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

US06510494B1 Time based mechanism for cached speculative data deallocation 失效
标题翻译：缓存的推测数据释放的基于时间的机制
公开(公告)号：US06510494B1
公开(公告)日：2003-01-21
申请号：US09345716
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1208
CPC分类号： G06F9/3802 , G06F9/383 , G06F12/0862 , G06F12/0897
摘要： A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the pref etch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit.
摘要翻译：一种操作计算机系统的处理单元的方法，通过从指令序列单元向处理单元的预取单元发出具有显式预取请求的指令。本发明适用于作为操作数数据或指令的值。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用pref蚀刻请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联。

2. 发明授权

US06421763B1 Method for instruction extensions for a tightly coupled speculative request unit 有权
标题翻译：紧耦合推测请求单元的指令扩展方法
公开(公告)号：US06421763B1
公开(公告)日：2002-07-16
申请号：US09345642
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1208
CPC分类号： G06F12/0862 , G06F9/3802 , G06F9/383 , G06F9/3885 , G06F12/0897 , G06F2212/6028
摘要： A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster). If another prefetch value is requested from the memory hierarchy, and it is determined that a prefetch limit of cache usage has been met by the cache, then a cache line in the cache containing one of the earlier prefetch values is allocated for receiving the other prefetch value. The prefetch limit of cache usage may be established with a maximum number of sets in a congruence class usable by the requesting processing unit. A flag in a directory of the cache may be set to indicate that the prefetch value was retrieved as the result of a prefetch operation. In the implementation wherein the cache is a multi-level cache, a second flag in the cache directory may be set to indicate that the prefetch value has been sourced to an upstream cache. A cache line containing prefetch data can be automatically invalidated after a preset amount of time has passed since the prefetch value was requested.
摘要翻译：一种操作计算机系统的处理单元的方法，通过从指令序列单元向处理单元的预取单元发出具有显式预取请求的指令。本发明适用于作为操作数数据或指令的值。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。如果从存储器层次结构请求另一个预取值，并且确定高速缓存的高速缓存使用的预取限制已经被高速缓存满足，则分配包含较早预取值之一的高速缓存行中的高速缓存行用于接收另一个预取值。高速缓存使用的预取限制可以由请求处理单元可用的同余类中的最大数量的集合来建立。高速缓存目录中的标志可以被设置为指示作为预取操作的结果检索预取值。在其中缓存是多级高速缓存的实现中，高速缓存目录中的第二标志可以被设置为指示预取值已经被提供给上游高速缓存。包含预取数据的缓存行可以在从请求预取值开始经过预设的时间后自动失效。

3. 发明授权

US06393528B1 Optimized cache allocation algorithm for multiple speculative requests 失效
标题翻译：针对多个推测请求的优化缓存分配算法
公开(公告)号：US06393528B1
公开(公告)日：2002-05-21
申请号：US09345714
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1200
CPC分类号： G06F12/0862 , G06F12/127
摘要： A method of operating a computer system is disclosed in which an instruction having an explicit prefetch request is issued directly from an instruction sequence unit to a prefetch unit of a processing unit. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster). If another prefetch value is requested from the memory hiearchy and it is determined that a prefetch limit of cache usage has been met by the cache, then a cache line in the cache containing one of the earlier prefetch values is allocated for receiving the other prefetch value.
摘要翻译：公开了一种操作计算机系统的方法，其中具有显式预取请求的指令直接从指令序列单元发送到处理单元的预取单元。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。如果从存储器hiearchy请求另一个预取值，并且确定高速缓存的高速缓存使用的预取限制已被满足，则包含先前预取值中的一个的高速缓存行中的高速缓存行被分配用于接收另一个预取值。

4. 发明授权

US06360299B1 Extended cache state with prefetched stream ID information 失效
标题翻译：扩展缓存状态与预取流ID信息
公开(公告)号：US06360299B1
公开(公告)日：2002-03-19
申请号：US09345644
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1200
CPC分类号： G06F12/0862 , G06F12/121 , G06F2212/6028
摘要： A method of operating a computer system is disclosed in which an instruction having an explicit prefetch request is issued directly from an instruction sequence unit to a prefetch unit of a processing unit. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster). If another prefetch value is requested from the memory hierarchy, and it is determined that a prefetch limit of cache usage has been met by the cache, then a cache line in the cache containing one of the earlier prefetch values is allocated for receiving the other prefetch value.
摘要翻译：公开了一种操作计算机系统的方法，其中具有显式预取请求的指令直接从指令序列单元发送到处理单元的预取单元。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。如果从存储器层次结构请求另一个预取值，并且确定高速缓存的高速缓存使用的预取限制已经被高速缓存满足，则分配包含较早预取值之一的高速缓存行中的高速缓存行用于接收另一个预取值。

