公开(公告)号：US5819026A

公开(公告)日：1998-10-06

申请号：US473279

申请日：1995-06-06

申请人： Vladimir Lhotak ,  Riaz A. Moledina

发明人： Vladimir Lhotak ,  Riaz A. Moledina

IPC分类号： G06F9/38 ,  G06T1/20 ,  G06F9/30 ,  G06F9/345

CPC分类号： G06F9/3885 ,  G06F9/3836 ,  G06T1/20

摘要： The present invention is a method and system for reducing delays due to a stream of digital data processing requests to a function specific hardware circuit. The system includes a first hardware stage implemented to perform the given function and a second parallel software code stage implemented to perform the same function. The hardware stage employs circuitry to implement the function whereas the software stage performs the function using software code including function specific processor instructions. The system also includes an arbitration stage that routes the data values to either of the hardware or software stages depending on the availability of the hardware stage and in accordance to pre-defined arbitration rules.

摘要翻译： 本发明是一种用于减少由于数字数据处理请求流到功能特定硬件电路引起的延迟的方法和系统。 该系统包括实现给定功能的第一硬件级和实现相同功能的第二并行软件代码级。 硬件级采用电路来实现该功能，而软件级使用包括功能特定处理器指令的软件代码执行功能。 该系统还包括仲裁阶段，该仲裁阶段根据硬件阶段的可用性并根据预定义的仲裁规则将数据值路由到硬件或软件阶段。

公开(公告)号：US09223631B2

公开(公告)日：2015-12-29

申请号：US13050904

申请日：2011-03-17

申请人： Daniel Lipton ,  Vladimir Lhotak

发明人： Daniel Lipton ,  Vladimir Lhotak

IPC分类号： G06F9/46 ,  G06F9/50

CPC分类号： G06F9/5066 ,  G06F2209/5017

摘要： Some embodiments provide a method for distributing an operation for processing by a set of background services. The method automatically determines a number of background services for performing an operation. The method partitions the operation into several sub-operations. The method distributes the several sub-operations across the determined number of background services.

摘要翻译： 一些实施例提供了一种用于分发由一组后台服务进行处理的操作的方法。 该方法自动确定执行操作的后台服务的数量。 该方法将操作分为几个子操作。 该方法在确定数量的后台服务中分配多个子操作。

公开(公告)号：US20120240124A1

公开(公告)日：2012-09-20

申请号：US13050904

申请日：2011-03-17

申请人： Daniel Lipton ,  Vladimir Lhotak

发明人： Daniel Lipton ,  Vladimir Lhotak

IPC分类号： G06F9/46

CPC分类号： G06F9/5066 ,  G06F2209/5017

摘要： Some embodiments provide a method for distributing an operation for processing by a set of background services. The method automatically determines a number of background services for performing an operation. The method partitions the operation into several sub-operations. The method distributes the several sub-operations across the determined number of background services.

摘要翻译： 一些实施例提供了一种用于分发由一组后台服务进行处理的操作的方法。 该方法自动确定执行操作的后台服务的数量。 该方法将操作分为几个子操作。 该方法在确定数量的后台服务中分配多个子操作。

公开(公告)号：US5736989A

公开(公告)日：1998-04-07

申请号：US587851

申请日：1996-01-11

申请人： Vladimir Lhotak

发明人： Vladimir Lhotak

IPC分类号： A61N1/08 ,  A61N1/37 ,  A61N1/372 ,  G06T1/60

CPC分类号： G06T1/60

摘要： Color conversion systems and methods using an interpolation table that minimizes interpolation color value generation times and reduces memory storage of interpolation tables. A first color conversion method and system reduces interpolation table generation times by generating interpolation color values on an "as needed" basis while performing color conversions. A second color conversion method minimizes interpolation table memory storage by dividing the interpolation table into segments, allocating primary memory storage to store only a given number of segments and establishing a segment status bit array to indicate whether a given segment is currently stored in primary memory. A third system and method combines both the first and second methods so that both interpolation table generation times and table memory storage is reduced.

