公开(公告)号：US08141051B2

公开(公告)日：2012-03-20

申请号：US11618350

申请日：2006-12-29

申请人： Eric Jian Huang ,  Hu Chen ,  Wenguang Chen ,  Robert Kuhn

发明人： Eric Jian Huang ,  Hu Chen ,  Wenguang Chen ,  Robert Kuhn

IPC分类号： G06F9/44

CPC分类号： G06F11/3409 ,  G06F2201/805 ,  G06F2201/86

摘要： Methods, apparatus, and articles of manufacture to perform runtime trace filtering associated with application performance analysis are disclosed. A disclosed example method involves generating a first performance value based on first performance data associated with a first function of a first application process. A difference value is generated based on the first performance value and a historical performance value associated with the first function. The difference value is compared to a threshold value, and first trace data associated with execution of the first application process is collected based on the comparison of the difference value to the threshold value.

摘要翻译： 公开了用于执行与应用性能分析相关联的运行时跟踪过滤的方法，装置和制品。 公开的示例性方法包括基于与第一应用进程的第一功能相关联的第一性能数据来生成第一性能值。 基于与第一功能相关联的第一性能值和历史性能值，生成差值。 将差值与阈值进行比较，并且基于差值与阈值的比较来收集与执行第一应用处理相关联的第一跟踪数据。

公开(公告)号：US20100118041A1

公开(公告)日：2010-05-13

申请号：US12317853

申请日：2008-12-30

申请人： Hu Chen ,  Ying Gao ,  Zhou Xiaocheng ,  Shoumeng Yan ,  Peinan Zhang ,  Mohan Rajagopalan ,  Jesse Fang ,  Avi Mendelson ,  Bratin Saha

发明人： Hu Chen ,  Ying Gao ,  Zhou Xiaocheng ,  Shoumeng Yan ,  Peinan Zhang ,  Mohan Rajagopalan ,  Jesse Fang ,  Avi Mendelson ,  Bratin Saha

IPC分类号： G06F15/167

CPC分类号： G06F9/544 ,  G06F12/0815 ,  G06F12/084 ,  G06F12/1009 ,  G06F12/1063 ,  G06F12/1072 ,  G06F12/1081 ,  G06F12/109 ,  G06F2212/161 ,  G06F2212/622 ,  G06F2212/656 ,  G06F2212/657 ,  G06F2212/682 ,  G06T1/20 ,  G06T1/60

摘要： Embodiments of the invention provide a programming model for CPU-GPU platforms. In particular, embodiments of the invention provide a uniform programming model for both integrated and discrete devices. The model also works uniformly for multiple GPU cards and hybrid GPU systems (discrete and integrated). This allows software vendors to write a single application stack and target it to all the different platforms. Additionally, embodiments of the invention provide a shared memory model between the CPU and GPU. Instead of sharing the entire virtual address space, only a part of the virtual address space needs to be shared. This allows efficient implementation in both discrete and integrated settings.

摘要翻译： 本发明的实施例提供了一种用于CPU-GPU平台的编程模型。 特别地，本发明的实施例为集成和分立设备提供统一的编程模型。 该模型还适用于多个GPU卡和混合GPU系统（分立和集成）。 这允许软件供应商编写单个应用程序堆栈并将其定位到所有不同的平台。 另外，本发明的实施例提供了CPU和GPU之间的共享存储器模型。 而不是共享整个虚拟地址空间，只需要共享虚拟地址空间的一部分。 这允许在离散和集成设置中有效实现。

公开(公告)号：US20090174811A1

公开(公告)日：2009-07-09

申请号：US12001190

申请日：2007-12-11

申请人： Chih-Ta Star Sung ,  Eckehard Steinbach ,  Yin-Chun Blue Lan ,  Hu Chen ,  Mingzhe Sun

发明人： Chih-Ta Star Sung ,  Eckehard Steinbach ,  Yin-Chun Blue Lan ,  Hu Chen ,  Mingzhe Sun

IPC分类号： H04N11/02

CPC分类号： H04N19/00387 ,  H04N1/6058 ,  H04N19/186 ,  H04N19/20 ,  H04N19/428 ,  H04N19/61

摘要： Applying a mechanism of image signal processing and color-space-conversion to convert the captured Green components to be Y, luminance components for only those pixels having raw Green data without interpolation, and to convert the Blue components to be U, chrominance components for only those pixels having raw Blue data, and Red components to be V, chrominance components for only those pixels having raw Red data. These converted YUV components are input to a predetermined video compression codec for reducing the intra- and inter-frame redundant information.

