Abstract: A parallel self-timed adder (PASTA) is disclosed. It is based on recursive formulation and uses only half adders for performing multi-bit binary addition. Theoretically the operation is parallel for those bits that do not need any carry chain propagation. Thus the new approach attains logarithmic performance without any special speed-up circuitry or look-ahead schema. The corresponding CMOS implementation of the design along with completion detection unit is also presented. The design is regular and does not have any practical limitations of fan-ins or fan-outs or complex interconnections. Thus it is more suitable for adoption in fast adder implementation in high-performance processors. The performance of the implementation is tested using SPICE circuit simulation tool by linear technology. Simulation results show its superiority over cascaded circuit adders. A constant time carry propagation is also achieved using the proposed implementation by tuning the CMOS parameters.

Abstract: A method includes receiving a packed data instruction indicating a first narrower source packed data operand and a narrower destination operand. The instruction is mapped to a masked packed data operation indicating a first wider source packed data operand that is wider than and includes the first narrower source operand, and indicating a wider destination operand that is wider than and includes the narrower destination operand. A packed data operation mask is generated that includes a mask element for each corresponding result data element of a packed data result to be stored by the masked packed data operation. All mask elements that correspond to result data elements to be stored by the masked operation that would not be stored by the packed data instruction are masking out. The masked operation is performed using the packed data operation mask. The packed data result is stored in the wider destination operand.

Abstract: Disclosed are an accumulator for reducing nonlinearity of a data converter and a data weighted average device including the accumulator. According to the accumulator including a register configured to output input data according to a clock signal; a first adder configured to receive a digital input signal having any bit width and an output signal from the register to perform an add operation; a preset unit configured to output a preset value or a 0 value according to whether a carry of the first adder is generated; and a second adder configured to receive an output signal of the first adder and an output signal of the preset unit to perform the add operation and input the add operation to the register and the data weighted average device including the accumulator, it is possible to improve the nonlinearity occurring in the data converter by generating a number of DAC codes in addition to 2n DAC codes.

Abstract: Methods and system for modeling the behavior of binary synapses are provided. In one aspect, a method of modeling synaptic behavior includes receiving an analog input signal and transforming the analog input signal into an N-bit codeword, wherein each bit of the N-bit codeword is represented by an electronic pulse. The method includes loading the N-bit codeword into a circular shift register and sending each bit of the N-bit codeword through one of N switches. Each switch applies a corresponding weight to the bit to produce a weighted bit. A signal corresponding to a summation of the weighted bits is output and represents a synaptic transfer function characterization of a binary synapse.

Abstract: A method for fast parallel adder processing. The method includes receiving parallel inputs from a communications path, wherein each input comprises one bit, adding the inputs using a parallel structure, wherein the parallel structure is optimized to accelerate the addition by utilizing a characteristic that the inputs are one bit each, and transmitting the resulting outputs to a subsequent stage.

Abstract: A parallel self-timed adder (PASTA) is disclosed. It is based on recursive formulation and uses only half adders for performing multi-bit binary addition. Theoretically the operation is parallel for those bits that do not need any carry chain propagation. Thus the new approach attains logarithmic performance without any special speed-up circuitry or look-ahead schema. The corresponding CMOS implementation of the design along with completion detection unit is also presented. The design is regular and does not have any practical limitations of fan-ins or fan-outs or complex interconnections. Thus it is more suitable for adoption in fast adder implementation in high-performance processors. The performance of the implementation is tested using SPICE circuit simulation tool by linear technology. Simulation results show its superiority over cascaded circuit adders. A constant time carry propagation is also achieved using the proposed implementation by tuning the CMOS parameters.

Abstract: A fast lookahead carry adder includes adder logic and lookahead carry-path logic coupled to the adder logic. The carry path logic has a main carry path, a carry entrance path and a carry exit path, the carry entrance path separate from the carry exit path.