5. 发明授权

US06532521B1 Mechanism for high performance transfer of speculative request data between levels of cache hierarchy 失效
标题翻译：在高速缓存层级之间高速传输推测请求数据的机制
公开(公告)号：US06532521B1
公开(公告)日：2003-03-11
申请号：US09345715
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1200
CPC分类号： G06F9/3802 , G06F9/30047 , G06F9/383 , G06F12/0811 , G06F12/0862 , G06F12/123 , G06F12/127
摘要： A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster). If another prefetch value is requested from the memory hierarchy, and it is determined that a prefetch limit of cache usage has been met by the cache, then a cache line in the cache containing one of the earlier prefetch values is allocated for receiving the other prefetch value. The prefetch limit of cache usage may be established with a maximum number of sets in a congruence class usable by the requesting processing unit. A flag in a directory of the cache may be set to indicate that the prefetch value was retrieved as the result of a prefetch operation. In the implementation wherein the cache is a multi-level cache, a second flag in the cache directory may be set to indicate that prefetch value has been sourced to an upstream cache. A cache line containing prefetch data can be automatically invalidated after a preset amount of time has passed since the prefetch value was requested.
摘要翻译：一种操作计算机系统的处理单元的方法，通过从指令序列单元向处理单元的预取单元发出具有显式预取请求的指令。本发明适用于作为操作数数据或指令的值。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。如果从存储器层次结构请求另一个预取值，并且确定高速缓存的高速缓存使用的预取限制已经被高速缓存满足，则分配包含较早预取值之一的高速缓存行中的高速缓存行用于接收另一个预取值。高速缓存使用的预取限制可以由请求处理单元可用的同余类中的最大数量的集合来建立。高速缓存目录中的标志可以被设置为指示作为预取操作的结果检索预取值。在其中高速缓存是多级高速缓存的实现中，高速缓存目录中的第二标志可以被设置为指示预取值已经被提供给上游高速缓存。包含预取数据的缓存行可以在从请求预取值开始经过预设的时间后自动失效。

6. 发明授权

US06496921B1 Layered speculative request unit with instruction optimized and storage hierarchy optimized partitions 失效
标题翻译：分层推测请求单元，具有指令优化和存储层次结构优化分区
公开(公告)号：US06496921B1
公开(公告)日：2002-12-17
申请号：US09345643
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F930
CPC分类号： G06F9/30047 , G06F9/3802 , G06F9/3885 , G06F12/0862 , G06F12/0897 , G06F2212/6028
摘要： A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster).
摘要翻译：一种操作计算机系统的处理单元的方法，通过从指令序列单元向处理单元的预取单元发出具有显式预取请求的指令。本发明适用于作为操作数数据或指令的值。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。

7. 发明授权

US06421762B1 Cache allocation policy based on speculative request history 有权
标题翻译：基于推测请求历史记录的缓存分配策略
公开(公告)号：US06421762B1
公开(公告)日：2002-07-16
申请号：US09345713
申请日：1999-06-30
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , Leo James Clark , John Steven Dodson , Guy Lynn Guthrie , James Stephen Fields, Jr.
IPC分类号： G06F1200
CPC分类号： G06F12/0862 , G06F12/0897 , G06F12/126 , G06F2212/6024
摘要： A method of operating a processing unit of a computer system, by issuing an instruction having an explicit prefetch request directly from an instruction sequence unit to a prefetch unit of the processing unit. The invention applies to values that are either operand data or instructions. In a preferred embodiment, two prefetch units are used, the first prefetch unit being hardware independent and dynamically monitoring one or more active streams associated with operations carried out by a core of the processing unit, and the second prefetch unit being aware of the lower level storage subsystem and sending with the prefetch request an indication that a prefetch value is to be loaded into a lower level cache of the processing unit. The invention may advantageously associate each prefetch request with a stream ID of an associated processor stream, or a processor ID of the requesting processing unit (the latter feature is particularly useful for caches which are shared by a processing unit cluster). If another prefetch value is requested from the memory hierarchy, and it is determined that a prefetch limit of cache usage has been met by the cache, then a cache line in the cache containing one of the earlier prefetch values is allocated for receiving the other prefetch value. The prefetch limit of cache usage may be established with a maximum number of sets in a congruence class usable by the requesting processing unit. A flag in a directory of the cache may be set to indicate that the prefetch value was retrieved as the result of a prefetch operation. In the implementation wherein the cache is a multi-level cache, a second flag in the cache directory may be set to indicate that the prefetch value has been sourced to an upstream cache. A cache line containing prefetch data can be automatically invalidated after a preset amount of time has passed since the prefetch value was requested.
摘要翻译：一种操作计算机系统的处理单元的方法，通过从指令序列单元向处理单元的预取单元发出具有显式预取请求的指令。本发明适用于作为操作数数据或指令的值。在优选实施例中，使用两个预取单元，第一预取单元是硬件独立的，并且动态地监视与由处理单元的核心执行的操作相关联的一个或多个活动流，并且第二预取单元知道较低级别存储子系统，并用预取请求发送将预取值加载到处理单元的较低级缓存中的指示。本发明可以有利地将每个预取请求与相关联的处理器流的流ID或请求处理单元的处理器ID相关联（后一特征对于由处理单元簇共享的高速缓存特别有用）。如果从存储器层次结构请求另一个预取值，并且确定高速缓存的高速缓存使用的预取限制已经被高速缓存满足，则分配包含较早预取值之一的高速缓存行中的高速缓存行用于接收另一个预取值。高速缓存使用的预取限制可以由请求处理单元可用的同余类中的最大数量的集合来建立。高速缓存目录中的标志可以被设置为指示作为预取操作的结果检索预取值。在其中缓存是多级高速缓存的实现中，高速缓存目录中的第二标志可以被设置为指示预取值已经被提供给上游高速缓存。包含预取数据的缓存行可以在从请求预取值开始经过预设的时间后自动失效。

