WO2004072781A2 - Buffered writes and memory page control - Google Patents
Buffered writes and memory page control Download PDFInfo
- Publication number
- WO2004072781A2 WO2004072781A2 PCT/US2004/000032 US2004000032W WO2004072781A2 WO 2004072781 A2 WO2004072781 A2 WO 2004072781A2 US 2004000032 W US2004000032 W US 2004000032W WO 2004072781 A2 WO2004072781 A2 WO 2004072781A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- memory
- write
- transactions
- response
- page
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0215—Addressing or allocation; Relocation with look ahead addressing means
Definitions
- Computing devices typically comprise a processor, memory, and a memory controller to provide the processor as well as other components of the computing device with access to the memory.
- the performance of such computing devices is strongly influenced by the memory latency of the computing device.
- the “memory read latency” is the length of time between when the processor requests the memory controller to retrieve data from the memory and when the memory controller provides the processor with the requested data.
- the “memory write latency” is generally the length of time between when the processor requests the memory controller to write data to the memory and when the memory controller indicates to the processor that the data has been or will be written to the memory.
- memory controllers typically buffer write transactions of the processor and later write the data of the transaction to memory at a more appropriate time. As far as the processor is concerned, the write transaction is complete once buffered by the memory controller. The processor, therefore, may continue without waiting for the data of the write transaction to be actual written to memory. Conversely, read transactions are not complete from the standpoint of the processor until the data is read from memory and returned to the processor. Accordingly, performance of a computing device is typically more dependent upon read latency than write latency. In light of this, memory controllers tend to favor servicing read transactions over servicing write transactions. Moreover, memory latency is influenced by the proportion of page-hit, page-miss, and page-empty transactions encountered.
- Computing devices typical comprise hierarchal memory arrangements in which memory is arranged in channels, ranks, banks, pages, and columns.
- each channel may comprise one or more ranks
- each rank may comprise one or more banks
- each bank may comprise one or more pages.
- each page may comprise one or more columns.
- the memory controller typically opens a page of the memory and then accesses one or more columns of the opened page.
- the memory controller may leave a page open after accessing a column of the page for a previous memory request and may access a different column of the open page.
- the memory controller may close an open page of a bank, may open another page of the same bank, and may access a column of the newly opened page.
- a page- miss access generally has about three times the latency as a page-hit access.
- the memory controller may open a closed page of a bank, and may access a column of the newly opened page for the memory transaction.
- a page-empty access generally has about twice the latency as a page-hit access.
- FIG. 1 illustrates an embodiment of a computing device.
- FIG. 2 illustrates an embodiment of a memory controller of the computing device of FIG. 1.
- FIG. 3 illustrates an embodiment of a method that may be used by the memory controller of FIG. 2 to schedule transactions and close pages of the memory.
- references in the specification to "one embodiment”, “an embodiment”, “an example embodiment”, etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
- Embodiments of the invention may be implemented in hardware, firmware, software, or any combination thereof. Embodiments of the invention may also be implemented as instructions stored on a machine-readable medium, which may be read and executed by one or more processors.
- a machine- readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device).
- a machine-readable medium may include read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustical or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and others.
- firmware, software, routines, instructions may be described herein as performing certain actions. However, it should be appreciated that such descriptions are merely for convenience and that such actions in fact result from computing devices, processors, controllers, or other devices executing the firmware, software, routines, instructions, etc.
- the computing device 100 may comprise one or more processors 102.
- the processors 102 may perform actions in response to executing instructions.
- the processors 102 may issue transactions such as memory read transactions and memory write transactions on a processor bus 104.
- the computing device 100 may further comprise a chipset 106.
- the chipset 106 may comprise one or more integrated circuit packages or chips that couple the processors 102 to memory 108, Basic Input/Output System (BIOS) firmware 110 and other components 112 (e.g. a mouse, keyboard, video controller, hard disk, floppy disk, etc.).
- the chipset 106 may comprise a processor bus interface 114 to receive transactions from the processors 102 and to issue transactions to the processors 102 via the processor bus 104.
- the chipset 106 may further comprise a memory controller 116 to issue read and write transactions to the memory 108 via a memory bus 118.
- the chipset 106 may further comprise one or more component interfaces (not shown) to access the other components 112 via buses 120 such as, for example, peripheral component interconnect (PCI) buses, accelerated graphics port (AGP) buses, universal serial bus (USB) buses, low pin count (LPC) buses, and/or other I/O buses.
