits of a multiplicand, the weights based on a multiplier, the summer generating a weighted sum of the multiplicand that represents a multiplication of the multiplicand and the multiplier.
Abstract
A circuit and method for deriving an adder output bit from adder input bits, a multiplier circuit, a method of multiplying, a microprocessor and digital signal processor (DSP) employing the circuit or the method and a method of selecting weights and thresholds for logic gates. In one embodiment, the circuit includes: (1) first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial logic that generates the adder output bit from the intermediate bits. In one embodiment, the multiplier includes a summer having at least two inputs with corresponding weights, the inputs corresponding to bits of a multiplicand, the weights based on a multiplier, the summer generating a weighted sum of the multiplicand that represents a multiplication of the multiplicand and the multiplier that is a function of the weighted sum.
Description
- The present invention is directed, in general, to adder and multiplier circuits and, more specifically, to adder and multiplier circuits employing logic gates having discrete, weighted inputs, combinations of the same, methods of performing combinatorial operations with such logic gates and combinations thereof.
- Digital systems are used extensively in computation and data processing, controls, communications and measurement. Digital systems use digital signals that may only assume discrete values. Typically, digital systems use binary signals that employ only two values. Since such systems only use two distinct values, errors caused by component variations are minimized. As a result, a digital system may be designed such that, for a given input, an output thereof is exactly correct and repeatable. This gives rise to the extreme accuracy for which digital systems are well known.
- Analog systems, on the other hand, use analog signals that vary continuously over a specified range. Analog systems are thus particularly vulnerable to error, depending on the accuracy of the components used therein. Since digital systems are generally capable of greater accuracy and reliability than analog systems, many tasks formerly performed by analog systems are now performed exclusively by digital systems.
- A digital system, such as a computer, typically includes an input device, an output device, a processor or central processing unit (CPU) and a data storage device (e.g., random access memory or hard disk). A CPU typically contains an arithmetic/logic unit (ALU) that performs arithmetic functions (e.g., add, subtract, multiply and divide) and logic functions (e.g., AND, OR and NOT). Additionally, a CPU may also contain a floating point unit (FPU) that performs floating point operations (e.g., add, subtract, multiply and divide).
- One basic building block of digital systems is a logic gate. Conventional logic gates have one output and one or more inputs. The number of inputs is called the “fan-in” of the gate. The state of the output is completely determined by the state(s) of the input(s).
- Logical and arithmetic functions are typically performed by a number of logic gates coupled together to form a multi-layer network. The maximum number of gates cascaded in series between the input and the output of such a network is typically referred to as the number of layers of gates. Designers are concerned with the number of layers in a network for several reasons. In some applications, increasing the number of layers may reduce the required number of gates and gate inputs (i.e., fan-in), thus reducing the cost (which may be expressed in terms of integrated circuit area) of building the network. Of course, cascading a large number of gates together may result in unacceptable input-output delays and data dependency conditions. When the input of a gate is switched, a finite time elapses before the output of the gate changes. If a large number of gates are cascaded together to form a network, the time between an input change and a corresponding change in the network output may become excessive, thereby slowing down the operation of the network.
- Arithmetic functions are particularly susceptible to the effects of cascaded gates. The serial solution for binary addition is given here as an example. Initially, a first augend bit and a first addend bit are added together, to produce a first sum bit and a first carry bit. The first carry bit is then added to the second augend and addend bits to produce the second sum and carry bits. Since the second sum bit is dependent on the value of the first carry bit, the second sum bit cannot be computed before the first carry bit is computed. While each input-output delay is small, the cumulative input-output delay perceived when adding large numbers, due to the propagation of the carry bit, is proportional to the number of bits added, and may be prohibitive. Techniques (e.g., carry look-ahead, conditional sum or prefix computation have been developed for reducing the delay to a logarithmic function of the number of input bits to be added. The number of Boolean gates (e.g., AND, OR or NOT) used by such techniques is in the range of from 8n to 35n or 2n log(n) to 3n log(n), where n is the number of bits to be added and the logarithms are base two.
- Increasing processing power is a continuing goal in the development of microprocessors. Microprocessor designers are generally familiar with three ways to increase the processing power of a CPU. The CPU's clock frequency may be increased so that the CPU can perform a greater number of operations in a given time period. Microprocessors are designed to operate at increasingly high clock frequencies. For instance, the 8080 (introduced in 1974 by the Intel Corporation) was designed to operate at about 2 to 3 MHZ. Today, Intel's Pentium II line of processors are designed to operate with clock frequencies over 300 MHZ. While a higher clock frequency generally results in increased processing power, the higher clock frequency also increases power dissipation, resulting in higher device operating temperatures. Microprocessor designers, therefore, must address these additional problems to avoid catastrophic device failures.
- Another way to increase processing power is to increase input and output data bus width, thereby allowing the CPU to process a greater amount of code and data. Early microprocessors were packaged using dual in-line packaging (DIP) technology. Increasing the width of the data buses was both expensive and unrealistic, often resulting in extremely large device packages. Today, with the use of pin grid array (PGA) packaging, increasing the size of the data buses no longer poses a packaging problem. Of course, a larger number of transistors is required to process the additional information conveyed by the wider data buses.
- Yet another way to increase processing power is to change the internal architecture of the microprocessor to overlap the execution of instructions by, for example, superscaling. This method also requires the addition of a large number of transistors, since entire processing stages or execution units must be duplicated. Performing a large number of instructions in parallel may also result in data dependency problems.
- Accordingly, what is needed in the art is new architectures for addition circuitry, multiplication circuitry and combinations of the same that increase the processing power of conventional digital systems.
- To address the above-discussed deficiencies of the prior art, the present invention provides a circuit and method for deriving an adder output bit (such as a carry out bit, a carry-generate bit or a carry-propagate bit) from adder input bits (such as a carry in bit, (at least) first and second addend and augend bits, (at least) first and second carry-generate bits or (at least) first and second carry-propagate bits. The present invention further provides a multiplier circuit, a method of multiplying, a microprocessor and digital signal processor (DSP) employing the circuit or the method and a method of generating weights for logic gates.
- In one embodiment, the circuit includes: (1) first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial logic that generates the adder output bit from the intermediate bits. Circuits may be coupled to one another in layers to yield a wider adder. In such configuration, addend and augend bits are transformed into carry-generate and carry-propagate bits, which are ultimately transformed into a carry out bit.
- The present invention introduces novel digital addition and multiplication circuits that take advantage of multiple discrete logic levels to perform respective addition and multiplication operations significantly faster than prior art adders and multipliers. Of course, the principles of the present invention extend to cover logic gates that process more than two adder input bits concurrently.
- In one embodiment of the present invention, the first logic gate generates a first intermediate bit based on a comparison between a concatenation of ones of the adder input bits and zero. In a related embodiment of the present invention, the second logic gate generates a second intermediate bit based on a comparison between a concatenation of ones of the adder input bits and two. In another related embodiment of the present invention, the third logic gate generates a third intermediate bit based on a comparison between a concatenation of ones of the adder input bits and four.
- The first, second and third logic gates cooperate to provide the correct intermediate bits to the combinatorial circuitry based on the values of the various adder input bits.
- In one embodiment of the present invention, the combinatorial logic comprises first, second and third AND gates and first and second OR gates coupled to outputs thereof. In an embodiment of the invention to be illustrated and described, the combinatorial logic generates the adder output bit by additionally employing the ones of the adder input bits.
