Generating parallel SIMD code for an arbitrary target architecture
    1.
    发明授权
    Generating parallel SIMD code for an arbitrary target architecture 失效
    为任意目标架构生成并行SIMD代码

    公开(公告)号:US08418155B2

    公开(公告)日:2013-04-09

    申请号:US12368424

    申请日:2009-02-10

    摘要: Techniques are disclosed for automating the generation of parallel SIMD native source code in three major functional areas of data transmission, synchronization, and SIMD operations. An annotation standard is defined that is independent from native compilers and, coupled with a source-to-source compiler that provides high-level abstractions of data transmission, synchronization, and SIMD operations, relieves the need for programmers to work in a hardware-specific manner, while addressing issues of productivity and portability in a parallel SIMD computing environment.

    摘要翻译: 公开了用于在数据传输,同步和SIMD操作的三个主要功能领域中自动生成并行SIMD本机源代码的技术。 定义了一个独立于本地编译器的注释标准,以及提供数据传输,同步和SIMD操作的高级抽象的源到源编译器,减轻了程序员在硬件特定情况下工作的需要 同时解决并行SIMD计算环境中的生产力和可移植性问题。

    Fast vector masking algorithm for conditional data selection in SIMD architectures
    2.
    发明授权
    Fast vector masking algorithm for conditional data selection in SIMD architectures 失效
    用于SIMD架构中条件数据选择的快速矢量遮蔽算法

    公开(公告)号:US08418154B2

    公开(公告)日:2013-04-09

    申请号:US12368409

    申请日:2009-02-10

    IPC分类号: G06F9/38

    摘要: Techniques are disclosed for generating fast vector masking SIMD code corresponding to source code having a conditional statement, where the SIMD code replaces the conditional statements with vector SIMD operations. One technique includes performing conditional masking using vector operations, bit masking operations, and bitwise logical operations. The need for conditional statements in SIMD code is thereby removed, allowing SIMD hardware to avoid having to use branch prediction. This reduces the number of pipeline stalls and results in increased utilization of the SIMD computational units.

    摘要翻译: 公开了用于生成与具有条件语句的源代码相对应的快速向量屏蔽SIMD代码的技术,其中SIMD代码用向量SIMD操作替换条件语句。 一种技术包括使用向量操作,位掩码操作和按位逻辑运算来执行条件掩蔽。 因此,SIMD代码中的条件语句的需求被消除,从而允许SIMD硬件避免使用分支预测。 这减少了流水线停顿的数量并导致SIMD计算单元的利用率的增加。

    REAL TIME MOTION INFORMATION CAPTURE IN AN MRI ENVIRONMENT
    3.
    发明申请
    REAL TIME MOTION INFORMATION CAPTURE IN AN MRI ENVIRONMENT 有权
    MRI环境中的实时运动信息捕获

    公开(公告)号:US20110105883A1

    公开(公告)日:2011-05-05

    申请号:US12612143

    申请日:2009-11-04

    IPC分类号: A61B5/05 G06K9/00

    摘要: Systems, methods and articles of manufacture are disclosed for capturing motion information in a magnetic resonance imaging (MRI) environment. A light sink in the MRI environment may detect light emitted from a plurality of light sources. Each of the plurality of light sources may emit light of a different frequency. Further, each of the plurality of light sources may be located at a different spatial position in the MRI environment. The detected light may be analyzed. A change in spatial position of the light sink may be computed based on the analysis.

    摘要翻译: 公开了用于在磁共振成像(MRI)环境中捕获运动信息的系统,方法和制品。 MRI环境中的光接收器可以检测从多个光源发射的光。 多个光源中的每一个可以发射不同频率的光。 此外,多个光源中的每一个可以位于MRI环境中不同的空间位置。 可以分析检测到的光。 可以基于分析来计算光吸收器的空间位置的变化。

    CORRECTING SUBJECT MOTION IN MULTIPLE RESOLUTIONS IN MAGNETIC RESONANCE IMAGING
    4.
    发明申请
    CORRECTING SUBJECT MOTION IN MULTIPLE RESOLUTIONS IN MAGNETIC RESONANCE IMAGING 失效
    修正磁共振成像中多项决议中的主题运动