Abstract: The digital propagate, digit generate, sum+0, and sum+1 terms used in typical carry-propagate adders are generated directly off the multiplicand. During the direct generation, the logic takes into account that each digit will be tripled and if each digit's next less significant digit is greater than 4. Using this technique, the generation of the multiplicand is significantly faster and uses less circuitry.

Abstract: A method for processing data includes generating one or more binary results based on one or more inputs and receiving one or more of the binary results. One or more conditional carryout signals may then be generated based on one or more of the binary results. The method also includes communicating one or more of the conditional carryout signals via one or more propagate cells. One or more carryout signals may be generated and received. A sum may then be generated based on the received carryout signals, the sum being communicated to a next destination.

Abstract: A carry-ripple adder has four summing inputs for receiving four input bits having the significance w that are to be summed, three carry inputs for receiving three input carry bits having the significance w, a summation output for outputting an output summation bit having the significance w, and three carry outputs for outputting three output carry bits having the significance 2w.

Abstract: An area efficient realization of an N-bit constant coefficient adder/subtractor implemented on FPGAs, utilizing N LUTs with single output generation capability. It includes three inputs from every LUT for addition/subtraction, without any requirement for extra logic for support of arithmetic mode and carry chains. For FPGAs supporting 4-input LUTs, the concept is further enhanced with the capability to perform addition and subtraction dynamically, by exploiting the fourth unused input of the LUTs. Another embodiment involves delay-optimized realization of an N-bit constant coefficient adder/subtractor implemented on FPGAs with 4-input LUTs. LUTs in the implementation have single output generation capability without any carry generation and propagation. The implementation utilizes N+1 LUTs and gives a delay proportional to N/2 of routing resource used. However, the implementation becomes more efficient by the use of cascade chains. The delay optimization is achieved by doing computation in two parallel chains.

Abstract: Disclosed is a mixed-type adder with optimized design costs. The mixed-type adder includes I sub adders, (where, I is a positive number larger than 1). An overall bit width of the mixed-type adder is divided into I bit groups which are respectively allocated to the I sub adders. The I sub adders have different carry propagation schemes and are connected in series through a carry signal.

Abstract: A carry select adder to add two binary addends to produce a binary sum. In a first section a first addition block adds 6-bit addend slices having 3-bit lower-half and higher-half slices. A first adder block receives and adds the lower-half slices and outputs an adder-carry-out and a 3-bit lower-half value. A zero-carry-loaded second adder block receives and adds the higher-half slices and outputs a 4-bit zero-related intermediate-value. A one-carry-loaded third adder block receives and adds the higher-half slices and outputs a 4-bit one-related intermediate-value. A 4-bit multiplexer then passes either the zero-related intermediate-value or the one-related intermediate-value as a 1-bit section-carry-out and a 3-bit higher-half value based on the adder-carry-out, wherein the higher-half value and the lower-half value form a 6-bit sum slice corresponding to the 6-bit addend slices.

Abstract: A cryptography processor includes a central processing unit and a co-processor, the co-processor comprising a plurality of calculating subunits as well as a single control unit which is coupled to each of the plurality of calculating subunits. A cryptographic operation is distributed among the individual calculating subunits in the form of sub-operations by the control unit. The central processing unit, the plurality of calculating subunits and the control unit are integrated on a single chip, the chip comprising a common supply current access for supplying the plurality of calculating subunits and the control unit with current. Due to the arrangement of the calculating subunit in parallel, on the hand, the throughput of the cryptography processor is increased. On the other hand, however, the current profile that may be detected at the supply current access is randomised to such an extent that an attacker can no longer infer numbers processed in the individual calculating subunits.

Abstract: An adder circuit includes a number of selectors and an adder. The selectors feed the adder with multiple input data bits. Each of the selectors includes a combination of a multiplexing network and a sense amplifier to select from a number of input values to generate the multiple input data bits. The combination of the multiplexing network and the sense amplifier acts as the state-holding element at the input of the adder, avoiding the overheads of an explicit latch stage.

