公开(公告)号：US08935510B2

公开(公告)日：2015-01-13

申请号：US12447513

申请日：2007-11-01

申请人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

发明人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

IPC分类号： G06F15/80 ,  G06F9/50 ,  H04L29/08 ,  G06F9/44

CPC分类号： G06F9/5077 ,  G06F9/4405 ,  H04L29/08144 ,  H04L67/34

摘要： For flexibly setting up an execution environment according to contents of processing to be executed while taking stability or a security level into consideration, the multiple processor system includes the execution environment main control unit 10 which determines CPU assignment at the time of deciding CPU assignment, the execution environment sub control unit 20 which controls starting, stopping and switching of an execution environment according to an instruction from the execution environment main control unit 10 to synchronize with the execution environment main control unit 10, and the execution environment management unit 30 which receives input of management information or reference refusal information of shared resources for each CPU 4 or each execution environment 100 to separate the execution environment main control unit 10 from the execution environment sub control units 20a through 20n, or the execution environment sub control units 20a through 20n from each other.

摘要翻译： 为了在考虑到稳定性或安全级别的同时根据要执行的处理的内容灵活地设置执行环境，多处理器系统包括确定CPU分配时的CPU分配的执行环境主控制单元10， 执行环境子控制单元20，其根据来自执行环境主控制单元10的指令来控制执行环境的启动，停止和切换，以与执行环境主控制单元10同步;以及执行环境管理单元30，其接收输入 对于每个CPU 4或每个执行环境100的共享资源的管理信息或参考拒绝信息，以将执行环境主控制单元10与执行环境子控制单元20a至20n或执行环境子控制单元20a至20n分离 彼此。

公开(公告)号：US20110209153A1

公开(公告)日：2011-08-25

申请号：US13063232

申请日：2009-08-20

申请人： Noriaki Suzuki ,  Junji Sakai

发明人： Noriaki Suzuki ,  Junji Sakai

IPC分类号： G06F9/46

CPC分类号： G06F9/5038 ,  G06F2209/5017 ,  G06F2209/506

摘要： A schedule decision method acquires dependencies of execution sequences required for a plurality of sub tasks into which a first task has been divided; generates a plurality of sub task structure candidates that satisfy said dependencies and for which a plurality of processing devices execute said plurality of sub tasks; generates a plurality of schedule candidates by further assigning at least one second task to each of said sub task structure candidates; computes an effective degree that represents effectiveness of executions of said first task and said second task for each of said plurality of schedule candidates; and decides a schedule candidate used for the executions of said first task and said second task from said plurality of schedule candidates based on said effective degrees.

摘要翻译： 时间表决定方法获取第一任务被划分到的多个子任务所需的执行序列的依赖关系; 生成满足所述依赖性的多个子任务结构候选，并且多个处理装置执行所述多个子任务; 通过对每个所述子任务结构候选进一步分配至少一个第二任务来生成多个调度候选; 计算表示对于所述多个日程表候选中的每一个的所述第一任务和所述第二任务的执行的有效性的有效程度; 并且基于所述有效度，从所述多个日程表候选中确定用于执行所述第一任务和所述第二任务的日程表候选。

公开(公告)号：US20100325329A1

公开(公告)日：2010-12-23

申请号：US12919636

申请日：2009-02-24

申请人： Junji Sakai

发明人： Junji Sakai

IPC分类号： G06F13/24 ,  G06F9/44

CPC分类号： G06F9/544 ,  G06F9/545

摘要： With a system in which a plurality of OSs run on a multi-core processor and which is based on a client-server approach where one OS performs device access on behalf of the other OSs, if a device is to be accessed from tasks on the plurality of OSs, there have been problems of a reduction in performance and an increase in design and manufacturing cost due to the necessity of providing proxy servers.In a multiprocessor system with a plurality of OSs 40, 50 running thereon, each of the plurality of OSs has a device driver 41, 51 which accesses devices for shared use among the OSs, wherein the device driver has at least either of a device interface part 45 or a task interface part 44, 54 which performs inter-OS communication at the OS kernel layer, and wherein the device interface part 45 accesses a device 14 to be operated by the device driver and the task interface part receives a device access request from a task running on each OS and returns a device access result to the task.

