Patents by Inventor Cheng-Gang Kong
Cheng-Gang Kong 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).
-
Publication number: 20090187873Abstract: A system for reducing the signal delay skew is disclosed, according to a variety of embodiments. One illustrative embodiment of the present disclosure is directed to a method. According to one illustrative embodiment, the method includes receiving an initial netlist comprising components and connection paths among the components. The method further includes identifying one or more skew-influencing features in a first connection path in the initial netlist that lack corresponding skew-influencing features in a second connection path in the initial netlist. The method also includes generating a skew-corrected netlist wherein the second connection path includes one or more added skew-influencing features corresponding to those of the first connection path. The method further includes outputting the skew-corrected netlist.Type: ApplicationFiled: January 17, 2008Publication date: July 23, 2009Applicant: LSI CorporationInventors: Andrey Nikitin, Ranko Scepanovic, Igor Kucherenko, William Lau, Cheng-Gang Kong, Hui-Yin Seto, Andrej Zolotykh, Ivan Pavisic, Sandeep Bhutani, Aiguo Lu, Ilya Lyalin
-
Publication number: 20090091349Abstract: An input/output (I/O) cell including one or more driver-capable segments and one or more on-die termination (ODT) capable segments. The I/O cell may be configured as an output driver in a first mode and Thevenin equivalent termination in a second mode.Type: ApplicationFiled: April 25, 2008Publication date: April 9, 2009Inventors: Dharmesh Bhakta, Hong-Him Lin, Cheng-Gang Kong, Todd Randazzo
-
Publication number: 20090091987Abstract: A memory interface physical layer macro including one or more embedded input/output (I/O) buffers, one or more memory interface hardmacros and control logic. The one or more embedded input/output (I/O) buffers support a plurality of I/O supply voltage levels. The one or more memory interface hardmacros are coupled to the one or more embedded I/O buffers. The control logic controls the one or more hardmacros and the one or more I/O buffers.Type: ApplicationFiled: April 25, 2008Publication date: April 9, 2009Inventors: Derrick Sai-Tang Butt, Cheng-Gang Kong, Terence J. Magee, Thomas Hughes
-
Publication number: 20090043955Abstract: A memory interface subsystem including a write logic and a read logic. The write logic may be configured to communicate data from a memory controller to a memory. The read logic may be configured to communicate data from the memory to the memory controller. The read logic may comprise a plurality of physical read datapaths. Each of the physical read datapaths may be configured to receive (i) a respective portion of read data signals from the memory, (ii) a respective read data strobe signal associated with the respective portion of the received read data signals, (iii) a gating signal, (iv) a base delay signal and (v) an offset delay signal.Type: ApplicationFiled: October 13, 2008Publication date: February 12, 2009Inventors: Derrick Sai-Tang Butt, Cheng-Gang Kong, Terence J. Magee
-
Patent number: 7454303Abstract: The present invention is directed to a method for compensating for process, voltage, and temperature variation without complex online/offline swapping of data paths requiring a dedicated FIFO(First-in First-out) buffer design. Delay cells are trained for each clock path (namely a Functional delay) and a spare delay cell is trained. A ratio is calculated for each Functional delay cell by dividing the Functional delay cells' setting into the spare delay cells' one-fourth cycle setting. These ratios reflect any process variation. Functional mode is then entered and a Master-Slave approach switched to, during which the spare delay cell repeats the training sequence continuously while the Functional delay cells delay the clocks from the RAM(Random Access Memory). Each Functional delay cell is updated at the end of each training sequence of the spare delay cell, compensating for voltage and temperature change, by dividing the ratio into the new spare delay cell one-fourth cycle setting.Type: GrantFiled: December 21, 2006Date of Patent: November 18, 2008Assignee: LSI Logic CorporationInventors: Terence Magee, Thomas Hughes, Cheng-Gang Kong
-
Patent number: 7437500Abstract: A core including a write logic IP block, a read logic IP block, a master delay IP block and an address and control IP block. The write logic IP block may be configured to communicate data from a memory controller to a double data rate (DDR) synchronous dynamic random access memory (SDRAM). The read logic IP block may be configured to communicate data from the double data rate (DDR) synchronous dynamic random access memory (SDRAM) to the memory controller. The master delay IP block may be configured to generate one or more delays for the read logic IP block. The address and control logic IP block may be configured to control the write logic IP block and the read logic IP block. The core is generally configured to couple the double data rate (DDR) synchronous dynamic random access memory (SDRAM) and the memory controller.Type: GrantFiled: August 5, 2005Date of Patent: October 14, 2008Assignee: LSI CorporationInventors: Derrick Sai-Tang Butt, Cheng-Gang Kong, Terence J. Magee
-
