专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

WO2016025591A1 ADAPTIVE RATE COMPRESSION HASH PROCESSING DEVICE 审中-公开
标题翻译：自适应速率压缩哈希处理器件
公开(公告)号：WO2016025591A1
公开(公告)日：2016-02-18
申请号：PCT/US2015/044846
申请日：2015-08-12
申请人： TIDAL SYSTEMS, INC.
发明人： HUBRIS, Alexander , WU, Yingquan
IPC分类号： H03M7/40
CPC分类号： G06F17/30153 , G06F17/30097 , G06F17/30138 , H03M7/3086
摘要： An input file is processed according to hash algorithm that references sets of literals to preceding sets of literals to facilitate copy-offset command generation. Preceding instances are identified by generating a hash of the literal set and looking up a corresponding entry in a hash table. The hash table may be accessed by placing look-up requests in a FIFO buffer. When the FIFO buffer is full, generation of the hash chain is suspended until it is no longer full. When repeated literals are found, generation of the hash chain is likewise suspended. The hash chain is used to generate a command file, such as according to the LZ algorithm. Runs of consecutive literals are replaced by a run-length command. The command file may then be encoded using Huffman encoding.
摘要翻译：根据散列算法对输入文件进行处理，该算法将文字集合引用到前面的文字集合，以便生成复制偏移命令。前一个实例通过生成文字集的散列并在散列表中查找相应的条目来识别。可以通过将查询请求放在FIFO缓冲器中来访问哈希表。当FIFO缓冲区已满时，哈希链的生成将被暂停，直到它不再满。当发现重复的文字时，哈希链的生成同样被暂停。哈希链用于生成命令文件，例如根据LZ算法。连续文字的运行由run-length命令替换。命令文件可以使用霍夫曼编码进行编码。

22. 发明申请

WO2015167559A1 PARTITIONABLE TERNARY CONTENT ADDRESSABLE MEMORY (TCAM) FOR USE WITH A BLOOM FILTER 审中-公开
标题翻译：可分离的内容可寻址存储器（TCAM），用于BLOOM FILTER
公开(公告)号：WO2015167559A1
公开(公告)日：2015-11-05
申请号：PCT/US2014/036236
申请日：2014-04-30
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
发明人： LI, Sheng , LIM, Kevin, T. , MILOJICIC, Dejan, S. , FARABOSCHI, Paolo
IPC分类号： G06F17/30
CPC分类号： G06F17/30495 , G06F3/0604 , G06F3/064 , G06F3/0673 , G06F17/30097 , G06F17/3033 , G06F17/30584
摘要： A bit vector for a Bloom filter is determined by performing one or more hash function operations on a set of ternary content addressable memory (TCAM) words. A TCAM array is partitioned into a first portion to store the bit vector for the Bloom filter and a second portion to store the set of TCAM words. The TCAM array can be searched using a search word by performing the one or more hash function operations on the search word to generate a hashed search word and determining whether bits at specified positions of the hashed search word match bits at corresponding positions of the bit vector stored in the first portion of the TCAM array before searching the second portion of the TCAM array with the search word.
摘要翻译：通过对一组三元内容可寻址存储器（TCAM）字进行一个或多个散列函数操作来确定布隆过滤器的位向量。将TCAM阵列划分为第一部分以存储布隆过滤器的位向量，以及存储该组TCAM字的第二部分。可以使用搜索词搜索TCAM阵列，通过对搜索词执行一个或多个哈希函数操作来产生散列搜索词，并确定散列搜索词的指定位置的比特是否与位向量的相应位置的比特匹配存储在TCAM阵列的第一部分中，然后用搜索词搜索TCAM阵列的第二部分。

