公开(公告)号：US06636949B2

公开(公告)日：2003-10-21

申请号：US10042008

申请日：2002-01-07

申请人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Robert J. Stets ,  Mosur K. Ravishankar

发明人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Robert J. Stets ,  Mosur K. Ravishankar

IPC分类号： G06F1200

CPC分类号： G06F12/0826 ,  G06F12/0828 ,  G06F2212/621 ,  Y10S707/99938 ,  Y10S707/99952

摘要： In a chip multiprocessor system, the coherence protocol is split into two cooperating protocols implemented by different hardware modules. One protocol is responsible for cache coherence management within the chip, and is implemented by a second-level cache controller. The other protocol is responsible for cache coherence management across chip multiprocessor nodes, and is implemented by separate cache coherence protocol engines. The cache controller and the protocol engine within each node communicate and synchronize memory transactions involving multiple nodes to maintain cache coherence within and across the nodes. The present invention addresses race conditions that arise during this communication and synchronization.

公开(公告)号：US06925537B2

公开(公告)日：2005-08-02

申请号：US10698130

申请日：2003-10-31

申请人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr.

发明人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr.

IPC分类号： G06F12/08 ,  G06F12/00

CPC分类号： G06F12/0817 ,  G06F2212/621

摘要： A computer system has a plurality of processor nodes and a plurality of input/output nodes. Each processor node includes a multiplicity of processor cores, an interface to a local memory system and a protocol engine implementing a predefined cache coherence protocol. Each processor core has an associated memory cache for caching memory lines of information. Each input/output node includes no processor cores, an input/output interface for interfacing to an input/output bus or input/output device, a memory cache for caching memory lines of information and an interface to a local memory subsystem. The local memory subsystem of each processor node and input/output node stores a multiplicity of memory lines of information. The protocol engine of each processor node and input/output node implements the same predefined cache coherence protocol.

摘要翻译： 计算机系统具有多个处理器节点和多个输入/输出节点。 每个处理器节点包括多个处理器核心，到本地存储器系统的接口和实现预定义高速缓存一致性协议的协议引擎。 每个处理器核心具有用于缓存存储器信息线的相关联的存储器缓存。 每个输入/输出节点不包括处理器内核，用于与输入/输出总线或输入/输出设备进行接口的输入/输出接口，用于缓存存储器信息线的存储器缓存和到本地存储器子系统的接口。 每个处理器节点和输入/输出节点的本地存储器子系统存储多个存储器信息线。 每个处理器节点和输入/输出节点的协议引擎实现相同的预定义缓存一致性协议。

公开(公告)号：US06751710B2

公开(公告)日：2004-06-15

申请号：US09878982

申请日：2001-06-11

申请人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr. ,  Daniel J. Scales

发明人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr. ,  Daniel J. Scales

IPC分类号： G06F1200

CPC分类号： G06F12/0826 ,  G06F12/0828 ,  G06F2212/621

摘要： The present invention relates generally to multiprocessor computer system, and particularly to a multiprocessor system designed to be highly scalable, using efficient cache coherence logic and methodologies. More specifically, the present invention is a system and method including a plurality of processor nodes configured to execute a cache coherence protocol that avoids the use of negative acknowledgment messages (NAKs) and ordering requirements on the underlying transaction-message interconnect/network and services most 3-hop transactions with only a single visit to the home node.

摘要翻译： 本发明一般涉及多处理器计算机系统，特别涉及使用有效的高速缓存一致性逻辑和方法来设计为高度可扩展的多处理器系统。 更具体地说，本发明是一种包括多个处理器节点的系统和方法，所述多个处理器节点被配置为执行避免使用否定确认消息（NAK）的高速缓存一致性协议以及对底层事务 - 消息互联/网络和服务的排序要求 只有一次访问家庭节点的3跳交易。

公开(公告)号：US06622217B2

公开(公告)日：2003-09-16

申请号：US09878983

申请日：2001-06-11

申请人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J Stets, Jr. ,  Andreas Nowatzyk

发明人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J Stets, Jr. ,  Andreas Nowatzyk

IPC分类号： G06F1200

CPC分类号： G06F12/0828 ,  G06F2212/621

摘要： The present invention relates generally to a protocol engine for use in a multiprocessor computer system. The protocol engine, which implements a cache coherence protocol, includes a clock signal generator for generating signals denoting interleaved even clock periods and odd clock periods, a memory transaction state array for storing entries, each denoting the state of a respective memory transaction, and processing logic. The memory transactions are divided into even and odd transactions whose states are stored in distinct sets of entries in the memory transaction state array. The processing logic has interleaving circuitry for processing during even clock periods the even memory transactions and for processing during odd clock periods the odd memory transactions.

