In Coding, Decoding Circuits, E.g. Parity Circuits (epo) Patents (Class 714/E11.057)
-
Patent number: 11656791Abstract: A memory controller coupled to a memory device and a host device and configured to control access operations of the memory device includes a buffer memory, a host interface, a microprocessor and a data protection engine. The host interface is coupled to the host device and configured to write data received from the host device into the buffer memory and issue a buffer memory write complete notification after the data has been written in the buffer memory. The microprocessor is configured to trigger a data protection operation in response to the buffer memory write complete notification. The protection engine is configured to perform the data protection operation to generate corresponding protection information according to the data written in the buffer memory. The microprocessor is configured to directly trigger the data protection operation after confirming that the data has been written in the buffer memory.Type: GrantFiled: May 25, 2021Date of Patent: May 23, 2023Assignee: Silicon Motion, Inc.Inventor: Shen-Ting Chiu
-
Publication number: 20130290798Abstract: Various embodiments of the present invention provide systems and methods for media defect detection.Type: ApplicationFiled: April 30, 2012Publication date: October 31, 2013Inventors: Fan Zhang, Weijun Tan, Haitao Xia, Shaohua Yang, Xuebin Wu, Wu Chang
-
Publication number: 20120297268Abstract: The present invention provides a nonvolatile semiconductor memory device that can optimize a timing of performing an error detection and correction process to shorten a processing time. Upon receiving a write request to a memory cell array including a variable resistive element where information is stored based on a resistance state of a variable resistor, an input/output buffer outputs write data to a write control unit and an ECC control unit. The write control unit performs a data write process of writing divided data, obtained by dividing the write data into a predetermined number of data, to the databanks. The ECC control unit generates a first error correction code by performing an error correction code generation process to the write data or the divided data, in parallel with the data write process. The write control unit performs a code write process of writing first test data into an ECC bank.Type: ApplicationFiled: May 3, 2012Publication date: November 22, 2012Inventors: Kazuya ISHIHARA, Yoshiaki Tabuchi
-
Publication number: 20120192032Abstract: According to one embodiment, a data storage apparatus includes a channel controller, an error correction controller, and an additional correction module. The channel controller is configured to control writing to and reading from the nonvolatile memories of respective channels. The error correction controller is configured to use inter-channel error correction codes during any read process, performing inter-channel correction process on those of the data items read under the control of the channel controller, which have been designated. The additional correction module is configured to designate, in accordance with errors detected by the channel controller, data items to additionally correct, and to notify the data items so designated to the error correction controller while the channel controller is reading the data necessary in the inter-channel correction process.Type: ApplicationFiled: November 21, 2011Publication date: July 26, 2012Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Kiyotaka IWASAKI
-
Publication number: 20120089865Abstract: A method begins by a processing module decoding a set of encoded data slices to produce a decoded data segment and determining whether the decoded data segment includes an error. When the decoded data segments includes the error, the processing module identifies one or more errant encoded data slices by decoding another set of encoded data slices to produce another decoded data segment. The method continues with the processing module determining whether the other decoded data segment includes the error. When the other decoded data segment does not include the error, the processing module identifies the one or more errant encoded data slices and corrects the one or more errant encoded data slices. When the other decoded data segment includes the error, the processing module repeats, for yet another set of encoded data slices, the decoding step, the determining step, and the identifying and correcting step or the repeating steps.Type: ApplicationFiled: September 13, 2011Publication date: April 12, 2012Applicant: CLEVERSAFE, INC.Inventors: GREG DHUSE, JASON K. RESCH
-
Publication number: 20110161750Abstract: A pre-code device includes firstly memory circuit, an address decoder, and an alternative logic circuit. The first memory circuit includes a number of memory blocks and at east a replacing block. The memory blocks are pointed by a number of respective physical addresses. The replacing block is pointed by a replacing address. The address decoder decodes an input address to provide a pre-code address. The alternative logic circuit looks up an address mapping table, which maps defect physical address among the physical addresses to the replacing address, to map the pre-code address to the replacing address when the pre-code address corresponds to the defect physical address. The alternative logic circuit correspondingly pre-codes the pre-code data to the replacing block.Type: ApplicationFiled: March 8, 2011Publication date: June 30, 2011Applicant: MACRONIX INTERNATIONAL CO., LTD.Inventors: Chun-Hsiung Hung, Wen-Chiao Ho
-
Publication number: 20110161781Abstract: A method begins by a processing module determining whether to error encode broadcast data. The method continues with the processing module encoding a portion of the broadcast data using an error coding storage dispersal function to produce a set of encoded broadcast data slices, determining whether to compress the set of encoded broadcast data slices for the set of encoded broadcast data slices, and when the set of encoded broadcast data slices is to be compressed, selecting a subset of encoded broadcast data slices of the set of encoded broadcast data slices, when the broadcast data is to be error encoded.Type: ApplicationFiled: October 13, 2010Publication date: June 30, 2011Applicant: CLEVERSAFE, INC.Inventors: S. CHRISTOPHER GLADWIN, KUMAR ABHIJEET, GREG DHUSE, JASON K. RESCH, GARY W. GRUBE, TIMOTHY W. MARKISON