Abstract: A system and method for converting two binary digits into redundant sign-digit format. The system comprises a first adder for adding the binary digits together to generate a first result. A second adder adds an input carry from a previous digit to the first result and subtracts a value equal to the radix of the of the binary digits form the first result if the first result is greater than an initial threshold in order to generate an intermediate result. The system further includes a third adder for adding a second input carry from the previous digit to the intermediate result and subtracting the value of the radix from the intermediate result if the intermediate result is greater than a prescribed value such that the addition of the two binary digits are in redundant sign-digit format.

Abstract: A fast pipelined adder/subtractor using increment/decrement functions with reduced register utilization. Embodiments of the present invention replace double width registers with incrementor elements, pipelined single width registers, and pipelined carry bits. This is made possible by positioning the adder elements at the first pipestage in each of the pipelines. Single width registers are used to hold the results of the initial add/subtract operation. Single bit registers pipeline the carry bits from the adders and incrementors to the next stage. The incrementor collects the sum from one of the adder elements, the pipelined carry bit from that adder element, and the carry bit from a previous stage adder and combines them to produce a new result and carry. This new result is passed along the pipeline to the output bus of the circuit. In this fashion, no double width busses or registers are required in between individual pipestages of the pipelines.

Abstract: An ultra low power adder with sum synchronization which provides a power reduction method in the binary carry propagate adders by using a carry skip technique. The invention eliminates glitches at the adder outputs by preventing signal transitions at the sum outputs until the corresponding carry signals have reached their final values, which is achieved by adding a synchronization circuitry to the sum calculation path.

Abstract: Calculating unit having adder blocks, each having single adders, a carry input, a carry output, and a carry pass output, wherein a signal at the carry pass output is indicative of a carry passing through the adder block. Depending on the carry pass output signal, a clock generator for feeding the adder blocks with operands to be processed is decelerated. A determining unit determines in which of the adder blocks a least significant bit of an operand to be subtracted is disposed. A deactivating unit deactivates a carry pass output of adder block(s) provided for lower order digits with respect to the adder block in which the least significant bit is disposed, and a feeding unit feeds a carry into the carry input of this adder block in which the least significant bit is disposed.

Abstract: A calculating unit comprises several adder blocks with single adders, a clock generator and control means. A carry pass means is associated with each adder block, which determines whether a carry passes fully through the respective adder block. If it is determined that the carry does not pass through any of the adder blocks, the calculating unit is clocked with a clock period, which is sufficient that the carry passes almost fully through an adder block, and passes through at least part of the upstream adder block. If it is determined, that the carry passes fully through an adder block, a panic signal is generated. The adder block is decelerated, so that the clock period is high enough that the carry additionally fully passes through another adder block. Only in a case of panic signals of two adjacent adder blocks, is the calculating unit is decreased so much, that the carry passes from the least significant digit of the calculating unit to the most significant digit of the calculating unit.

Abstract: A pipelined processor such as an averaging filter including at least one subtractor section and at least one adder section. Both of the subtractor section and the adder section have a plurality of adder logic units. In comparison to the conventional processor, the processor of the present invention is streamlined by the application of one or more of three techniques. First, there is the interleaving approach where the subtractor section and the adder section are interleaved with one another. Second, there is the one delay feedback approach where the adder section includes a one delay feedback for each of the adder logic units. Third, there is the delay enable signal output approach where the averaging filter includes a delay enable signal output for each of the adder logic units of the adder section.

Abstract: An adder based circuit embodied in an integrated circuit includes an input module, a carry module and an output module. The carry module has a minimum depth defined by a recursive expansion of at least one function associated with the carry module based on a variable k derived from a Fibonacci series. Invertor, XOR, XNOR (more preferably, OR(NOT(a),b)) and multiplexer elements are selectively coupled to the input and output modules to configure the adder based circuit as a subtractor, adder-subtractor, incrementor, decrementor, incrementer-decrementor or absolute value calculator. A computer process of designing the adder base circuit recursively expands the functions, and optimization of death, fanout and distribution of negations is performed.