- In one embodiment of the present invention, each of the first, second and third logic gates includes: (1) a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at the at least two binary inputs and (2) a quantizer, coupled to the summer, that generates an output binary digit at a binary output thereof that is a function of the weighted sum. In this embodiment, the logic gates employ an internal representation having more than two logic levels to perform combinatorial operations, but nonetheless have purely binary inputs and outputs. The binary inputs and outputs ensure that the logic gates can be employed in an otherwise conventional binary digital architecture without requiring the architecture to be modified apart from insertion of the logic gates or circuits that employ the logic gates in combination with more conventional gates, e.g., Boolean gates.
- In one embodiment of the present invention, the discrete weights are integer multiples of a predetermined number. The predetermined number may be “1,” allowing the discrete weights to assume integer values. Of course, the predetermined number may be any suitable number.
- In one embodiment of the present invention, each of the at least two binary inputs includes: (1) a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight and (2) a switch, coupled to the current source, that switches the electrical current as a function of a corresponding particular input binary digit. The current source may be derived from a voltage source by way of a resistance. The voltage source may be provided by a power supply that provides power to other logic circuitry (such as other microprocessor circuitry) that may surround, and interact with, the logic gate. For purposes of the present invention, “substantially constant electrical current” is defined to be sufficiently constant such that the accuracy of the logic gate is not adversely affected. The level of precision required of the current is or can be a function of the range of discrete integer weights employed in the logic gate.
- In one embodiment of the present invention, the circuit further includes a threshold input that provides a threshold number to the quantizer, the output binary digit being a function of a relationship between the weighted sum and the threshold number. The threshold number provides a bias to the quantizer, allowing a threshold between the binary output states to assume a value other than zero. In an embodiment to be illustrated and described, the discrete weights are advantageously selected to minimize (ideally to zero) the threshold number. This has the advantage of minimizing the number or size of current sources or sinks and thus potentially reducing the area (and therefore the cost) of the logic gate.
- In one embodiment of the present invention, the corresponding discrete weights are provided by a selected one of: (1) current sources and (2) current sinks. The current sources may be made to correspond to positive discrete weights and the current sinks may be made to correspond to negative discrete weights, such that currents are added and subtracted in the summer to obtain the desired weighted sum. In this way, the logic gates of the present invention can be adapted to operate with respect to discrete weights of either positive or negative sign or a combination thereof.
- In one embodiment of the present invention, the minimum integer weights and thresholds determining the threshold gates of arbitrary fan-ins able to compute the group carry-generate bit from multiple carry-generate and carry-propagate bits are also presented together with the method of determining them for gates of arbitrary fan-ins (larger than two).
- In one embodiment of the present invention, the circuit further includes a plurality of other of the circuits coupled together to form a multiplier circuit. Those skilled in the art will readily perceive other highly advantageous applications for the logic gates of the present invention. The present invention fully encompasses all applications.
- The present invention further provides a multiplier circuit, including a summer having at least two inputs with corresponding weights, the inputs corresponding to bits of a multiplicand, the weights based on a multiplier, the summer generating a weighted sum of the multiplicand. The weighted sum represents the result of a multiplication of the multiplier and the multiplicand and is analog in nature. A digital equivalent of the weighted sum may be derived by either successive comparisons with known analog levels (thereby producing a succession of result bits) or by converting the analog weighted sum to a digital number in an analog-to-digital (A/D) converter. The weights are preferably created by bit-shifting the multiplier. A bias may also be applied to the multiplier circuit to accommodate equations of the type: AxB+C; called inner product or multiply accumulate.
- The foregoing has outlined, rather broadly, preferred and alternative features of the present invention so that those skilled in the art may better understand the detailed description of the invention that follows. Additional features of the invention will be described hereinafter that form the subject of the claims of the invention. Those skilled in the art should appreciate that they can readily use the disclosed conception and specific embodiment as a basis for designing or modifying other structures for carrying out the same purposes of the present invention. Those skilled in the art should also realize that such equivalent constructions do not depart from the spirit and scope of the invention in its broadest form.
- For a more complete understanding of the present invention, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:
- FIG. 1 illustrates an embodiment of a logic gate constructed according to the principles of the present invention;
- FIG. 2 illustrates an embodiment of a carry bit generating circuit constructed according to the present invention;
- FIGS. 3A, 3B and3C illustrate schematic representations of weights and varying threshold values for the logic gate of FIG. 1 with fan-ins of three, five and seven, respectively;
- FIGS. 4A, 4B and4C illustrate schematic representations of weights and fixed threshold values for the logic gate of FIG. 1 with fan-ins of three, five and seven, respectively;
- FIG. 5 illustrates an embodiment of a portion of a multiplier circuit constructed according to the present invention;
- FIG. 6 illustrates a microprocessor employing the gate of FIGS. 1, 3A,3B, 3C, 4A, 4B or 4C or the circuits of FIGS. 2 or 5; and
- FIG. 7 illustrates a digital signal processor (DSP) employing the gate of FIGS. 1, 3A,3B, 3C, 4A, 4B or 4C or the circuits of FIGS. 2 or 5.
- Referring initially to FIG. 1, illustrated is an embodiment of a
logic gate 100 constructed according to the principles of the present invention. Thelogic gate 100 includes a summer 140, having first and secondbinary inputs discrete weights binary inputs logic gate 100 further includes aquantizer 150, coupled to the summer 140. Thequantizer 150 generates an output binary digit at abinary output 130 thereof that is a function of the weighted sum. - In the illustrated embodiment, the
logic gate 100 still further includes athreshold input 160 that provides a threshold number to thequantizer 150, which is subtracted from the weighted sum. The output binary digit is, therefore, a function of a relationship between the weighted sum and the threshold number. Thelogic gate 100 may thus be reconfigured to provide different logic functions by changing the values of the first and seconddiscrete weights threshold input 160 or both. - In the illustrated embodiment, the first and second
binary inputs current sources binary inputs second switches current sources current sources discrete weights second switches binary digits - In the illustrated embodiment, with the first and second
discrete weights threshold number 160 set at a current corresponding to the number “0.5,” thelogic gate 100 functions as a conventional OR gate. - The
logic gate 100 operates as follows. If the first and second input binary digits are both zero, the first andsecond switches quantizer 150 provides a zero to thebinary output 130. If, however, either the first or second input binary digit is one, one of the first orsecond switches quantizer 150 provides a one to thebinary output 130. If both the first and second input binary digits are one, then both the first andsecond switches quantizer 150 also provide a one to thebinary output 130, thelogic gate 100 thus functioning as an OR gate. - Of course, the threshold number may be modified as required by changing the threshold input. For example, the threshold number may be set at “1.5” to enable the
logic gate 100 to perform an AND function. Thequantizer 150 then provides a one to thebinary output 130 only when a current corresponding to more than “1.5” appears at the summer 140. - Turning now to FIG. 2, illustrated is an embodiment of a carry bit generating circuit, generally designated200, constructed according to the present invention. The carry bit generating circuit 200 may be employed as part of a half or full adder and takes advantage of the logic gates of the type illustrated in FIG. 1 and is illustrated as one type of a circuit for generating an adder output bit from adder input bits.
- The carry bit generating circuit200 derives a carry out bit (one type of adder output bit) from a carry in bit and first and second addend and augend bits (types of adder input bits). If the carry bit generating circuit 200 is employed as part of a larger logic circuit (such as may occur in a multiplier circuit), the addend or augend bits may represent sums generated by logic circuits located upstream of the carry bit generating circuit 200.