摘要翻译： 应用图像信号处理和颜色空间转换的机制将捕获的绿色分量转换为Y，仅对那些没有插值的原始绿色数据的像素的亮度分量，并将蓝色分量转换为U，仅将色度分量转换为 那些具有原始蓝色数据的像素，并且红色分量为V，仅具有原始红色数据的像素的色度分量。 这些转换的YUV分量被输入到预定的视频压缩编解码器，以减少帧内和帧间冗余信息。

公开(公告)号：US20080072022A1

公开(公告)日：2008-03-20

申请号：US10585016

申请日：2004-06-22

申请人： Zong Zhao ,  Min Ren ,  Hu Chen

发明人： Zong Zhao ,  Min Ren ,  Hu Chen

IPC分类号： G06F9/30

CPC分类号： G06F9/3867 ,  G06F9/3836 ,  G06F9/3857 ,  G06F9/3879

摘要： The invention discloses an overlapping command committing method of dynamic cycle pipeline, for a chip having pipeline structure, the method comprising the following steps: reading the command from command buffer, decoding the command, judging whether operator is reasonable or not, if a illegal command, then deleting, otherwise preprocessing the operator of command, preparing the initial operator of each pipeline, and observing the status of pipeline, waiting for pipeline command exiting signal, and judging whether there is command relevance or not, if not, then committing a new command to pipeline when the command exiting a last cycle of pipeline. Overlapping command committing method of the invention can avoid appearing of bubble, improve parallelism of pipeline performing unit, and thus shorten the processing period of command in chip, let the chip process more command in unit time.

摘要翻译： 本发明公开了一种动态循环流水线重叠命令提交方法，对于具有流水线结构的芯片，该方法包括以下步骤：从命令缓冲器读取命令，解码命令，判断操作符是否合理，如果非法命令 ，然后删除，否则预处理命令的运算符，准备每个流水线的初始运算符，并观察流水线的状态，等待管道命令退出信号，并判断是否有命令相关性，否则，然后提交新的 当命令退出管道的最后一个循环时，命令管道。 本发明的重叠命令提交方法可以避免出现气泡，提高流水线执行单元的并行性，从而缩短芯片中命令的处理周期，使芯片在单位时间内处理更多命令。

公开(公告)号：US20140330546A1

公开(公告)日：2014-11-06

申请号：US14333535

申请日：2014-07-17

申请人： Huinan Deng ,  Hu Chen

发明人： Huinan Deng ,  Hu Chen ,  Bo Song ,  Yi Chen

IPC分类号： G06F19/12 ,  G06F17/50

CPC分类号： G16H50/50

摘要： This invention relates to a noninvasive method for urodynamics testing and analysis, comprising: modeling a bladder before a releasing of the urine as a topological sphere, modeling a circle formed by cutting the topological sphere through its center as an elastic element, determining a functional relation between a length L of the elastic element and a urine volume a within the bladder: L=F(a), determining a functional relation between a length contraction ΔL of the elastic element and both of a urinary flow rate Q and the urine volume a within the bladder: ΔL=ξ(Q,a), determining a functional relation between a contraction velocity ν of the elastic element and the length contraction ΔL of the elastic element: ν=ΔL, calculating a value of an index DC for assessing a bladder contractility to determine the bladder contractility of the subject.

