公开(公告)号：US5634068A

公开(公告)日：1997-05-27

申请号：US415175

申请日：1995-03-31

申请人： Satyanarayana Nishtala ,  Zahir Ebrahim ,  William C. Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

发明人： Satyanarayana Nishtala ,  Zahir Ebrahim ,  William C. Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

IPC分类号： G06F12/08 ,  G06F13/00

CPC分类号： G06F12/0822

摘要： A multiprocessor computer system has a multiplicity of sub-systems and a main memory coupled to a system controller. An interconnect module, interconnects the main memory and sub-systems in accordance with interconnect control signals received from the system controller. All of the sub-systems include a port that transmits and receives data as data packets of a fixed size. At least two of the sub-systems are data processors, each having a respective cache memory and a respective set of master cache tags (Etags), including one cache tag for each data block stored by the cache memory. The system controller maintains a set of duplicate cache tags (Dtags) for each of the data processors. The data processors each include master cache logic for updating the master cache tags, while the system controller includes logic for updating the duplicate cache tags. Memory transaction request logic simultaneously looks up the second cache tag in each of the sets of duplicate cache tags corresponding to the memory transaction request. It then determines which one of the cache memories and main memory to couple to the requesting data processor based on the second cache states and the address tags stored in the corresponding second cache tags. Duplicate cache update logic simultaneously updates all of the corresponding second cache tags in accordance with predefined cache tag update criteria.

摘要翻译： 多处理器计算机系统具有多个子系统和耦合到系统控制器的主存储器。 互连模块根据从系统控制器接收的互连控制信号，互连主存储器和子系统。 所有子系统都包括一个端口，该端口作为固定大小的数据包发送和接收数据。 至少两个子系统是数据处理器，每个数据处理器具有相应的高速缓冲存储器和相应的主缓存标签集（Etags），包括由高速缓存存储器存储的每个数据块的一个高速缓存标签。 系统控制器为每个数据处理器维护一组重复的缓存标签（Dtags）。 数据处理器各自包括用于更新主缓存标签的主缓存逻辑，而系统控制器包括用于更新重复高速缓存标签的逻辑。 存储器事务请求逻辑同时查找对应于存储器事务请求的每组重复高速缓存标签中的第二高速缓存标签。 然后，基于存储在相应的第二高速缓存标签中的第二高速缓存状态和地址标签，确定哪个高速缓冲存储器和主存储器耦合到请求数据处理器。 重复的高速缓存更新逻辑根据预定义的缓存标签更新标准同时更新所有相应的第二高速缓存标签。

公开(公告)号：US5657472A

公开(公告)日：1997-08-12

申请号：US414922

申请日：1995-03-31

申请人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III ,  Charles E. Narad

发明人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III ,  Charles E. Narad

IPC分类号： G06F12/08 ,  G06F12/00

CPC分类号： G06F12/0828

摘要： A multiprocessor computer system is provided having a multiplicity of sub-systems and a main memory coupled to a system controller. An interconnect module, interconnects the main memory and sub-systems in accordance with interconnect control signals received from the system controller. At least two of the sub-systems are data processors, each having a respective cache memory that stores multiple blocks of data and a respective master cache index. Each master cache index has a set of master cache tags (Etags), including one cache tag for each data block stored by the cache memory. Each data processor includes a master interface for sending memory transaction requests to the system controller and for receiving cache access requests from the system controller corresponding to memory transaction requests by other ones of the data processors. In the preferred embodiment, each memory transaction request is classified into one of two distinct master classes: a first transaction class including read memory access requests and a second transaction class including writeback memory access requests. The master interface and system controller have corresponding parallel request queues, one for each master class, for transmitting and receiving memory access requests. The system controller further includes memory transaction request logic for processing each memory transaction request and a duplicate cache index having a set of duplicate cache tags (Dtags), including one cache tag corresponding to each master cache tag in an associated data processor.