Abstract: An apparatus having two or more parallel carry chain structures, each of the carry chain structures comprising a series of logical structures, where at least one of the logical structures within each of the carry chain structures has an associated input node, output node and carry node. The input node corresponds to a function input term, the output node corresponds to an output term of the function and the carry node corresponds to a carry value to a following logical structure in the series of logical structures.

Abstract: A fixed-point arithmetic unit comprises a plurality of full-adders and half-adders arranged in at least an input row and an output row. A plurality of inputs to the input row is arranged to receive bits comprising a sparse-redundant representation of the integer. A converter converts 1-redundant representations of the integer to the space (1/K)-redundant representations. A process is described to design rows of a multiplier by identifying a distribution of multiplication product groups, and transforming the distribution of multiplication product groups to adders to occupy a highest unoccupied row of the multiplier.

Abstract: A parallel-prefix modulo 2n−1 adder (201) that is as fast as the fastest parallel prefix 2n integer adders, does not require an extra level of logic to generate the carry values, and has a very regular structure to which pipeline registers can easily be added. All nodes of the adder have a fanout ≦2. In the prefix structure (203) of the adder, each carry value term output by the parallel prefix structure is determined by the all of the bits in the operands input to the adder. In one embodiment, there are log2n stages in the prefix structure. Each stage has n logical operators, and all of the logical operators in the prefix structure are of the same kind. Pipeline registers may be inserted before and/or after a stage in the prefix structure.

Abstract: A carry skip adder has a plurality of ripple adders, in which at least one part of the plurality of ripple adders is divided into a plurality of groups, and a carry signal is transferred from one group to one upper group. In addition, a circuit for calculating C=C2+F*C1 is included, in which the C1 denotes a carry signal from the one group to the one upper group, and the F denotes a signal indicating whether or not outputs of all adders in the one upper group are 1s, and the C2 denotes a carry signal associated with the most upper ripple adder in the one upper group.

Abstract: An arithmetic logic unit (ALU) implemented with complementary pass gate logic using propagate, generate, and kill is provided. Broadly speaking, the ALU is a 64-bit ALU using a multi-stage global carry chain to generate intermediate fourth-bit carries that are folded with local four-bit sums to efficiently generate a final sum output. The ALU implements ones complement subtraction by incorporating a subtraction select signal to invert each bit of a second operand. The ALU circuitry implements a push-pull methodology to improve performance.

Abstract: The process for performing operations with a variable arithmetic does not call for any shifting of the data in the different registers that come into play in the operation. The input registers can have empty parts which are completed by appropriate bit sequences to ensure a propagation of a possible outgoing carry over in order to recover that carry over from a result register.

Abstract: An n-bit carry-skip adder includes a number of carry-skip stages and a logic circuit associated with one or more of the stages. The logic circuit includes split-adder logic and carry-skip logic configured such that a split control signal associated with the split-adder logic is applied to at least one gate of the carry-skip logic, so as to reduce a carry propagation delay of the adder. In an illustrative embodiment, the logic circuit is associated with an (n/2+1)th carry-skip stage of the adder, and the adder is configured to perform two parallel n/2-bit additions when the split control signal is at a first logic level, and to perform a single n-bit addition when the split control signal is at a second logic level. Advantageously, the invention allows the split-adder logic to be incorporated in a manner which minimizes the carry propagation delay without increasing the required circuit area.

Abstract: A high-speed, wide dynamic range, digital accumulator includes a first adder stage in which an input addend is added to a value of a least significant part of an output of an accumulator from a preceding clock period. The accumulator also includes at least one second stage having incrementer/decrementer means for performing an increment, decrement or identity operation on a most significant part of the output of the accumulator. The incrementer/decrementer means includes logic means for triggering the increment, a decrement or identity operation on the most significant part of the accumulator output based on a decision made on results obtained at the previous clock period.