    公开(公告)号:US20110105882A1

    公开(公告)日:2011-05-05

    申请号:US12612105

    申请日:2009-11-04

    IPC分类号: A61B5/055 G06K9/00

    摘要: Systems, methods and articles of manufacture are disclosed for compensating for motion of a subject during an MRI scan of the subject. k-space data may be received from the MRI scan of the subject. A first graphical image may be generated from a first set of data elements from the k-space data. Similarly, a second graphical image may be generated from a second set of data elements from the k-space data. An offset in pixels may be determined by which to translate the second graphical image from the first graphical image to compensate for the motion. The k-space data may be modified at a sub-pixel offset relative to the determined offset. A motion-compensated graphical image of the subject may be generated from the modified k-space data. Doing so reduces the search space evaluated to sharpen images generated from the k-space data.

    摘要翻译: 公开了用于在对象的MRI扫描期间补偿对象的运动的系统,方法和制品。 可以从对象的MRI扫描接收k空间数据。 可以从k空间数据的第一组数据元素生成第一图形图像。 类似地,可以从k空间数据的第二组数据元素生成第二图形图像。 像素中的偏移量可以由第一图形图像的第二图形图像转换为补偿运动来确定。 可以在相对于所确定的偏移的子像素偏移处修改k空间数据。 可以从修改的k空间数据生成被摄体的运动补偿图形图像。 这样做减少了评估的搜索空间,以锐化从k空间数据生成的图像。

    MOTION INFORMATION CAPTURE AND AUTOMATIC MOTION CORRECTION FOR IMAGING SYSTEMS
    5.
    发明申请
    MOTION INFORMATION CAPTURE AND AUTOMATIC MOTION CORRECTION FOR IMAGING SYSTEMS 失效
    成像系统的运动信息捕获和自动运动校正

    公开(公告)号:US20110101978A1

    公开(公告)日:2011-05-05

    申请号:US12612172

    申请日:2009-11-04

    IPC分类号: G01R33/48

    CPC分类号: G01R33/56509

    摘要: Systems, methods and articles of manufacture are disclosed for compensating for motion of a subject during an MRI scan of the subject. k-space data may be received from the MRI scan of the subject. Motion information may be received for the subject. Based on the received motion information, a translational motion of the subject may be determined between a first point in time and a second point in time. A search space for motion correction may be reduced using the determined change and an error margin of the capturing technique. A motion-compensated, graphical image of the subject may be generated using the reduced search space.

    摘要翻译: 公开了用于在对象的MRI扫描期间补偿对象的运动的系统,方法和制品。 可以从对象的MRI扫描接收k空间数据。 运动信息可能会被收到。 基于接收到的运动信息,可以在第一时间点和第二时间点之间确定对象的平移运动。 可以使用确定的改变和捕获技术的误差范围来减少用于运动校正的搜索空间。 可以使用缩小的搜索空间来生成被摄体的运动补偿的图形图像。

    PROCESSING ARRAY DATA ON SIMD MULTI-CORE PROCESSOR ARCHITECTURES
    6.
    发明申请
    PROCESSING ARRAY DATA ON SIMD MULTI-CORE PROCESSOR ARCHITECTURES 失效
    在SIMD多核处理器架构上处理阵列数据

    公开(公告)号:US20100241824A1

    公开(公告)日:2010-09-23

    申请号:US12406247

    申请日:2009-03-18

    IPC分类号: G06F15/76 G06F9/06

    摘要: Techniques are disclosed for converting data into a format tailored for efficient multidimensional fast Fourier transforms (FFTS) on single instruction, multiple data (SIMD) multi-core processor architectures. The technique includes converting data from a multidimensional array stored in a conventional row-major order into SIMD format. Converted data in SIMD format consists of a sequence of blocks, where each block interleaves s rows such that SIMD vector processors may operate on s rows simultaneously. As a result, the converted data in SIMD format enables smaller-sized 1D FFTs to be optimized in SIMD multi-core processor architectures.

    摘要翻译: 公开了用于将数据转换成针对单指令,多数据(SIMD)多核处理器架构的有效多维快速傅里叶变换(FFTS)的格式的技术。 该技术包括将以常规行主序列存储的多维数组的数据转换为SIMD格式。 SIMD格式的转换数据由块序列组成,其中每个块交错行,使得SIMD向量处理器可以同时对s行进行操作。 因此,以SIMD格式转换的数据使得能够在SIMD多核处理器架构中优化较小尺寸的一维FFT。

    Real time motion information capture in an MRI environment
    8.
    发明授权
    Real time motion information capture in an MRI environment 有权
    在MRI环境中实时运动信息捕获

    公开(公告)号:US08498689B2

    公开(公告)日:2013-07-30

    申请号:US12612143

    申请日:2009-11-04

    IPC分类号: A61B5/05

    摘要: Systems, methods and articles of manufacture are disclosed for capturing motion information in a magnetic resonance imaging (MRI) environment. A light sink in the MRI environment may detect light emitted from a plurality of light sources. Each of the plurality of light sources may emit light of a different frequency. Further, each of the plurality of light sources may be located at a different spatial position in the MRI environment. The detected light may be analyzed. A change in spatial position of the light sink may be computed based on the analysis.

    摘要翻译: 公开了用于在磁共振成像(MRI)环境中捕获运动信息的系统,方法和制品。 MRI环境中的光接收器可以检测从多个光源发射的光。 多个光源中的每一个可以发射不同频率的光。 此外,多个光源中的每一个可以位于MRI环境中不同的空间位置。 可以分析检测到的光。 可以基于分析来计算光吸收器的空间位置的变化。

    Processing array data on SIMD multi-core processor architectures
    9.
    发明授权
    Processing array data on SIMD multi-core processor architectures 失效
    处理SIMD多核处理器架构的阵列数据

    公开(公告)号:US08484276B2

    公开(公告)日:2013-07-09

    申请号:US12406247

    申请日:2009-03-18

    IPC分类号: G06F15/76 G06F9/06

    摘要: Techniques are disclosed for converting data into a format tailored for efficient multidimensional fast Fourier transforms (FFTS) on single instruction, multiple data (SIMD) multi-core processor architectures. The technique includes converting data from a multidimensional array stored in a conventional row-major order into SIMD format. Converted data in SIMD format consists of a sequence of blocks, where each block interleaves s rows such that SIMD vector processors may operate on s rows simultaneously. As a result, the converted data in SIMD format enables smaller-sized 1D FFTs to be optimized in SIMD multi-core processor architectures.

    摘要翻译: 公开了用于将数据转换成针对单指令,多数据(SIMD)多核处理器架构的有效多维快速傅里叶变换(FFTS)的格式的技术。 该技术包括将以常规行主序列存储的多维数组的数据转换为SIMD格式。 SIMD格式的转换数据由块序列组成,其中每个块交错行,使得SIMD向量处理器可以同时对s行进行操作。 因此,以SIMD格式转换的数据使得能够在SIMD多核处理器架构中优化较小尺寸的一维FFT。

    Distributed runtime diagnostics in hierarchical parallel environments
    10.
    发明授权
    Distributed runtime diagnostics in hierarchical parallel environments 失效
    分层并行环境中的分布式运行时诊断

    公开(公告)号:US08060783B2

    公开(公告)日:2011-11-15

    申请号:US12389926

    申请日:2009-02-20

    IPC分类号: G06F11/00

    CPC分类号: G06F11/366 G06F11/3644

    摘要: A technique is disclosed for distributed runtime diagnostics in hierarchical parallel environments. In one embodiment, a user is allowed to configure, during runtime, a processing element on which to perform diagnostics, an algorithm for the processing element to execute, a data set for the algorithm to execute against, a diagnostic function for the processing element to execute, a condition for executing the diagnostic function, and visualization parameters for memory local to the processing element. As a result, runtime diagnostics can be performed with sufficient degree of control and customization to aid debugging in a hierarchical parallel environment.

    摘要翻译: 公开了一种分层并行环境中分布式运行时诊断的技术。 在一个实施例中,允许用户在运行时期间配置一个处理元件,在该处理元件上执行诊断,该处理元件执行用于该算法执行的数据集,用于处理元件的诊断功能, 执行,用于执行诊断功能的条件,以及用于处理元件本地的存储器的可视化参数。 因此,可以以足够程度的控制和定制来执行运行时诊断,以帮助分层并行环境中的调试。