摘要翻译： 提供了具有多个子系统和耦合到系统控制器的主存储器的多处理器计算机系统。 互连模块根据从系统控制器接收的互连控制信号，互连主存储器和子系统。 至少两个子系统是数据处理器，每个数据处理器具有存储多个数据块的相应高速缓存存储器和相应的主高速缓存索引。 每个主缓存索引具有一组主缓存标签（Etags），包括缓存存储器存储的每个数据块的一个缓存标签。 每个数据处理器包括主界面，用于向系统控制器发送存储器事务请求，以及从其他数据处理器接收来自系统控制器的对应于存储器事务请求的高速缓存访​​问请求。 在优选实施例中，每个存储器事务请求被分类为两个不同的主类之一：包括读存储器访问请求的第一事务类和包括回写存储器访问请求的第二事务类。 主接口和系统控制器具有对应的并行请求队列，每个主类一个，用于发送和接收存储器访问请求。 系统控制器还包括用于处理每个存储器事务请求的存储器事务请求逻辑和具有一组重复高速缓存标签（Dtags）的重复高速缓存索引，包括与相关联的数据处理器中的每个主高速缓存标签相对应的一个高速缓存标签。

公开(公告)号：US5684977A

公开(公告)日：1997-11-04

申请号：US415040

申请日：1995-03-31

申请人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

发明人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

IPC分类号： G06F12/08

CPC分类号： G06F12/0828 ,  G06F12/0822

摘要： A multiprocessor computer system is provided having a multiplicity of sub-systems and a main memory coupled to a system controller. An interconnect module, interconnects the main memory and sub-systems in accordance with interconnect control signals received from the system controller. At least two of the sub-systems are data processors, each having a respective cache memory that stores multiple blocks of data and a set of master cache tags (Etags), including one cache tag for each data block stored by the cache memory. Each data processor includes a master interface for sending memory transaction requests to the system controller. The system controller processes each memory transaction and maintains a set of duplicate cache tags (Dtags) for each data processor. Finally, the system controller contains transaction execution circuitry for activating a transaction for servicing by the interconnect. The transaction execution circuitry pipelines memory access requests from the data processors, and includes invalidation circuitry for processing each writeback request from a given data processor prior to activation to determine if the Dtag index corresponding to the victimized cache line is invalid. Thereafter, the invalidation circuitry activates writeback requests only if the Dtag index is not invalid and cancels the writeback request if the Dtag index is invalid.

摘要翻译： 提供了具有多个子系统和耦合到系统控制器的主存储器的多处理器计算机系统。 互连模块根据从系统控制器接收的互连控制信号，互连主存储器和子系统。 至少两个子系统是数据处理器，每个数据处理器具有存储多个数据块的相应缓存存储器和一组主缓存标签（Etags），包括由高速缓存存储器存储的每个数据块的一个高速缓存标签。 每个数据处理器包括用于向系统控制器发送存储器事务请求的主接口。 系统控制器处理每个存储器事务，并为每个数据处理器维护一组重复的缓存标签（Dtags）。 最后，系统控制器包含用于激活交易以进行互连维修的事务执行电路。 交易执行电路管理来自数据处理器的存储器访问请求，并且包括用于在激活之前处理来自给定数据处理器的每个回写请求的无效电路，以确定与受害高速缓存行对应的Dtag索引是否无效。 此后，无效电路仅在Dtag索引无效时才激活写回请求，如果Dtag索引无效则取消写回请求。

公开(公告)号：US5655100A

公开(公告)日：1997-08-05

申请号：US414772

申请日：1995-03-31

申请人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

发明人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

IPC分类号： G06F12/08

CPC分类号： G06F12/0828 ,  G06F12/0822

摘要： A multiprocessor computer system has a multiplicity of sub-systems and a main memory coupled to a system controller. Some of the sub-systems are data processors, each having a respective cache memory that stores multiple blocks of data and a respective set of master cache tags (Etags), including one Etag for each data block stored by the cache memory. Each data processor includes an interface for sending memory transaction requests to the system controller and for receiving cache transaction requests from the system controller corresponding to memory transaction requests by other ones of the data processors. The system controller includes transaction activation logic for activating each said memory transaction request when it meets predefined activation criteria, and for blocking each said memory transaction request until the predefined activation criteria are met. An active transaction status table stores status data representing memory transaction requests that have been activated, including an address value for each activated transaction. The transaction activation logic includes comparator logic for comparing each memory transaction request with the active transaction status data for all activated memory transaction requests so as to detect whether activation of a particular memory transaction request would violate the predefined activation criteria. With certain exceptions concerning writeback transactions, an incoming transaction for accessing a data block that maps to the same cache line a pending, previously activated transaction, will be blocked until the pending transaction that maps to the same cache line is completed.

