公开(公告)号：US07707359B2

公开(公告)日：2010-04-27

申请号：US11390896

申请日：2006-03-27

申请人： Wayne Mesard ,  Paul Caprioli

发明人： Wayne Mesard ,  Paul Caprioli

IPC分类号： G06F12/00

CPC分类号： G06F12/0862 ,  G06F9/30047 ,  G06F9/30072 ,  G06F9/3802 ,  G06F9/383 ,  G06F2212/6028

摘要： One embodiment of the present invention provides a system which facilitates selective prefetching based on resource availability. During operation, the system executes instructions in a processor. While executing the instructions, the system monitors the availability of one or more system resources and dynamically adjusts an availability indicator for each system resource based on the current availability of the system resource. Upon encountering a prefetch instruction which involves the system resource, the system checks the availability indicator. If the availability indicator indicates that the system resource is not sufficiently available, the system terminates the execution of the prefetch instruction, whereby terminating execution prevents prefetch instructions from overwhelming the system resource.

摘要翻译： 本发明的一个实施例提供一种基于资源可用性促进选择性预取的系统。 在操作期间，系统在处理器中执行指令。 在执行指令时，系统监视一个或多个系统资源的可用性，并根据系统资源的当前可用性动态调整每个系统资源的可用性指标。 在遇到涉及系统资源的预取指令时，系统检查可用性指标。 如果可用性指示符指示系统资源不够可用，则系统终止预取指令的执行，由此终止执行防止预取指令压倒系统资源。

公开(公告)号：US08875145B2

公开(公告)日：2014-10-28

申请号：US13161010

申请日：2011-06-15

申请人： Matthew Darcy Atterbury ,  H. Mark Bromley ,  Wayne Mesard ,  Arkadi Popov ,  Stephen Schmidt ,  Craig W. Stanfill ,  Joseph Skeffington Wholey, III

发明人： Matthew Darcy Atterbury ,  H. Mark Bromley ,  Wayne Mesard ,  Arkadi Popov ,  Stephen Schmidt ,  Craig W. Stanfill ,  Joseph Skeffington Wholey, III

IPC分类号： G06F9/46 ,  G06F9/45 ,  G06F9/445 ,  G06F9/44

CPC分类号： G06F9/44521 ,  G06F9/44536 ,  G06F9/4494

摘要： Processing data includes: receiving units of work that each include one or more work elements, and processing a first unit of work using a first compiled dataflow graph (160) loaded into a data processing system (100) in response to receiving the first unit of work. The processing includes: analysis to determine a characteristic of the first unit of work; identifying one or more compiled dataflow graphs from graphs stored in a data storage system (107) that include at least some that were compiled for processing a unit of work having the determined characteristic; loading one of the identified compiled dataflow graphs into the data processing system (100) as the first compiled dataflow graph (160); and generating one or more output work elements from at least one work element in the first unit of work.

摘要翻译： 处理数据包括：接收每个工作单元包括一个或多个工作单元，以及响应于接收到第一单元的第一单元而处理加载到数据处理系统（100）中的第一编译数据流图（160）来处理第一工作单元 工作。 处理包括：分析确定第一工作单元的特征; 从存储在数据存储系统（107）中的图形中识别一个或多个编译数据流图，所述图形包括至少一些被编译用于处理具有所确定的特征的工作单元的编译数据流图; 将所识别的编译数据流图中的一个加载到数据处理系统（100）中作为第一编译数据流图（160）; 以及从所述第一工作单元中的至少一个工作元件生成一个或多个输出工作元件。

公开(公告)号：US20110307897A1

公开(公告)日：2011-12-15

申请号：US13161010

申请日：2011-06-15

申请人： Matthew Darcy Atterbury ,  H. Mark Bromley ,  Wayne Mesard ,  Arkadi Popov ,  Stephen Schmidt ,  Craig W. Stanfill ,  Joseph Skeffington Wholey, III