摘要翻译： 本发明一般涉及在多处理器计算机系统中使用的协议引擎。 实现高速缓存一致性协议的协议引擎包​​括时钟信号发生器，用于产生表示交织的偶数时钟周期和奇数时钟周期的信号，存储事务状态阵列，用于存储条目，每个表示各自的存储器事务的状态，以及处理 逻辑。 存储器事务被分为偶数和奇数事务，其状态存储在存储器事务状态数组中的不同的条目集合中。 处理逻辑具有交织电路，用于在甚至时钟周期期间处理偶数存储器事务并且用于在奇数时钟周期期间处理奇数存储器事务。

公开(公告)号：US07389389B2

公开(公告)日：2008-06-17

申请号：US10672960

申请日：2003-09-26

申请人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Robert J. Stets, Jr. ,  Mosur K. Ravishankar ,  Andreas Nowatzyk

发明人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Robert J. Stets, Jr. ,  Mosur K. Ravishankar ,  Andreas Nowatzyk

IPC分类号： G06F12/00 ,  G06F13/00 ,  G06F13/28 ,  G06F7/00 ,  G06F15/16

CPC分类号： G06F12/0826 ,  G06F2212/621 ,  Y10S707/99952

摘要： A protocol engine is for use in each node of a computer system having a plurality of nodes. Each node includes an interface to a local memory subsystem that stores memory lines of information, a directory, and a memory cache. The directory includes an entry associated with a memory line of information stored in the local memory subsystem. The directory entry includes an identification field for identifying sharer nodes that potentially cache the memory line of information. The identification field has a plurality of bits at associated positions within the identification field. Each respective bit of the identification field is associated with one or more nodes. The protocol engine furthermore sets each bit in the identification field for which the memory line is cached in at least one of the associated nodes. In response to a request for exclusive ownership of a memory line, the protocol engine sends an initial invalidation request to no more than a first predefined number of the nodes associated with set bits in the identification field of the directory entry associated with the memory line.

摘要翻译： 协议引擎用于具有多个节点的计算机系统的每个节点。 每个节点包括存储信息存储线，目录和存储器高速缓存的本地存储器子系统的接口。 目录包括与存储在本地存储器子系统中的信息的存储器线相关联的条目。 目录条目包括用于识别可能缓存信息的存储器线的共享者节点的标识字段。 识别字段在识别字段内的关联位置具有多个位。 识别字段的每个相应位与一个或多个节点相关联。 协议引擎还将存储线被高速缓存的标识字段中的每一位设置在相关联的节点中的至少一个中。 响应于对存储器线路的独占所有权的请求，协议引擎将初始无效请求发送到与存储器线相关联的目录条目的标识字段中与设置位相关联的不超过第一预定数量的节点。

公开(公告)号：US06697919B2

公开(公告)日：2004-02-24

申请号：US09878985

申请日：2001-06-11

申请人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Robert J. Stets, Jr. ,  Mosur K. Ravishankar ,  Andreas Nowatzyk

发明人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Robert J. Stets, Jr. ,  Mosur K. Ravishankar ,  Andreas Nowatzyk

IPC分类号： G06F1200

CPC分类号： G06F12/0826 ,  G06F2212/621 ,  Y10S707/99952

摘要： A protocol engine is for use in each node of a computer system having a plurality of nodes. Each node includes an interface to a local memory subsystem that stores memory lines of information, a directory, and a memory cache. The directory includes an entry associated with a memory line of information stored in the local memory subsystem. The directory entry includes an identification field for identifying sharer nodes that potentially cache the memory line of information. The identification field has a plurality of bits at associated positions within the identification field. Each respective bit of the identification field is associated with one or more nodes. The protocol engine furthermore sets each bit in the identification field for which the memory line is cached in at least one of the associated nodes. In response to a request for exclusive ownership of a memory line, the protocol engine sends an initial invalidation request to no more than a first predefined number of the nodes associated with set bits in the identification field of the directory entry associated with the memory line.

公开(公告)号：US06675265B2

公开(公告)日：2004-01-06

申请号：US09878984

申请日：2001-06-11

申请人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr.

发明人： Luiz A. Barroso ,  Kourosh Gharachorloo ,  Andreas Nowatzyk ,  Mosur K. Ravishankar ,  Robert J. Stets, Jr.

IPC分类号： G06F1200

CPC分类号： G06F12/0828 ,  G06F12/0826 ,  G06F2212/621

摘要： A computer system has a plurality of processor nodes and a plurality of input/output nodes. Each processor node includes a multiplicity of processor cores, an interface to a local memory system and a protocol engine implementing a predefined cache coherence protocol. Each processor core has an associated memory cache for caching memory lines of information. Each input/output node includes no processor cores, an input/output interface for interfacing to an input/output bus or input/output device, a memory cache for caching memory lines of information and an interface to a local memory subsystem. The local memory subsystem of each processor node and input/output node stores a multiplicity of memory lines of information. The protocol engine of each processor node and input/output node implements the same predefined cache coherence protocol.