摘要翻译： 本发明涉及一种用于尿动力学测试和分析的非侵入性方法，包括：在将尿液释放为拓扑球之前对膀胱进行建模，对通过其中心切割拓扑球作为弹性元件形成的圆进行建模，确定功能关系 在弹性元件的长度L和膀胱内的尿量a之间，L = F（a），确定弹性元件的长度收缩＆Dgr; L与尿流量Q和尿液之间的功能关系 膀胱内的体积a：＆Dgr; L =＆xgr;（Q，a），确定收缩速度与ngr之间的函数关系; 的弹性元件和弹性元件的长度收缩＆Dgr; L;计算用于评估膀胱收缩力以确定受试者的膀胱收缩力的指数DC的值。

公开(公告)号：US20130173894A1

公开(公告)日：2013-07-04

申请号：US13000621

申请日：2010-09-24

申请人： Shoumeng Yan ,  Sai Luo ,  Xiaocheng Zhou ,  Ying Gao ,  Hu Chen ,  Bratin Saha

发明人： Shoumeng Yan ,  Sai Luo ,  Xiaocheng Zhou ,  Ying Gao ,  Hu Chen ,  Bratin Saha

IPC分类号： G06F9/38

CPC分类号： G06F12/1072 ,  G06F8/447 ,  G06F9/3863 ,  G06F9/3885 ,  G06F9/548 ,  G06F2212/657

摘要： A computing platform may include heterogeneous processors (e.g., CPU and a GPU) to support sharing of virtual functions between such processors. In one embodiment, a CPU side vtable pointer used to access a shared object from the CPU 110 may be used to determine a GPU vtable if a GPU-side table exists. In other embodiment, a shared non-coherent region, which may not maintain data consistency, may be created within the shared virtual memory. The CPU and the GPU side data stored within the shared non-coherent region may have a same address as seen from the CPU and the GPU side. However, the contents of the CPU-side data may be different from that of GPU-side data as shared virtual memory may not maintain coherency during the run-time. In one embodiment, the vptr may be modified to point to the CPU vtable and GPU vtable stored in the shared virtual memory.

摘要翻译： 计算平台可以包括异构处理器（例如，CPU和GPU），以支持这些处理器之间的虚拟功能的共享。 在一个实施例中，如果GPU侧表存在，则用于从CPU 110访问共享对象的CPU侧vtable指针可用于确定GPU vtable。 在另一实施例中，可以在共享虚拟存储器内创建可能不维持数据一致性的共享非相干区域。 存储在共享非相干区域内的CP​​U和GPU侧数据可以具有与CPU和GPU侧所见相同的地址。 然而，CPU侧数据的内容可能与GPU侧数据的内容不同，因为共享虚拟存储器可能在运行期间不能维持一致性。 在一个实施例中，可以修改vptr以指向存储在共享虚拟存储器中的CPU vtable和GPU vtable。

公开(公告)号：US08397241B2

公开(公告)日：2013-03-12

申请号：US12317854

申请日：2008-12-30

申请人： Zhou Xiaocheng ,  Shoumeng Yan ,  Ying Gao ,  Hu Chen ,  Peinan Zhang ,  Mohan Rajagopalan ,  Avi Mendelson ,  Bratin Saha

发明人： Zhou Xiaocheng ,  Shoumeng Yan ,  Ying Gao ,  Hu Chen ,  Peinan Zhang ,  Mohan Rajagopalan ,  Avi Mendelson ,  Bratin Saha

IPC分类号： G06F9/44 ,  G06F13/14 ,  G06F13/00

CPC分类号： G06F9/544 ,  G06F12/0815 ,  G06F12/084 ,  G06F12/1009 ,  G06F12/1063 ,  G06F12/1072 ,  G06F12/1081 ,  G06F12/109 ,  G06F2212/161 ,  G06F2212/622 ,  G06F2212/656 ,  G06F2212/657 ,  G06F2212/682 ,  G06T1/20 ,  G06T1/60

摘要： Embodiments of the invention provide language support for CPU-GPU platforms. In one embodiment, code can be flexibly executed on both the CPU and GPU. CPU code can offload a kernel to the GPU. That kernel may in turn call preexisting libraries on the CPU, or make other calls into CPU functions. This allows an application to be built without requiring the entire call chain to be recompiled. Additionally, in one embodiment data may be shared seamlessly between CPU and GPU. This includes sharing objects that may have virtual functions. Embodiments thus ensure the right virtual function gets invoked on the CPU or the GPU if a virtual function is called by either the CPU or GPU.

