Abstract: A system for and a method of generating a four phase clock signal is disclosed. The system includes an oscillator circuit that generates a clocking signal of frequency F. A flip-flop, under control of a Master Clear signal, establishes the first stage of a shift register in an active state while the clocking signal drives the shaft register to serial, end-around, shift the active state through the shift register. The parallel outputs of the shift register are coupled to respectively associated pulse generators which are also triggered by the clock signal to emit the four phase clock signal therefrom. The method ensures that the first phase signal is always the first signal to be emitted from the system while compatible semiconductor circuitry is used throughout and is operated at or near the frequency limit of the semiconductor circuitry used.

Abstract: A large capacity (8 memory banks of 524K error-corrected 36 bit words stored) high performance (latency as low as 240 nanoseconds, 12.8 gigabits/second aggregate data transfer capability with up to 11.4 gigabits/second utilized) pipelined (8 deep request pipeline) random access memory store simultaneously (to the limit of bank addressing conflicts) services intermixed requests from an internal exerciser plus ported requestors (up to 10) of plural types (3 types), which requestors are not of the same interface cycle time (30 nsec vs. 60 nsec). Furthermore, to such nonuniform interface cycle times, the bit-width of the data transfer interfaces (ports) to the requestors of plural types is also not uniform, but is actually wider (4 interface words of 36 bits each=144 bits) to faster (30 nanosecond) requestors than is that data transfer bit-width (2 interface words=72 bits) to slower (60 nsec) requestors.

Abstract: An economical circuit of n transistors and m resistors (n=4, m=1 for Emitter Coupled Logic (ECL); n=3, m=0 for Current Mode Logic (CML)) interconnects to a fast differential feedback latch of r transistors and s resistors (r=12, s=9 for ECl; r=7, s=3 for CML) using two levels of series gating and one current source in order to establish scan/set testability of such latch. An additional interconnected circuit of v transistors and w resistors (b=2, w-1 for ECL; v=1, w=0 for CML) further establishes either a reset or a set capability for such latch. The economical total scan/set testable latch of x transistors and y resistors (x=18, y=11 for ECL; x=11, y=3 for CML) exhibits an excellent delay-power product since a single current is selectively steered into one of four different paths, the remaining three of which paths are shut down. Use of but a single current source provides further economy of silicon implementation.

Abstract: A system for accelerating the granting of prioritized memory requests to a multi port memory system of a data processing system is disclosed. The priority requestor accelerator system detects the fact that one remaining requestor is in the priority memory system. The priority system logic is cleared out before the end of the normal requestor cycle. This allows the acceptance of a new set of requestors to be presented to the priority circuits at that time rather than waiting until presentation of the final request. Thus, the accelerator detects that the requestors from a previous requesting snap are on their last cycle. This allows a preclearance of the lower ranks as the priority circuit finishes its last cycle. The new requests are then loaded and the priority inputs are snapped shut beginning a new set of cycles. The overall operation happens as if the priority circuit is just moving from one requestor to another that is already in residence after the snap.

Abstract: A method of fabricating a thin magnetic film having improved magnetoresistive readout characteristics as a binary memory device is disclosed. The film is initially formed from a metal vapor as a series of discrete grains upon a substrate surface that is heated to approximately 300.degree. C. Upon continued growth of the film, the grains merge at their boundaries forming a continuous thin film, the grain boundary heights of which, e.g., 1000 .ANG., are substantially greater than the thickness, e.g., 320 .ANG., of the eventual thin magnetizable film. The thin film is then rotated while being ion milled at an oblique angle to a substantially uniform film thickness of e.g. 320 .ANG..

Abstract: A high performance pipelined virtual first-in first-out stack structure has a data stack portion and a split control stack portion. The stack structure is intended for use in a pipelined high performance storage unit that can pipeline up to R input requests without having received an acknowledge that a request has been honored. The data stack incorporates R+1 data stack registers to provide over-write protection to ensure that at least R data stack registers are protected from over-write. The split control stack utilizes even address and odd address stack registers. Memory bank request signals are stored sequentially and alternately between the even address and odd address stack registers.

