专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明申请

US20050125581A1 Method of resource arbitration 失效
标题翻译：资源仲裁方法
公开(公告)号：US20050125581A1
公开(公告)日：2005-06-09
申请号：US10730952
申请日：2003-12-09
申请人： Jeffrey Brown , Scott Clark , Charles Johns , Takeshi Yamazaki
发明人： Jeffrey Brown , Scott Clark , Charles Johns , Takeshi Yamazaki
IPC分类号： G06F13/14 , G06F13/362
CPC分类号： G06F13/3625
摘要： An improved method and apparatus for resource arbitration. Four priority classes, managed high (MH), managed low (ML), opportunistic high (OH) and opportunistic low (OL), are defined. A priority class is assigned to each resource access request. An access request concentrator (ARC) is created for each resource, through which the resource is accessed. An access request is chosen at each ARC using the priority order MH, ML, OH, and OL, in decreasing order of priority. If OH priority class resource access requests are locked out, the priority order is temporarily changed to OH, OL, MH, and ML, in decreasing order of priority. If OL priority class resource access requests are locked out, the priority order is temporarily changed to MH, OL, OH, and ML, in decreasing order of priority.
摘要翻译：一种改进的资源仲裁方法和装置。定义了四个优先级，管理高（MH），管理低（ML），机会高（OH）和机会主义低（OL）。优先级分配给每个资源访问请求。为每个资源创建访问请求集中器（ARC），通过该资源访问资源。在优先级顺序为MH，ML，OH和OL的每个ARC中选择访问请求。如果OH优先级资源访问请求被锁定，优先级顺序将按照优先级的降序暂时更改为OH，OL，MH和ML。如果OL优先级资源访问请求被锁定，优先级顺序将按照优先级的降序临时更改为MH，OL，OH和ML。

82. 发明申请

US20050120254A1 Power management for processing modules 有权
标题翻译：处理模块的电源管理
公开(公告)号：US20050120254A1
公开(公告)日：2005-06-02
申请号：US10959700
申请日：2004-10-05
申请人： Masakazu Suzuoki , Takeshi Yamazaki
发明人： Masakazu Suzuoki , Takeshi Yamazaki
IPC分类号： G06F1/26 , G06F12/00
CPC分类号： G06F1/206 , G06F1/3203 , G06F1/3243 , G06F9/30145 , G06F9/30167 , Y02D10/152 , Y02D10/16
摘要： A processing element (PE) includes a processing unit (PU) and a number of attached processing units (APUs). The instruction set of each APU is divided a priori into a number of types, each type associated with a different amount of heat generation. Each APU keeps track of the amount of each type of instruction executed over a time period,—the power information,—and provides this power information to the PU. The PU then performs power management as a function of the provided power information from each APU,—such as directing a particular APU to enter an idle state to reduce power consumption.
摘要翻译：处理单元（PE）包括处理单元（PU）和多个附加处理单元（APU）。每个APU的指令集被预先划分成多种类型，每种类型与不同的发热量相关联。每个APU跟踪在一段时间内执行的每种类型的指令的数量 - 功率信息，并将该功率信息提供给PU。然后，PU根据来自每个APU的所提供的功率信息执行功率管理，例如指示特定APU进入空闲状态以降低功耗。

