中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

2517 records (took 0.036 seconds)

    FLOATING POINT ADDER
    61.
    发明公开
    FLOATING POINT ADDER 审中-公开

    公开(公告)号：US20240103807A1

    公开(公告)日：2024-03-28

    申请号：US18518972

    申请日：2023-11-25

    Applicant: Imagination Technologies Limited

    Inventor： Max Freiburghaus

    IPC: G06F7/485

    CPC classification number: G06F7/485

    Abstract: An adder and a method for calculating 2n+x are provided, where x is a variable input expressed in a floating point format and n is an integer. The adder comprises: a first path configured to calculate 2n+x for x

    MULTI-OUTPUT DECODER FOR TEXTURE DECOMPRESSION
    62.
    发明公开
    MULTI-OUTPUT DECODER FOR TEXTURE DECOMPRESSION 审中-公开

    公开(公告)号：US20240095975A1

    公开(公告)日：2024-03-21

    申请号：US18525715

    申请日：2023-11-30

    Applicant: Imagination Technologies Limited

    Inventor： Kenneth Rovers ,  Yoong Chert Foo

    IPC: G06T11/00 ,  G06T9/00 ,  G06T15/04 ,  H04N19/436 ,  H04N19/44

    CPC classification number: G06T11/001 ,  G06T9/00 ,  G06T15/04 ,  H04N19/436 ,  H04N19/44

    Abstract: A decoder decodes a plurality of texels from a received block of texture data encoded according to the Adaptive Scalable Texture Compression (ASTC) format. A parameter decode unit decodes configuration data for the received block of texture data, a colour decode unit decodes colour endpoint data for the plurality of texels in dependence on the configuration data, a weight decode unit decodes interpolation weight data for each of the plurality of texels in dependence on the configuration data, and at least one interpolator unit calculates a colour value for each of the plurality of texels using the interpolation weight data for that texel and a pair of colour endpoints from the colour endpoint data. At least one of the parameter decode unit, colour decode unit and weight decode unit decodes intermediate data from the received block that is common to the decoding of a subset of texels of that block and uses that decoded data as part of the decoding of at least two of the plurality of texels.

    IMAGE DATA COMPRESSION
    63.
    发明公开
    IMAGE DATA COMPRESSION 审中-公开

    公开(公告)号：US20240087172A1

    公开(公告)日：2024-03-14

    申请号：US18515491

    申请日：2023-11-21

    Applicant: Imagination Technologies Limited

    Inventor： Paul Higginbottom ,  Mark Jackson Pulver ,  Seyed Ahamed

    IPC: G06T9/00 ,  G06F7/50 ,  G06F7/72 ,  G06T3/40

    CPC classification number: G06T9/00 ,  G06F7/50 ,  G06F7/727 ,  G06T3/40

    Abstract: A method and compression unit for compressing a block of image data to satisfy a target level of compression, wherein the block of image data comprises a plurality of image element values, each image element value comprising one or more data values relating to a respective channel. For each of the channels: (i) an origin value for the channel for the block is determined, (ii) difference values are determined representing differences between the data values and the determined origin value for the channel for the block, and (iii) a first number of bits for losslessly representing a maximum difference value of the difference values for the channel for the block is determined. The determined first number of bits for each of the channels is used to determine a respective second number of bits for each of the channels, the second number of bits being determined such that representing each of the difference values for the channels with the respective second number of bits satisfies the target level of compression for compressing the block of image data. Compressed data is formed, having for each of the one or more channels an indication of the determined origin value for the channel, an indication of the determined first number of bits for the channel, and representations of the determined difference values for the channel, wherein each of the representations of the determined difference values for the channel uses the determined second number of bits for the channel, such that the target level of compression is satisfied.

    COMPRESSED RAY DIRECTION DATA IN A RAY TRACING SYSTEM
    64.
    发明公开
    COMPRESSED RAY DIRECTION DATA IN A RAY TRACING SYSTEM 审中-公开

    公开(公告)号：US20240078740A1

    公开(公告)日：2024-03-07

    申请号：US18388914

    申请日：2023-11-13

    Applicant: Imagination Technologies Limited

    Inventor： Luke T. Peterson ,  Simon Fenney

    IPC: G06T15/06 ,  G06T9/00 ,  G06T15/30 ,  G06T15/55

    CPC classification number: G06T15/06 ,  G06T9/00 ,  G06T15/30 ,  G06T15/55 ,  G06T15/506

    Abstract: Ray tracing systems process rays through a 3D scene to determine intersections between rays and geometry in the scene, for rendering an image of the scene. Ray direction data for a ray can be compressed, e.g. into an octahedral vector format. The compressed ray direction data for a ray may be represented by two parameters (u,v) which indicate a point on the surface of an octahedron. In order to perform intersection testing on the ray, the ray direction data for the ray is unpacked to determine x, y and z components of a vector to a point on the surface of the octahedron. The unpacked ray direction vector is an unnormalised ray direction vector. Rather than normalising the ray direction vector, the intersection testing is performed on the unnormalised ray direction vector. This avoids the processing steps involved in normalising the ray direction vector.

