Method and apparatus for performing tangent space lighting and bump mapping in a deferred shading graphics processor
    71.
    发明授权
    Method and apparatus for performing tangent space lighting and bump mapping in a deferred shading graphics processor 有权
    在延迟着色图形处理器中执行切线空间照明和凹凸贴图的方法和装置

    公开(公告)号:US06771264B1

    公开(公告)日:2004-08-03

    申请号:US09213990

    申请日:1999-12-17

    IPC分类号: G06T1560

    摘要: A system and method for performing tangent space lighting in a deferred shading graphics processor (DSGP) encompasses blocks of the DSGP that preprocess data and a Phong shader that executes only after all fragments have been preprocessed. A preprocessor block receives texture maps specified in a variety of formats and converts those texture maps to a common format for use by the Phong shader. The preprocessor blocks provide the Phong shader with interpolated surface basis vectors (vs, vt, n), a vector Tb that represents in tangen/object space the texture/bump data from the texture maps, light data, material data, eye coordinates and other information used by the Phong shader to perform the lighting and bump mapping computations. The data from the preprocessor is provided for each fragment for which lighting effects need to be computed. The Phong shader computes the color of a fragment using the information provided by the preprocessor. The Phong shader performs all lighting computations in eye space, which requires it first to transform bump data from tangent space to eye space. In one embodiment the Phong hardware does this by multiplying a matrix M whose columns comprise eye space basis vectors (bs, bt, n) derived from the surface basis vectors (vs, vt, n) and the vector Tb of bump map data. The eye space basis vectors are derived by the DSGP preprocessor so that the multiplication (M×Tb) gives the perturbed surface normal N′ in eye space, reflecting the bump effects. The perturbed surface normal N′ is subsequently used in the lighting computations.

    摘要翻译: 用于在延迟着色图形处理器(DSGP)中执行切线空间照明的系统和方法包括预处理数据的DSGP的块和仅在所有片段被预处理之后才执行的Phong着色器。 预处理器块接收以各种格式指定的纹理贴图,并将这些纹理贴图转换为普通格式供Phong着色器使用。 预处理器块为Phong着色器提供了内插表面基向量(vs,vt,n),一个向量Tb,它在切向/对象空间中表示纹理贴图中的纹理/凹凸数据,光数据,材料数据,眼睛坐标等 Phong着色器使用的信息执行照明和凹凸贴图计算。 为需要计算照明效果的每个片段提供来自预处理器的数据。 Phong着色器使用预处理器提供的信息计算片段的颜色。 Phong着色器执行眼睛空间中的所有照明计算,这需要它首先将凹凸数据从切线空间转换为眼睛空间。 在一个实施例中,Phong硬件通过乘以其列包括从表面基矢量(vs,vt,n)导出的凹凸贴图数据的矢量Tb的基准矢量(bs,bt,n)的矩阵M来实现。 通过DSGP预处理器导出眼空间基矢量,使得乘法(MxTb)给出了眼空间中的扰动表面法线N',反映了碰撞效应。 扰动表面法线N'随后用于照明计算。

    Method for preventing multi-level cache system deadlock in a
multi-processor system
    74.
    发明授权
    Method for preventing multi-level cache system deadlock in a multi-processor system 失效
    防止多处理器系统中多级缓存系统死锁的方法

    公开(公告)号:US5632025A

    公开(公告)日:1997-05-20

    申请号:US696788

    申请日:1996-08-14

    IPC分类号: G06F12/08 G06F12/14

    CPC分类号: G06F12/0811

    摘要: A method for preventing deadlock due to the need for data exclusivity when performing forced atomic instructions in a multi-level cache in a multi-processor system. The system determines whether an aligned multi-byte word in which the data of a forced atomic instruction, such as an integer store operation, is exclusive in a first level cache. If so, the forced atomic instruction is allowed to enter a second level cache pipeline. If not, the forced atomic instruction is prevented from entering the second level cache pipeline and a cache miss and fill operation is initiated to cause the aligned word to be exclusive in the first level cache.

    摘要翻译: 一种用于在多处理器系统中的多级缓存中执行强制原子指令时由于需要数据排他性而防止死锁的方法。 系统确定其中诸如整数存储操作的强制原子指令的数据在第一级高速缓存中是否排他的对齐的多字节字。 如果是这样,则强制原子指令被允许进入第二级高速缓存流水线。 如果不是,则强制原子指令被阻止进入第二级高速缓存流水线并且启动高速缓存未命中和填充操作以使对齐的字在第一级高速缓存中是排他的。