83. 发明申请

US20050081209A1 System and method for data synchronization for a computer architecture for broadband networks 有权
标题翻译：宽带网络计算机架构的数据同步系统和方法
公开(公告)号：US20050081209A1
公开(公告)日：2005-04-14
申请号：US10967433
申请日：2004-10-18
申请人： Masakazu Suzuoki , Takeshi Yamazaki
发明人： Masakazu Suzuoki , Takeshi Yamazaki
IPC分类号： G06F12/14 , G06F15/16 , G06F15/80 , G06F21/24 , H04L29/06 , G06F9/46
CPC分类号： G06F12/1466 , H04L69/12
摘要： A computer architecture and programming model for high speed processing over broadband networks are provided. The architecture employs a consistent modular structure, a common computing module and uniform software cells. The common computing module includes a control processor, a plurality of processing units, a plurality of local memories from which the processing units process programs, a direct memory access controller and a shared main memory. A synchronized system and method for the coordinated reading and writing of data to and from the shared main memory by the processing units also are provided. A processing system for processing computer tasks is also provided. A first processor is of a first processor type and a number of second processors are of a second processor type. One of the second processors manages process scheduling of computing tasks by providing tasks to at least one of the first and second processors.
摘要翻译：提供了一种用于宽带网络高速处理的计算机体系结构和编程模型。该架构采用一致的模块化结构，通用的计算模块和统一的软件单元。公共计算模块包括控制处理器，多个处理单元，处理单元处理程序的多个本地存储器，直接存储器存取控制器和共享主存储器。还提供了一种用于由处理单元协调地读取和从共享主存储器写入数据的同步系统和方法。还提供了一种用于处理计算机任务的处理系统。第一处理器是第一处理器类型，并且多个第二处理器是第二处理器类型。第二处理器之一通过向第一和第二处理器中的至少一个提供任务来管理计算任务的进程调度。

84. 发明授权

US06549676B1 Encoding device 失效
标题翻译：编码设备
公开(公告)号：US06549676B1
公开(公告)日：2003-04-15
申请号：US09412432
申请日：1999-10-05
申请人： Tadayoshi Nakayama , Hiroshi Kajiwara , Takeshi Yamazaki
发明人： Tadayoshi Nakayama , Hiroshi Kajiwara , Takeshi Yamazaki
IPC分类号： G06K936
CPC分类号： G06T9/004
摘要： The objective of the present invention is to perform fast variable-length coding that is applied for lossless compression and encoding. To achieve this objective, an encoding device comprises a unit for determining, from a plurality of states, states of peripheral pixels of an object pixel to be encoded, a unit for producing a predicted value of the object pixel based on the peripheral pixels, a memory used for storing a k parameter (k≦0) for each of the plurality of states, a unit for encoding a prediction difference between the value of the object pixel and a predicted value to variable-length code having a code length that is obtained by using the prediction difference and the k parameter that is stored in the memory and corresponds to the state determined by the state determination unit and a unit for, after variable-length encoding is performed for the object pixel, updating in advance the k parameter in order to perform variable-length encoding for another pixel that has the same state as the state determined by the state determination unit, and for writing the k parameter to the memory.
摘要翻译：本发明的目的是执行用于无损压缩和编码的快速可变长度编码。为了实现该目的，编码装置包括用于从多个状态确定要编码的对象像素的周边像素的状态的单元，用于基于周边像素产生对象像素的预测值的单元，用于存储多个状态中的每一个的ak参数（k <= 0）的存储器，用于将对象像素的值与预测值之间的预测差编码为具有获得的代码长度的可变长度代码的单元通过使用存储在存储器中的预测差和k参数，并且对应于由状态确定单元确定的状态，并且在针对对象像素执行可变长度编码之后的单元，预先更新k参数为与由状态判定单元确定的状态具有相同状态的另一像素执行可变长度编码，并将k参数写入存储器。