- PCI peripheral component interconnect
- AGP accelerated graphics port
- USB universal serial bus
- LPC low pin count
- the BIOS firmware 110 comprises routines which the computing device 100 may execute during system startup in order to initialize the processors 102, chipset 106, and other components of the computing device 100. Moreover, the BIOS firmware 110 may comprise routines or drivers which the computing device 100 may execute to communicate with one or more components of the computing device 100.
- the memory 108 may comprise memory devices providing addressable storage locations that the memory controller 116 may read data from and/or write data to.
- the memory 108 may comprise one or more different types of memory devices such as, for example, dynamic random access memory (DRAM) devices, synchronous dynamic random access memory (SDRAM) devices, double data rate (DDR) SDRAM devices, quad data rate (QDR) SDRAM devices, or other volatile or non-volatile memory devices.
- DRAM dynamic random access memory
- SDRAM synchronous dynamic random access memory
- DDR double data rate SDRAM devices
- QDR quad data rate SDRAM devices
- the memory 108 may be arranged in a hierarchal manner. For example, the memory 108 may be arranged in channels, ranks, banks, pages, and columns.
- the memory controller 116 may comprise a write- cache 198 that comprises a read buffer 200 and a write buffer 202.
- the memory controller 116 may further comprise control logic 204 and a memory interface 206.
- the read buffer 200 may buffer the address and data of a read transaction until the requested data is retrieved from the memory 108 and returned to the requester (e.g. processor 102).
- the write buffer 202 may buffer the address and data of a write transaction until the data is written to the memory 108.
- the read buffer 200 and write buffer 202 may each support buffering of one or more transactions.
- the control logic 204 may select a transaction from the buffers 200, 202 based upon various criteria and may request the memory interface 206 to service the selected transaction.
- control logic 204 in one embodiment in general favors read transactions over write transactions and thus generally causes write transactions to wait until the read buffer is empty. In another embodiment, the control logic 204 may further wait until data needs to be evicted from the write-cache 198 before writing data of the write buffer 202 back to the memory 108.
- the control logic 204 may select write transactions over read transactions under certain conditions such as, for example, the write buffer 202 becoming full or the number of pending write transactions in the write buffer 202 having a predetermined relationship to an upper threshold that indicates that the write buffer 202 is nearly full. In which case, the control logic 204 may completely flush the write buffer thus presenting all pending write transactions to memory interface 206 for servicing.
- the control logic 204 may alternatively partially flush the write buffer 202.
- the control logic 204 may present the memory interface 206 with a predetermined number of write transactions (e.g. 4) or may present the memory interface 206 with write transactions from the write buffer 202 until the number of pending write transactions has a predetermined relationship with a lower threshold.
- the control logic 204 may further satisfy a read transaction with data stored in the write cache 198. Satisfying the read transaction with data from the write buffer 202 may reduce the latency of the read transactions since the memory controller 116 is able to satisfy the request without retrieving the data from memory 108. Further, servicing read transactions with cached data of the write buffer 202 may help reduce the latency of other read transactions due to fewer read transactions consuming bandwidth between the memory controller 116 and the memory 108. Furthermore, the control logic 204 may combine, in the write buffer 202, data of write transactions that target the same locations of the memory 108. Again, combining write transactions in the write buffer 202 may reduce the latency of memory transactions since write combining may reduce the number of write transactions between the memory controller 116 and the memory 108.
- the memory interface 206 may read data from memory 108 in response to read transactions and may write data to memory 108 in response to write transactions.
- the memory interface 206 may decode an address of a transaction and may apply memory select signals to the memory in order to open pages of the memory 108 for reading and/or writing.
- the memory interface 208 may close an opened page by issuing a precharge command or by issuing a transaction to the memory 108 with an auto-precharge qualifier that causes the memory 108 to close the page of the transaction after servicing the transaction.
- control logic 204 favors read transactions over write transactions. Accordingly, write transactions tend to be interspersed between read transactions that were issued by the processor 102 considerably after the write transactions. Read transactions in such an environment tend to exhibit poor spatial locality of reference to the write transactions due to their temporal separation. If pages accessed by write transactions are left open, then read transactions that follow the last write transactions of write transaction series tend to result in a higher proportion of page-miss accesses to page-hit access. In an effort to reduce overall memory latency, the control logic 204 in one embodiment closes a page accessed by a last write transaction to reduce the likelihood that a read transaction following the last write transaction results in a page-miss access.