- The illustrated embodiment of the carry bit generating circuit200 includes a
first logic gate 210 that generates a first intermediate bit based on a comparison between a concatenation of the second addend and augend bits a2, b2 and zero. In other words, the second addend and augend bits a2, b2 are concatenated into a string. For the sake of simplicity, the second addend and augend bits a2, b2 are illustrated as being provided as a single input to thefirst logic gate 210. In practice, the second addend and augend bits a2, b2 are provided at separate inputs (as is illustrated with respect to thelogic gate 100 of FIG. 1). The concatenation of the second addend and augend bits a2, b2 is compared with zero in thefirst logic gate 210 to determine whether or not the concatenation exceeds zero. If so, thefirst logic gate 210 generates a one as a first intermediate bit. If not, thefirst logic gate 210 generates a zero as a first intermediate bit. - The carry bit generating circuit further includes a
second logic gate 220 that generates a second intermediate bit based on a comparison between the concatenation of the second addend and augend bits a2, b2 and two (as with thelogic gate 210, the second addend and augend bits a2, b2 are illustrated as being provided as a single input for simplicity's sake) . In other words, the concatenation that was employed in a comparison with zero in thefirst logic gate 210 is likewise compared with two in thesecond logic gate 220 to determine whether or not the concatenation exceeds two. If so, thesecond logic gate 220 generates a one as a second intermediate bit. If not, thesecond logic gate 210 generates a zero as a second intermediate bit. - The carry bit generating circuit200 further includes a
third logic gate 230 that generates a third intermediate bit based on a comparison between a concatenation of the first addend and augend bits a1, b1 and the carry in bit and four (again, as with thelogic gate 210, the second addend and augend bits a2, b2 and the carry in bit are illustrated as being provided as a single input for simplicity's sake). In other words, the first addend and augend bits a1, b1 and the carry in bit are concatenated into a string. This concatenation is then compared with four in thethird logic gate 230 to determine whether or not the concatenation exceeds four. If so, thethird logic gate 230 generates a one as a third intermediate bit. If not, thethird logic gate 230 generates a zero as a third intermediate bit. - The carry bit generating circuit200 further includes a first OR
gate 240 that generates a fourth intermediate bit from the first addend and augend bits a1, b1. If either or both of the first addend and augend bits a1, b1 is one, the first ORgate 240 generates a one as a fourth intermediate bit; otherwise, the first ORgate 240 generates a zero as a fourth intermediate bit. - The carry bit generating circuit200 further includes a first AND
gate 250 that generates a fifth intermediate bit from the first addend and augend bits a1, b1. If both of the first addend and augend bits a1, b1, are one, the first ANDgate 250 generates a one as a fifth intermediate bit; otherwise, the first ANDgate 250 generates a zero as a fifth intermediate bit. - The carry bit generating circuit200 further includes a second AND
gate 260. The second ANDgate 260 is coupled to the first andthird logic gates gate 260 generates a one as a sixth intermediate bit. Otherwise, the second ANDgate 260 generates a zero as a sixth intermediate bit. - The carry bit generating circuit200 further includes a third AND
gate 270. The third ANDgate 270 is coupled to thesecond logic gate 220 and the first ORgate 240. The third ANDgate 270 generates a seventh intermediate bit based on the first intermediate bit and the fourth intermediate bit. If the first intermediate bit and the fourth intermediate bit are one, the third ANDgate 270 generates a one as a seventh intermediate bit. Otherwise, the third ANDgate 270 generates a zero as a seventh intermediate bit. - Finally, the carry bit generating circuit200 includes a second OR
gate 280 that is coupled to the second ANDgate 260, the third ANDgate 270 and the first ANDgate 250. The second ORgate 280 generates the carry out bit based on the sixth, seventh and fifth intermediate bits. If any one of the sixth, seventh and fifth intermediate bits is one, the second ORgate 280 generates a one as a carry out bit. Otherwise, the second ORgate 280 generates a zero as a carry out bit. - Those skilled in the art will note two aspects of the carry bit generating circuit200 of FIG. 2. First, the carry bit generating circuit 200 produces a carry out bit that is appropriate to the values of the incoming addend, augend and carry in bits. Second, the carry bit generating circuit 200 involves only three layers of logic. The unique architecture and characteristics of the first, second and
third logic gates - The following discussion introduces carry-generate and carry-propagate bits as employed in certain adders. Those skilled in the art will understand such bits. However, for a greater understanding of their derivation, see V. Beiu and J. Taylor,On the Circuit Complexity of Sigmoid Feedforward Neural Networks, Neural Networks, Vol. 9, No. 7, 1996, which is incorporated herein by reference.
- At this point, it is instructive to set forth a method for obtaining the weights to be employed in a given logic gate, such as the
logic gate 100 of FIG. 1. It has been found that the following Equations (1), (2) and (3) may be employed to choose weights corresponding to incoming carry-generate (vΔ/2 for g1) and carry-propagate (wΔ/2 for pi) bits, respectively, and threshold values (tΔ+2) for a logic gate having a given fan-in: - wherein w0=0, v0=1, w1=1 and v1=2. One of the advantages of the Equations (1), (2) and (3) is that the weights and threshold values allow the logic gates to be used in any layer of an adder (thus not restricting the logic gates to use in only the first layer of the adder, which is a significant limitation of the V. Beiu article cited above and incorporated herein).
- Turning now to FIGS. 3A, 3B and3C, illustrated are schematic representations of weights and varying threshold values for the
logic gate 100 of FIG. 1 with fan-ins of three, five and seven, respectively. The weights (vΔ/2 and wΔ/2) and threshold values (t66 +2) were generated in accordance with the Equations (1), (2) and (3) set forth above, with the initial conditions w0=0, v0=1, w1=1 and v1=2. - In FIG. 3A, the
gate 100 has threeinputs gate 100 does not need to provide an input for it. The weights corresponding to theseinputs threshold input 390 having a corresponding weight of “-2.”. - In FIG. 3B, the
gate 100 has fiveinputs inputs gate 100 is illustrated as having athreshold input 390 having a corresponding weight of “-5.” - In FIG. 3C, the
gate 100 has seveninputs inputs gate 100 is illustrated as having athreshold input 390 having a corresponding weight of “-13.” - Those skilled in the art will perceive an advantage to having weights and threshold values as small as possible. Accordingly, FIGS. 4A, 4B and4C, illustrate schematic representations of minimal weights and threshold values for the
logic gate 100 of FIG. 1 with fan-ins of three, five and seven, respectively. In FIG. 4A, thegate 100 has threeinputs inputs gate 100 is illustrated as having athreshold input 490 having a corresponding weight of “-1.” - In FIG. 4B, the
gate 100 has fiveinputs inputs gate 100 is illustrated as having athreshold input 490 having a corresponding weight of “-1.” - In FIG. 4C, the
gate 100 has seveninputs inputs gate 100 is illustrated as having athreshold input 490 having a corresponding weight of “-1.” - Turning now to FIG. 5, illustrated is an embodiment of a portion of a multiplier circuit, generally designated500, constructed according to the present invention. The
multiplier 500 primarily includes a summer 510 (symbolized by a “Σ”) and may, in some embodiments, further include a quantizer 520 (a broken line signifies the optionality of the quantizer 520). Thesummer 510 has at least twoinputs 511, 512 (513 . . . 514, 515) that correspond to bits b0, b1 (b2 . . . bn-1, bn) of a multiplier. Themultiplier 500 may be of any width or may be packed (advantageously provided with interspersed zeros to separate individual multipliers packed therein). - Each of the at least two
inputs 511, 512 (513 . . . 514, 515) further has correspondingweights 521, 522 (523 . . . 524, 525). The weights correspond to bits a0, a1 (a2 . . . an-1, an) of a multiplicand. As with the multiplier, the multiplicand may be of any width or may be packed. As illustrated, theweights 521, 522 (523 . . . 524, 525) are bit-shifted versions of the full multiplicand (illustrated in FIG. 5 by appending a progressing number of zeros to the full multiplicand). - From this point, the
multiplier circuit 500 functions like thelogic gate 100 of FIG. 1. Theweights 521, 522 (523 . . . 524, 525) can be currents of appropriate magnitude, provided to thesummer 510 as a function of the state of the corresponding at least twoinputs 511, 512 (513 . . . 514, 515). Thesummer 510 generates a weighted sum of the bits b0, b1, b2 . . . bn-1, bn (which amounts to multiple addition of the bits b0, b1, b2 . . . bn-1, bn with the bits a0, a1, a2 . . . an-1, an) and provides an analog signal that has a current value equaling the weighted sum. If the weights are embodied in currents of given magnitudes, thesummer 510 generates a current having a magnitude substantially equal to the weighted sum of the bits b0, b1, b2 . . . bn-1, bn. As previously described, a digital equivalent of the current (the weighted sum) may be derived by either successive comparisons with known analog levels, perhaps provided by way of a nonlinear function incorporated into the quantizer 520 (thereby producing a corresponding succession of result bits) or by converting the analog weighted sum to a digital number in an A/D converter (not shown). - The quantizer520 (which preferably embodies a nonlinear function) receives the weighted sum and provides a signal representing one bit of the result of a multiplication of the multiplicand and the multiplier.