公开(公告)号：US06622218B2

公开(公告)日：2003-09-16

申请号：US10042029

申请日：2002-01-07

申请人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets

发明人： Kourosh Gharachorloo ,  Luiz A. Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets

IPC分类号： G06F1200

CPC分类号： G06F12/0826 ,  G06F12/0828 ,  G06F2212/621

摘要： The present invention relates generally to a protocol engine for use in a multiprocessor computer system. The protocol engine, which implements a cache coherence protocol, includes a clock signal generator for generating signals denoting interleaved even clock periods and odd clock periods, a memory transaction state array for storing entries, each denoting the state of a respective memory transaction, and processing logic. The memory transactions are divided into even and odd transactions whose states are stored in distinct sets of entries in the memory transaction state array. The processing logic has interleaving circuitry for processing during even clock periods the even memory transactions and for processing during odd clock periods the odd memory transactions. Moreover, the protocol engine is configured to transition from one memory transaction to another in a minimum number of clock cycles. This design improves efficiency for processing commercial workloads, such as on-line transaction processing (OLTP) by taking certain steps in parallel.

公开(公告)号：US06748498B2

公开(公告)日：2004-06-08

申请号：US10042053

申请日：2002-01-07

申请人： Kourosh Gharachorloo ,  Luiz Andre Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets ,  Daniel J. Scales

发明人： Kourosh Gharachorloo ,  Luiz Andre Barroso ,  Mosur K. Ravishankar ,  Robert J. Stets ,  Daniel J. Scales

IPC分类号： G06F1200

CPC分类号： G06F12/0826 ,  G06F12/0828 ,  G06F2212/621 ,  Y10S707/99952

摘要： A system including a plurality of processor nodes is configured to execute a cache coherence protocol that avoids the use of negative acknowledgments and ordering requirements on the underlying transaction-message interconnect/network, and implements store-conditional memory transactions. A store-conditional memory transaction succeeds if a directory tracking the state of a memory line of information unambiguously indicates that the requesting node is the exclusive owner of the memory line, if the directory ambiguously indicates that the requesting node is sharing the memory line and the requesting node is in fact sharing the memory line, or if the directory unambiguously indicates that the requesting node is sharing the memory line. The store-conditional memory transaction fails if the directory unambiguously indicates that the requesting node is not sharing the memory line, or if the directory ambiguously indicates that the requesting node may be sharing the memory line and the requesting node is in fact not sharing the memory line.

摘要翻译： 包括多个处理器节点的系统被配置为执行高速缓存一致性协议，其避免对底层事务消息互连/网络使用否定确认和排序要求，并且实现存储条件存储器事务。 如果跟踪存储器线的状态的目录明确地指示请求节点是存储器线的专有所有者，则存储条件存储器事务成功，如果目录模糊地指示请求节点正在共享存储器线，并且 请求节点实际上共享内存线，或者如果目录明确地指示请求节点正在共享存储器线。 如果目录明确地指示请求节点不共享存储器线路，或者如果目录模糊地指示请求节点可能共享存储器线且请求节点实际上不共享存储器，则存储条件存储器事务将失败 线。

公开(公告)号：US08744856B1

公开(公告)日：2014-06-03

申请号：US13401483

申请日：2012-02-21

申请人： Mosur K. Ravishankar

发明人： Mosur K. Ravishankar

IPC分类号： G10L21/00 ,  G10L15/00 ,  G10L15/04 ,  G10L21/06 ,  G09B19/04 ,  G10L25/60

CPC分类号： G10L25/60 ,  G09B19/04

摘要： A computer implemented method, system and computer program product for evaluating pronunciation. Known phonemes are stored in a computer memory. A spoken utterance corresponding to a target utterance, comprised of a sequence of target phonemes, is received and stored in a computer memory. The spoken utterance is segmented into a sequence of spoken phonemes, each corresponding to a target phoneme. For each spoken phoneme, a relative posterior probability is calculated that the spoken phoneme is the corresponding target phoneme. If the calculated probability is greater than a first threshold, an indication that the target phoneme was pronounced correctly is output; if less than a first threshold, an indication that the target phoneme was pronounced incorrectly is output. If the probability is less than a first threshold and greater than a second threshold, an indication that pronunciation of the target phoneme was acceptable is output.

摘要翻译： 一种用于评估发音的计算机实现方法，系统和计算机程序产品。 已知的音素被存储在计算机存储器中。 由目标音素序列组成的与目标语音对应的语音话语被接收并存储在计算机存储器中。 讲话的话语被分割成一系列的语音音素，每个对应的是一个目标音素。 对于每个口语音素，计算相对后验概率，即口语音素是相应的目标音素。 如果计算出的概率大于第一阈值，则输出目标音素被正确发音的指示; 如果小于第一阈值，则输出目标音素发音不正确的指示。 如果概率小于第一阈值且大于第二阈值，则输出目标音素的发音是可接受的指示。