Abstract: A circuit and method for deriving an adder output bit from adder input bits. In one embodiment, the circuit includes: (1) first, second and third threshold logic gates that generate intermediate bits based on threshold comparisons of concatenations of ones of the adder input bits and (2) combinatorial boolean logic that generates the adder output bit from the intermediate bits.

Abstract: A bus encoding/decoding apparatus and method for a low power digital signal processor (DSP), which uses a narrow data bus, is provided. The apparatus for encoding n bits of data of a data bus, includes a conditional inverting unit for inverting each of (n−1) lower bits of n data when the most significant bit of the n bits of data is 1, a storage unit for storing the last n bits of data which is output to the bus, and a first exclusive OR operating unit for performing a bitwise exclusive OR operation on the lower (n−1) bits or data, which has been inverted by the conditional inverting unit, and the lower (n−1) bits of the n data, which has been stored in the storage unit, wherein the most significant bit of the n bits of data and (n−1) bits of data, which is obtained as the result of the bitwise exclusive OR operation performed by the first exclusive OR operating unit, are output.

Abstract: A carry ripple adder contains five first inputs for accepting five input bits having equal significance w that are to be summed and two second inputs for accepting two carry bits having the significance w. It also contains an output for a sum bit having the significance w and two outputs for two carry bits having the significances 2w and 4w.

Abstract: An adder includes a number of computational stages each associated with one or more bit positions. Particular ones of the computational stages generate a sum output signal and a primary carry-output signal of the adder. A flag generation circuit is coupled to at least one of the stages and is operative to generate an overflow flag for the adder substantially in parallel with the generation of the sum output signal and the primary carry-output signal of the adder. Advantageously, the invention substantially reduces the computational delay associated with generation of the overflow flag, relative to that of conventional adders, without requiring an increase in transistor count or circuit area.

Abstract: A data processing circuit has an adder unit divided into plural sections. Each section receives a subset of the bits of the operands and generates a subset of the bits of the resultant. A carry multiplexer is disposed between the sections. This carry multiplexer selects one of a plurality of possible carry inputs to the following sections. The data processing circuit may make the specification of the selection of the carry control multiplexers by: the opcode of the instruction; a combination of the opcode and an opcode modification field; an immediate field directly specifying carry control signals; or designation a carry control register which stores the carry control signals. The adder unit may be divided into sections of equal size or of unequal size.

Abstract: When performing data processing operations upon data words 2, 4 including a plurality of abutting data values a0, a1, a2, a3, b0, b1, b2 and b3 the results of the operation upon one data value may influence a neighboring data value in an undesired manner. An error correcting value 34 may be determined from the input data words 2, 4 and then combined with the intermediate result 32 to correct for any undesired interactions between adjacent data values.

Abstract: A single chip microprocessor has at least two parallel pipelines that each have multiple processing stages, one of which is an instruction execution stage with a full functioned arithmetic logic unit (ALU). The ALU of one pipeline includes an adder that has the usual two input ports while the adder of the ALU of the other pipeline has at least one extra input port. Two successive arithmetically data dependent instructions are executed by the larger adder alone, while the smaller adder is used as part of a logic circuit that determines the carry bit for the instruction execution result obtained from the larger adder. The smaller adder is thus efficiently used, in an operation where it would otherwise be idle. The additional logic circuitry necessary to determine the carry bit is thus minimized.

Abstract: Shift of input data without split by a shifter, generation of code extension data by a code extension data generator, and generation of a mask signal by a mask signal generator are carried out in parallel. The mask signal generator generates the mask signal based on an amount of shift and split mode information. An output selector replaces data shifted by the shifter with code extension data bit by bit based on the mask signal, and outputs data which are shifted and code-extended according to the split mode information and arithmetic/logical shift information. In a carry-select type adder/subtractor as another embodiment, if split parallel process is to be executed, both a pair of unit adders/subtractors execute an arithmetic operation to be carried out for the case where no carry is supplied from lower digits, and then a selector selects an arithmetic result, which is obtained when no carry is supplied from lower digits, regardless of the carry from the lower digits.