85. 发明授权

US06546129B1 Image processing apparatus, method, and medium for adding identification information 失效
标题翻译：图像处理装置，方法和用于添加识别信息的介质
公开(公告)号：US06546129B1
公开(公告)日：2003-04-08
申请号：US08963984
申请日：1997-11-04
申请人： Takatoshi Ohta , Ryuichi Arai , Munehiko Ohta , Hiroaki Sugiura , Toshihiro Nakazawa , Takeshi Yamazaki
发明人： Takatoshi Ohta , Ryuichi Arai , Munehiko Ohta , Hiroaki Sugiura , Toshihiro Nakazawa , Takeshi Yamazaki
IPC分类号： G06K900
CPC分类号： H04N1/00867 , G07D7/12 , G07D7/20 , H04N1/0087 , H04N2201/3205 , H04N2201/327
摘要： In case of managing image data among plural image processing apparatuses, an object of the present invention is to suppress or restrain, as much as possible, that the image data is illegally or unfairly used. In order to achieve the object, e.g., it is provided an image processing apparatus which is connected to an external apparatus being an output destination of the image data, the image processing apparatus comprises an input means for inputting the image data representing an image, an addition means for adding additional information capable of specifying the external apparatus to the image data inputted by the input means, in a state that the additional information is difficult to be perceived by human eyes, and an output means for outputting the image data to which the additional information was added by the addition means, to the external apparatus.
摘要翻译：在多个图像处理装置中管理图像数据的情况下，本发明的目的是尽可能地抑制或限制图像数据被非法或不公平地使用。为了实现该目的，例如，提供了连接到作为图像数据的输出目的地的外部设备的图像处理装置，图像处理装置包括用于输入表示图像的图像数据的输入装置，附加装置，用于在附加信息难以被人眼察觉的状态下，将能够指定外部装置的附加信息添加到由输入装置输入的图像数据;以及输出装置，用于输出图像数据，通过添加装置将附加信息添加到外部设备。

86. 发明授权

US6054793A Piezoelectric resonator method for adjusting frequency of piezoelectric resonator and communication apparatus including piezoelectric resonator 失效
标题翻译：用于调节压电谐振器的频率的压电谐振器和包括压电谐振器的通信装置
公开(公告)号：US6054793A
公开(公告)日：2000-04-25
申请号：US159713
申请日：1998-09-24
申请人： Yutaka Kawai , Takeshi Yamazaki
发明人： Yutaka Kawai , Takeshi Yamazaki
IPC分类号： H01L41/08 , H01L41/083 , H03H20060101 , H03H3/04 , H03H9/00 , H03H9/02 , H03H9/10 , H03H9/15 , H03H9/17 , H03H9/205 , H03H9/58 , H04B1/26
CPC分类号： H03H9/178 , H03H3/04 , H03H9/1014
摘要： A base member of a piezoelectric resonator includes a laminated body having a plurality of piezoelectric layers which are alternately polarized in opposite directions along the longitudinal direction of the base member and inner electrodes provided between the piezoelectric layers. On a first side surface of the base member, each of two external electrodes is arranged so as to be connected to one of two groups of alternate inner electrodes. Cut portions for adjusting a frequency of the piezoelectric resonator to a higher frequency are respectively formed at edge portions of the base member at opposite ends in the longitudinal direction of a second side surface opposite from the first side surface of the base member.
摘要翻译：压电谐振器的基座部件包括具有多个压电层的叠层体，所述多个压电层沿着基底部件的长度方向相反的方向交替极化，而内部电极设置在压电层之间。在基体的第一侧表面上，两个外部电极中的每一个被布置成连接到两组交替的内部电极中的一组。用于将压电谐振器的频率调节到较高频率的切割部分分别形成在与基底构件的第一侧表面相对的第二侧表面的纵向方向上的相对端处的基底构件的边缘部分处。

87. 发明授权

US5923855A Multi-processor system and method for synchronizing among processors with cache memory having reset state, invalid state, and valid state 失效
标题翻译：具有复位状态，无效状态和有效状态的高速缓冲存储器的处理器同步化的多处理器系统和方法
公开(公告)号：US5923855A
公开(公告)日：1999-07-13
申请号：US692346
申请日：1996-08-05
申请人： Takeshi Yamazaki
发明人： Takeshi Yamazaki
IPC分类号： G06F15/16 , G06F12/08 , G06F15/163
CPC分类号： G06F12/0815
摘要： In a multi-processor system including a plurality of processing units each having a cache memory, the processing units each include a synchronization counter for indicating a present synchronization state of the respective processing unit, and a cache state table for holding information regarding the respective entries of the cache memory. The cache state table includes a cache state and a cache synchronization count. The cache state holds the respective cache state used in a cache protocol. The cache synchronization count holds a value of the synchronization counter when an entry is loaded. A cache protocol in the multi-processor system is simplified to realize a high-speed processing.
摘要翻译：在包括多个具有高速缓存存储器的处理单元的多处理器系统中，处理单元各自包括用于指示各个处理单元的当前同步状态的同步计数器，以及用于保存关于各个条目的信息的高速缓存状态表的缓存内存。高速缓存状态表包括高速缓存状态和高速缓存同步计数。高速缓存状态保持缓存协议中使用的各自的高速缓存状态。当加载条目时，高速缓存同步计数保持同步计数器的值。多处理器系统中的缓存协议被简化以实现高速处理。