- FIG. 5 further illustrates a
further input 516 that allows abias 526 to be provided to the multiplication. Thebias 526 permits themultiplier circuit 500 to calculate functions of the type AxB+C, where C is the bias. To activate thebias 526, a one is applied at thefurther input 516, as shown. - Turning now to FIG. 6, illustrated is a
microprocessor 600 employing the gates of FIGS. 1, 3A, 3B, 3C, 4A, 4B or 4C (or gates of larger fan-in) or the circuits of FIGS. 2 or 5. Themicroprocessor 600 is illustrated as comprising a cache memory 610 for containing data, instructions or a combination thereof. Anexecution core 620 interacts with the cache memory 610 to draw data or instructions therefrom and to execute the instructions with respect to the data. Theexecution core 620 comprises an arithmetic and logic unit (ALU) 630 that actually manipulates the data in accordance with the instructions. TheALU 630 may be pipelined and may be superscalar, allowing instructions to be executed faster or in parallel, as may be advantageous in some applications. Of course, such need not be the case. - The ALU includes either or both of an
adder 631 or amultiplier 632 designed to add or multiply incoming data. Both theadder 631 and themultiplier 632 contain one ormore logic gates 100 as illustrated in FIGS. 1, 3A, 3B, 3C, 4A, 4B, 4C or one ormore circuits 200, 500 as illustrated in FIGS. 2 and 5. Those skilled in the art will readily understand, however, that thelogic gate 100 andcircuits 200, 500 of the present invention may be employed to advantage in other circuitry within a microprocessor. Further, thelogic gate 100 andcircuits 200, 500 of the present invention may be employed in other processing units that are not microprocessors. - Turning now to FIG. 7, illustrated is a digital signal processor (DSP)700 employing the
gate 100 of FIGS. 1, 3A, 3B, 3C, 4A, 4B or 4C (or gates of larger fan-in) or the circuits of FIGS. 2 or 5. A DSP is, in essence, a microprocessor that is optimized to handle data that streams in real time (a signal). The signal may be a sound, a video or any other data stream. Accordingly, theDSP 700 is illustrated as comprising asignal input 710 and asignal output 720. Thesignal input 710 receives either digital data representing a signal or, if equipped with an analog-to-digital converter, receives analog data representing the signal. Likewise, thesignal input 720 can produce either digital data representing a transformed version of the signal or, if equipped with a digital-to-analog converter, analog data representing the transformed version of the signal. - Interposed between the
signal input 710 and thesignal output 720 is asignal transformation unit 730 that transforms the signals passing therethrough. Transformations carried out in the signal transformation unit often involve addition or multiplication operations (in fact, one can think of a signal transformation unit as a microprocessor). Thus, thesignal transformation unit 730 is provided with at least anadder 731 and/or amultiplier 732 designed to add or multiply portions of an incoming signal. Both the adder(s) and multiplier(s) 731 and themultiplier 732 contain one ormore logic gates 100 as illustrated in FIGS. 1, 3A, 3B, 3C, 4A, 4B, 4C or one ormore circuits 200, 500 as illustrated in FIGS. 2 and 5. Those skilled in the art will readily understand, however, that thelogic gate 100 andcircuits 200, 500 of the present invention may be employed to advantage in other circuitry within a DSP. Further, thelogic gate 100 andcircuits 200, 500 of the present invention may be employed in other DSP that are not microprocessor-based. - From the above, it is apparent that the present invention provides a circuit and method for deriving an adder output bit from adder input bits, a multiplier circuit, a method of multiplying and a microprocessor and DSP employing the circuit or the method. In one embodiment, the circuit includes: (1) first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial logic that generates the adder output bit from the intermediate bits. In one embodiment, the multiplier includes a summer having at least two inputs with corresponding weights, the inputs corresponding to bits of a multiplicand, the weights based on a multiplier, the summer generating a weighted sum of the multiplicand that represents a multiplication of the multiplicand and the multiplier.
- Although the present invention has been described in detail, those skilled in the art should understand that they can make various changes, substitutions and alterations herein without departing from the spirit and scope of the invention in its broadest form.
Claims (69)
1. A circuit for deriving an adder output bit from adder input bits, comprising:
first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of said adder input bits; and
combinatorial logic that generates said adder output bit from said intermediate bits.
2. The circuit as recited in wherein said adder output bit is selected from the group consisting of:
claim 1
a carry out bit,
a carry-generate bit, and
a carry-propagate bit.
3. The circuit as recited in wherein said adder input bits are selected from the group consisting of:
claim 1
a carry in bit,
first and second addend and augend bits,
first and second carry-generate bits, and
first and second carry-propagate bits.
4. The circuit as recited in wherein said first logic gate generates a first intermediate bit based on a comparison between a concatenation of ones of said adder input bits and zero.
claim 1
5. The circuit as recited in wherein said second logic gate generates a second intermediate bit based on a comparison between a concatenation of ones of said adder input bits and two.
claim 1
6. The circuit as recited in wherein said third logic gate generates a third intermediate bit based on a comparison between a concatenation of ones of said adder input bits and four.
claim 1
7. The circuit as recited in wherein said combinatorial logic comprises first and second AND gates and an OR gate coupled to outputs thereof.
claim 1
8. The circuit as recited in wherein said combinatorial logic generates said carry out bit from ones of said adder input bits.
claim 1
9. The circuit as recited in wherein each of said first, second and third logic gates comprises:
claim 1
a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at said at least two binary inputs; and
a quantizer, coupled to said summer, that generates an output binary digit at a binary output thereof that is a function of said weighted sum.
10. The circuit as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 9
11. The circuit as recited in wherein each of said at least two binary inputs comprises:
claim 9
a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular input binary digit.
12. The circuit as recited in further comprising a threshold input that provides a threshold number to said quantizer, said output binary digit being a function of a relationship between said weighted sum and said threshold number.
claim 9
13. The circuit as recited in further comprising a plurality of other of said circuits coupled together to form a multiplier circuit.
claim 1
14. A method of deriving an adder output bit from adder input bits, comprising:
generating intermediate bits based on threshold comparisons of concatenations of said adder input bits; and
generating said adder output bit from said intermediate bits.
15. The method as recited in wherein said adder output bit is selected from the group consisting of:
claim 14
a carry out bit,
a carry-generate bit, and
a carry-propagate bit.
16. The method as recited in wherein said adder input bits are selected from the group consisting of:
claim 14
a carry in bit,
first and second addend and augend bits,
first and second carry-generate bits, and
first and second carry-propagate bits.