摘要翻译： 多处理器计算机系统具有多个子系统和耦合到系统控制器的主存储器。 一些子系统是数据处理器，每个数据处理器具有存储多个数据块的相应高速缓存存储器以及相应的主缓存标签集（Etag），包括由高速缓冲存储器存储的每个数据块的一个Etag。 每个数据处理器包括一个接口，用于向系统控制器发送存储器事务请求，并接收来自系统控制器的高速缓存事务请求，对应于其他数据处理器的存储器事务请求。 系统控制器包括事务激活逻辑，用于当其满足预定义的激活准则时激活每个所述存储器事务请求，并且用于阻止每个所述存储器事务请求直到满足预定义的激活标准。 活动事务状态表存储表示已激活的存储器事务请求的状态数据，包括每个激活的事务的地址值。 事务激活逻辑包括比较器逻辑，用于将每个存储器事务请求与所有激活的存储器事务请求的活动事务状态数据进行比较，以便检测特定存储器事务请求的激活是否违反预定义的激活标准。 对于回写事务有一些例外，用于访问映射到相同高速缓存行的未决事务，先前激活的事务的数据块的传入事务将被阻止，直到映射到同一高速缓存行的挂起事务完成。

公开(公告)号：US5905998A

公开(公告)日：1999-05-18

申请号：US858792

申请日：1997-05-19

申请人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

发明人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin Normoyle ,  Paul Loewenstein ,  Louis F. Coffin, III

IPC分类号： G06F12/08

CPC分类号： G06F12/0828 ,  G06F12/0822

摘要： A multiprocessor computer system has a multiplicity of sub-systems and a main memory coupled to a system controller. Some of the sub-systems are data processors, each having a respective cache memory that stores multiple blocks of data and a respective set of master cache tags (Etags), including one Etag for each data block stored by the cache memory. Each data processor includes an interface for sending memory transaction requests to the system controller and for receiving cache transaction requests from the system controller corresponding to memory transaction requests by other ones of the data processors. The system controller includes transaction activation logic for activating each said memory transaction request when it meets predefined activation criteria, and for blocking each said memory transaction request until the predefined activation criteria are met. An active transaction status table stores status data representing memory transaction requests that have been activated, including an address value for each activated transaction. The transaction activation logic includes comparator logic for comparing each memory transaction request with the active transaction status data for all activated memory transaction requests so as to detect whether activation of a particular memory transaction request would violate the predefined activation criteria. With certain exceptions concerning writeback transactions, an incoming transaction for accessing a data block that maps to the same cache line a pending, previously activated transaction, will be blocked until the pending transaction that maps to the same cache line is completed.

摘要翻译： 多处理器计算机系统具有多个子系统和耦合到系统控制器的主存储器。 一些子系统是数据处理器，每个数据处理器具有存储多个数据块的相应高速缓存存储器以及相应的主缓存标签集（Etag），包括由高速缓冲存储器存储的每个数据块的一个Etag。 每个数据处理器包括一个接口，用于向系统控制器发送存储器事务请求，并接收来自系统控制器的高速缓存事务请求，对应于其他数据处理器的存储器事务请求。 系统控制器包括事务激活逻辑，用于当其满足预定义的激活准则时激活每个所述存储器事务请求，并且用于阻止每个所述存储器事务请求直到满足预定义的激活标准。 活动事务状态表存储表示已激活的存储器事务请求的状态数据，包括每个激活的事务的地址值。 事务激活逻辑包括比较器逻辑，用于将每个存储器事务请求与所有激活的存储器事务请求的活动事务状态数据进行比较，以便检测特定存储器事务请求的激活是否违反预定义的激活标准。 对于回写事务有一些例外，用于访问映射到相同高速缓存行的未决事务，先前激活的事务的数据块的传入事务将被阻止，直到映射到同一高速缓存行的挂起事务完成。

公开(公告)号：US5907485A

公开(公告)日：1999-05-25

申请号：US414875

申请日：1995-03-31

申请人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin B. Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

发明人： William C. Van Loo ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  Kevin B. Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

IPC分类号： G06F9/46 ,  G06F13/24 ,  G05B15/00

CPC分类号： G06F9/546 ,  G06F13/24

摘要： This invention describes a link-by-link flow control method for packet-switched uniprocessor and multiprocessor computer systems that maximizes system resource utilization and throughput, and minimizes system latency. The computer system comprises one or more master interfaces, one or more slave interfaces, and an interconnect system controller which provides dedicated transaction request queues for each master interface and controls the forwarding of transactions to each slave interface. The master interface keeps track of the number of requests in the dedicated queue in the system controller, and the system controller keeps track of the number of requests in each slave interface queue. Both the master interface, and system controller know the maximum capacity of the queue immediately downstream from it, and does not issue more transaction requests than what the downstream queue can accommodate. An acknowledgment from the downstream queue indicates to the sender that there is space in it for another transaction. Thus no system resources are wasted trying to send a request to a queue that is already full.