88. 发明授权

US5649141A Multiprocessor system for locally managing address translation table 失效
标题翻译：用于本地管理地址转换表的多处理器系统
公开(公告)号：US5649141A
公开(公告)日：1997-07-15
申请号：US497447
申请日：1995-06-30
申请人： Takeshi Yamazaki
发明人： Takeshi Yamazaki
IPC分类号： G06F15/16 , G06F12/02 , G06F12/10 , G06F15/177
CPC分类号： G06F12/1072 , G06F12/0284
摘要： An address translation technique used in a multiprocessor system is disclosed. In a multiprocessor system for connecting a plurality of clusters with each other via a network, each of these clusters is arranged by comprising a plurality of processors; a cluster translator for translating a cluster number; a cluster translation table for storing therein a correspondence relationship between a logical cluster number and a physical cluster number; an address translator for translating an address; and an address translation table for storing therein a correspondence relationship between a logical address and a physical address. The address translation table stores only the data corresponding to a memory employed in the cluster. Accordingly, a total storage capacity of the address translation tables is reduced, and an updating operation of the address translation tables is simplified. Furthermore, the address translation table is exclusively identified based on a local job number and the cluster number, so that operation to update the address translation table is simplified.
摘要翻译：公开了一种在多处理器系统中使用的地址转换技术。在用于经由网络将多个集群彼此连接的多处理器系统中，通过包括多个处理器来布置这些集群中的每一个; 用于翻译簇号的群集翻译器; 集群转换表，用于在其中存储逻辑簇号和物理簇号之间的对应关系; 用于翻译地址的地址转换器; 以及用于在其中存储逻辑地址和物理地址之间的对应关系的地址转换表。地址转换表仅存储与集群中使用的存储器相对应的数据。因此，减少了地址转换表的总存储容量，并简化了地址转换表的更新操作。此外，地址转换表是基于本地作业号和簇号唯一地标识的，因此简化了更新地址转换表的操作。

