EMULATION OF FLOATING POINT CALCULATION
    2.
    发明公开

    公开(公告)号:EP4155900A1

    公开(公告)日:2023-03-29

    申请号:EP22184044.0

    申请日:2022-07-11

    申请人: INTEL Corporation

    IPC分类号: G06F7/544 G06F7/483

    摘要: Emulating floating point calculation using lower precision format calculations is described. An example of a processor includes a floating point unit (FPU) to provide a native floating point operation in a first precision format; and systolic array hardware including multiple data processing units, wherein the processor is to receive data for performance of a matrix multiplication operation in the first precision format; enable an emulated floating point multiplication operation using one or more values with a second precision format, the second precision format having a lower precision than the first precision format, the emulated floating point multiplication including operation of the systolic array hardware; and generate an emulated result for the matrix multiplication operation

    MOTION ESTIMATION METHODS FOR RESIDUAL PREDICTION
    9.
    发明公开
    MOTION ESTIMATION METHODS FOR RESIDUAL PREDICTION 有权
    测量在REST预测运动

    公开(公告)号:EP2786576A1

    公开(公告)日:2014-10-08

    申请号:EP11876665.8

    申请日:2011-12-01

    申请人: Intel Corporation

    IPC分类号: H04N7/32 H04N7/26 H04N7/36

    摘要: Systems, apparatus and methods are described including determining a first value by reducing a bit-length of a reference pixel value and adding a first predetermined value to the result and determining a second value by subtracting a residual pixel value from a current pixel value to generate a difference value, reducing a bit-length of the difference value and adding the first predetermined value to the result. The range of the second value may then be clipped by setting the second value to zero when the second value is equal to or less than a second predetermined value and setting the second value to a third predetermined value when the second value is equal to or greater than a fourth predetermined value. The first value and the second value may then be used for inter-layer residual prediction in Scalable Video Coding (SVC) systems.