摘要翻译： 本发明描述了一种用于分组交换单处理器和多处理器计算机系统的链路链路流控制方法，其使系统资源利用率和吞吐量最大化，并最小化系统等待时间。 计算机系统包括一个或多个主接口，一个或多个从接口和互连系统控制器，其为每个主接口提供专用事务请求队列，并且控制事务到每个从接口的转发。 主接口跟踪系统控制器中专用队列中的请求数，系统控制器跟踪每个从接口队列中的请求数。 主接口和系统控制器都知道其下游队列的最大容量，并且不会比下游队列可以容纳更多的事务请求。 来自下游队列的确认向发送方指示在其中存在另一个事务的空间。 因此，尝试将请求发送到已满的队列时，不会浪费任何系统资源。

公开(公告)号：US5692197A

公开(公告)日：1997-11-25

申请号：US414879

申请日：1995-03-31

申请人： Charles E. Narad ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin B. Normoyle ,  Louis F. Coffin, III ,  Leslie Kohn

发明人： Charles E. Narad ,  Zahir Ebrahim ,  Satyanarayana Nishtala ,  William C. Van Loo ,  Kevin B. Normoyle ,  Louis F. Coffin, III ,  Leslie Kohn

IPC分类号： G06F1/32 ,  G06F15/16 ,  G06F15/177

CPC分类号： G06F1/3209

摘要： A method and apparatus for actively managing the overall power consumption of a computer network which includes a plurality of computer systems interconnected to each other. In turn, each computer system has one or more modules. Each computer system of the computer network is capable of independently initiating a transition into a power-conserving mode, i.e., a "sleep" state, while keeping its network interface "alive" and fully operational. Subsequently, each computer system can independently transition back into fully operational state, i.e., an "awake" state, when triggered by either a deterministic or an asynchronous event. As a result, the sleep states of the computer systems are transparent to the computer network. Deterministic events are events triggered internally by a computer system, e.g., an internal timer waking the computer system up at midnight to perform housekeeping chores such as daily tape backups. Conversely, the source of asynchronous events are external in nature and include input/output (I/O) activity. The illusion of the entire network being always fully operational is possible because the system controllers, the interconnects and network interfaces of each computer system remain fully operational while selected modules and peripheral devices are powered down. As a result, each computer system is able to rapidly awake from sleep state in response to stimuli by powering down selected modules thereby accomplishing power conservation without requiring a static shut down of the computer network, i.e., without the overall performance and response of the computer network.

摘要翻译： 一种用于主动管理计算机网络的整体功耗的方法和装置，其包括彼此互连的多个计算机系统。 反过来，每个计算机系统具有一个或多个模块。 计算机网络的每个计算机系统能够独立地启动向省电模式转变，即“休眠”状态，同时保持其网络接口“活着”并且完全可操作。 随后，当由确定性或异步事件触发时，每个计算机系统可以独立地转换回完全操作状态，即“清醒”状态。 因此，计算机系统的睡眠状态对于计算机网络是透明的。 确定性事件是由计算机系统在内部触发的事件，例如内部定时器在午夜唤醒计算机系统以执行诸如日常磁带备份的家务杂务。 相反，异步事件的来源本质上是外部的，包括输入/​​输出（I / O）活动。 整个网络的错觉始终是完全可操作的，因为每个计算机系统的系统控制器，互连和网络接口在选定的模块和外围设备关闭电源时保持完全可操作。 因此，每个计算机系统能够通过断电所选择的模块来迅速地从睡眠状态唤醒，从而实现功率节省，而不需要静态关闭计算机网络，即没有计算机的整体性能和响应 网络。

公开(公告)号：US5737755A

公开(公告)日：1998-04-07

申请号：US797995

申请日：1997-02-12

申请人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

发明人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

IPC分类号： G06F12/08 ,  G06F13/00

CPC分类号： G06F12/0808 ,  G06F12/0817

摘要： A computer system is disclosed including a memory subsystem and a processor subsystem having an external cache and an external mechanism for invalidating cached datablocks in the processor subsystem and for reducing false invalidation operations. The processor subsystem issues a write invalidate message to the memory subsystem that specifies a datablock and that includes an invalidate advisory indication that indicates whether the datablock is present in the external cache. The invalidate advisory indication determines whether the memory subsystem returns an invalidate message to the processor subsystem for the write invalidate operation.