Publication number: 20080150610Abstract: The present invention is directed to a method for compensating for process, voltage, and temperature variation without complex online/offline swapping of data paths requiring a dedicated FIFO (First-in First-out) buffer design. Delay cells are trained for each clock path (namely a Functional delay) and a spare delay cell is trained. A ratio is calculated for each Functional delay cell by dividing the Functional delay cells' setting into the spare delay cells' one-fourth cycle setting. These ratios reflect any process variation. Functional mode is then entered and a Master-Slave approach switched to, during which the spare delay cell repeats the training sequence continuously while the Functional delay cells delay the clocks from the RAM (Random Access Memory). Each Functional delay cell is updated at the end of each training sequence of the spare delay cell, compensating for voltage and temperature change, by dividing the ratio into the new spare delay cell one-fourth cycle setting.Type: ApplicationFiled: December 21, 2006Publication date: June 26, 2008Inventors: Terence Magee, Thomas Hughes, Cheng- Gang Kong
-
Publication number: 20080068911Abstract: The present invention is a method for data path voltage and temperature compensation. The method includes configuring an offline data path to match an online data path. The method further includes compensating the offline data path for voltage and temperature variation. The method further includes swapping the offline data path with the online data path. Further, swapping occurs automatically without interruption of data flow along the data paths.Type: ApplicationFiled: September 19, 2006Publication date: March 20, 2008Inventors: Thomas Hughes, Cheng-Gang Kong
-
Patent number: 7239170Abstract: Apparatus and methods are provided for improving data exchanges between electronic devices, such as memory controllers and RLDRAMs. An I/O cell includes a signal pad for transferring a first signal to an electronic device coupled thereto and for receiving a second signal from the electronic device. In one aspect, a duty cycle controller is coupled to the signal pad for balancing a duty cycle of the first signal with respect to a clock signal. In another aspect, dynamic switchable termination is coupled to the signal pad for providing termination impedance when the I/O cell is receiving the second signal.Type: GrantFiled: July 8, 2003Date of Patent: July 3, 2007Assignee: LSI CorporationInventors: Victor Suen, William Lau, Hong-Him Lim, Cheng-Gang Kong
-
Publication number: 20070033337Abstract: A core including a write logic IP block, a read logic IP block, a master delay IP block and an address and control IP block. The write logic IP block may be configured to communicate data from a memory controller to a double data rate (DDR) synchronous dynamic random access memory (SDRAM). The read logic IP block may be configured to communicate data from the double data rate (DDR) synchronous dynamic random access memory (SDRAM) to the memory controller. The master delay IP block may be configured to generate one or more delays for the read logic IP block. The address and control logic IP block may be configured to control the write logic IP block and the read logic IP block. The core is generally configured to couple the double data rate (DDR) synchronous dynamic random access memory (SDRAM) and the memory controller.Type: ApplicationFiled: August 5, 2005Publication date: February 8, 2007Inventors: Derrick Butt, Cheng-Gang Kong, Terence Magee
-
Publication number: 20060288175Abstract: An apparatus comprising a first circuit and a second circuit. The first circuit may be configured to read and write data through a plurality of input/output lines. The second circuit may include a plurality of sections. Each section may be configured to present a control signal to a load output line and receive a feedback of the control signal through a load input line. The load input line and the load output line of each of the sections may be connected to a load circuit configured to match a respective memory load connected to each of the plurality of input/output lines.Type: ApplicationFiled: June 16, 2005Publication date: December 21, 2006Inventors: Hui-Yin Seto, Derrick Butt, Cheng-Gang Kong
-
Patent number: 7119596Abstract: An apparatus comprising an input section, a first delay circuit and a second delay circuit. The input section may be configured to present a first intermediate signal by selecting either (i) an input clock signal or (ii) a feedback of an output signal. The first delay circuit may be configured to generate a second intermediate signal by delaying the first intermediate signal by inserting one of a plurality of fixed delays in response to a first control signal. The second delay circuit may be configured to generate the output signal by delaying the second intermediate signal by inserting a programmable delay in response to a second control signal.Type: GrantFiled: December 22, 2004Date of Patent: October 10, 2006Assignee: LSI Logic CorporationInventors: Cheng-Gang Kong, Victor Suen
-
Publication number: 20060224847Abstract: An apparatus comprising a control circuit, a buffer circuit and a memory. The control circuit may be configured to present a plurality of pairs of signals in response to (i) one or more input signals operating at a first data rate and (ii) an input clock signal operating at a second data rate. The second signal in each of the pairs comprises a clock signal operating at the second data rate. The buffer circuit may be configured to generate a buffered signal in response to each of the pairs of signals. Each of the buffered signals operates at the second data rate. The memory may be configured to read and write data at the second data rate in response to the buffered signals.Type: ApplicationFiled: April 1, 2005Publication date: October 5, 2006Inventors: Hui-Yin Seto, Cheng-Gang Kong
-
