中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.063 seconds)

    Compiling for programmable culling unit
    1.
    发明专利
    Compiling for programmable culling unit 有权
    编程可编程单元

    公开(公告)号：JP2011134326A

    公开(公告)日：2011-07-07

    申请号：JP2010280179

    申请日：2010-12-16

    Applicant: Intel Corp ,  インテル コーポレイション

    Inventor： TOTH ROBERT M ,  FRANZ P CLARBERG ,  HASSELGREN JON N ,  MUNKBERG CARL J ,  AKENINE-MOELLER TOMAS G

    IPC: G06T15/00 ,  G06F9/45 ,  G06T15/30

    CPC classification number: G06F8/41 ,  G06F8/443 ,  G06T15/40

    Abstract: PROBLEM TO BE SOLVED: To improve the performance of generating digitally represented graphics. SOLUTION: During compilation, the interval bounds for a programmable culling unit are calculated if possible. For each variable, interval bounds are calculated during the compilation, and the bounds together with other metadata are used to generate an optimized culling program. If not possible, then an assumption may be made and the assumption may be used to compile the code. If the assumption proves to be invalid, a new assumption may be made and the code may be recompiled in some embodiments. COPYRIGHT: (C)2011,JPO&INPIT

    Abstract translation: 要解决的问题：提高生成数字化图形的性能。

    解决方案：在编译期间，如果可能，计算可编程剔除单元的间隔范围。 对于每个变量，在编译期间计算间隔边界，并且边界与其他元数据一起用于生成优化的剔除程序。 如果不可能，则可以作出假设，并且可以使用该假设来编译代码。 如果假设证明是无效的，则可以作出新的假设，并且在一些实施例中代码可以被重新编译。 版权所有（C）2011，JPO＆INPIT

    AUF MINIMUM/MAXIMUM UND BITWEISER UND/ODER BASIERTER GROBER SCHABLONENTEST
    2.
    发明专利
    AUF MINIMUM/MAXIMUM UND BITWEISER UND/ODER BASIERTER GROBER SCHABLONENTEST 未知

    公开(公告)号：DE112017004550T5

    公开(公告)日：2019-05-23

    申请号：DE112017004550

    申请日：2017-08-08

    Applicant: INTEL CORP

    Inventor： TOTH ROBERT M ,  MUNKBERG CARL JACOB ,  HASSELGREN JON N

    IPC: G06T1/20 ,  G06T1/60

    Abstract: Verfahren und Vorrichtungen, die sich auf Techniken zur Bereitstellung von auf Minimum oder Maximum und bitweiser Logik UND oder Logik ODER basierten groben Schablonentests beziehen, werden beschrieben. In einer Ausführungsform werden Metadaten (die mehreren Pixeln entsprechen) im Speicher gespeichert. Eine oder mehrere Operationen werden an den Metadaten ausgeführt, um ein Schablonenergebnis zu erzeugen. Die eine oder mehreren Operationen umfassen eine bitweise Schnittmengenoperation oder eine bitweise Vereinigungsoperation und/oder eine Minimum-Operation oder eine Maximum-Operation. Andere Ausführungsformen werden ebenfalls offenbart und beansprucht.

    DEPTH OF FIELD RASTERIZATION
    6.
    发明申请
    DEPTH OF FIELD RASTERIZATION 审中-公开
    场地雷射深度

    公开(公告)号：WO2012148737A2

    公开(公告)日：2012-11-01

    申请号：PCT/US2012033979

    申请日：2012-04-18

    Applicant: INTEL CORP ,  AKENINE-MOELLER THOMAS G ,  MUNKBERG CARL J ,  HASSELGREN JON N ,  TOTH ROBERT M

    Inventor： AKENINE-MOELLER THOMAS G ,  MUNKBERG CARL J ,  HASSELGREN JON N ,  TOTH ROBERT M

    IPC: G06T15/00

    CPC classification number: G06T15/40 ,  G06T17/20

    Abstract: Depth of field may be rasterized by culling half-space regions on a lens from which a triangle to be rendered is not visible. Then, inside tests are only performed on the remaining unculled half-space regions. Separating planes between the triangle to be rendered and the tile being processed can be used to define the half-space regions.

    Abstract translation: 可以通过剔除要被渲染的三角形不可见的透镜上的半空间区域来光栅化景深。 然后，内部测试仅对剩余的未被空白的半空间区域进行。 要渲染的三角形和正在处理的瓷砖之间的分离平面可用于定义半空间区域。

    compressão de deslocamento adaptativo de profundidade
    7.
    发明专利
    compressão de deslocamento adaptativo de profundidade 未知

    公开(公告)号：BR102014029498A2

    公开(公告)日：2015-09-15

    申请号：BR102014029498

    申请日：2014-11-26

    Applicant: INTEL CORP

    Inventor： MUNKBERG CARL J ,  HASSELGREN JON N ,  ANDERSSON MAGNUS ,  TOTH ROBERT M ,  AKENINE-MOLLER TOMAS G

    IPC: G06F3/14 ,  G06T15/00 ,  G09G5/393

    Abstract: compressão de deslocamento adaptativo de profundidade. uma vez que o uso do mesmo número de bits por compressão de deslocamento de profundidade residual não é a melhor distribuição de bits, os bits por residual podem ser distribuídos de acordo com o conteúdo das profundidades de um tile. por exemplo, se as diferenças de profundidade próximas à zmax forem pequenas, será possível gastar menos bits em residuais para as amostras que são codificadas em relação à zmax. consequentemente, será possível gastar mais bits em residuais para as amostras que são codificadas em relação à zmin. como resultado, mais tiles terão êxito na compressão até atingir o número exigido de bits.

    COMPILING FOR PROGRAMMABLE CULLING UNIT
    8.
    发明专利
    COMPILING FOR PROGRAMMABLE CULLING UNIT 未知

    公开(公告)号：SG172542A1

    公开(公告)日：2011-07-28

    申请号：SG2010085710

    申请日：2010-11-22

    Applicant: INTEL CORP

    Inventor： TOTH ROBERT M ,  CLARBERG FRANZ P ,  HASSELGREN JON N ,  MUNKBERG CARL J ,  AKENINE-MOLLER TOMAS G

    Abstract: COMPILING FOR PROGRAMMABLE CULLING UNITAbstract of the DisclosureDuring compilation, the interval bounds for a programmable culling unit arecalculated if possible. For each variable, interval bounds are calculated during the compilation, and the bounds together with other metadata are used to generate an optimized culling program. If not possible, then an assumption may be made and the assumption used to compile the code. If the assumption proves to be invalid, a newassumption could be made and the code may be recompiled in some embodiments.(Fig. 4a)

Patent Agency Ranking