23. 发明申请

WO2015153259A1 NAMESPACE MANAGEMENT IN DISTRIBUTED STORAGE SYSTEMS 审中-公开
标题翻译：分布式存储系统中的名称管理
公开(公告)号：WO2015153259A1
公开(公告)日：2015-10-08
申请号：PCT/US2015/022647
申请日：2015-03-26
申请人： AMAZON TECHNOLOGIES, INC.
发明人： HENDRICKSON, Joshua Samuel , OIKARINEN, Matti Juhani , HAUGLAND, Alex , VINCENT, Pradeep , FRIGO, Matteo , WU, Xiaobin
IPC分类号： G06F17/30
CPC分类号： G06F17/30958 , G06F17/30097
摘要： A directed acyclic graph (DAG) is generated to represent a namespace of a directory. In response to a request to create a new object with a specified name, a hash value bit sequence is computed for the name. A plurality of levels of the DAG are navigated using successive subsequences of the bit sequence to identify a candidate node for storing a new entry corresponding to the specified name. If the candidate node meets a split criterion, the new entry and at least a selected subset of entries of the candidate node's list of entries are distributed among a plurality of DAG nodes, including at least one new DAG node, using respective bit sequences obtained by applying the hash function for each distributed entry.
摘要翻译：生成有向无环图（DAG）来表示目录的命名空间。响应于创建具有指定名称的新对象的请求，为该名称计算哈希值比特序列。使用比特序列的连续子序列导航多个DAG级别，以识别用于存储与指定名称相对应的新条目的候选节点。如果候选节点满足分割标准，则候选节点的条目列表的新条目和至少一个选定的条目子集在包括至少一个新的DAG节点的多个DAG节点之间分配，使用由对每个分布式条目应用散列函数。

24. 发明申请

WO2015120071A2 CONTENT BASED ORGANIZATION OF FILE SYSTEMS 审中-公开
标题翻译：基于内容的文件系统组织
公开(公告)号：WO2015120071A2
公开(公告)日：2015-08-13
申请号：PCT/US2015/014492
申请日：2015-02-04
申请人： EXABLOX CORPORATION
发明人： HUNT, Tad , BARRUS, Frank E.
IPC分类号： G06F17/30
CPC分类号： G06F17/30097
摘要： The methods and systems for organizing and managing a file system on top of a content addressable object store are provided. User content is associated with a record including a content hash associated with an address in the content addressable object store. The content hash is a function of user content and determined by dividing the file into data objects, generating a pointer tree of hashes on top of the data objects, and calculating a hash of the root of the pointer tree. The record, the pointer tree, and the file are stored in the object store. Reading user content from the object store includes reading the record, fetching the content hash to find a root of the pointer tree, descending leaves of the pointer tree to read the hashes of the data objects associated with user content, and reassembling the data objects in sequential file data.
摘要翻译：提供了用于在内容可寻址对象存储之上组织和管理文件系统的方法和系统。用户内容与包括与内容可寻址对象存储中的地址相关联的内容散列的记录相关联。内容散列是用户内容的函数，通过将文件划分为数据对象，生成数据对象顶部的散列指针树，并计算指针树根的散列值来确定。记录，指针树和文件存储在对象存储中。从对象存储器读取用户内容包括读取记录，获取内容散列以找到指针树的根，指针树的下降沿读取与用户内容相关联的数据对象的散列，并重新组合数据对象顺序文件数据。

25. 发明申请

WO2015067035A1 数据拷贝管理装置及其数据拷贝方法审中-公开
公开(公告)号：WO2015067035A1
公开(公告)日：2015-05-14
申请号：PCT/CN2014/078475
申请日：2014-05-27
申请人：华为技术有限公司
发明人：任努努 , 金添福 , 李明君
IPC分类号： G06F12/02
CPC分类号： G06F17/30097 , H04L67/06 , H04L67/1095 , H04L67/1097
摘要：本发明提供一种数据拷贝管理装置及其数据拷贝方法。该数据拷贝方法包括：采用哈希算法获得由源数据分块成的多个源数据块的哈希值；将哈希值发送至目标存储侧，以使目标存储侧基于接收的哈希值判断是由目标存储侧直接生成源数据块还是由源存储侧发送源数据块至目标存储侧；在接收目标存储侧反馈的第一反馈时，忽略源数据块；在接收目标存储侧反馈的第二反馈时，发送源数据块至目标存储侧。通过上述方式，本发明能够提高对特殊数据块的拷贝速度，从而节省CPU和网络资源，減少拷贝时间。

26. 发明申请

WO2015055035A1 一种对元数据对象进行散列的方法及装置审中-公开
公开(公告)号：WO2015055035A1
公开(公告)日：2015-04-23
申请号：PCT/CN2014/083044
申请日：2014-07-25
申请人：华为技术有限公司
发明人：李永健 , 高峰
IPC分类号： G06F17/30
CPC分类号： G06F17/3023 , G06F17/30097
摘要：公开了一种对元数据对象进行散列的方法，包括：判断元数据对象是否为快照元数据对象；若所述元数据对象不是快照元数据对象，则将所述元数据对象的名称作为输入值计算所述元数据对象的散列值；若所述元数据对象为快照元数据对象，则将所述元数据对象的名称中的版本名称作为输入值计算所述元数据对象的散列值；根据所述元数据对象的散列值将所述元数据对象散列到相应的元数据服务器节点。还公开了一种对元数据对象进行散列的装置。具有可降低元数据对象被散列到不同元数据服务器节点的随机性，提高快照数据的访问效率，提高快照的访问性能和系统的整体性能的优点。

27. 发明申请

WO2015054877A1 METHOD AND APPARATUS FOR DATA STORAGE AND RETRIEVAL 审中-公开
标题翻译：数据存储和检索的方法和装置
公开(公告)号：WO2015054877A1
公开(公告)日：2015-04-23
申请号：PCT/CN2013/085432
申请日：2013-10-18
申请人： TELEFONAKTIEBOLAGET L M ERICSSON (PUBL) , LI, Qingsong
发明人： LI, Qingsong
IPC分类号： G06F12/00
CPC分类号： G06F17/3033 , G06F12/0864 , G06F17/30097
摘要： Methods and apparatuses for data storage and retrieval have been provided. More specifically, a hash table is provided. The hash table comprises a first level slot array with a constant number of slots and at least one second level slot array with a variant number of slots. Each slot of the first level slot array is associated with a hash code range, and each slot of the first level slot array is linked to at most one second level slot array. V arious operations, such as PUT, GET, RANGE_SEARCH of the hash table have been described. Moreover, a hash method has been provided for network management information to use the proposed hash table.
摘要翻译：已经提供了用于数据存储和检索的方法和装置。更具体地，提供了散列表。哈希表包括具有恒定数量的时隙的第一级时隙阵列和具有不同数目的时隙的至少一个第二级时隙阵列。第一级时隙阵列的每个时隙与散列码范围相关联，并且第一级时隙阵列的每个时隙被链接到至多一个第二级时隙阵列。已经描述了诸如PUT，GET，RANGE_SEARCH的哈希表的丰富的操作。此外，已经提供了一种用于网络管理信息以使用所提出的散列表的哈希方法。

28. 发明申请

WO2014185974A2 EFFICIENT DATA REPLICATION AND GARBAGE COLLECTION PREDICTIONS 审中-公开
标题翻译：有效的数据复制和收集预测
公开(公告)号：WO2014185974A2
公开(公告)日：2014-11-20
申请号：PCT/US2014/000111
申请日：2014-05-14
申请人： ABERCROMBIE, Philip, J. , PROVENZANO, Christopher, A. , GOLDBERG, Keith
发明人： ABERCROMBIE, Philip, J. , PROVENZANO, Christopher, A. , GOLDBERG, Keith
IPC分类号： G06F17/30
CPC分类号： G06F17/30575 , G06F11/1448 , G06F12/0253 , G06F17/30097 , G06F17/30138 , G06F17/30159
摘要： Described herein are systems and methods for efficient data replication. The remote server generates a set of object hashes representative of data in the source object that is already present on the remote server, and data indicative of source object hashes that are not present on the remote server. The source local deduplication store transmits the identified portions of the source object to the remote server to replicate the source object on the remote server. Also described herein are systems and methods for garbage collection prediction. An accumulated difference count is updated when a node is added to a temporal graph, and a divested difference count is updated when a node is removed from the temporal graph. The outcome of the garbage collection is predicted based on at least one of the accumulated difference count and the divested difference count.
摘要翻译：这里描述了用于有效数据复制的系统和方法。远程服务器生成代表远程服务器上已存在的源对象中的数据的一组对象散列，以及指示远程服务器上不存在的源对象散列的数据。源本地重复数据删除存储将源对象的标识部分发送到远程服务器以复制远程服务器上的源对象。本文还描述了用于垃圾收集预测的系统和方法。当将节点添加到时间图时，更新积累的差异计数，并且当从时间图中移除节点时更新已删除的差异计数。垃圾收集的结果基于累计差异计数和被删除的差异计数中的至少一个来预测。

29. 发明申请

WO2014028261A1 DE-DUPLICATING ATTACHMENTS ON MESSAGE DELIVERY AND AUTOMATED REPAIR OF ATTACHMENTS 审中-公开
标题翻译：关于消息传递的附件和附件的自动修复
公开(公告)号：WO2014028261A1
公开(公告)日：2014-02-20
申请号：PCT/US2013/053678
申请日：2013-08-06
申请人： MICROSOFT CORPORATION
发明人： ROOMP, Kristof , DHARIWAL, Alok , DIMITROV, Ivaylo , HO, Cheng , LIU, Lincoln , PAI, Brandon , PASUMARTHY, Kumar , PITIGOI-ARON, Gruia , RODRIGUES, John
IPC分类号： G06F17/30
CPC分类号： G06F17/30156 , G06F17/30097 , G06F17/30371 , H04L51/08
摘要： Systems and techniques of de-duplicating file and/or blobs within a file system are presented. In one embodiment, an email system is disclosed wherein the email system receives email messages comprising a set of associated attachments. The system determines whether the associated attachments have been previously stored in the email system, the state of the stored attachment, and if the state of the attachment is appropriate for sharing copies of the attachment, then providing a reference to the attachment upon a request to share the attachment. In another embodiment, the system may detect whether stored attachments are corrupted and, if so, attempt to repair the attachment, and possibly, prior to sharing references to the attachment.
摘要翻译：介绍了在文件系统内解除复制文件和/或blob的系统和技术。在一个实施例中，公开了一种电子邮件系统，其中电子邮件系统接收包括一组相关附件的电子邮件消息。该系统确定相关联的附件是否已经先前存储在电子邮件系统中，所存储的附件的状态以及附件的状态是否适于共享附件的副本，然后在请求时提供对附件的引用分享附件。在另一个实施例中，系统可以检测存储的附件是否被破坏，并且如果是，则尝试修复附件，并且可能在共享对附件的引用之前。

30. 发明申请

WO2013142943A8 METHOD FOR PROTECTING DATA 审中-公开
标题翻译：保护数据的方法
公开(公告)号：WO2013142943A8
公开(公告)日：2013-12-05
申请号：PCT/CA2012000269
申请日：2012-03-26
申请人： IRDETO CANADA CORP , KRTEN ROBERT , DONG HONGRUI , LIEM CLIFFORD
发明人： KRTEN ROBERT , DONG HONGRUI , LIEM CLIFFORD
CPC分类号： G06F21/60 , G06F17/30097 , G06F21/125 , G06F21/14 , G06F21/64 , G06F2221/2107 , H04L9/0894 , H04L9/3239 , H04L2209/16
摘要： In the present disclosure, a hash function is computed over a known image, for example, an address range in a program. The result of the hash function is known to be the same at two distinct points in time, before the program is run, i.e. signing at build-time, and during the running of the program, i.e. run time. The value that the programmer wishes to hide, i.e. the secret value, is also known at build-time. At build-time, the secret value is combined with the hash in such a way that the combining operation can be reversed at run time. This combined value, i.e. the salt, is stored along with the program. Later, at runtime, the program computes the same hash value as was computed at signing time, and does the reverse combining operation in order to reveal the secret value.
摘要翻译：在本公开中，在已知图像上计算散列函数，例如程序中的地址范围。散列函数的结果在程序运行之前的两个不同的时间点是相同的，即在构建时和在程序运行期间（即运行时）进行签名。程序员希望隐藏的值，即秘密值，在构建时也是已知的。在构建时，秘密值与散列组合在一起，使得组合操作可以在运行时反转。这个组合的值，即盐，与程序一起存储。之后，在运行时，程序会计算与签署时计算出的相同的散列值，并执行反向组合操作以揭示秘密值。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式