- a page-empty access has about twice the latency of a page- hit access, but a page-miss access has about thrice the latency of a page-hit access. Therefore, if leaving the page accessed by the last write transaction of one or more consecutive write transactions would result in more page-miss accesses than page-hit access, then closing the page would reduce the latency of read transactions following write transactions.
- the memory controller 116 in an attempt to reduce memory latency may schedule transactions and close pages in a manner that attempts to reduce overall memory latency experienced by the processor 102.
- the method of FIG. 3 in general favors read transactions over write transactions and generally closes pages of a memory 08 that were accessed by the last write transactions of a series of one or more write transactions. However, the memory controller 116 may close pages of the memory 108 based upon additional criteria.
- the control logic 204 in block 300 may determine whether there are any pending memory transactions. In particular, the control logic 204 may determine that there are no pending memory transactions if neither the read buffer 200 nor the write buffer 202 comprise transactions to be issued to the memory 108. In response to determining there are no pending transactions, the control logic 204 may enter an idle state or exit the scheduling method of FIG. 3 until the next available time slot for issuing a memory transaction. Otherwise, the control logic 204 in block 302 may select a transaction from the read buffer 200 or the write buffer 202 based upon selection criteria or rules.
- control logic 204 may favor read transaction over write transactions and may select a read transaction if the read buffer 200 comprises a read transaction. In response to the read buffer 200 comprising no read transactions to be issued to the memory 108, the control logic 204 may select a write transaction from the write buffer 202. In another embodiment, the control logic 204 may further select a write transaction from the write buffer 202 even though the read buffer 200 comprises pending read transactions. In particular, the control logic 204 may select a write transaction in response to determining that the write buffer 202 is full or in response to determining that the write buffer 202 comprises an upper threshold of write transactions that indicates the write buffer 202 is nearly full.
- control logic 204 may continue to select write transactions over read transactions until a predetermined number (e.g. 4) of write transactions have been selected, until the write buffer 202 is empty, or until the write buffer 202 comprises a lower threshold of write transactions.
- a predetermined number e.g. 4
- the lower threshold may correspond to the write buffer 202 being half filled.
- the control logic 204 may determine whether the selected transaction is a read transaction or a write transaction. In response to determining that the selected transaction is a read transaction, the control logic 204 in block 306 may cause the memory interface 206 to issue the selected read transaction to the memory to obtain the requested data from the memory 108. Otherwise, the control logic 204 in block 308 may determine whether the selected write transaction is the last write transaction of a series of one or more write transactions. For example, in one embodiment, the control logic 204 may determine that selected write transaction is the last write transaction in response to determining that the write buffer 202 comprise no other pending transactions.
- control logic 204 may further determine that the selected write transaction is the last write transaction in response to determining that the read buffer 200 comprises at least one read transaction to issue to the memory 108.
- the control logic 204 may further determine that the selected write transaction is the last write transaction of the series in response to determining that the write buffer comprises no more write transactions to the page of memory 108 to be accessed by the selected write transaction.
- the control logic 204 may also determine that the select write transaction is the last write transaction in response to memory interface 206 issuing a predetermined number of consecutive write transactions to the memory 108. Further yet, the control logic 204 may determine that the selected write transaction is the last write transaction of the series in response to determining that write buffer 202 comprises a lower threshold of write transactions.
- control logic 204 may determine the last write transaction of a series of one or more write transactions based upon one or more of the above identified criteria and/or other criteria. In response to determining that the selected write transaction is not the last write transaction of a series of write transactions, the control logic 204 in block 310 may cause the memory interface 206 to issue the selected write transaction to the memory 108 in order to write the data supplied by the write transaction to the memory 108. Otherwise, the control logic 204 in block 312 may instruct the memory interface 206 to close a page accessed by the write transaction.
- the memory interface 206 in block 314 may issue the selected write transaction to the memory 108 and may close the page accessed by the write transaction.
- the memory interface 206 may issue the write transaction to the memory 108 and then may issue a precharge command to the memory 108 to close the page after the write transaction.
- the memory interface 206 may issue the write transaction to the memory 108 with an auto-precharge qualifier that causes the memory 108 to close the page accessed by the write transaction after the data of the write transaction is written to the page.
- the computing device 100 may perform all or a subset of the example method in response to executing instructions of a machine readable medium such as, for example, read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; and/or electrical, optical, acoustical or other form of propagated signals such as, for example, carrier waves, infrared signals, digital signals, analog signals.