摘要翻译： 使用内插表的颜色转换系统和方法，其使内插色彩值生成时间最小化并减少插值表的存储器存储。 第一颜色转换方法和系统通过在执行颜色转换的同时根据需要生成内插颜色值来减少内插表生成时间。 第二颜色转换方法通过将内插表划分成段来最小化插值表存储器存储，分配主存储器存储仅存储给定数量的段并建立段状态位阵列以指示给定段当前是否存储在主存储器中。 第三种系统和方法结合了第一种和第二种方法，从而降低了插值表生成时间和表格存储器存储。

公开(公告)号：US09727373B2

公开(公告)日：2017-08-08

申请号：US12057237

申请日：2008-03-27

申请人： Daniel Lipton ,  Vladimir Lhotak

发明人： Daniel Lipton ,  Vladimir Lhotak

IPC分类号： G06F17/30 ,  G06F7/00 ,  G06F9/48 ,  G06F9/50 ,  G06F11/34

CPC分类号： G06F9/485 ,  G06F9/5072 ,  G06F11/3433

摘要： An approach for providing a user with resumption data before pausing or terminating a partially-processed job that is processing in a distributed system. Certain applications, when paused, are not able to resume processing data at precisely the point where it was paused. As a result, users surrender some, or all, of the processed portion of the data when processing is paused. In one embodiment of the invention, a user is provided with resumption data before the user confirms a request to pause the processing. Resumption data from each of the service nodes that is processing a segment of source data are collected and aggregated. Resumption data reflects a measure of processed data that would require re-processing if the processing were paused and resumed. Alternatively, resumption data includes a duration of spent processing time that would be lost if the processing were paused and resumed.

公开(公告)号：US20090248754A1

公开(公告)日：2009-10-01

申请号：US12057237

申请日：2008-03-27

申请人： Daniel Lipton ,  Vladimir Lhotak

发明人： Daniel Lipton ,  Vladimir Lhotak

IPC分类号： G06F9/46 ,  G06F17/30

CPC分类号： G06F9/485 ,  G06F9/5072 ,  G06F11/3433

摘要： An approach for providing a user with resumption data before pausing or terminating a partially-processed job that is processing in a distributed system. Certain applications, when paused, are not able to resume processing data at precisely the point where it was paused. As a result, users surrender some, or all, of the processed portion of the data when processing is paused. In one embodiment of the invention, a user is provided with resumption data before the user confirms a request to pause the processing. Resumption data from each of the service nodes that is processing a segment of source data are collected and aggregated. Resumption data reflects a measure of processed data that would require re-processing if the processing were paused and resumed. Alternatively, resumption data includes a duration of spent processing time that would be lost if the processing were paused and resumed.

摘要翻译： 一种用于在暂停或终止在分布式系统中处理的部分处理的作业之前向用户提供恢复数据的方法。 某些应用程序暂停时，无法在其暂停点精确恢复处理数据。 结果，当处理暂停时，用户投降处理的数据部分或全部。 在本发明的一个实施例中，在用户确认暂停处理的请求之前，向用户提供恢复数据。 收集和聚合来自处理一段源数据的每个服务节点的恢复数据。 恢复数据反映了处理数据的量度，如果处理被暂停和恢复，则需要重新处理。 或者，恢复数据包括如果处理被暂停和恢复将丢失的花费的处理时间的持续时间。

公开(公告)号：US5671345A

公开(公告)日：1997-09-23

申请号：US475039

申请日：1995-06-06

申请人： Vladimir Lhotak

发明人： Vladimir Lhotak

IPC分类号： G06T11/60 ,  G06T11/00

CPC分类号： G06T11/60

摘要： The present invention is a method and system employing a glue code for: 1) intercepting low-level device dependent information from a graphics management interpreter software tool and 2) re-construct the low-level device dependent information into a high-level object oriented data representation for each object on a given page. The interpreter software is configured such that it transmits marking request signals and associated data to a fictitious frame buffer. However, the glue code of the present invention intercepts the marking request signals and associated data and transmits back receipt acknowledgment signals to the interpreter to make it think that it is writing to a frame buffer. As a result, the interpreter software transmits all marking requests and associated data to the glue code. The glue code then processes the low level device dependent information transmitted from the interpreter and reconstructs it into a high-level object oriented data representation using the information provided by the marking request.

摘要翻译： 本发明是一种采用胶接代码的方法和系统，其特征在于：1）从图形管理解释器软件工具截取低级设备相关信息，以及2）将低级设备相关信息重构为高级面向对象 给定页面上每个对象的数据表示。 解释器软件被配置为使得其将标记请求信号和相关联的数据传输到虚拟帧缓冲器。 然而，本发明的胶合码拦截标记请求信号和相关数据，并将回传确认信号发送给解释器，以使其认为它正在向帧缓冲器写入。 因此，解释器软件将所有标记请求和相关联的数据传送到胶合代码。 胶合码然后处理从解释器发送的低级设备相关信息，并使用标记请求提供的信息将其重构为高级面向对象的数据表示。