发明人： Matthew Darcy Atterbury ,  H. Mark Bromley ,  Wayne Mesard ,  Arkadi Popov ,  Stephen Schmidt ,  Craig W. Stanfill ,  Joseph Skeffington Wholey, III

IPC分类号： G06F9/46

CPC分类号： G06F9/44521 ,  G06F9/44536 ,  G06F9/4494

摘要： Processing data includes: receiving units of work that each include one or more work elements, and processing a first unit of work using a first compiled dataflow graph (160) loaded into a data processing system (100) in response to receiving the first unit of work. The processing includes: analysis to determine a characteristic of the first unit of work; identifying one or more compiled dataflow graphs from graphs stored in a data storage system (107) that include at least some that were compiled for processing a unit of work having the determined characteristic; loading one of the identified compiled dataflow graphs into the data processing system (100) as the first compiled dataflow graph (160); and generating one or more output work elements from at least one work element in the first unit of work.

摘要翻译： 处理数据包括：接收工作单元，每个工作单元包括一个或多个工作元件，以及响应于接收到第一单元的第一单元来处理加载到数据处理系统（100）中的第一编译数据流图（160）来处理第一工作单元 工作。 处理包括：分析确定第一工作单元的特征; 从存储在数据存储系统（107）中的图形中识别一个或多个编译数据流图，所述图形包括至少一些被编译用于处理具有所确定的特征的工作单元的编译数据流图; 将所识别的编译数据流图中的一个加载到数据处理系统（100）中作为第一编译数据流图（160）; 以及从所述第一工作单元中的至少一个工作元件生成一个或多个输出工作元件。

公开(公告)号：US07395418B1

公开(公告)日：2008-07-01

申请号：US11234669

申请日：2005-09-22

申请人： Paul Caprioli ,  Wayne Mesard

发明人： Paul Caprioli ,  Wayne Mesard

IPC分类号： G06F9/44

CPC分类号： G06F9/467 ,  G06F9/3004 ,  G06F9/3005 ,  G06F9/30087 ,  G06F9/3009 ,  G06F9/30181 ,  G06F9/30189 ,  G06F9/3842 ,  G06F9/3851 ,  G06F9/3863 ,  G06F9/3885 ,  G06F9/526

摘要： A technique for improving the performance of a system that supports simultaneous multi-threading (SMT). When a first thread encounters a halt sequence, the system starts a transactional memory operation by generating a checkpoint and entering a transactional-execution mode. Next, the system loads from a mailbox address associated with the halt sequence. The system then stalls execution of the first thread, so that the first thread does not execute instructions within the halt sequence, thereby freeing up processor resources for other threads. To terminate the halt sequence, a second thread stores to the mailbox address, which causes a transactional-memory mechanism within the processor to detect an interference with the previous load from the mailbox address by the first thread and which causes the first thread to exit from the halt sequence. The system then continues executing instructions following the halt sequence.

摘要翻译： 一种用于提高支持同时多线程（SMT）的系统性能的技术。 当第一个线程遇到停止序列时，系统通过生成检查点并进入事务执行模式来启动事务内存操作。 接下来，系统从与停止序列相关联的邮箱地址加载。 然后，系统停止第一个线程的执行，使得第一个线程不执行停止序列中的指令，从而释放其他线程的处理器资源。 为了终止停止序列，第二个线程存储到邮箱地址，这导致处理器内的事务存储器机制检测到来自邮箱地址的先前负载与第一线程的干扰，并且导致第一线程退出 停止序列。 然后系统在停止序列之后继续执行指令。

公开(公告)号：US08065670B2

公开(公告)日：2011-11-22

申请号：US11542577

申请日：2006-10-03

申请人： Tycho G. Nightingale ,  Wayne Mesard

发明人： Tycho G. Nightingale ,  Wayne Mesard

IPC分类号： G06F9/45

CPC分类号： G06F9/3863 ,  G06F9/30087 ,  G06F9/30105 ,  G06F9/30116 ,  G06F9/30123 ,  G06F9/3834 ,  G06F9/3842

摘要： A system that reduces overly optimistic program execution. During operation, the system encounters a bounded-execution block while executing a program, wherein the bounded execution block includes a primary path and a secondary path. Next, the system executes the bounded execution block. After executing the bounded execution block, the system determines whether executing instructions on the primary path is preferable to executing instructions on the secondary path based on information gathered while executing the bounded-execution block. If not, the system dynamically modifies the instructions of the bounded-execution block so that during subsequent passes through the bounded-execution block, the instructions on the secondary path are executed instead of the instructions on the primary path.