Abstract: A high speed system utilizing programmably controlled ranks of multiplexers for reformatting data from programmably selected first formats to second formats is described. Interleaved input data is utilized to optimize reformatting rates. The reformatting system provides field selection and justification together with the capability of complementing and magnitude generation of the selected fields. Floating-point operands in two different floating-point formats can be unpacked, that is the characteristic separated from the mantissa and properly aligned, and can be packed by positioning and recombining the characteristic with that associated mantissa. Throughout the entire reformatting process, parity for selected bit groupings is maintained, thereby allowing through checking of reformatting operations. The reformatting system includes programmably selectable constant generation.

Abstract: A binary division circuit for use in a large data processing system is disclosed which performs division with floating or fixed point numbers. It includes a multiplier unit which is modified to produce the higher precision calculation necessary to the division operation. This modification includes an augmented multiplier circuit which is combined with a quotient correction technique to provide a binary division circuit which produces identical quotients to those obtained by restoring or non-restoring divide techniques in less time than is required by other divide techniques.

Abstract: An improved masked arithmetic logic unit is disclosed which incorporates at least three principle unique features to optimize implementation in a high speed environment. These features are (1) the inclusion of a mask operand to facilitate mask compares and mask substitute operations without adding logic levels to the arithmetic logic unit; (2) the inclusion of a sum minus one network to speed up system performance by minimizing the delay usually associated with group borrow input to final sum output and (3) the inclusion of a mode control register internal to the arithmetic logic unit to minimize or camouflage the delay always found in the mode switching control of contemporary arithmetic logic units.

Abstract: The memory system incorporates a memory element storing binary digital data in the presence, vel non, of a Y-domain cross-tie. The memory element has a planar contour that is substantially symmetrical about a longitudinal axis and that has edge portions that are nowhere perpendicular or parallel to the longitudinal axis. A stabilizing magnetic field applied perpendicular to the longitudinal axis and in the plane of the memory element forms a first Neel wall along the longitudinal axis and causes the magnetization in the memory element to be formed into first and second domains on opposite sides of the Neel wall. When a writing magnetic field oriented in the plane of the memory element and perpendicular to the longitudinal axis but opposite to the stabilizing magnetic field orientation is coupled to the memory element, there is formed in the memory element a third domain separated from the first and second domains by second and third Neel walls having a join with one end of the first Neel wall.

Abstract: An integrated circuit package having an auxiliary heating element incorporated therein is described. The integral heating element is accessible for application of electric power from an external source to cause heating of the integral circuit package to a predetermined level at which solder will melt and flow, thereby allowing removal and reinsertion of the integrated circuit package with relationship to associated pins in a support assembly. The integral heating element provides a means for applying controlled heat to the integrated circuit package such that the package can be unsoldered from or soldered to associated electrical interconnection pins, some of which may be hidden from view or physical access.

Abstract: A 72-bit shift matrix, suitable for LSI implementation in gate arrays, is disclosed. Eight byte shifters and eight bit shifters are combined to produce shifts of 0-72 places in either direction, circularly or open ended with zero or sign fill. A means is additionally provided to regenerate original source parity from the matrix outputs for use in thru checking. A single 9-bit parity generator is all that is required to check the correctness of the matrix.

Abstract: A level sensitive scan design (LSSD) Latch Cell that is adaptable to very large scale integrated (VLSI) Semiconductor circuit fabrication is disclosed. The Latch Cell includes a static functional latch and a dynamic test latch, both of which are controlled by a data selector that selects input data from either a functional data source or test data from another test latch in a scan data path.

Abstract: A multiply pipeline with parity circuit to be used as a building block in a multiplication pipeline of arbitrary size is disclosed. It includes circuits for generating and checking parity. The parity of the output carries leaving the component chips of the multiply pipeline are explicitly generated internally to those chips. By generating output carry parity on-chip, all single-bit errors except for those caused by on-chip internal gate or metallization faults will be detected. Thus, means are provided for detection of single-bit errors in the multiplication circuitry. The proposed multiply pipeline with parity circuit includes a pair of gate arrays, or chips, which participate as follows. A 6-bit by 6-bit multiply with parity chip is used as a building block in a portion of the pipeline in which all logical products are initially generated, and reduction of these logical products, or partial products, commences.