公开(公告)号：US08296549B2

公开(公告)日：2012-10-23

申请号：US10585016

申请日：2004-06-22

申请人： Zong Zhao ,  Min Ren ,  Hu Chen

发明人： Zong Zhao ,  Min Ren ,  Hu Chen

IPC分类号： G06F9/30

CPC分类号： G06F9/3867 ,  G06F9/3836 ,  G06F9/3857 ,  G06F9/3879

摘要： The invention discloses an overlapping command committing method of dynamic cycle pipeline, for a chip having pipeline structure, the method comprising the following steps: reading the command from command buffer, decoding the command, judging whether operator is reasonable or not, if a illegal command, then deleting, otherwise preprocessing the operator of command, preparing the initial operator of each pipeline, and observing the status of pipeline, waiting for pipeline command exiting signal, and judging whether there is command relevance or not, if not, then committing a new command to pipeline when the command exiting a last cycle of pipeline. Overlapping command committing method of the invention can avoid appearing of bubble, improve parallelism of pipeline performing unit, and thus shorten the processing period of command in chip, let the chip process more command in unit time.

摘要翻译： 本发明公开了一种动态循环流水线重叠命令提交方法，对于具有流水线结构的芯片，该方法包括以下步骤：从命令缓冲器读取命令，解码命令，判断操作符是否合理，如果非法命令 ，然后删除，否则预处理命令的运算符，准备每个流水线的初始运算符，并观察流水线的状态，等待管道命令退出信号，并判断是否有命令相关性，否则，然后提交新的 当命令退出管道的最后一个循环时，命令管道。 本发明的重叠命令提交方法可以避免出现气泡，提高流水线执行单元的并行性，从而缩短芯片中命令的处理周期，使芯片在单位时间内处理更多命令。

公开(公告)号：US09727342B2

公开(公告)日：2017-08-08

申请号：US14567824

申请日：2014-12-11

申请人： Koushik Chakraborty ,  Sanghamitra Roy ,  Hu Chen

发明人： Koushik Chakraborty ,  Sanghamitra Roy ,  Hu Chen

IPC分类号： G06F11/00 ,  G06F9/38 ,  G06F1/08 ,  G06F11/07

CPC分类号： G06F9/3861 ,  G06F1/08 ,  G06F9/3869 ,  G06F11/0721 ,  G06F11/076

摘要： For an error resilient pipeline, a Dynamically Adaptable Resilient Pipeline (DARP) controller determines a minimum error pipeline stage of a processor instruction pipeline with a minimum number of errors. In addition, the DARP controller determines a maximum error pipeline stage of the instruction pipeline with a maximum number of errors. The DARP controller increases a clock frequency for the instruction pipeline if the minimum number of errors of the minimum error pipeline stage is zero and the maximum number of errors of the maximum error pipeline stage does not exceed an error threshold. In addition, the DARP controller decreases the clock frequency if the minimum number of errors exceeds an error constant.

公开(公告)号：US09384015B2

公开(公告)日：2016-07-05

申请号：US14129934

申请日：2013-07-16

申请人： Xiaocheng Zhou ,  Hu Chen ,  Shoumeng Yan ,  Ying Gao

发明人： Xiaocheng Zhou ,  Hu Chen ,  Shoumeng Yan ,  Ying Gao

IPC分类号： G06F9/445 ,  G06F9/44 ,  G06F12/02

CPC分类号： G06F9/44505 ,  G06F9/4411 ,  G06F12/023 ,  G06F2212/251

摘要： Various embodiments are generally directed an apparatus and method for configuring an execution environment in a user space for device driver operations and redirecting a device driver operation for execution in the execution environment in the user space including copying instructions of the device driver operation from the kernel space to a user process in the user space. In addition, the redirected device driver operation may be executed in the execution environment in the user space.

摘要翻译： 各种实施例通常涉及用于在用户空间中配置用于设备驱动器操作的执行环境并重定向设备驱动器操作以在用户空间中的执行环境中执行的装置和方法，包括来自内核空间的设备驱动器操作的复制指令 到用户空间中的用户进程。 此外，可以在用户空间中的执行环境中执行重定向设备驱动器操作。