摘要翻译： 一个减少过于乐观程序执行的系统。 在操作期间，系统在执行程序时遇到有界执行块，其中有界执行块包括主路径和次路径。 接下来，系统执行有界执行块。 在执行有界执行块之后，系统基于在执行有界执行块时收集的信息确定在主路径上执行指令是否优于执行辅路径上的指令。 如果没有，则系统动态修改有界执行块的指令，以便在随后的通过有界执行块期间，执行副路径上的指令而不是主路径上的指令。

公开(公告)号：US20080082804A1

公开(公告)日：2008-04-03

申请号：US11542577

申请日：2006-10-03

申请人： Tycho G. Nightingale ,  Wayne Mesard

发明人： Tycho G. Nightingale ,  Wayne Mesard

IPC分类号： G06F15/00

CPC分类号： G06F9/3863 ,  G06F9/30087 ,  G06F9/30105 ,  G06F9/30116 ,  G06F9/30123 ,  G06F9/3834 ,  G06F9/3842

摘要： A system that reduces overly optimistic program execution. During operation, the system encounters a bounded-execution block while executing a program, wherein the bounded execution block includes a primary path and a secondary path. Next, the system executes the bounded execution block. After executing the bounded execution block, the system determines whether executing instructions on the primary path is preferable to executing instructions on the secondary path based on information gathered while executing the bounded-execution block. If not, the system dynamically modifies the instructions of the bounded-execution block so that during subsequent passes through the bounded-execution block, the instructions on the secondary path are executed instead of the instructions on the primary path.

摘要翻译： 一个减少过于乐观程序执行的系统。 在操作期间，系统在执行程序时遇到有界执行块，其中有界执行块包括主路径和次路径。 接下来，系统执行有界执行块。 在执行有界执行块之后，系统基于在执行有界执行块时收集的信息确定在主路径上执行指令是否优于执行辅路径上的指令。 如果没有，则系统动态修改有界执行块的指令，以便在随后的通过有界执行块期间，执行副路径上的指令而不是主路径上的指令。

公开(公告)号：US20070136534A1

公开(公告)日：2007-06-14

申请号：US11390896

申请日：2006-03-27

申请人： Wayne Mesard ,  Paul Caprioli

发明人： Wayne Mesard ,  Paul Caprioli

IPC分类号： G06F12/00

CPC分类号： G06F12/0862 ,  G06F9/30047 ,  G06F9/30072 ,  G06F9/3802 ,  G06F9/383 ,  G06F2212/6028

摘要： One embodiment of the present invention provides a system which facilitates selective prefetching based on resource availability. During operation, the system executes instructions in a processor. While executing the instructions, the system monitors the availability of one or more system resources and dynamically adjusts an availability indicator for each system resource based on the current availability of the system resource. Upon encountering a prefetch instruction which involves the system resource, the system checks the availability indicator. If the availability indicator indicates that the system resource is not sufficiently available, the system terminates the execution of the prefetch instruction, whereby terminating execution prevents prefetch instructions from overwhelming the system resource.

摘要翻译： 本发明的一个实施例提供一种基于资源可用性促进选择性预取的系统。 在操作期间，系统在处理器中执行指令。 在执行指令时，系统监视一个或多个系统资源的可用性，并根据系统资源的当前可用性动态调整每个系统资源的可用性指标。 在遇到涉及系统资源的预取指令时，系统检查可用性指标。 如果可用性指示符指示系统资源不够可用，则系统终止预取指令的执行，由此终止执行防止预取指令压倒系统资源。