89. 发明授权

US5648946A Optical pick-up apparatus with holographic optical element to diffract both forward and return light beams 失效
$Optical pick-up apparatus with holographic optical element to diffract both forward and return light beams$
标题翻译：具有全息光学元件的光学拾取装置，用于衍射光束和反射光束
公开(公告)号：US5648946A
公开(公告)日：1997-07-15
申请号：US341087
申请日：1994-11-17
申请人： Takeshi Yamazaki
发明人： Takeshi Yamazaki
IPC分类号： G11B7/09 , G11B7/12 , G11B7/13 , G11B7/135
CPC分类号： G11B7/1353 , G11B7/0943 , G11B7/123 , G11B7/131 , G11B7/0903 , G11B7/0909 , G11B7/0912
摘要： An optical pick-up apparatus for recording and/or reading information on and/or from an optical record medium including a semiconductor substrate, a semiconductor laser arranged on the semiconductor substrate, plurality of photodetectors formed in the surface of the semiconductor substrate, a diffraction gratings dividing a laser beam into main beam and two sub-beams, an objective lens projecting the main and sub-beams onto the record medium and directing these beams reflected by the record medium toward a hologram which diffracts each of the main and sub-beams into .+-.1-order beams which are received by the photodetectors. The apparatus is constructed to satisfy the following conditions:NA.multidot.d d/.beta..sup.2 >0.01 mmwherein L mm is a distance between a spot of the main beam and a spot of a sub-beam on the record medium, NA is a numerical aperture of the objective lens on a side of the semiconductor laser, .beta. is a magnification of the objective lens viewed from the record medium to the semiconductor laser and d is a deviation of focal points of +1-order beams and -1-order beams viewed along an optical axis.
摘要翻译：一种光学拾取装置，用于在包括半导体衬底的光学记录介质和布置在半导体衬底上的半导体激光器，在半导体衬底的表面中形成的多个光电检测器，和/ 将激光束分成主光束和两个子光束的光栅，物镜将主光束和子光束投影到记录介质上，并将这些由记录介质反射的光束引向全息图，衍射各主光束和副光束由光电检测器接收的+/- 1级光束。该装置被构造成满足以下条件：NAxd <|Lxβ| 0.04mm> d /β2> 0.01mm其中L mm是主波束的点与记录上的子光束点之间的距离介质NA是半导体激光器一侧的物镜的数值孔径，β是从记录介质到半导体激光器的物镜的倍率，d是+ 1级光束的焦点偏差和沿光轴观察的-1级光束。

90. 发明授权

US5621714A Optical pick-up apparatus having hologram and beam splitter with birefringent member and polarizing film 失效
标题翻译：具有全息图的光学拾取装置和具有双折射元件和偏光膜的分束器
公开(公告)号：US5621714A
公开(公告)日：1997-04-15
申请号：US400757
申请日：1995-03-08
申请人： Shohei Kobayashi , Takeshi Yamazaki , Hiroyuki Imabayashi
发明人： Shohei Kobayashi , Takeshi Yamazaki , Hiroyuki Imabayashi
IPC分类号： G11B7/09 , G11B7/12 , G11B7/125 , G11B7/13 , G11B7/135 , G11B11/105 , G11B7/00
CPC分类号： G11B7/1356 , G11B11/10543 , G11B7/124 , G11B7/126 , G11B7/127 , G11B7/131 , G11B7/1353 , G11B11/10576 , G11B7/09
摘要： An optical pick-up apparatus for reproducing information recorded on a magneto-optical record medium including a semiconductor laser emitting a linearly polarized laser beam, and a polarizing film provided between a glass prism and a uniaxial birefringent crystal prism. The laser beam emitted by the semiconductor laser is made incident upon the polarizing film via the glass prism and is reflected thereby. The apparatus further includes an objective lens projecting the laser beam reflected by the polarizing film onto the magneto-optical record medium as a fine spot and converging a return laser beam reflected by the record medium toward the polarizing film. The return beam transmitted through the polarizing film is refracted by the uniaxial birefringent crystal prism and is divided into ordinary light and extraordinary light, which are received by a first photodetector to produce a reproduced information signal. The return beam reflected by the polarizing film is made incident upon a hologram and is diffracted thereby into .+-.1-order beams which are received by a second photodetector to produce a focusing error signal and a tracking error signal.
摘要翻译：一种用于再现记录在包括发射线性偏振激光束的半导体激光器的磁光记录介质上的信息的光学拾取装置，以及设置在玻璃棱镜和单轴双折射晶体棱镜之间的偏振膜。由半导体激光器发射的激光束经由玻璃棱镜入射到偏振膜上并被反射。该装置还包括将由偏振膜反射的激光束投影到磁光记录介质上的物镜作为细微点，并将由记录介质反射的返回激光束会聚到偏振膜。透过偏光膜的返回光束被单轴双折射晶体棱镜折射，分为普通的光和非常的光，由第一光电检测器接收以产生再现的信息信号。由偏振膜反射的返回光束入射到全息图上，并被衍射为由第二光电检测器接收的+/- 1次光束，以产生聚焦误差信号和跟踪误差信号。

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