- a machine readable medium such as, for example, read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; and/or electrical, optical, acoustical or other form of propagated signals such as, for example, carrier waves, infrared signals, digital signals, analog signals.
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2005518463A JP2006514385A (en) | 2003-02-10 | 2004-01-02 | Buffered write and memory page control |
EP04700072A EP1593042A2 (en) | 2003-02-10 | 2004-01-02 | Buffered writes and memory page control |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/364,280 | 2003-02-10 | ||
US10/364,280 US7469316B2 (en) | 2003-02-10 | 2003-02-10 | Buffered writes and memory page control |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2004072781A2 true WO2004072781A2 (en) | 2004-08-26 |
WO2004072781A3 WO2004072781A3 (en) | 2005-05-26 |
Family
ID=32824415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2004/000032 WO2004072781A2 (en) | 2003-02-10 | 2004-01-02 | Buffered writes and memory page control |
Country Status (7)
Country | Link |
---|---|
US (1) | US7469316B2 (en) |
EP (1) | EP1593042A2 (en) |
JP (1) | JP2006514385A (en) |
KR (1) | KR100824487B1 (en) |
CN (1) | CN1742264A (en) |
TW (1) | TWI316179B (en) |
WO (1) | WO2004072781A2 (en) |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7133972B2 (en) | 2002-06-07 | 2006-11-07 | Micron Technology, Inc. | Memory hub with internal cache and/or memory access prediction |
US7117316B2 (en) | 2002-08-05 | 2006-10-03 | Micron Technology, Inc. | Memory hub and access method having internal row caching |
US6888777B2 (en) * | 2002-08-27 | 2005-05-03 | Intel Corporation | Address decode |
US7159066B2 (en) * | 2002-08-27 | 2007-01-02 | Intel Corporation | Precharge suggestion |
US6820181B2 (en) | 2002-08-29 | 2004-11-16 | Micron Technology, Inc. | Method and system for controlling memory accesses to memory modules having a memory hub architecture |
US7120765B2 (en) * | 2002-10-30 | 2006-10-10 | Intel Corporation | Memory transaction ordering |
US7120727B2 (en) | 2003-06-19 | 2006-10-10 | Micron Technology, Inc. | Reconfigurable memory module and method |
US7260685B2 (en) | 2003-06-20 | 2007-08-21 | Micron Technology, Inc. | Memory hub and access method having internal prefetch buffers |
US7389364B2 (en) | 2003-07-22 | 2008-06-17 | Micron Technology, Inc. | Apparatus and method for direct memory access in a hub-based memory system |
US7076617B2 (en) * | 2003-09-30 | 2006-07-11 | Intel Corporation | Adaptive page management |
US7120743B2 (en) | 2003-10-20 | 2006-10-10 | Micron Technology, Inc. | Arbitration system and method for memory responses in a hub-based memory system |
US7310703B2 (en) * | 2003-10-23 | 2007-12-18 | Hewlett-Packard Development Company, L.P. | Methods of reading and writing data |
US7457936B2 (en) * | 2003-11-19 | 2008-11-25 | Intel Corporation | Memory access instruction vectorization |
US7330992B2 (en) | 2003-12-29 | 2008-02-12 | Micron Technology, Inc. | System and method for read synchronization of memory modules |
US7188219B2 (en) | 2004-01-30 | 2007-03-06 | Micron Technology, Inc. | Buffer control system and method for a memory system having outstanding read and write request buffers |
US7788451B2 (en) * | 2004-02-05 | 2010-08-31 | Micron Technology, Inc. | Apparatus and method for data bypass for a bi-directional data bus in a hub-based memory sub-system |
US7257683B2 (en) | 2004-03-24 | 2007-08-14 | Micron Technology, Inc. | Memory arbitration system and method having an arbitration packet protocol |
US7519788B2 (en) | 2004-06-04 | 2009-04-14 | Micron Technology, Inc. | System and method for an asynchronous data buffer having buffer write and read pointers |
US20060080574A1 (en) * | 2004-10-08 | 2006-04-13 | Yasushi Saito | Redundant data storage reconfiguration |
US7353301B2 (en) * | 2004-10-29 | 2008-04-01 | Intel Corporation | Methodology and apparatus for implementing write combining |
JP4804803B2 (en) * | 2005-06-08 | 2011-11-02 | 京セラミタ株式会社 | Memory access control device and computer program |
JP4569628B2 (en) * | 2007-12-28 | 2010-10-27 | 日本電気株式会社 | Load store queue control method and control system thereof |
JP2009157887A (en) * | 2007-12-28 | 2009-07-16 | Nec Corp | Method and system for controlling load store queue |
