Patent application number | Description | Published |
20080218525 | MEMORY SYSTEM AND METHOD FOR IMPROVED UTILIZATION OF READ AND WRITE BANDWIDTH OF A GRAPHICS PROCESSING SYSTEM - A system and method for processing graphics data which improves utilization of read and write bandwidth of a graphics processing system. The graphics processing system includes an embedded memory array having at least three separate banks of single-ported memory in which graphics data are stored in memory page format. A memory controller coupled to the banks of memory writes post-processed data to a first bank of memory concurrently with reading data from a second bank of memory. A synchronous graphics processing pipeline processes the data read from the second bank of memory and provides the post-processed graphics data to the memory controller to be written back to the bank of memory from which the pre-processed data was read. The processing pipeline is capable of concurrently processing an amount of graphics data at least equal to the amount of graphics data included in a page of memory. A third bank of memory is precharged concurrently with writing data to the first bank and reading data from the second bank in preparation for access when reading data from the second bank of memory is completed. | 09-11-2008 |
20080266306 | MEMORY SYSTEM HAVING MULTIPLE ADDRESS ALLOCATION FORMATS AND METHOD FOR USE THEREOF - A memory system having multiple address allocation methods for graphics data in a computer graphics processing system. The memory system includes a plurality of memory arrays, and a format register having a programmable format flag. The status of the format flag indicates the memory address allocation format in which the memory addresses for each of the memory arrays are allocated. An address decoder is coupled to the format register to obtain the status of the format flag in order to determine the address allocation method for an array being accessed. The address decoder is further coupled to receive a requested address for a memory location in one of the memory arrays and then provide a requested memory address to the memory arrays to access. The requested address is translated by the address decoder to the requested memory address according to the memory address allocation format indicated by the format flag status for the memory array. | 10-30-2008 |
20100220103 | MEMORY SYSTEM AND METHOD FOR IMPROVED UTILIZATION OF READ AND WRITE BANDWIDTH OF A GRAPHICS PROCESSING SYSTEM - A system and method for processing graphics data which requires less read and write bandwidth. The graphics processing system includes an embedded memory array having at least three separate banks of single-ported memory in which graphics data are stored. A memory controller coupled to the banks of memory writes post-processed data to a first bank of memory while reading data from a second bank of memory. A synchronous graphics processing pipeline processes the data read from the second bank of memory and provides the post-processed graphics data to the memory controller to be written back to a bank of memory. The processing pipeline concurrently processes an amount of graphics data at least equal to that included in a page of memory. A third bank of memory is precharged concurrently with writing data to the first bank and reading data from the second bank in preparation for access when reading data from the second bank of memory is completed. | 09-02-2010 |
20110169846 | MEMORY SYSTEM AND METHOD FOR IMPROVED UTILIZATION OF READ AND WRITE BANDWIDTH OF A GRAPHICS PROCESSING SYSTEM - A system and method for processing graphics data which requires less read and write bandwidth. The graphics processing system includes an embedded memory array having at least three separate banks of single-ported memory in which graphics data are stored. A memory controller coupled to the banks of memory writes post-processed data to a first bank of memory while reading data from a second bank of memory. A synchronous graphics processing pipeline processes the data read from the second bank of memory and provides the post-processed graphics data to the memory controller to be written back to a bank of memory. The processing pipeline concurrently processes an amount of graphics data at least equal to that included in a page of memory. A third bank of memory is precharged concurrently with writing data to the first bank and reading data from the second bank in preparation for access when reading data from the second bank of memory is completed. | 07-14-2011 |
20110279465 | MEMORY SYSTEM HAVING MULTIPLE ADDRESS ALLOCATION FORMATS AND METHOD FOR USE THEREOF - A memory system having multiple address allocation methods for graphics data in a computer graphics processing system. The memory system includes a plurality of memory arrays, and a format register having a programmable format flag. The status of the format flag indicates the memory address allocation format in which the memory addresses for each of the memory arrays are allocated. An address decoder is coupled to the format register to obtain the status of the format flag in order to determine the address allocation method for an array being accessed. The address decoder is further coupled to receive a requested address for a memory location in one of the memory arrays and then provide a requested memory address to the memory arrays to access. The requested address is translated by the address decoder to the requested memory address according to the memory address allocation format indicated by the format flag status for the memory array. | 11-17-2011 |