17. The method as recited in wherein said generating said intermediate bits comprises generating a first intermediate bit based on a comparison between a concatenation of ones of said adder input bits and zero.
claim 14
18. The method as recited in wherein said generating said intermediate bits comprises generating a second intermediate bit based on a comparison between a concatenation of ones of said adder input bits and two.
claim 14
19. The method as recited in wherein said generating said intermediate bits comprises generating a third intermediate bit based on a comparison between a concatenation of ones of said adder input bits and four.
claim 14
20. The method as recited in wherein said generating said adder output bit is carried out by first and second AND gates and an OR gate coupled to outputs thereof.
claim 14
21. The method as recited in wherein said generating said adder output bit comprises generating said adder output bit from ones of said adder input bits.
claim 14
22. The method as recited in wherein said generating said intermediate bits comprises:
claim 14
generating a weighted sum of input binary digits presented at said at least two binary inputs; and
generating an output binary digit at a binary output thereof that is a function of said weighted sum.
23. The method as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 22
24. The method as recited in wherein each of said at least two binary inputs comprises:
claim 22
a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular input binary digit.
25. The method as recited in further comprising providing a threshold number, said output binary digit being a function of a relationship between said weighted sum and said threshold number.
claim 22
26. A circuit for deriving a carry out bit from a carry in bit and first and second addend and augend bits, comprising:
a first logic gate that generates a first intermediate bit based on a comparison between a concatenation of said second addend and augend bits and zero;
a second logic gate that generates a second intermediate bit based on a comparison between said concatenation of said second addend and augend bits and two;
a third logic gate that generates a third intermediate bit based on a comparison between a concatenation of said first addend and augend bits and said carry in bit and four;
a first OR gate that generates a fourth intermediate bit based on said first addend and augend bits;
a first AND gate that generates a fifth intermediate bit based on said first addend and augend bits;
a second AND gate that generates a sixth intermediate bit based on said first and third intermediate bits;
a third AND gate that generates a seventh intermediate bit based on said second and fourth intermediate bits; and
a second OR gate that generates said carry out bit based on said sixth, seventh and fifth intermediate bits.
27. The circuit as recited in wherein each of said first, second and third logic gates comprises:
claim 26
a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at said at least two binary inputs; and
a quantizer, coupled to said summer, that generates an output binary digit at a binary output thereof that is a function of said weighted sum.
28. A multiplier circuit, comprising a summer having at least two inputs with corresponding weights, said inputs corresponding to bits of a multiplicand, said weights based on a multiplier, said summer generating a weighted sum of said multiplicand that represents a multiplication of said multiplicand and said multiplier.
29. The multiplier as recited in wherein said weights are created by bit-shifting said multiplier.
claim 28
30. The multiplier as recited in further comprising a further input that provides a bias to said quantizer to bias said multiplication.
claim 28
31. The multiplier as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 28
32. The multiplier as recited in wherein each of said at least two inputs comprises:
claim 28
a current source capable of producing a substantially constant electrical current corresponding to a particular weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular bits of said multiplicand.
33. A method of multiplying a multiplicand by a multiplier, comprising generating a weighted sum of said multiplicand with a summer having at least two inputs with corresponding weights, said inputs corresponding to bits of said multiplicand, said weights based on a multiplier; and
generating an output representing a multiplication of said multiplicand and said multiplier that is a function of said weighted sum.
34. The method as recited in wherein said generating said weighted sum comprises bit-shifting said multiplier to create said weights.
claim 33
35. The method as recited in further comprising providing a bias to said multiplication.
claim 33
36. The method as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 33
37. The method as recited in wherein each of said at least two inputs comprises:
claim 33
a current source capable of producing a substantially constant electrical current corresponding to a particular weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular bits of said multiplicand.
38. A microprocessor, comprising:
a cache memory; and
an arithmetic and logic unit containing at least one of an adder and a multiplier, said at least one including a circuit for deriving a carry out bit from a carry in bit and first and second addend and augend bits, including:
first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of said carry in bit and said first and second addend and augend bits, and
combinatorial logic that generates said carry out bit from said intermediate bits.
39. The microprocessor as recited in wherein said first logic gate generates a first intermediate bit based on a comparison between a concatenation of said second addend and augend bits and zero.
claim 38
40. The microprocessor as recited in wherein said second logic gate generates a second intermediate bit based on a comparison between a concatenation of said second addend and augend bits and two.
claim 38
41. The microprocessor as recited in wherein said third logic gate generates a third intermediate bit based on a comparison between a concatenation of said first addend and augend bits and said carry in bit and four.
claim 38
42. The microprocessor as recited in wherein said combinatorial logic comprises first, second and third AND gates and first and second OR gates coupled to outputs thereof.
claim 38
43. The microprocessor as recited in wherein said combinatorial logic generates said carry out bit from said first augend bit and said carry in bit.
claim 38
44. The microprocessor as recited in wherein each of said first, second and third logic gates comprises:
claim 38
a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at said at least two binary inputs; and
a quantizer, coupled to said summer, that generates an output binary digit at a binary output thereof that is a function of said weighted sum.
45. The microprocessor as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 44
46. The microprocessor as recited in wherein each of said at least two binary inputs comprises:
claim 44
a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular input binary digit.
47. The microprocessor as recited in wherein said circuit further includes a threshold input that provides a threshold number to said quantizer, said output binary digit being a function of a relationship between said weighted sum and said threshold number.
claim 44
48. The microprocessor as recited in wherein said circuit further includes a plurality of other of said circuits coupled together to form a multiplier circuit.
claim 38
49. A digital signal processor, comprising:
a signal input;
a signal output; and
a signal transformation unit containing at least one of an adder and a multiplier, said at least one including a circuit for deriving a carry out bit from a carry in bit and first and second addend and augend bits, including:
first, second and third logic gates that generate intermediate bits based on threshold comparisons of concatenations of said carry in bit and said first and second addend and augend bits, and
combinatorial logic that generates said carry out bit from said intermediate bits.
50. The DSP as recited in wherein said first logic gate generates a first intermediate bit based on a comparison between a concatenation of said second addend and augend bits and zero.
claim 49
51. The DSP as recited in wherein said second logic gate generates a second intermediate bit based on a comparison between a concatenation of said second addend and augend bits and two.
claim 49
52. The DSP as recited in wherein said third logic gate generates a third intermediate bit based on a comparison between a concatenation of said first addend and augend bits and said carry in bit and four.
claim 49
53. The DSP as recited in wherein said combinatorial logic comprises first, second and third AND gates and first and second OR gates coupled to outputs thereof.
claim 49
54. The DSP as recited in wherein said combinatorial logic generates said carry out bit from said first augend bit and said carry in bit.
claim 49
55. The DSP as recited in wherein each of said first, second and third logic gates comprises:
claim 49
a summer, having at least two binary inputs with corresponding discrete weights, that generates a weighted sum of input binary digits presented at said at least two binary inputs; and
a quantizer, coupled to said summer, that generates an output binary digit at a binary output thereof that is a function of said weighted sum.
56. The DSP as recited in wherein said discrete weights are integer multiples of a predetermined number.
claim 55
57. The DSP as recited in wherein each of said at least two binary inputs comprises:
claim 55
a current source capable of producing a substantially constant electrical current corresponding to a particular discrete weight; and
a switch, coupled to said current source, that switches said electrical current as a function of a corresponding particular input binary digit.