Abstract: A low insertion force connector for making electrical connection between electrical contacts on a printed circuit board assembly and external circuitry, and having an improved linear cam actuating mechanism is described. An elongated outer housing having a centrally located opening with a longitudinal channel along the bottom thereof, has spaced apart ramps positioned at the bottom of the channel. The housing has an aperture at each end thereof, and has external ramps on each end of the outer housing in a predetermined relationship to the associated aperture. A plurality of contacts are mounted within the outer housing on either side of the channel, with first ends interior the housing being bowed inwardly for contacting the printed circuit board assembly, and second ends extending through said outer housing for making electrical connection to external circuitry.

Abstract: A decoder for forward-error-correcting (FEC) convolutional codes. The decoder uses the Viterbi algorithm for decoding the rate 1/2, constraint length 7 code with generator polynomials x.sup.6 +x.sup.5 +x.sup.3 +x.sup.2 +1, and x.sup.6 +x.sup.3 +x.sup.2 +x+1. The architecture of the instant decoder is appropriate for implementation on a single, monolithic VLSI integrated circuit chip and includes a branch metric calculator circuit which produces output signals representative of input symbol signals. These output signals are supplied to a metric update circuit which evaluates the signals from the calculator circuit and provides decisions to a path update circuit which converges the signals thereto and the output signals of which are evaluated by a majority vote circuit which produces data output signals representative of data input signals.

Abstract: For use with a digital memory system that generates error correction code signals for storage with associated data words and for correction of detected error(s) in the associated data words when accessed, a system for through checking the accuracy of generation of the error correction codes and the decoding of error correction code is described. A data word parity signal is generated for storage with the associated data word and its associated check bit. When a data word is accessed, the read data word and its associated check bits are applied to error correction circuitry that results in a determination of whether or not any bits of the read data word are in error. Correction circuitry corrects those error in the read data word that are correctable. The corrected read data word is applied to a parity generator circuit that generates that parity of the corrected read data word. A comparison circuit compares the word parity calculated for the corrected read data word.

Abstract: A method and a means are disclosed for the throughchecking of the normalizer operations of an arithmetic unit of a data processing system involving both integer and floating-point formats in single and double precision operations. A post normalizer is used in conjunction with the main normalizer of the arithmetic unit to determine if the result is indeed normalized. Where the post normalize count is zero, an error designator remains inactivated. However, where the count is non-zero, the error designator is activated to indicate an error exists, unless it is disabled by separate circuitry which detects that the number being shifted is .+-..0.. The preferred embodiment disclosed herein checks the operation of a pair of 72-bit main normalizers with a single 13-bit post normalizer. A plurality of instructions in which this check is significant are illustrated.

Abstract: An improved dynamic memory system including through-checking and error detection of the refresh counter is described. A refresh counter that provides parity of the refresh count for through-checking, of refresh addresses is shown. Error detecting circuitry is utilized in conjunction with the refresh counter and the parity generating circuitry to detect errors in functionality of the refresh counter. The refresh counter is a Gray code counter constructed of a double rank of latches operable with code generating logic circuits for determining the sequence of generation of Gray code groupings.

Abstract: A clock source for timing and synchronizing the operation of digital data processing equipment and having automatic duty cycle correction is described. A source of signals provides clock signals at a predetermined frequency. A buffer circuit provides the true and complement clock signals to low pass filters that function to filter the true and complement clock signals to DC levels proportional to the duty cycle of the source signals. The DC voltages represent instantaneous deviation voltages from a known reference and are applied to a differential amplifier circuit for providing a feedback signal for adjusting the duty cycle of the clock output pulses that are available. One embodiment has the source of signals directly coupled to the buffer circuitry and utilizes the feedback signal to adjust the duty cycle of the signal source circuitry. A second embodiment has the source signals capacitively coupled to the self-correcting circuitry and the feedback signals adjust the duty cycle of the clock output signal.