Patent application number | Description | Published |
20090129169 | METHOD AND APPARATUS FOR READING DATA FROM FLASH MEMORY - Methods and apparatus are disclosed, such as those involving a flash memory device that includes an array of memory cells. One such method includes detecting values of charges stored in selected memory cells in the memory cell array. The method also includes processing the detected values in accordance with a Viterbi algorithm so as to determine data stored in the selected memory cells. In one embodiment, the flash memory cell array includes word lines and bit lines. Detecting the values of charges includes detecting values of charges stored in a selected row of memory cells by selecting one of the word lines. The Viterbi algorithm provides correct data where inter-signal interference between the cells affects the accuracy of read data. For example, the Viterbi algorithm can be used to supplement error correction codes (ECC). | 05-21-2009 |
20120242670 | MEMORY SYSTEM AND METHOD FOR IMPROVED UTILIZATION OF READ AND WRITE BANDWIDTH OF A GRAPHICS PROCESSING SYSTEM - A system for processing graphics data. The graphics processing system includes an embedded memory array having at least three separate banks of single-ported memory in which graphics data are stored. A memory controller coupled to the banks of memory writes post-processed data to a first bank of memory while reading data from a second bank of memory. A synchronous graphics processing pipeline processes the data read from the second bank of memory and provides the post-processed graphics data to the memory controller to be written back to a bank of memory. The processing pipeline concurrently processes an amount of graphics data at least equal to that included in a page of memory. A third bank of memory is precharged concurrently with writing data to the first bank and reading data from the second bank in preparation for access when reading data from the second bank of memory is completed. | 09-27-2012 |
20130073807 | HYBRID MEMORY MANAGEMENT - Methods and apparatus for managing data storage in hybrid memory devices utilizing single level and multi-level memory cells. Logical addresses can be distributed between single level and multilevel memory cells based on a frequency of write operations performed. Initial storage of data corresponding to a logical address in memory can be determined by various methods including initially writing all data to single level memory or initially writing all data to multilevel memory. Other methods permit a host to direct logical address writes to single level or multilevel memory cells based on anticipated usage. | 03-21-2013 |
20130286745 | METHOD AND APPARATUS FOR READING DATA FROM NON-VOLATILE MEMORY - Methods and apparatus are disclosed, such as those involving a flash memory device that includes an array of memory cells. One such method includes detecting values of charges stored in selected memory cells in the memory cell array. The method also includes processing the detected values in accordance with a Viterbi algorithm so as to determine data stored in the selected memory cells. In one embodiment, the flash memory cell array includes word lines and bit lines. Detecting the values of charges includes detecting values of charges stored in a selected row of memory cells by selecting one of the word lines. The Viterbi algorithm provides correct data where inter-signal interference between the cells affects the accuracy of read data. For example, the Viterbi algorithm can be used to supplement error correction codes (ECC). | 10-31-2013 |
20140237326 | METHOD AND APPARATUS FOR READING DATA FROM NON-VOLATILE MEMORY - Methods and apparatus are disclosed, such as those involving a flash memory device that includes an array of memory cells. One such method includes detecting values of charges stored in selected memory cells in the memory cell array. The method also includes processing the detected values in accordance with a Viterbi algorithm so as to determine data stored in the selected memory cells. In one embodiment, the flash memory cell array includes word lines and bit lines. Detecting the values of charges includes detecting values of charges stored in a selected row of memory cells by selecting one of the word lines. The Viterbi algorithm provides correct data where inter-signal interference between the cells affects the accuracy of read data. For example, the Viterbi algorithm can be used to supplement error correction codes (ECC). | 08-21-2014 |
20140268536 | HIGH DENSITY SERVER STORAGE UNIT - A rack mountable 1U storage unit includes a plurality of memory modules arranged in two groups. The storage unit also has control circuitry. The memory modules have a dedicated exhaust channel to draw heat away from the memory modules. The exhaust channel for the memory modules is disposed over and is physically separated from the exhaust channel for the control circuitry. The storage unit can accommodate up to 42 memory modules due to a unique method of placing the individual memory modules. | 09-18-2014 |