-
Publication number: 20110119560Abstract: An ECC controller for a flash memory device storing M-bit data (M: a positive integer equal to or greater than 2) includes an encoder and a decoder. The encoder generates first ECC data for input data to be stored in the flash memory device using a first error correction scheme and generates second ECC data for the input data using a second error correction scheme. The input data, the first ECC data, and the second ECC data are stored in the flash memory device. The decoder calculates the number of errors in data read from the flash memory device and corrects the errors in the read data using one of the first ECC data and the second ECC data selectively based on the number of the errors.Type: ApplicationFiled: January 25, 2011Publication date: May 19, 2011Inventors: Chang-Duck Lee, Seok-won Heo, Si-Yung Park, Dong-Ryoul Lee
-
Publication number: 20100269012Abstract: An enhanced four rank enabled buffer device that includes input ports for receiving input data that includes address and command data directed to one or more of up to four ranks of memory devices. The buffer device also includes one or more buffer circuits for driving one or more of the address and command data, a plurality of chip select input lines for selecting between the up to four ranks of memory devices, and a plurality of chip select output lines for accessing the up to four ranks of memory devices. The buffer device further includes a power savings means for causing one or more of the buffer circuits to be in an inactive mode when corresponding chip select input lines are not active. The buffer device is operable to access the up to four ranks of memory devices.Type: ApplicationFiled: June 30, 2010Publication date: October 21, 2010Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventor: Bruce G. Hazelzet
-
Patent number: 7774673Abstract: The invention relates to a decoding device particularly adapted to decode a digital input signal (E) in a transmission system using direct sequence spread spectrum, this digital input signal (E) being composed of symbols, each symbol representing a bit satisfying a Barker code, and comprising several symbol elements. This device comprises several finite response filters (FLT1 to FLT4) each of which receives the digital input signal (E), a clock circuit (CLK_GEN) outputting clock signals (CLK1 to CLK4) to the filters with a frequency equal to the frequency at which symbol elements are produced and uniformly distributed phase shifts, and an analysis circuit (ANL) designed to identify which of the filters is best tuned to the input signal (E) and to control the clock circuit to make it generated a clock signal (CLK5) optimised for decoding and an analysis circuit.Type: GrantFiled: November 7, 2005Date of Patent: August 10, 2010Assignees: STMicroelectronics SAS, Universite de ProvenceInventors: Benoit Durand, Christophe Fraschini
-
Patent number: 7774678Abstract: An apparatus and method for decoding a Low Density Parity Check (LDPC) code having a maximum error correction capability and an error detection capability. In the apparatus, a decoder receives a signal, and decodes the received signal according to a second parity check matrix having parity check expressions obtained by selecting a predetermined number of dependent parity check expressions among dependent parity check expressions generated by combining, with a predetermined scheme, parity check expressions representing rows of a first parity check matrix obtained by encoding information data into a block code having an optimum minimum distance considering a predetermined coding rate, and adding the selected dependent parity check expressions to the parity check expressions of the first parity check matrix. An error detector determines if there is an error in a signal output from the decoder.Type: GrantFiled: February 14, 2005Date of Patent: August 10, 2010Assignee: Samsung Electronics Co., LtdInventors: Seung-Hoon Choi, Gyu-Bum Kyung, Hong-Sil Jeong, Jae-Yoel Kim
-
Patent number: 7765455Abstract: A semiconductor memory device includes a parity generation circuit which generates a parity bit corresponding to a first number of data bits, a memory cell array including memory cells, and having first and second areas, the first area storing data, the second area storing the parity bit, a syndrome generation circuit which generates a syndrome bit for correcting an error in read data which are read from the first area, has the first number of data bits and corresponds to the parity bit read from the second area, based on the parity bit and the read data, and a parity correction circuit which corrects the parity bit generated by the parity generation circuit. The parity generation circuit generates the parity bit for data which includes input data and a part of the read data.Type: GrantFiled: April 5, 2006Date of Patent: July 27, 2010Assignee: Kabushiki Kaisha ToshibaInventors: Katsuhiko Hoya, Shinichiro Shiratake
-
Publication number: 20090150734Abstract: The present invention discloses a tri-state I/O port. The tri-state I/O port comprises a tri-state logic block, a weak buffer and a delay block. The input terminals of the tri-state logic block are connected to data and OE (output enable) signals. When OE signal is enabled, the output terminal of the tri-state I/O block is pulled high when the data is high while the output terminal is pulled low when the data is low. The input terminal and the output terminal of the weak buffer are connected to the output terminal of the tri-state logic block. And the input terminal of the delay block is connected to the output terminal of the tri-state logic block while the output terminal of the delay block is fed back to the tri-state logic block. When the output terminal of the tri-state logic block is low to high/high to low, the weak buffer is active and maintains the output terminal of the tri-state logic block weak high/low while the delay block turns off the pull high/low function of the tri-state logic block.Type: ApplicationFiled: May 8, 2008Publication date: June 11, 2009Applicant: RDC SEMICONDUCTOR CO., LTD.Inventor: Shih-Jen CHUANG