Patents by Inventor Sudarshan Kumar

Sudarshan Kumar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 5889693
    Abstract: A method and apparatus for a CMOS inverter is provided for incrementing a first number by a one, three, or multiple of two. The incrementing unit includes an extract/restore unit for extracting a number of least significant bits from the first number, thereby producing a second number. The number of least significant bits extracted is determined by the incrementing value. The incrementing unit further includes an adjusting unit for adding an adjusting value to the least significant bits extracted from the first number, thereby producing an adjusted least significant bits. The incrementing unit further includes an incrementor block for receiving the second number and incrementing the second number, thereby producing a fourth number. The the extract/restore unit further for restoring the adjusted least significant bits to the fourth number, thereby producing a final result.
    Type: Grant
    Filed: May 5, 1997
    Date of Patent: March 30, 1999
    Assignee: Intel Corporation
    Inventors: Vivek Joshi, Sudarshan Kumar
  • Patent number: 5661675
    Abstract: A logic circuit is described. The logic circuit generates a first signal state in response to a first set of input signals, generates a second signal state in response to a second set of input signals, activates a bypass switch in response to the first signal state, and bypasses a domino logic unit in response to the first signal state.
    Type: Grant
    Filed: March 31, 1995
    Date of Patent: August 26, 1997
    Assignee: Intel Corporation
    Inventors: Kai J. Chin, Sudarshan Kumar
  • Patent number: 5608741
    Abstract: The present invention discloses a fast parity bit generator using 4-bit XOR cells implemented using complement pass-transistor logic. For 2.sup.2n inputs, where n is an arbitrary positive integer, the parity bit is generated in n stages using only ##EQU1## 4-bit XOR cells. For 2.sup.2n+1 inputs, where n is an arbitrary positive integer, the parity bit is generated using ##EQU2## 4-bit XOR cells disposed in n rows and one 2-bit XOR cell disposed in the last row. The speed of operation of the XOR cells is further enhanced by using NMOS transistor logic within the XOR cells.
    Type: Grant
    Filed: November 23, 1993
    Date of Patent: March 4, 1997
    Assignee: Intel Corporation
    Inventors: Sudarshan Kumar, Shyue L. Kuo, Chung Y. Yip
  • Patent number: 5581497
    Abstract: An adder is described. The adder generates a block generate signal after one domino gate delay. The adder can also generate a carry out signal, generate a first plurality of sum signals in response to the carry out signal, generate a block generate signal, generate a group generate signal, and generate a second plurality of sum signals in response to the carry out signal, block generate signal and group generate signal.
    Type: Grant
    Filed: October 17, 1994
    Date of Patent: December 3, 1996
    Assignee: Intel Corporation
    Inventor: Sudarshan Kumar
  • Patent number: 5579254
    Abstract: An N-bit conditional sum adder comprised of a number of 2-bit adders coupled in series. The 2-bit adders have a sum generation circuit which computes two sum bits from two 2-bit inputs. Each sum bit is processed by a maximum of two multiplexers in series for factoring any carry-ins from preceding 2-bit adders, regardless of the total number of N bits to be added. A carry generation circuit generates two carry signals. The appropriate carry signal is selected for propagation by a multiplexer comprised of a number of p-n passgates. The two carry signals plus their complements are first buffered before being input to the multiplexer. The multiplexer outputs the appropriate carry signal and its complement to be input to a succeeding 2-bit adder and for controlling a succeeding multiplexer selection.
    Type: Grant
    Filed: June 6, 1995
    Date of Patent: November 26, 1996
    Assignee: Intel Corporation
    Inventors: Sudarshan Kumar, Jashojiban Banik
  • Patent number: 5471414
    Abstract: An N-bit conditional sum adder comprised of a number of 2-bit adders coupled in series. The 2-bit adders have a sum generation circuit which computes two sum bits from two 2-bit inputs. Each sum bit is processed by a maximum of two multiplexers in series for factoring any carry-ins from preceding 2-bit adders, regardless of the total number of N bits to be added. A carry generation circuit generates two carry signals. The appropriate carry signal is selected for propagation by a multiplexer comprised of a number of p-n passgates. The two carry signals plus their complements are first buffered before being input to the multiplexer. The multiplexer outputs the appropriate carry signal and its complement to be input to a succeeding 2-bit adder and for controlling a succeeding multiplexer selection.
    Type: Grant
    Filed: March 17, 1993
    Date of Patent: November 28, 1995
    Assignee: Intel Corporation
    Inventors: Sudarshan Kumar, Jashojiban Banik
  • Patent number: 5136539
    Abstract: An metal-oxide-semiconductor (MOS) partitioned carry lookahead adder fabricated from a plurality of four bit slice blocks. Each block provides four sum signals and provides a block carry signal. The blocks are organized into groups of optimum size with logic in each group to generate a group propagate signals. Each block has a block carry line with a single transistor connected between the input and output terminals of the block. The blocks employ an intermediate carry circuit for computing sums in place of full adders. In addition, there is a main carry line with transistors controlled by the group propagate signals. For a 32 bit adder, the maximum pass gate delay in the carry chain is three pass gates.
    Type: Grant
    Filed: December 16, 1988
    Date of Patent: August 4, 1992
    Assignee: Intel Corporation
    Inventor: Sudarshan Kumar
  • Patent number: 4905180
    Abstract: A metal-oxide-semiconductor (MOS) partitioned carry lookahead adder fabricated from a plurality of four bit slice blocks. Each block provides four sum signals and provides a block carry signal. The blocks are organized into groups of optimum size with logic in each group to generate a group propagate signals. Each block has a block carry line with a single transistor connected between the input and output terminals of the block. The blocks employ an intermediate carry circuit for computing sums in place of full adders. In addition, there is a main carry line with transistors controlled by the group propagate signals for a 32 bit adder, the maximum pass gate delay in the carry chain is three pass gates.
    Type: Grant
    Filed: December 16, 1988
    Date of Patent: February 27, 1990
    Assignee: Intel Corporation
    Inventor: Sudarshan Kumar