Publication number: 20060132210Abstract: An apparatus comprising an input section, a first delay circuit and a second delay circuit. The input section may be configured to present a first intermediate signal by selecting either (i) an input clock signal or (ii) a feedback of an output signal. The first delay circuit may be configured to generate a second intermediate signal by delaying the first intermediate signal by inserting one of a plurality of fixed delays in response to a first control signal. The second delay circuit may be configured to generate the output signal by delaying the second intermediate signal by inserting a programmable delay in response to a second control signal.Type: ApplicationFiled: December 22, 2004Publication date: June 22, 2006Inventors: Cheng-Gang Kong, Victor Suen
-
Publication number: 20050010833Abstract: Apparatus and methods are provided for improving data exchanges between electronic devices, such as memory controllers and RLDRAMs. An I/O cell includes a signal pad for transferring a first signal to an electronic device coupled thereto and for receiving a second signal from the electronic device. In one aspect, a duty cycle controller is coupled to the signal pad for balancing a duty cycle of the first signal with respect to a clock signal. In another aspect, dynamic switchable termination is coupled to the signal pad for providing termination impedance when the I/O cell is receiving the second signal.Type: ApplicationFiled: July 8, 2003Publication date: January 13, 2005Inventors: Victor Suen, William Lau, Hong-Him Lim, Cheng-Gang Kong
-
Patent number: 5450455Abstract: A scannable logic unit includes one or more storage registers that maintain copies of data communicated from the scannable unit to registers in a nonscannable unit. When the scannable unit is subjected to a scan test, the registers will contain state information respecting that transfer to the nonscannable unit. When the scannable and nonscannable units are placed in a run condition, the registers supply to the nonscannable unit state information for continuing operation.Type: GrantFiled: June 28, 1993Date of Patent: September 12, 1995Assignee: Tandem Computers IncorporatedInventors: Stephen W. Hamilton, Walter E. Gibson, Cheng-Gang Kong
-
Patent number: 5396505Abstract: A programmable system for checking for protocol errors in a communication system includes a matrix for generating error checking signals selected by data fields utilized to implement a communication. If the configuration or protocol is changed the system facilitates reprogramming to compensate for the change.Type: GrantFiled: July 6, 1993Date of Patent: March 7, 1995Assignee: Tandem Computers IncorporatedInventors: Jon C. Freeman, Cheng-Gang Kong
-
Patent number: 4926323Abstract: A streamlined instruction processor processes data in response to a program composed of prespecified instructions in pipeline cycles. The processor comprises an instruction fetch unit, including an instruction interface adapted for connection to an instruction memory and for fetching instructions from the instruction memory. The instruction fetch unit includes an instruction prefetch buffer coupled to the instruction interface for buffering a sequence of instructions supplied to the instruction interface. A branch target cache is coupled with the prefetch buffer for storing sets of instructions retrieved from a corresponding set of locations in the instruction memory, having sequential instruction addresses. The first instruction in each such set is a branch target instruction in the program.In addition, an execution unit including a data interface adapted for connection to the data memory, executes the instructions in pipeline cycles.Type: GrantFiled: March 3, 1988Date of Patent: May 15, 1990Assignee: Advanced Micro Devices, Inc.Inventors: Gigy Baror, Brian W. Case, Rod G. Fleck, Philip M. Freidin, Smeeta Gupta, William M. Johnson, Cheng-Gang Kong, Ole H. Moller, Timothy A. Olson, David I. Sorensen
-
Patent number: 4777588Abstract: A high speed register file for use by an instruction processor suitable for reduced instruction-set computers (RISCs) is disclosed which is preferably used with an efficient register allocation method. The register file facilitates the passing of parameters between procedures by dynamically providing overlapping registers which are accessible to both procedures. Each procedure also has a set of "local" registers assigned to it which are inaccessible from other procedures. The register file is divided into a number of blocks and a protection register stores a word which proscribes access by a particular procedure or task to certain blocks. In this manner, an instruction processor using the register file can operate on multiple tasks maintaining the integrity of each from undesired changes occuring in the others.Type: GrantFiled: August 30, 1985Date of Patent: October 11, 1988Assignee: Advanced Micro Devices, Inc.Inventors: Brian W. Case, Rod G. Fleck, William M. Johnson, Cheng-Gang Kong, Ole Moller
-
Patent number: 4777587Abstract: An instruction processor suitable for use in a reduced instruction-set computer employs an instruction pipeline which performs conditional branching in a single processor cycle. The processor treats a branch condition as a normal instruction operand rather than a special case within a separate condition code register. The condition bit and the branch target address determine which instruction is to be fetched, the branch not taking effect until the next-following instruction is executed. In this manner, no replacement of the instruction which physically follows the branch instruction in the pipeline need be made, and the branch occurs within the single cycle of the pipeline allocated to it. A simple circuit implements this delayed-branch method. A computer incorporating the processor readily executes special-handling techniques for calls on subroutine, interrupts and traps.Type: GrantFiled: August 30, 1985Date of Patent: October 11, 1988Assignee: Advanced Micro Devices, Inc.Inventors: Brian W. Case, Rod G. Fleck, Cheng-Gang Kong, Ole Moller