58. The DSP as recited in wherein said circuit further includes a threshold input that provides a threshold number to said quantizer, said output binary digit being a function of a relationship between said weighted sum and said threshold number.
claim 55
59. The DSP as recited in wherein said circuit further includes a plurality of other of said circuits coupled together to form a multiplier circuit.
claim 55
60. A logic gate, comprising:
first, second and third current paths having preset current magnitudes representing discrete weights;
first, second and third switches coupled to said first, second and third current paths, respectively, and adapted to receive binary digits to open or close said first, second and third switches; and
a quantizer, coupled to said first, second and third switches, that receives an electrical current that is a function of a value of said discrete weights and said binary digits, said electrical current representing a result of an operation with respect to said binary digits.
61. The logic gate as recited in wherein said first current path is selected from the group consisting of:
claim 60
a current source, and
a current sink.
62. The logic gate as recited in wherein said second current path is selected from the group consisting of:
claim 60
a current source, and
a current sink.
63. The logic gate as recited in wherein said third current path is selected from the group consisting of:
claim 60
a current source, and
a current sink.
64. The logic gate as recited in wherein said quantizer comprises a threshold input that provides a threshold current to the quantizer, said quantizer producing an output that represents a relationship between said electrical current and said threshold current.
claim 60
65. A processor containing the logic gate as recited in .
claim 60
66. A DSP containing the logic gate as recited in .
claim 60
67. A method of selecting weights and a threshold value for a threshold gate having a given fan-in (A), comprising:
for vΔ/2;
for wΔ/2;
solving tΔ+2; =-πΔ/2 for tΔ+2, wherein w0 =0, v0=1, w1=1 and v1=2; and
employing said vΔ/2 and said wΔ/2 as said weights and said tΔ-2 as said threshold value in said threshold gate.
68. The method as recited in wherein said vΔ/2 and said wΔ/2 are of minimum value.
claim 67
69. The method as recited in wherein said tΔ+2 is of minimum value.
claim 67
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/758,080 US20010001860A1 (en) | 1998-09-21 | 2001-01-10 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/158,947 US6205458B1 (en) | 1998-09-21 | 1998-09-21 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
US09/758,080 US20010001860A1 (en) | 1998-09-21 | 2001-01-10 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/158,947 Division US6205458B1 (en) | 1998-09-21 | 1998-09-21 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
Publications (1)
Publication Number | Publication Date |
---|---|
US20010001860A1 true US20010001860A1 (en) | 2001-05-24 |
Family
ID=22570404
Family Applications (6)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/158,947 Expired - Fee Related US6205458B1 (en) | 1998-09-21 | 1998-09-21 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
US09/758,080 Abandoned US20010001860A1 (en) | 1998-09-21 | 2001-01-10 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
US09/757,978 Expired - Fee Related US6502120B2 (en) | 1998-09-21 | 2001-01-10 | Adder circuit employing logic gates having discrete weighted inputs and a method of operation therewith |
US09/758,071 Expired - Fee Related US6516331B2 (en) | 1998-09-21 | 2001-01-10 | Microprocessor and a digital signal processor including adder and multiplier circuits employing logic gates having discrete and weighted inputs |
US10/211,866 Abandoned US20030009504A1 (en) | 1998-09-21 | 2002-08-02 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
US10/219,714 Abandoned US20030028575A1 (en) | 1998-09-21 | 2002-08-15 | A Microprocessor and a digital signal processor including adder and multiplier circuits employing logic gates having discrete and weighted inputs |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/158,947 Expired - Fee Related US6205458B1 (en) | 1998-09-21 | 1998-09-21 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
Family Applications After (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/757,978 Expired - Fee Related US6502120B2 (en) | 1998-09-21 | 2001-01-10 | Adder circuit employing logic gates having discrete weighted inputs and a method of operation therewith |
US09/758,071 Expired - Fee Related US6516331B2 (en) | 1998-09-21 | 2001-01-10 | Microprocessor and a digital signal processor including adder and multiplier circuits employing logic gates having discrete and weighted inputs |
US10/211,866 Abandoned US20030009504A1 (en) | 1998-09-21 | 2002-08-02 | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith |
US10/219,714 Abandoned US20030028575A1 (en) | 1998-09-21 | 2002-08-15 | A Microprocessor and a digital signal processor including adder and multiplier circuits employing logic gates having discrete and weighted inputs |
Country Status (3)
Country | Link |
---|---|
US (6) | US6205458B1 (en) |
AU (1) | AU5815599A (en) |
WO (1) | WO2000017802A2 (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040128474A1 (en) * | 2000-10-09 | 2004-07-01 | Martin Vorbach | Method and device |
US20070150637A1 (en) * | 2002-02-18 | 2007-06-28 | Martin Vorbach | Bus systems and method for reconfiguration |
US7650448B2 (en) | 1996-12-20 | 2010-01-19 | Pact Xpp Technologies Ag | I/O and memory bus system for DFPS and units with two- or multi-dimensional programmable cell architectures |
US7657861B2 (en) | 2002-08-07 | 2010-02-02 | Pact Xpp Technologies Ag | Method and device for processing data |
US7657877B2 (en) | 2001-06-20 | 2010-02-02 | Pact Xpp Technologies Ag | Method for processing data |
US7782087B2 (en) | 2002-09-06 | 2010-08-24 | Martin Vorbach | Reconfigurable sequencer structure |
US7822968B2 (en) | 1996-12-09 | 2010-10-26 | Martin Vorbach | Circuit having a multidimensional structure of configurable cells that include multi-bit-wide inputs and outputs |
US7822881B2 (en) | 1996-12-27 | 2010-10-26 | Martin Vorbach | Process for automatic dynamic reloading of data flow processors (DFPs) and units with two- or three-dimensional programmable cell architectures (FPGAs, DPGAs, and the like) |
US7840842B2 (en) | 2001-09-03 | 2010-11-23 | Martin Vorbach | Method for debugging reconfigurable architectures |
US7844796B2 (en) | 2001-03-05 | 2010-11-30 | Martin Vorbach | Data processing device and method |
US7996827B2 (en) | 2001-08-16 | 2011-08-09 | Martin Vorbach | Method for the translation of programs for reconfigurable architectures |
US8058899B2 (en) | 2000-10-06 | 2011-11-15 | Martin Vorbach | Logic cell array and bus system |
US8099618B2 (en) | 2001-03-05 | 2012-01-17 | Martin Vorbach | Methods and devices for treating and processing data |
US8156284B2 (en) | 2002-08-07 | 2012-04-10 | Martin Vorbach | Data processing method and device |
US8209653B2 (en) | 2001-09-03 | 2012-06-26 | Martin Vorbach | Router |
US8230411B1 (en) | 1999-06-10 | 2012-07-24 | Martin Vorbach | Method for interleaving a program over a plurality of cells |