20140281177 | HYBRID MEMORY MANAGEMENT - Methods and apparatus for managing data storage in hybrid memory devices utilizing single level and multi-level memory cells. Logical addresses can be distributed between single level and multilevel memory cells based on a frequency of write operations performed. Initial storage of data corresponding to a logical address in memory can be determined by various methods including initially writing all data to single level memory or initially writing all data to multilevel memory. Other methods permit a host to direct logical address writes to single level or multilevel memory cells based on anticipated usage. | 09-18-2014 |
20150077922 | HIGH CAPACITY STORAGE UNIT - A rack mountable 10U storage unit includes a plurality of memory modules arranged in multiple rows. The storage unit also has control circuitry. Each of the memory modules have multiple heating zones and a heat spreader coupled to it. The memory modules may have heat spreaders having differing thermal dissipation capacity coupled to them. The storage unit can accommodate up to 120 memory modules due to a unique method of placing the individual memory modules. | 03-19-2015 |
Patent application number | Description | Published |
20090019340 | NON-SYSTEMATIC CODED ERROR CORRECTION - Methods are described that facilitate the detection and correction of data in memory systems or devices by encoding the data bits of a memory row or block in a non-systematic ECC code. This allows memory embodiments of the present invention to utilize reduced complexity error detection and correction hardware and/or routines to efficiently detect and correct corrupted user data in a segment of memory, such as a sector, word line row, or erase block. User data is not stored in a plaintext format in the memory array, allowing for an increased level of data security. The ECC code is distributed throughout the stored data in the memory segment, increasing the robustness of the ECC code and its resistance to damage or data corruption. | 01-15-2009 |
20100306626 | METHODS OF DATA HANDLING - Methods of data handling include receiving data having a previously-generated error correction code and generating one or more error correction codes for the data, with each error correction code corresponding to the data having one or more particular bits of the data in differing data states. Such methods further include comparing the generated one or more error correction codes to the previously-generated error correction code, and if a particular one of the generated one or more error correction codes matches the previously-generated error correction code, transmitting the data having its one or more particular bits in the data states corresponding to that particular one of the generated one or more error correction codes. Methods of data handling may further include prioritizing the error correction in response to at least locations of known bad or questionable bits of the data. | 12-02-2010 |
20110022932 | VARIABLE SECTOR-COUNT ECC - Improved memory devices, circuitry, and data methods are described that facilitate the detection and correction of data in memory systems or devices by increasing the data area of user data being covered by the ECC code. This averages any possible bit errors over a larger data area and allows a greater number of errors to be corrected by a combining the ECC codes in the coverage area without substantially changing the overall size of ECC codes being stored over a single sector approach. In one embodiment of the present invention, the size of the data block utilized for ECC coverage is variable and can be selected such that differing areas of the memory array or data types can have a differing ECC data coverage sizes. It is also noted that the ECC algorithm, math base or encoding scheme can also be varied between these differing areas of the memory array. | 01-27-2011 |
20110185254 | ERROR DETECTION AND CORRECTION SCHEME FOR A MEMORY DEVICE - Data is read from a memory array. Before being stored in a data buffer, a Hamming code detection operation and a Reed-Solomon code detection operation are operated in parallel to determine if the data word has any errors. The results of the parallel detection operations are communicated to a controller circuit. If an error is present that can be corrected by the Hamming code correction operation, this is performed and the Reed-Solomon code detection operation is performed on the corrected word. If the error is uncorrectable by the Hamming code, the Reed-Solomon code correction operation is performed on the word. | 07-28-2011 |
20120144263 | METHODS OF DATA HANDLING - Methods include receiving data and an ECC code read from a memory array, generating an ECC code from the received data, and determining whether the received data is corrupted by evaluating the generated ECC code against the ECC code read from the memory array. If the received data is determined to be corrupted, a correction algorithm and a recorded likely state of a known bad/questionable bit of the received data may be used to correct error in the received data. Alternatively, if the received data is determined to be corrupted, the correction algorithm and a recorded location of a known bad/questionable bit of the received data may be used to correct error in the received data. | 06-07-2012 |