8. 发明授权

US06581139B1 Set-associative cache memory having asymmetric latency among sets 有权
标题翻译：集合中具有不对称延迟的集合关联高速缓存存储器
公开(公告)号：US06581139B1
公开(公告)日：2003-06-17
申请号：US09339411
申请日：1999-06-24
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
IPC分类号： G06F1200
CPC分类号： G06F12/0864
摘要： A set-associative cache memory having asymmetric latency among sets is disclosed. The cache memory has multiple congruence classes of cache lines. Each congruence class includes a number of sets organized in a set-associative manner. The cache memory further includes a means for accessing at least one of the sets faster than the remaining sets having an identical access latency.
摘要翻译：公开了一组在集合中具有非对称等待时间的组合高速缓冲存储器。高速缓存存储器具有多个一致的缓存行类。每个同余类包括以组合方式组织的多个集合。高速缓冲存储器还包括用于比具有相同访问延迟的其余集合更快地访问集合中的至少一个集合的装置。

9. 发明授权

US06460118B1 Set-associative cache memory having incremental access latencies among sets 失效
标题翻译：集合中具有增量访问延迟的集合关联缓存存储器
公开(公告)号：US06460118B1
公开(公告)日：2002-10-01
申请号：US09339410
申请日：1999-06-24
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
IPC分类号： C06F1200
CPC分类号： G06F12/0864 , G06F12/1054
摘要： A set-associative cache memory having incremental access latencies among sets is disclosed. The cache memory has multiple congruence classes of cache lines. Each congruence class includes a number of sets organized in a set-associative manner. In accordance with a preferred embodiment of the present invention, the cache memory further includes a means for accessing each of the sets with an access time dependent on a relative location of each of the sets such that access latency varies incrementally among sets.
摘要翻译：公开了一种在集合中具有增量接入延迟的集合关联高速缓冲存储器。高速缓存存储器具有多个一致的缓存行类。每个同余类包括以组合方式组织的多个集合。根据本发明的优选实施例，高速缓存存储器还包括用于以取决于每个集合的相对位置的访问时间来访问每个集合的装置，使得访问延迟在集合之间递增地变化。

10. 发明授权

US06460117B1 Set-associative cache memory having a mechanism for migrating a most recently used set 失效
标题翻译：具有用于迁移最近使用的集合的机制的集合关联缓存存储器
公开(公告)号：US06460117B1
公开(公告)日：2002-10-01
申请号：US09339409
申请日：1999-06-24
申请人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
发明人： Ravi Kumar Arimilli , Lakshminarayana Baba Arimilli , John Steven Dodson , James Stephen Fields, Jr. , Guy Lynn Guthrie
IPC分类号： G06F1200
CPC分类号： G06F12/0893 , G06F12/0864 , G06F12/123
摘要： A set-associative cache memory having a mechanism for migrating a most recently used set is disclosed. The cache memory has multiple congruence classes of cache lines. Each congruence class includes a number of sets organized in a set-associative manner. The cache memory further includes a migration means for directing the information from a cache “hit” to a predetermined set of the cache memory.
摘要翻译：公开了具有用于迁移最近使用的集合的机制的集合关联缓存存储器。高速缓存存储器具有多个一致的缓存行类。每个同余类包括以组合方式组织的多个集合。高速缓冲存储器还包括用于将信息从高速缓存“命中”引导到高速缓冲存储器的预定集合的迁移装置。

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