摘要翻译： 利用其中多个OS在多核处理器上运行并且基于客户机 - 服务器方法的系统，其中一个OS代表其他OS执行设备访问，如果要从设备上的任务访问设备 多个OS，由于需要提供代理服务器，存在性能下降和设计和制造成本增加的问题。 在其上运行多个OS40,50的多处理器系统中，多个OS中的每一个具有一个设备驱动器41,51，该驱动器访问OS之间共享使用的设备，其中该设备驱动器具有至少一个设备接口 部分45或任务接口部分44,54，其在OS内核层执行OS间通信，并且其中设备接口部分45访问要由设备驱动器操作的设备14，并且任务接口部分接收设备访问请求 从每个操作系统上运行的任务，并将设备访问结果返回给任务。

公开(公告)号：US20090235233A1

公开(公告)日：2009-09-17

申请号：US11921437

申请日：2006-05-08

申请人： Noriaki Suzuki ,  Junji Sakai

发明人： Noriaki Suzuki ,  Junji Sakai

IPC分类号： G06F11/36 ,  G06F9/44

CPC分类号： G06F11/366 ,  G06F11/3632

摘要： Upon receiving debugging program activation instructions sent from a communication port (1), debugging program activation instruction distribution units (61 and 71) distribute the received debugging program activation instructions to execution units designated by these activation instructions. Debugging program activation units (62 and 72) are provided for each execution unit (A and B) and, based on the activation instructions distributed by the activation instruction distribution units (61 and 71), activate debugging programs (63 and 73) on the execution units designated by these activation instructions.

摘要翻译： 调试程序激活指令分配单元（61和71）接收从通信端口（1）发送的调试程序激活指令时，将接收的调试程序激活指令分配给由这些激活指令指定的执行单元。 为每个执行单元（A和B）提供调试程序激活单元（62和72），并且基于由激活指令分配单元（61和71）分发的激活指令，激活调试程序（63和73） 由这些激活指令指定的执行单元。

公开(公告)号：US6113650A

公开(公告)日：2000-09-05

申请号：US108387

申请日：1998-07-01

申请人： Junji Sakai

发明人： Junji Sakai

IPC分类号： G06F15/16 ,  G06F9/45 ,  G06F15/80

CPC分类号： G06F8/4442 ,  G06F8/452

摘要： A compiler has optimization processing part which comprise a loop normalization processing part for normalizing a loop structure in an intermediate language program, a subscript expression analyzing part for analyzing the presence or not of non-aligned access in the normalized loop structure, an SIMD instruction converting part for modifying an intermediate code so to perform computing of the array elements by using an SIMD instruction sequence, and a non-aligned access processing part for recognizing parts which are not word-aligned access in the array elements on a main storage subjected to the SIMD computing and converting a part of the non-aligned access into a combination of wored-aligned access instructions and shift instructions with logical instructions.

摘要翻译： 编译器具有优化处理部分，其包括用于对中间语言程序中的循环结构进行归一化的循环归一化处理部分，用于分析归一化循环结构中不对准访问的存在与否的下标表达分析部分，SIMD指令转换 用于修改中间代码的部分，以便通过使用SIMD指令序列来执行阵列元素的计算;以及非对齐访问处理部分，用于识别经受所述主体存储器的主存储器上的数组元素中不是字对齐访问的部分 SIMD计算并将一部分非对准访问转换为具有逻辑指令的错位对齐访问指令和移位指令的组合。

公开(公告)号：US4243420A

公开(公告)日：1981-01-06

申请号：US30924

申请日：1979-04-17

申请人： Junji Sakai ,  Syogo Morimoto ,  Takashi Shimaguchi

发明人： Junji Sakai ,  Syogo Morimoto ,  Takashi Shimaguchi

IPC分类号： B22C1/08 ,  B22C1/18 ,  B22C1/20

CPC分类号： B22C1/205

摘要： Particulate material for forming molds produced by mixing particulate refractory material with one material selected from the group consisting of colloidal silica, colloidal alumina, colloidal zirconia and ethyl silicate, drying the mixture and allowing same to set, and crushing the dried mixture into particulate form again. The particulate material includes refractory particles provided with a coat of silica or alumina or zirconia on the surface and increases the strength and surface precision of a mold.

摘要翻译： 通过将颗粒状耐火材料与选自胶体二氧化硅，胶体氧化铝，胶体氧化锆和硅酸乙酯的一种材料混合而制成的模具的颗粒材料，干燥混合物并使其相同，并将干燥的混合物再次粉碎成颗粒形式 。 颗粒材料包括在表面上具有二氧化硅或氧化铝或氧化锆涂层的耐火材料颗粒，并提高模具的强度和表面精度。

公开(公告)号：US08881158B2

公开(公告)日：2014-11-04

申请号：US13063232

申请日：2009-08-20

申请人： Noriaki Suzuki ,  Junji Sakai

发明人： Noriaki Suzuki ,  Junji Sakai

IPC分类号： G06F9/46 ,  G06F9/50

CPC分类号： G06F9/5038 ,  G06F2209/5017 ,  G06F2209/506

摘要： A schedule decision method acquires dependencies of execution sequences required for a plurality of sub tasks into which a first task has been divided; generates a plurality of sub task structure candidates that satisfy said dependencies and for which a plurality of processing devices execute said plurality of sub tasks; generates a plurality of schedule candidates by further assigning at least one second task to each of said sub task structure candidates; computes an effective degree that represents effectiveness of executions of said first task and said second task for each of said plurality of schedule candidates; and decides a schedule candidate used for the executions of said first task and said second task from said plurality of schedule candidates based on said effective degrees.