US7957216B2 (en) * | 2008-09-30 | 2011-06-07 | Intel Corporation | Common memory device for variable device width and scalable pre-fetch and page size |
US8683128B2 (en) | 2010-05-07 | 2014-03-25 | International Business Machines Corporation | Memory bus write prioritization |
US8838901B2 (en) | 2010-05-07 | 2014-09-16 | International Business Machines Corporation | Coordinated writeback of dirty cachelines |
US8996817B2 (en) * | 2012-07-12 | 2015-03-31 | Harman International Industries, Inc. | Memory access system |
US10474389B2 (en) * | 2016-07-05 | 2019-11-12 | Hewlett Packard Enterprise Development Lp | Write tracking for memories |
CN116991611A (en) * | 2023-05-22 | 2023-11-03 | 苏州科美信息技术有限公司 | Memory page subdivision state identification method, system, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4354232A (en) * | 1977-12-16 | 1982-10-12 | Honeywell Information Systems Inc. | Cache memory command buffer circuit |
US5666494A (en) * | 1995-03-31 | 1997-09-09 | Samsung Electronics Co., Ltd. | Queue management mechanism which allows entries to be processed in any order |
US5953743A (en) * | 1997-03-12 | 1999-09-14 | Micron Electronics, Inc. | Method for accelerating memory bandwidth |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6505282B1 (en) * | 1994-11-30 | 2003-01-07 | Intel Corporation | Method and apparatus for determining memory types of a multi-type memory subsystem where memory of the different types are accessed using column control signals with different timing characteristics |
US6725349B2 (en) * | 1994-12-23 | 2004-04-20 | Intel Corporation | Method and apparatus for controlling of a memory subsystem installed with standard page mode memory and an extended data out memory |
TW388982B (en) | 1995-03-31 | 2000-05-01 | Samsung Electronics Co Ltd | Memory controller which executes read and write commands out of order |
US5603010A (en) * | 1995-12-28 | 1997-02-11 | Intel Corporation | Performing speculative system memory reads prior to decoding device code |
US6128716A (en) * | 1998-01-23 | 2000-10-03 | Motorola Inc. | Memory controller with continuous page mode and method therefor |
US6742098B1 (en) * | 2000-10-03 | 2004-05-25 | Intel Corporation | Dual-port buffer-to-memory interface |
US6269433B1 (en) * | 1998-04-29 | 2001-07-31 | Compaq Computer Corporation | Memory controller using queue look-ahead to reduce memory latency |
US6219764B1 (en) * | 1998-08-03 | 2001-04-17 | Micron Technology, Inc. | Memory paging control method |
US6219765B1 (en) * | 1998-08-03 | 2001-04-17 | Micron Technology, Inc. | Memory paging control apparatus |
US6556952B1 (en) * | 2000-05-04 | 2003-04-29 | Advanced Micro Devices, Inc. | Performance monitoring and optimizing of controller parameters |
US6400631B1 (en) * | 2000-09-15 | 2002-06-04 | Intel Corporation | Circuit, system and method for executing a refresh in an active memory bank |
US6697888B1 (en) * | 2000-09-29 | 2004-02-24 | Intel Corporation | Buffering and interleaving data transfer between a chipset and memory modules |
US6553449B1 (en) * | 2000-09-29 | 2003-04-22 | Intel Corporation | System and method for providing concurrent row and column commands |
US6785793B2 (en) * | 2001-09-27 | 2004-08-31 | Intel Corporation | Method and apparatus for memory access scheduling to reduce memory access latency |
US6507530B1 (en) * | 2001-09-28 | 2003-01-14 | Intel Corporation | Weighted throttling mechanism with rank based throttling for a memory system |
US6766385B2 (en) * | 2002-01-07 | 2004-07-20 | Intel Corporation | Device and method for maximizing performance on a memory interface with a variable number of channels |
US6795899B2 (en) * | 2002-03-22 | 2004-09-21 | Intel Corporation | Memory system with burst length shorter than prefetch length |
US20040015645A1 (en) * | 2002-07-19 | 2004-01-22 | Dodd James M. | System, apparatus, and method for a flexible DRAM architecture |
US7159066B2 (en) * | 2002-08-27 | 2007-01-02 | Intel Corporation | Precharge suggestion |
US6888777B2 (en) * | 2002-08-27 | 2005-05-03 | Intel Corporation | Address decode |
KR100472416B1 (en) * | 2002-11-01 | 2005-03-11 | 삼성전자주식회사 | Device and Method for Controlling Packet Flow |