US8250503B2 (en) | 2006-01-18 | 2012-08-21 | Martin Vorbach | Hardware definition method including determining whether to implement a function as hardware or software |
US8281108B2 (en) | 2002-01-19 | 2012-10-02 | Martin Vorbach | Reconfigurable general purpose processor having time restricted configurations |
US8301872B2 (en) | 2000-06-13 | 2012-10-30 | Martin Vorbach | Pipeline configuration protocol and configuration unit communication |
USRE44365E1 (en) | 1997-02-08 | 2013-07-09 | Martin Vorbach | Method of self-synchronization of configurable elements of a programmable module |
US8686549B2 (en) | 2001-09-03 | 2014-04-01 | Martin Vorbach | Reconfigurable elements |
US8686475B2 (en) | 2001-09-19 | 2014-04-01 | Pact Xpp Technologies Ag | Reconfigurable elements |
US8812820B2 (en) | 2003-08-28 | 2014-08-19 | Pact Xpp Technologies Ag | Data processing device and method |
US8819505B2 (en) | 1997-12-22 | 2014-08-26 | Pact Xpp Technologies Ag | Data processor having disabled cores |
US8914590B2 (en) | 2002-08-07 | 2014-12-16 | Pact Xpp Technologies Ag | Data processing method and device |
US9037807B2 (en) | 2001-03-05 | 2015-05-19 | Pact Xpp Technologies Ag | Processor arrangement on a chip including data processing, memory, and interface elements |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6430585B1 (en) | 1998-09-21 | 2002-08-06 | Rn2R, L.L.C. | Noise tolerant conductance-based logic gate and methods of operation and manufacturing thereof |
US7526519B2 (en) * | 2002-05-01 | 2009-04-28 | Bea Systems, Inc. | High availability application view deployment |
US7621963B2 (en) * | 2005-04-13 | 2009-11-24 | Ebi, Llc | Composite bone graft material |
US20060233849A1 (en) * | 2005-04-13 | 2006-10-19 | Simon Bruce J | Composite bone graft material |
US20070045157A1 (en) * | 2005-08-29 | 2007-03-01 | Kajzer Wieslaw C | Recovery of pin chips from a chip washing reject stream |
US7292069B2 (en) * | 2005-12-30 | 2007-11-06 | Intel Corporation | Locally asynchronous, block-level synchronous, configurable logic blocks with sub-threshold analog circuits |
US7991820B1 (en) | 2007-08-07 | 2011-08-02 | Leslie Imre Sohay | One step binary summarizer |
US10790829B2 (en) | 2018-09-27 | 2020-09-29 | Intel Corporation | Logic circuits with simultaneous dual function capability |
US10715144B2 (en) | 2019-06-06 | 2020-07-14 | Intel Corporation | Logic circuits with augmented arithmetic densities |
US11416218B1 (en) | 2020-07-10 | 2022-08-16 | Ali Tasdighi Far | Digital approximate squarer for machine learning |
US11467805B1 (en) | 2020-07-10 | 2022-10-11 | Ali Tasdighi Far | Digital approximate multipliers for machine learning and artificial intelligence applications |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE1211006B (en) | 1961-08-14 | 1966-02-17 | Sperry Rand Corp | Data processing system |
US3280316A (en) * | 1963-04-29 | 1966-10-18 | Westinghouse Electric Corp | High-speed tunnel diode adder |
US3275812A (en) | 1963-07-29 | 1966-09-27 | Gen Electric | Threshold gate adder for minimizing carry propagation |
US3423577A (en) * | 1965-12-28 | 1969-01-21 | Sperry Rand Corp | Full adder stage utilizing dual-threshold logic |
US3609329A (en) * | 1969-05-05 | 1971-09-28 | Shell Oil Co | Threshold logic for integrated full adder and the like |
US4140920A (en) * | 1976-08-27 | 1979-02-20 | Signetics Corporation | Multivalued integrated injection logic circuitry and method |
KR920007504B1 (en) | 1989-02-02 | 1992-09-04 | 정호선 | Adder by using neural network |
KR910009445B1 (en) | 1989-02-02 | 1991-11-16 | 정호선 | Associative memory using neuron network |
KR920007505B1 (en) | 1989-02-02 | 1992-09-04 | 정호선 | Multiplier by using neural network |
KR920008271B1 (en) | 1990-04-03 | 1992-09-26 | 정호선 | Floating point type adder using neural network |
JPH04251389A (en) | 1991-01-08 | 1992-09-07 | Canon Inc | Arithmetic unit |
KR100225594B1 (en) * | 1991-03-29 | 1999-10-15 | 가나이 쯔도무 | Current-driven signal interface implemented in semiconductor integrated circuit device |
US5248956A (en) | 1991-04-05 | 1993-09-28 | Center For Innovative Technology | Electronically controllable resistor |
DE19521089C1 (en) | 1995-06-09 | 1996-08-08 | Siemens Ag | Logic circuit with elements representable by threshold value equations |
JP3244707B2 (en) | 1995-06-09 | 2002-01-07 | シーメンス アクチエンゲゼルシヤフト | Two-quantity comparison circuit device that can be realized by a first neuron MOS field-effect transistor and a reference source |
KR100244396B1 (en) * | 1996-12-30 | 2000-02-01 | 김영환 | A carry lookahead adder |
-
1998
- 1998-09-21 US US09/158,947 patent/US6205458B1/en not_active Expired - Fee Related
-
1999
- 1999-09-07 WO PCT/US1999/020543 patent/WO2000017802A2/en active Application Filing
- 1999-09-07 AU AU58155/99A patent/AU5815599A/en not_active Abandoned
-
2001
- 2001-01-10 US US09/758,080 patent/US20010001860A1/en not_active Abandoned
- 2001-01-10 US US09/757,978 patent/US6502120B2/en not_active Expired - Fee Related
- 2001-01-10 US US09/758,071 patent/US6516331B2/en not_active Expired - Fee Related
-
2002
- 2002-08-02 US US10/211,866 patent/US20030009504A1/en not_active Abandoned
- 2002-08-15 US US10/219,714 patent/US20030028575A1/en not_active Abandoned
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8156312B2 (en) | 1996-12-09 | 2012-04-10 | Martin Vorbach | Processor chip for reconfigurable data processing, for processing numeric and logic operations and including function and interconnection control units |
US7822968B2 (en) | 1996-12-09 | 2010-10-26 | Martin Vorbach | Circuit having a multidimensional structure of configurable cells that include multi-bit-wide inputs and outputs |
US7899962B2 (en) | 1996-12-20 | 2011-03-01 | Martin Vorbach | I/O and memory bus system for DFPs and units with two- or multi-dimensional programmable cell architectures |
US8195856B2 (en) | 1996-12-20 | 2012-06-05 | Martin Vorbach | I/O and memory bus system for DFPS and units with two- or multi-dimensional programmable cell architectures |
US7650448B2 (en) | 1996-12-20 | 2010-01-19 | Pact Xpp Technologies Ag | I/O and memory bus system for DFPS and units with two- or multi-dimensional programmable cell architectures |
US7822881B2 (en) | 1996-12-27 | 2010-10-26 | Martin Vorbach | Process for automatic dynamic reloading of data flow processors (DFPs) and units with two- or three-dimensional programmable cell architectures (FPGAs, DPGAs, and the like) |
USRE45109E1 (en) | 1997-02-08 | 2014-09-02 | Pact Xpp Technologies Ag | Method of self-synchronization of configurable elements of a programmable module |
USRE45223E1 (en) | 1997-02-08 | 2014-10-28 | Pact Xpp Technologies Ag | Method of self-synchronization of configurable elements of a programmable module |
USRE44365E1 (en) | 1997-02-08 | 2013-07-09 | Martin Vorbach | Method of self-synchronization of configurable elements of a programmable module |
US8819505B2 (en) | 1997-12-22 | 2014-08-26 | Pact Xpp Technologies Ag | Data processor having disabled cores |
US8468329B2 (en) | 1999-02-25 | 2013-06-18 | Martin Vorbach | Pipeline configuration protocol and configuration unit communication |
US8312200B2 (en) | 1999-06-10 | 2012-11-13 | Martin Vorbach | Processor chip including a plurality of cache elements connected to a plurality of processor cores |