摘要翻译： 公开了一种计算机系统，其包括存储器子系统和具有外部高速缓存的处理器子系统和用于使处理器子系统中的高速缓存的数据块无效并用于减少假无效操作的外部机制。 处理器子系统向指定数据块的存储器子系统发出写入无效消息，并且包括指示数据块是否存在于外部高速缓存中的无效咨询指示。 无效咨询指示确定存储器子系统是否向处理器子系统返回无效消息以用于写入无效操作。

公开(公告)号：US5706463A

公开(公告)日：1998-01-06

申请号：US854418

申请日：1997-05-12

申请人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

发明人： Zahir Ebrahim ,  Satyanarayana Nishtala ,  William Van Loo ,  Kevin Normoyle ,  Leslie Kohn ,  Louis F. Coffin, III

IPC分类号： G06F12/08

CPC分类号： G06F12/0822 ,  G06F12/0815

摘要： A multi-processor computer system is disclosed that reduces the occurrences of invalidate and copyback operations through a memory interconnect by disabling a first write optimization of a cache coherency protocol for data that is not likely to be written by a requesting processor. Such data include read-only code segments. The code segments, including instructions and data, are shared among the multiple processors. The requesting processor generates a Read to Share Always request upon a cache miss of a read-only datablock, and generates a Read to Share request otherwise. The Read to Share Always request results in the datablock stored in cache memory being labeled as in a "shared" state, while the Read to Share request results in the datablock being labeled as in an "exclusive" state.

摘要翻译： 公开了一种多处理器计算机系统，其通过禁用用于不可能由请求处理器写入的数据的高速缓存一致性协议的第一写入优化来减少通过存储器互连的无效和复制操作的发生。 这样的数据包括只读代码段。 代码段（包括指令和数据）在多个处理器之间共享。 请求处理器在只读数据块的高速缓存未命中时生成“读取共享始终”请求，否则生成“读取共享”请求。 读共享始终请求将存储在高速缓冲存储器中的数据块中的结果标记为“共享”状态，而读共享请求导致数据块标记为“独占”状态。

公开(公告)号：US5987579A

公开(公告)日：1999-11-16

申请号：US825404

申请日：1997-03-27

申请人： Satyanarayana Nishtala ,  Zahir Ebrahim ,  William C. Van Loo ,  Raymond Ng ,  Louis F. Coffin, III

发明人： Satyanarayana Nishtala ,  Zahir Ebrahim ,  William C. Van Loo ,  Raymond Ng ,  Louis F. Coffin, III

IPC分类号： G06F13/16 ,  G06F12/08 ,  G06F12/00

CPC分类号： G06F12/0822 ,  G06F12/0884

摘要： In a computer system including a packet-switched bus, a method for requesting transactions such that memory accesses are initiated quickly. A master transmits a first portion of a transaction request packet having multiple portion. A memory controller receives the first portion of the transaction request, which includes a row address portion of a memory address. The memory controller initiates a memory access by applying a row address strobe signal to the row of the memory location in response to receiving the first portion of the request packet, and the master transmits any remaining portion of the transaction request. After the full memory address has been received, it is determined whether data stored at the memory location is to be read from a source other than the memory location. The memory controller aborts the memory access by inhibiting assertion of a column access strobe signal to the memory location if the data is to be read from a source other than the memory location.

摘要翻译： 在包括分组交换总线的计算机系统中，用于请求事务的方法使得快速启动存储器访问。 主设备发送具有多个部分的事务请求分组的第一部分。 存储器控制器接收事务请求的第一部分，其包括存储器地址的行地址部分。 响应于接收到请求分组的第一部分，存储器控制器通过将行地址选通信号施加到存储器位置的行来启动存储器访问，并且主机传输事务请求的任何剩余部分。 在接收到完整存储器地址之后，确定存储在存储器位置的数据是否要从存储器位置以外的源读取。 如果要从除存储器位置之外的源读取数据，则存储器控制器通过禁止对存储器位置的列存取选通信号的断言来中止存储器访问。