US7404047B2 (en) * | 2003-05-27 | 2008-07-22 | Intel Corporation | Method and apparatus to improve multi-CPU system performance for accesses to memory |
-
2003
- 2003-02-10 US US10/364,280 patent/US7469316B2/en not_active Expired - Fee Related
-
2004
- 2004-01-02 WO PCT/US2004/000032 patent/WO2004072781A2/en active Application Filing
- 2004-01-02 JP JP2005518463A patent/JP2006514385A/en active Pending
- 2004-01-02 EP EP04700072A patent/EP1593042A2/en not_active Withdrawn
- 2004-01-02 KR KR1020057014759A patent/KR100824487B1/en not_active IP Right Cessation
- 2004-01-02 CN CNA2004800027723A patent/CN1742264A/en active Pending
- 2004-01-05 TW TW093100149A patent/TWI316179B/en not_active IP Right Cessation
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4354232A (en) * | 1977-12-16 | 1982-10-12 | Honeywell Information Systems Inc. | Cache memory command buffer circuit |
US5666494A (en) * | 1995-03-31 | 1997-09-09 | Samsung Electronics Co., Ltd. | Queue management mechanism which allows entries to be processed in any order |
US5953743A (en) * | 1997-03-12 | 1999-09-14 | Micron Electronics, Inc. | Method for accelerating memory bandwidth |
Non-Patent Citations (1)
Title |
---|
ZHAO ZHANG ET AL: "A permutation-based page interleaving scheme to reduce row-buffer conflicts and exploit data locality" 10 December 2000 (2000-12-10), MICRO-33. PROCEEDINGS OF THE 33RD. ANNUAL ACM/IEEE INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE. MONTEREY, CA, DEC. 10 - 13, 2000, PROCEEDINGS OF THE ANNUAL ACM/IEEE INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE, LOS ALAMITOS, CA : IEEE COMP. SOC, US, , XP010528873 ISBN: 0-7695-0924-X page 33, column 1, lines 25-46 * |
Also Published As
Publication number | Publication date |
---|---|
KR100824487B1 (en) | 2008-04-22 |
US20040158677A1 (en) | 2004-08-12 |
CN1742264A (en) | 2006-03-01 |
WO2004072781A3 (en) | 2005-05-26 |
KR20050108352A (en) | 2005-11-16 |
US7469316B2 (en) | 2008-12-23 |
EP1593042A2 (en) | 2005-11-09 |
TWI316179B (en) | 2009-10-21 |
TW200508859A (en) | 2005-03-01 |
JP2006514385A (en) | 2006-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7469316B2 (en) | Buffered writes and memory page control | |
US7536530B2 (en) | Method and apparatus for determining a dynamic random access memory page management implementation | |
US7945737B2 (en) | Memory hub with internal cache and/or memory access prediction | |
US6112265A (en) | System for issuing a command to a memory having a reorder module for priority commands and an arbiter tracking address of recently issued command | |
TWI457753B (en) | Memory controller and method for managing access to memory | |
US5889714A (en) | Adaptive precharge management for synchronous DRAM | |
US6088772A (en) | Method and apparatus for improving system performance when reordering commands | |
KR20070086640A (en) | Priority scheme for executing commands in memories | |
CN112088368A (en) | Dynamic per bank and full bank refresh | |
US7120765B2 (en) | Memory transaction ordering | |
CN111684427A (en) | Cache control aware memory controller | |
US20080098176A1 (en) | Method and Apparatus for Implementing Memory Accesses Using Open Page Mode for Data Prefetching | |
US7159066B2 (en) | Precharge suggestion | |
US6836831B2 (en) | Independent sequencers in a DRAM control structure | |
US7080217B2 (en) | Cycle type based throttling | |
US7076617B2 (en) | Adaptive page management | |
US6888777B2 (en) | Address decode | |
US6392935B1 (en) | Maximum bandwidth/minimum latency SDRAM interface | |
US20060090059A1 (en) | Methods and devices for memory paging management | |
WO2009092037A1 (en) | Content addressable memory augmented memory |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): BW GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
REEP | Request for entry into the european phase |
Ref document number: 2004700072 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2004700072 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 20048027723 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2005518463 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020057014759 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 2004700072 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 1020057014759 Country of ref document: KR |