摘要翻译： 时间表决定方法获取第一任务被划分到的多个子任务所需的执行序列的依赖关系; 生成满足所述依赖性的多个子任务结构候选，并且多个处理装置执行所述多个子任务; 通过对每个所述子任务结构候选进一步分配至少一个第二任务来生成多个调度候选; 计算表示对于所述多个日程表候选中的每一个的所述第一任务和所述第二任务的执行的有效性的有效程度; 并且基于所述有效度，从所述多个日程表候选中确定用于执行所述第一任务和所述第二任务的日程表候选。

公开(公告)号：US08799753B2

公开(公告)日：2014-08-05

申请号：US12863934

申请日：2009-02-03

申请人： Noriaki Suzuki ,  Junji Sakai

发明人： Noriaki Suzuki ,  Junji Sakai

IPC分类号： G06F7/02 ,  G06F11/00 ,  G06F11/36

CPC分类号： G06F11/3636 ,  G06F11/3648

摘要： There is provided a trace/failure observation system which is capable of comprehensive collection of information that is needed for checking a desired operation in a system or the like where the amount of information to be observed is large, and which allows easy analysis of the desired operation. The system includes, in a system LSI to be subjected to trace/failure observation: an event detecting means for observing behavior of a portion to be observed; a first data reducing means for performing observation data reduction processing so that observation data from the event detecting means has an amount of information processable to a second data reducing means; and the second data reducing means for performing one or more steps of observation data reduction processing.

摘要翻译： 提供了一种跟踪/故障观察系统，其能够综合地收集在要观察的信息量大的系统等中检查所需操作所需的信息，并且允许容易地分析所需的 操作。 该系统包括在要进行跟踪/故障观察的系统LSI中：事件检测装置，用于观察待观察部分的行为; 第一数据减少装置，用于执行观察数据缩减处理，使得来自事件检测装置的观察数据具有可处理到第二数据减少装置的信息量; 以及用于执行观察数据缩减处理的一个或多个步骤的第二数据减少装置。

公开(公告)号：US20100100706A1

公开(公告)日：2010-04-22

申请号：US12447513

申请日：2007-11-01

申请人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

发明人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

IPC分类号： G06F15/80

CPC分类号： G06F9/5077 ,  G06F9/4405 ,  H04L29/08144 ,  H04L67/34

摘要： For flexibly setting up an execution environment according to contents of processing to be executed while taking stability or a security level into consideration, the multiple processor system includes the execution environment main control unit 10 which determines CPU assignment at the time of deciding CPU assignment, the execution environment sub control unit 20 which controls starting, stopping and switching of an execution environment according to an instruction from the execution environment main control unit 10 to synchronize with the execution environment main control unit 10, and the execution environment management unit 30 which receives input of management information or reference refusal information of shared resources for each CPU 4 or each execution environment 100 to separate the execution environment main control unit 10 from the execution environment sub control units 20a through 20n, or the execution environment sub control units 20aA through 20n from each other.

摘要翻译： 为了在考虑到稳定性或安全级别的同时根据要执行的处理的内容灵活地设置执行环境，多处理器系统包括确定CPU分配时的CPU分配的执行环境主控制单元10， 执行环境子控制单元20，其根据来自执行环境主控制单元10的指令控制执行环境的启动，停止和切换，以与执行环境主控制单元10同步;以及执行环境管理单元30，其接收输入 对于每个CPU 4或每个执行环境100的共享资源的管理信息或参考拒绝信息，以将执行环境主控制单元10与执行环境子控制单元20a至20n或执行环境子控制单元20aA至20n分离 彼此。

公开(公告)号：US20050229184A1

公开(公告)日：2005-10-13

申请号：US11080730

申请日：2005-03-16

申请人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

发明人： Hiroaki Inoue ,  Junji Sakai ,  Tsuyoshi Abe ,  Masato Edahiro

IPC分类号： G06F9/46 ,  G06F3/00 ,  G06F15/163

CPC分类号： G06F9/544

摘要： On a parallel processing system by an OS for single processors which operates, on a multiprocessor, an OS for single processors and an existing application to realize parallel processing by the multiprocessor with respect to the application, each processor includes a communication proxy unit which transfers data between tasks spreading over the processors by proxy and the communication proxy unit on a processor in which a task on a transmission side operates holds information about an address, on a processor, of a task on a reception side to receive data transferred from the task on the transmission side as proxy for the task on the reception side.

摘要翻译： 在用于单处理器的操作系统的并行处理系统中，在多处理器上操作用于单个处理器的OS和现有应用以实现多处理器相对于应用的并行处理，每个处理器包括传送数据的通信代理单元 在处理器之间通过代理扩展的任务和处理器之间的通信代理单元，其中传输侧的任务在其上操作，在处理器上保存关于接收侧的任务的地址的信息，以接收从任务传送的数据 发送方作为接收方的任务的代理。