摘要:
An apparatus and method for maintaining a circular FIFO (first-in, first-out) queue in an I/O (input-output) subsystem of a computer system such as a server, workstation, or storage machine. The queue is coupled to a bypass circuit, used to provide access to data items out of the order in which they were stored in the queue, thus bypassing the latency inherent in retrieving the items from the queue. Control logic maintains write and read pointers indicating locations in the queue for writing and reading data items. The write pointer is incremented upon every data event to the queue, thereby maintaining a history of data that has been written to the queue, which is useful for diagnostic purposes. A history flag is maintained to indicate whether the write pointer has wrapped around the addresses in the queue, indicating whether all data items in the queue are valid for diagnostic purposes.
摘要:
A method and structure for transposing a rectangular matrix A in a computer includes subdividing the rectangular matrix A into one or more square submatrices and executing an in-place transposition for each of the square submatrices Aij.
摘要:
A queuing architecture and method for scheduling disk drive access requests in a video server. The queuing architecture employs a controlled admission policy that determines how a new user is assigned to a specific disk drive in a disk drive array.
摘要:
In order to enable enlargement/reduction of data with a simple structure in a first-in first-out memory device thereby reducing the circuit scale of this device, output terminals (Q.sub.0 to Q.sub.3) of a read clock counter (16) are shifted to low order digits and connected to input terminals (A.sub.0 to A.sub.2) of a read address decoder (18). The read clock counter (16) and a read data sense amplifier (19) operate in response to read clocks (RK2). Enlarged read data (RD) are outputted from the read data sense amplifier (19). It is possible to implement enlargement/reduction of data by changing connection between the read clock counter (16) and the read address decoder (18), thereby remarkably simplifying the circuit structure of the first-in first-out memory device having an enlargement/reduction function.
摘要:
A data shuffler of the pipeline type receives successive trains of n sequential data words and rearranges data words in each train according to a predetermined order. It comprises p (p.ltoreq.n) elementary processing units arranged in series. Each unit comprises an input, an output, a one-word storage register (20), a steering means (21) in order, in response to a binary control, to connect the input to the output either directly or through the register; and means for periodically supplying to each of the p steering means a sequence of n control bits determined as a function of said predetermined order.
摘要:
A serializer/deserializer for a flow of n-bits of data shifted according to the rate of a clock includes an n-rows and n-columns matrix of 1-bit registers (00-77). Each 1-bit register is connected through its input to a first switch connected to the output of the register in the same row and lower rank column and to a second switch connected to the output of the register in the same column and upper rank row. Input terminals (E0-E7) are connected to the registers of the lower rank column and of the upper rank row. Output terminals (S0-S7) are connected to the registers of the upper rank column and of the lower rank row. The matrix cells are arranged according to a triangle, the cells being arranged one with respect to the other according to the structural corresponding to folding a square matrix along its diagonal.
摘要:
A data processing apparatus includes two data transmission paths formed likewise in a loop fashion. These data transmission paths include a plurality of latch registers connected in a cascade fashion respectively and are constituted as a so-called self-running type shift register wherein each data word constituting a data packet is shifted in sequence provided that a pre-stage register is vacant. Data packets are transmitted in the directions reverse to each other on the two loop-shaped data transmission paths an identification data included in each data packet being transmitted is detected in a section defined as a data packet pair detecting section. The detected identification data are compared in a comparing circuit and, one new data packet is produced from the two data packets in a manner that a data packet is joined from one data transmission path to the other data transmission path.
摘要:
A memory cell is comprised of a cross-coupled master latch and a cross-coupled slave latch. The memory cell includes means for switching on and off power supplies connected to the master latch and the slave latch so as to control the direction of shift in a bidirectional shift. Data is shifted in a first direction when the power supply connected to the master latch is switched off, and data is shifted in a second direction when the power supply connected to the slave latch is switched off.
摘要:
A fracturable x-y random access memory array for performing pushing and popping of data and fracturing the array simultaneously at a common address includes a row fracture circuit responsive to row addresses to fracture the array in the Y-direction and a column fracture circuit responsive to column addresses for fracturing the array in the X-direction. A plurality of memory cells are stacked in a plurality of columns to form an x-y organization which can be randomly accessed in response to the row and column addresses. The memory cells are responsive to a shift control driver circuit for bidirectional shifting of data by either pushing data into or popping data from at any point within one of the plurality of randomly addressable column at the same row and column addresses used to fracture the array defining a fracture point. Data in all of the memory cells in the array with addresses higher (or lower) than the fracture point shift and the memory cells with addresses lower (or higher) than the fracture point maintain their data unchanged.
摘要:
A control unit supplies information and includes a memory for storing information. A data bus connected to the control unit transfers the information. A controlled unit connected to the data bus receives information transferred from the control unit. The controlled unit comprises a plurality of n circuit stages, wherein n is a whole number, connected in tandem. The controlled unit includes first to n.sup.th circuit stages and an i.sup.th circuit stage intermediate the first and n.sup.th circuit stages and designated by the control unit. Information transferred from the control unit is stored in the first circuit stage and is transferred sequentially from the first to the i.sup.th circuit stages. Information stored in the first to (i-1).sup.th circuit stages is transferred to the memory of the control unit via the data bus for storage in the memory when the control unit requires alteration of information stored in the i.sup.th circuit stage. Alternative information is transferred from the control unit to the first circuit stage. The information stored in the memory of the control unit is sequentially transferred to the first circuit stage thereby shifting the alternative information to the i.sup.th circuit stage.