Abstract: A carry skip adder comprises a plurality of ripple adders, wherein at least one part of the plurality of ripple adders is divided into a plurality of groups, and a carry signal is transferred from one group to one upper group. In addition, a circuit for calculating C=C2+F*C1 is included, wherein the C1 denotes a carry signal from the one group to the one upper group, and the F denotes a signal indicating whether or not outputs of all adders in the one upper group are is, and the C2 denotes a carry signal associated with the most upper ripple adder in the one upper group.

Abstract: Custom operations are useable in processor systems for performing functions including multimedia functions. These custom operations enhance a system, such as PC system, to provide real-time multimedia capabilities while maintaining advantages of a special-purpose, embedded solution, i.e., low cost and chip count, and advantages of a general-purpose processor reprogramability. These custom operations work in a computer system which supplies input data having at least two operand data, performs operations on the operand data, and supplies result data to a destination register.

Abstract: An execute unit including an integer operation circuit is provided. The integer operation circuit is dynamically configurable to operate upon many different widths of operands. A single pair of operands may be operated upon, wherein the width of the operands is the maximum width the integer operation circuit is configured to handle. Alternatively, multiple pairs of operands having narrower widths may be operated upon. The instruction being executed defines the width of the operands and therefore the number of operands. Wide operand operations are performed at a rate of one per instruction, and a rate of more than one instruction is achieved for narrow operands. The same integer operation circuitry is employed to perform both narrow and wide integer operations. Silicon area consumed by the integer operation circuitry may be reduced as compared to a wide integer operation circuit and multiple narrow integer operation circuits.

Abstract: A circuit is disclosed herein which generates the sum of two numbers (A and B) and the sum plus 1 in parallel so as not to take any additional time to generate the sum plus 1 value. The circuit comprises a carry look-ahead (CLA) tree portion and a summer portion. The CLA tree portion generates carry bits, as well as the logical relationship A.sub.i XOR B.sub.i, for application to a summer for bit position i. The carry bits contain information for either inverting or not inverting the A.sub.i XOR B.sub.i bit for both the sum and the sum plus 1 output of the summer. The sum bit and sum plus 1 bit are generated at approximately the same time.

Abstract: A circuit and method is provided which employs an adder for a sign extending a m bit operand. The circuit m method employs a n adder having first and second sets of n inputs and a set of n outputs. The m.sup.th bit or sign bit of the m bit operand to be extended, is inverted to generate a sign inverted m bit operand. This sign inverted m bit operand is inputted into m least significant first inputs of the n bit adder. Thereafter, a (n-m) bit operand is inputted into the (n-m) most significant first inputs of the n bit adder wherein each bit of the (n-m) bit operand represents logical 1. Additionally, n bit operand is inputted into the second n inputs of the n bit adder. The (m+1) most significant bit of the n bit operand represents a logical 1, while the remaining bits of the n bit operand represent logical 0. Upon parallel input of the sign inverted m bit operand, the (n-m) bit operand and the n bit operand into the n bit adder, the n bit adder generates an n bit output operand.

Abstract: A pulse-density modulator (10) for producing a pulse density output signal on an output line (36) representing successive parallel digital input words on input terminals (12) has a plurality of full adders (14, 16, 18), each having a carry output (C), and an input (A) for receiving a respective bit of a concurrently applied bit of the parallel input digital words. The overflow output (C) of each of the adders (14, 16, 18) is added as an input (B) of an adder of a next successively higher bit order. A latch (30) receives the carry output (C) of one of the adders (14) in a most significant bit position, with an output of the latch provides a pulse density modulated signal on an output line (36) representing the input digital words. A clock (35) applies clock pulses to the latches (20, 22, 24, 30) at a frequency at least as high as the frequency at which the successive parallel digital input words are applied to the inputs (12) of the adders (14, 16, 18).