公开(公告)号：US20140185687A1

公开(公告)日：2014-07-03

申请号：US13968719

申请日：2013-08-16

Applicant: Pexip AS

Inventor： Lars Petter Endresen

IPC: H04N7/30

CPC classification number: H04N19/60 ,  H04N19/436 ,  H04N19/91 ,  H04N19/93

Abstract: A method and a decoding or coding device for calculating at least one of run and level representations of respective quantized transform coefficients representing pixel values in a block of a video picture inserted in a coefficient array is disclosed. The method and the decoding or coding device are adjusted to generate a bitmask of the quantized transform coefficients, respectively perform a look up of the 8 least significant bits and the 8 most significant bits of the bitmask in a look up table, patch the looked up lower part and upper part bytemap values and insert the bytes of the first bytemap array from index position 8 minus the number of non-zeros in the 8 least significant bits of the bitmask.

Abstract translation: 公开了一种方法和解码或编码装置，用于计算表示插入系数数组中的视频图像的块中的像素值的各个量化变换系数的运行和电平表示中的至少一个。 调整方法和解码或编码装置以产生量化变换系数的位掩码，分别在查找表中查找位掩码的8个最低有效位和8个最高有效位，修补查找 下部分和上部的地图值，并从索引位置8插入第一个bytemap数组的字节减去位掩码的8个最低有效位中的非零数。

公开(公告)号：US20140133555A1

公开(公告)日：2014-05-15

申请号：US13945152

申请日：2013-07-18

Applicant: Pexip AS

Inventor： Lars Petter Endresen

IPC: H04N7/50

CPC classification number: H04N19/00781 ,  G06F17/147 ,  H04N19/109 ,  H04N19/132 ,  H04N19/14 ,  H04N19/176 ,  H04N19/436 ,  H04N19/61 ,  H04N19/625

Abstract: A method to quickly determine whether a macroblock in H.264 or other similar standards should be encoded in skip mode in a SIMD processor environment is provided. The method exploits the fact that the processor provides enough register space to store N=4 4x4 set of 8 bits data. By performing 4 consecutive reads of 16 linear aligned values into 16 SIMD register variables each capable of storing 16 values, the entire data set for operating can be stored within the processors SIMD register variables and can be operated upon, without any memory related latency.

Abstract translation: 提供了一种快速确定H.264或其他类似标准中的宏块是否应在SIMD处理器环境中以跳过模式进行编码的方法。 该方法利用了处理器提供足够的寄存器空间来存储N = 4个4×4组8位数据的事实。 通过对16个SIMD寄存器变量执行4个连续读取16个线性对齐值，每个能够存储16个值，用于操作的整个数据集可以存储在处理器SIMD寄存器变量中，可以在没有任何内存相关延迟的情况下进行操作。

公开(公告)号：US09407933B2

公开(公告)日：2016-08-02

申请号：US13968719

申请日：2013-08-16

Applicant: Pexip AS

Inventor： Lars Petter Endresen

IPC: H04N19/60 ,  H04N19/436 ,  H04N19/91 ,  H04N19/93

CPC classification number: H04N19/60 ,  H04N19/436 ,  H04N19/91 ,  H04N19/93

Abstract: A method and a decoding or coding device for calculating at least one of run and level representations of respective quantized transform coefficients representing pixel values in a block of a video picture inserted in a coefficient array is disclosed. The method and the decoding or coding device are adjusted to generate a bitmask of the quantized transform coefficients, respectively perform a look up of the 8 least significant bits and the 8 most significant bits of the bitmask in a look up table, patch the looked up lower part and upper part bytemap values and insert the bytes of the first bytemap array from index position 8 minus the number of non-zeros in the 8 least significant bits of the bitmask.

Abstract translation: 公开了一种方法和解码或编码装置，用于计算表示插入系数数组中的视频图像的块中的像素值的各个量化变换系数的运行和电平表示中的至少一个。 调整方法和解码或编码装置以产生量化变换系数的位掩码，分别在查找表中查找位掩码的8个最低有效位和8个最高有效位，修补查找 下部分和上部的地图值，并从索引位置8插入第一个bytemap数组的字节减去位掩码的8个最低有效位中的非零数。

公开(公告)号：US08971407B2

公开(公告)日：2015-03-03

申请号：US13945152

申请日：2013-07-18

Applicant: Pexip AS

Inventor： Lars Petter Endresen

IPC: H04N7/12 ,  H04N11/02 ,  H04N11/04 ,  H04B1/66 ,  H04N5/14 ,  H04N9/64 ,  H04N19/61

CPC classification number: H04N19/00781 ,  G06F17/147 ,  H04N19/109 ,  H04N19/132 ,  H04N19/14 ,  H04N19/176 ,  H04N19/436 ,  H04N19/61 ,  H04N19/625

Abstract: A method to quickly determine whether a macroblock in H.264 or other similar standards should be encoded in skip mode in a SIMD processor environment is provided. The method exploits the fact that the processor provides enough register space to store N=4 4×4 set of 8 bits data. By performing 4 consecutive reads of 16 linear aligned values into 16 SIMD register variables each capable of storing 16 values, the entire data set for operating can be stored within the processors SIMD register variables and can be operated upon, without any memory related latency.

Abstract translation: 提供了一种快速确定H.264或其他类似标准中的宏块是否应在SIMD处理器环境中以跳过模式进行编码的方法。 该方法利用了处理器提供足够的寄存器空间来存储N = 4×4×4的8位数据的事实。 通过对16个SIMD寄存器变量执行4个连续读取16个线性对齐值，每个能够存储16个值，用于操作的整个数据集可以存储在处理器SIMD寄存器变量中，可以在没有任何内存相关延迟的情况下进行操作。