    Input/output filter unit for graphics processing unit
    65.
    发明授权
    Input/output filter unit for graphics processing unit 有权

    公开(公告)号：US11922536B2

    公开(公告)日：2024-03-05

    申请号：US17350534

    申请日：2021-06-17

    Applicant: Imagination Technologies Limited

    Inventor： Kristof Beets

    IPC: G06T1/60 ,  G06F7/57 ,  G06F13/12 ,  G06T11/00

    CPC classification number: G06T1/60 ,  G06F7/57 ,  G06F13/122 ,  G06T11/001

    Abstract: Input/output filter units for use in a graphics processing unit include a first buffer configured to store data received from, and output to, a first component of the graphics processing unit; a second buffer configured to store data received from, and output to, a second component of the graphics processing unit; a weight buffer configured to store filter weights; a filter bank configurable to perform any of a plurality of types of filtering on a set of input data, the plurality of types of filtering comprising one or more texture filtering types and one or more pixel filtering types; and control logic configured to cause the filter bank to: (i) perform one of the plurality of types of filtering on a set of data stored in one of the first and second buffers using a set of weights stored, and (ii) store the results of the filtering in one of the first and second buffers.

    Transformed geometry data cache for graphics processing systems
    67.
    发明授权
    Transformed geometry data cache for graphics processing systems 有权

    公开(公告)号：US11915363B2

    公开(公告)日：2024-02-27

    申请号：US18202933

    申请日：2023-05-28

    Applicant: Imagination Technologies Limited

    Inventor： Robert Brigg ,  John W. Howson ,  Xile Yang

    IPC: G06T15/40 ,  G06T15/00 ,  G06T1/60

    CPC classification number: G06T15/40 ,  G06T1/60 ,  G06T15/005

    Abstract: A tag buffer implements a tag buffer stage of a rasterization phase in a tile-based rendering graphics processing system having a rendering space sub-divided into a plurality of tiles to which primitives can be associated. A buffer stores an identifier that identifies a visible primitive fragment at each sample position of a tile of the plurality of tiles. A look-up table stores an entry for transformed primitive blocks that indicates whether the tag buffer has received information identifying a primitive fragment associated with that transformed primitive block. The tag buffer receives information identifying primitive fragments that have survived a depth test, updates the buffer to indicate that an identified primitive fragment is the visible primitive fragment at the associated sample position, updates the look-up table to indicate which transformed primitive blocks the identified primitive fragments are associated with, and in response to flushing the contents of the buffer, compares the flushed contents of the buffer to the look-up table to thereby identify transformed primitive blocks that did not survive the tag buffer stage.

    Neural network architecture using control logic determining convolution operation sequence
    69.
    发明授权
    Neural network architecture using control logic determining convolution operation sequence 有权

    公开(公告)号：US11907830B2

    公开(公告)日：2024-02-20

    申请号：US18093768

    申请日：2023-01-05

    Applicant: Imagination Technologies Limited

    Inventor： Christopher Martin

    IPC: G06N3/063 ,  G06F7/544 ,  G06F17/15 ,  G06N3/04 ,  G06N3/048 ,  G06N3/0464 ,  G06N3/045

    CPC classification number: G06N3/063 ,  G06F7/5443 ,  G06F17/15 ,  G06N3/04 ,  G06N3/048 ,  G06N3/0464 ,  G06N3/045

    Abstract: Hardware for implementing a Deep Neural Network (DNN) having a convolution layer. A plurality of convolution engines each perform a convolution operation by applying a filter to a data window. Each of the plurality of convolution engines includes multiplication logic that combines a weight of a filter with a respective data value of a data window; control logic that receives configuration information identifying a set of filters for operation on a set of data windows at the plurality of convolution engines; determines a sequence of convolution operations for evaluation at the multiplication logic; requests weights and data values for at least partially applying a filter to a data window; and causes the multiplication logic to combine the weights with their respective data values. Accumulation logic accumulates the results of a plurality of combinations performed by the multiplication logic to form an output for a convolution operation of the determined sequence.

Patent Agency Ranking