US8726250B2 (en) | 1999-06-10 | 2014-05-13 | Pact Xpp Technologies Ag | Configurable logic integrated circuit having a multidimensional structure of configurable elements |
US8230411B1 (en) | 1999-06-10 | 2012-07-24 | Martin Vorbach | Method for interleaving a program over a plurality of cells |
US8301872B2 (en) | 2000-06-13 | 2012-10-30 | Martin Vorbach | Pipeline configuration protocol and configuration unit communication |
US8471593B2 (en) | 2000-10-06 | 2013-06-25 | Martin Vorbach | Logic cell array and bus system |
US8058899B2 (en) | 2000-10-06 | 2011-11-15 | Martin Vorbach | Logic cell array and bus system |
US9047440B2 (en) | 2000-10-06 | 2015-06-02 | Pact Xpp Technologies Ag | Logical cell array and bus system |
US20040128474A1 (en) * | 2000-10-09 | 2004-07-01 | Martin Vorbach | Method and device |
US7595659B2 (en) * | 2000-10-09 | 2009-09-29 | Pact Xpp Technologies Ag | Logic cell array and bus system |
US7844796B2 (en) | 2001-03-05 | 2010-11-30 | Martin Vorbach | Data processing device and method |
US9037807B2 (en) | 2001-03-05 | 2015-05-19 | Pact Xpp Technologies Ag | Processor arrangement on a chip including data processing, memory, and interface elements |
US8145881B2 (en) | 2001-03-05 | 2012-03-27 | Martin Vorbach | Data processing device and method |
US9075605B2 (en) | 2001-03-05 | 2015-07-07 | Pact Xpp Technologies Ag | Methods and devices for treating and processing data |
US8099618B2 (en) | 2001-03-05 | 2012-01-17 | Martin Vorbach | Methods and devices for treating and processing data |
US8312301B2 (en) | 2001-03-05 | 2012-11-13 | Martin Vorbach | Methods and devices for treating and processing data |
US7657877B2 (en) | 2001-06-20 | 2010-02-02 | Pact Xpp Technologies Ag | Method for processing data |
US8869121B2 (en) | 2001-08-16 | 2014-10-21 | Pact Xpp Technologies Ag | Method for the translation of programs for reconfigurable architectures |
US7996827B2 (en) | 2001-08-16 | 2011-08-09 | Martin Vorbach | Method for the translation of programs for reconfigurable architectures |
US8686549B2 (en) | 2001-09-03 | 2014-04-01 | Martin Vorbach | Reconfigurable elements |
US8209653B2 (en) | 2001-09-03 | 2012-06-26 | Martin Vorbach | Router |
US8407525B2 (en) | 2001-09-03 | 2013-03-26 | Pact Xpp Technologies Ag | Method for debugging reconfigurable architectures |
US8429385B2 (en) | 2001-09-03 | 2013-04-23 | Martin Vorbach | Device including a field having function cells and information providing cells controlled by the function cells |
US7840842B2 (en) | 2001-09-03 | 2010-11-23 | Martin Vorbach | Method for debugging reconfigurable architectures |
US8069373B2 (en) | 2001-09-03 | 2011-11-29 | Martin Vorbach | Method for debugging reconfigurable architectures |
US8686475B2 (en) | 2001-09-19 | 2014-04-01 | Pact Xpp Technologies Ag | Reconfigurable elements |
US8281108B2 (en) | 2002-01-19 | 2012-10-02 | Martin Vorbach | Reconfigurable general purpose processor having time restricted configurations |
US20070150637A1 (en) * | 2002-02-18 | 2007-06-28 | Martin Vorbach | Bus systems and method for reconfiguration |
US8127061B2 (en) | 2002-02-18 | 2012-02-28 | Martin Vorbach | Bus systems and reconfiguration methods |
US8156284B2 (en) | 2002-08-07 | 2012-04-10 | Martin Vorbach | Data processing method and device |
US8914590B2 (en) | 2002-08-07 | 2014-12-16 | Pact Xpp Technologies Ag | Data processing method and device |
US7657861B2 (en) | 2002-08-07 | 2010-02-02 | Pact Xpp Technologies Ag | Method and device for processing data |
US8281265B2 (en) | 2002-08-07 | 2012-10-02 | Martin Vorbach | Method and device for processing data |
US7928763B2 (en) | 2002-09-06 | 2011-04-19 | Martin Vorbach | Multi-core processing system |
US8803552B2 (en) | 2002-09-06 | 2014-08-12 | Pact Xpp Technologies Ag | Reconfigurable sequencer structure |
US8310274B2 (en) | 2002-09-06 | 2012-11-13 | Martin Vorbach | Reconfigurable sequencer structure |
US7782087B2 (en) | 2002-09-06 | 2010-08-24 | Martin Vorbach | Reconfigurable sequencer structure |
US8812820B2 (en) | 2003-08-28 | 2014-08-19 | Pact Xpp Technologies Ag | Data processing device and method |
US8250503B2 (en) | 2006-01-18 | 2012-08-21 | Martin Vorbach | Hardware definition method including determining whether to implement a function as hardware or software |
Also Published As
Publication number | Publication date |
---|---|
US20010001862A1 (en) | 2001-05-24 |
US6205458B1 (en) | 2001-03-20 |
US20030009504A1 (en) | 2003-01-09 |
WO2000017802A3 (en) | 2000-07-20 |
AU5815599A (en) | 2000-04-10 |
US6516331B2 (en) | 2003-02-04 |
WO2000017802A2 (en) | 2000-03-30 |
US6502120B2 (en) | 2002-12-31 |
US20010001861A1 (en) | 2001-05-24 |
US20030028575A1 (en) | 2003-02-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6205458B1 (en) | Adder and multiplier circuits employing logic gates having discrete, weighted inputs and methods of performing combinatorial operations therewith | |
US7043520B2 (en) | High-speed/low power finite impulse response filter | |
US10402166B2 (en) | System and method for processing data in an adder based circuit | |
US7395304B2 (en) | Method and apparatus for performing single-cycle addition or subtraction and comparison in redundant form arithmetic | |
US5508952A (en) | Carry-lookahead/carry-select binary adder | |
Kaivani et al. | Floating-point butterfly architecture based on binary signed-digit representation | |
Nielsen et al. | An IEEE compliant floating-point adder that conforms with the pipeline packet-forwarding paradigm | |
Rakesh et al. | A comprehensive review on the VLSI design performance of different Parallel Prefix Adders | |
Sakthivel et al. | Low power area optimized and high speed carry select adder using optimized half sum and carry generation unit for FIR filter | |
Gudala et al. | Implementation of high speed and low power carry select adder with BEC | |
CA2078319C (en) | Control signal method and device | |
Ykuntam et al. | Design of speed and area efficient non linear carry select adder (NLCSLA) architecture using XOR less adder module | |
Gowreesrinivas et al. | Comparative study on performance of single precision floating point multiplier using vedic multiplier and different types of adders | |
Kuang et al. | Variable-latency floating-point multipliers for low-power applications | |
Rashidi et al. | Design of a low-power and low-cost booth-shift/add multiplexer-based multiplier | |
Ebrahimi-Azandaryani et al. | Accuracy configurable adders with negligible delay overhead in exact operating mode | |
Pawar et al. | Review on multiply-accumulate unit | |
Najafi et al. | Stochastic mixed-PR: A stochastically-tunable low-error adder | |
Ragunath et al. | Delay optimized binary to BCD converter for multi-operand parallel decimal adder | |
Kwak et al. | High-speed CORDIC based on an overlapped architecture and a novel σ-prediction method | |
Thamizharasi | Design and implementation of efficient carry select adder using novel logic algorithm | |
Gottem | A Critical Analysis of Approximate Adders: Correctness and Analysis of Performance | |
Rao et al. | IMPLEMENTATION OF MULTIPLEXER BASED HIGH SPEED AND LOW POWER CONSUMPTION MULTIPLIER | |
Sravanthi et al. | DESIGN OF POWER AND AREA EFFICIENT CSLA BASED MULTIPLIER FOR GAUSSIAN FILTER | |
US6438572B1 (en) | Adder having reduced number of internal layers and method of operation thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |