专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07555634B1 Multiple data hazards detection and resolution unit 有权
标题翻译：多重数据危害检测和分辨率单位
公开(公告)号：US07555634B1
公开(公告)日：2009-06-30
申请号：US10830244
申请日：2004-04-22
申请人： Krishna M. Thatipelli , Balakrishna Venkatrao
发明人： Krishna M. Thatipelli , Balakrishna Venkatrao
IPC分类号： G06F13/00
CPC分类号： G06F9/383 , G06F9/3834 , G06F9/3836 , G06F9/3838
摘要： Order indication logic can be recycled for at least two different data hazards, thus reducing the amount of processor real estate consumed by data hazard resolution logic. The logic also allows a single priority picker to be utilized for coloring without the cost of additional pipeline stages. A single priority picker can be utilized to identify memory operations for performing RAW bypass and for resolving OERs. For instance, a data hazard resolution unit resolves at least two different data hazards between resident memory operations and incoming memory operations with a set of logic that indicates order of the resident memory operations relative to the incoming memory operations. The indicated order corresponds to the data hazard being resolved. The data hazard resolution unit includes a priority picker to select one of the indicated resident memory operations for either data hazard.
摘要翻译：订单指示逻辑可以回收至少两个不同的数据危害，从而减少数据危害解决逻辑所消耗的处理器的数量。该逻辑还允许单个优先选择器用于着色，而不需要额外的流水线阶段的成本。可以使用单个优先选择器来识别用于执行RAW旁路和解析OER的存储器操作。例如，数据危险解决单元利用指示驻留存储器操作相对于进入存储器操作的顺序的一组逻辑来解决驻留存储器操作和进入的存储器操作之间的至少两个不同的数据危害。指示的顺序对应于正在解决的数据危险。数据危险解决单元包括优先选择器，用于为数据危险选择所指示的驻留存储器操作之一。

2. 发明授权

US07343477B1 Efficient read after write bypass 有权
标题翻译：写旁路后有效读取
公开(公告)号：US07343477B1
公开(公告)日：2008-03-11
申请号：US10747584
申请日：2003-12-29
申请人： Krishna Thatipelli , Balakrishna Venkatrao
发明人： Krishna Thatipelli , Balakrishna Venkatrao
IPC分类号： G06F9/34
CPC分类号： G06F9/3826 , G06F9/3832 , G06F9/3834 , G06F9/3861
摘要： Predicting address matches between a read type operation and a write type operation based on address representations allows for efficient RAW bypass. The spatial locality characteristic of code allows for address match prediction with address representations that are smaller than the actual addresses, thus allowing for faster comparison. Operations for performing the RAW bypass commence upon predicting an address match. While these operations are being performed, other operations for verifying the prediction are performed. If the address match prediction is verified, then the RAW bypass has been performed without hindrance. If the address match is proved incorrect, then the corresponding read type operation is reissued and/or re-executed.
摘要翻译：基于地址表示预测读取类型操作和写入类型操作之间的地址匹配可以实现高效的RAW旁路。代码的空间位置特征允许地址匹配预测与地址表示小于实际地址，从而允许更快的比较。在预测地址匹配时开始执行RAW旁路的操作。在执行这些操作时，执行用于验证预测的其他操作。如果地址匹配预测被验证，则RAW旁路已被执行而没有障碍。如果地址匹配被证明不正确，则相应的读取类型操作被重新发行和/或重新执行。

3. 发明授权

US07496710B1 Reducing resource consumption by ineffective write operations 有权
标题翻译：通过无效的写入操作减少资源消耗
公开(公告)号：US07496710B1
公开(公告)日：2009-02-24
申请号：US11096518
申请日：2005-04-01
申请人： Balakrishna Venkatrao
发明人： Balakrishna Venkatrao
IPC分类号： G06F12/12 , G06F12/04
CPC分类号： G06F12/126
摘要： It has been discovered that preventing performance of ineffective write operations reduces demand on memory bandwidth, as well as preventing unnecessary consumption of resources. A write operation is inspected to determine whether the write operation will effectively modify the destination of the write operation (i.e., whether a net change will occur). Those ineffective write operations are not performed. Preventing performance of the write operation includes not changing contents of locations in a memory hierarchy that correspond to the destination of the write operation.
摘要翻译：已经发现，防止无效写入操作的性能降低了对存储器带宽的需求，并且防止了资源的不必要的消耗。检查写入操作以确定写入操作是否将有效地修改写入操作的目的地（即，是否将发生净更改）。无法执行无效的写入操作。防止写入操作的性能包括不改变与写入操作的目的地相对应的存储器层级中的位置的内容。

4. 发明授权

US07366848B1 Reducing resource consumption by ineffective write operations in a shared memory system 有权
标题翻译：通过在共享存储器系统中的无效写入操作来减少资源消耗
公开(公告)号：US07366848B1
公开(公告)日：2008-04-29
申请号：US11143165
申请日：2005-06-02
申请人： Balakrishna Venkatrao
发明人： Balakrishna Venkatrao
IPC分类号： G06F12/00
CPC分类号： G06F12/082
摘要： In a shared memory system, ineffective write operations (“dead stores”) can be handled in a manner to reduce unnecessary consumption of resources. In a shared memory system, when a non-owning processing unit requests data from a shared memory location owned by another processing unit, the memory controller for the shared memory requests a most current copy of the data from the owner processing unit. Instead of the owner processing unit reflexively sending its data to the memory controller, the owner processing unit determines whether the data has been changed, and, if it has not changed, transmits indication of such to the memory controller. Since the data has not changed, then the data at the shared memory location is proper and can be sent to satisfy the requesting processing unit.
摘要翻译：在共享存储器系统中，可以以减少不必要的资源消耗的方式来处理无效的写操作（“死存储”）。在共享存储器系统中，当非拥有处理单元从另一处理单元所拥有的共享存储器位置请求数据时，共享存储器的存储器控制器从所有者处理单元请求最新的数据副本。所有者处理单元代替所有者处理单元将其数据反馈发送到存储器控制器，所有者处理单元确定数据是否已经改变，并且如果没有改变，则向存储器控制器发送这样的指示。由于数据没有改变，所以共享存储器位置处的数据是适当的，并且可以被发送以满足请求处理单元。

5. 发明申请

US20110213712A1 Cloud Broker and Procurement System and Method 审中-公开
标题翻译：云经纪和采购系统与方法
公开(公告)号：US20110213712A1
公开(公告)日：2011-09-01
申请号：US12713557
申请日：2010-02-26
申请人： Ethan Hadar , Gregory Lewis Bodine , Balakrishna Venkatrao
发明人： Ethan Hadar , Gregory Lewis Bodine , Balakrishna Venkatrao
IPC分类号： G06Q10/00 , G06F15/16 , G06Q30/00
CPC分类号： G06Q30/08 , G06Q30/04 , G06Q50/188 , H04L41/5009
摘要： A cloud broker and procurement system and method is closed. In particular embodiments, the method includes receiving an offer of a computing resource from each of a plurality of providers. The method further includes receiving, from each of the plurality of providers, a service level agreement associated with each respective offered computing resource. Additionally, the method includes normalizing each of the service level agreements associated with the offered computing resources. The method further includes receiving a request from a requesting computer for a computing resource and selecting, based at least in part on the normalized service level agreements, one of the providers to provide the requested computing resource. The method also includes transmitting a service match indicator to the client, wherein the service match indicator indicates a time at which the offered computing resource will be utilized, and utilizing the computing resource on the selected provider.
摘要翻译：一个云代理和采购系统和方法被关闭。在特定实施例中，该方法包括从多个提供者中的每一个接收计算资源的提议。该方法还包括从多个提供商中的每一个接收与每个相应的提供的计算资源相关联的服务级别协议。另外，该方法包括对与所提供的计算资源相关联的每个服务级别协议进行归一化。该方法还包括从请求计算机接收计算资源的请求，并且至少部分地基于归一化的服务水平协议来选择提供所请求的计算资源的提供者之一。该方法还包括向客户端发送服务匹配指示符，其中服务匹配指示符指示所提供的计算资源将被利用的时间，以及利用所选择的提供者上的计算资源。

6. 发明申请

US20070088918A1 Tracking dependencies among memory requests 审中-公开
标题翻译：跟踪内存请求之间的依赖关系
公开(公告)号：US20070088918A1
公开(公告)日：2007-04-19
申请号：US11249254
申请日：2005-10-13
申请人： Balakrishna Venkatrao
发明人： Balakrishna Venkatrao
IPC分类号： G06F13/00
CPC分类号： G06F13/1631
摘要： Encoding positional information to track dependencies among memory requests resident in a memory request buffer increases efficiency of submitting those requests to memory. With the encoded positional information representing dependencies, a mechanism that selects memory requests for submission to memory can select memory requests without being hindered by determining dependencies repeatedly. In addition, the encoded positional information can be update incident with return of service indication from memory for a memory request.
摘要翻译：编码位置信息以跟踪驻留在存储器请求缓冲器中的存储器请求之间的依赖性，提高将这些请求提交给存储器的效率。利用代表依赖性的编码位置信息，选择存储器请求以提交给存储器的机制可以通过重复地确定依赖关系来选择存储器请求而不受阻碍。此外，编码的位置信息可以从存储器请求的存储器返回服务指示而进行更新。

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