公开(公告)号：US06675376B2

公开(公告)日：2004-01-06

申请号：US09752233

申请日：2000-12-29

申请人： Ronny Ronen ,  Alexander Peleg ,  Nathaniel Hoffman

发明人： Ronny Ronen ,  Alexander Peleg ,  Nathaniel Hoffman

IPC分类号： G06F945

CPC分类号： G06F9/3001 ,  G06F9/30123 ,  G06F9/3017 ,  G06F9/3853 ,  G06F9/3893

摘要： A system and method for producing a fused instruction is described. In one embodiment, a first instruction and a second instruction that are both simple instructions (e.g., perform only one operation) and are dependent are fused together to create the fused instruction. The fused instruction has an opcode that represents the operation performed by the first instruction and the operation performed by the second instruction. The fused instruction has three source operands and one destination operand. Two of the three source operands are the two source operands of the first instruction, and the third source operand is the source operand of the second instruction that is not the destination operand of the first instruction. The destination operand of the fused instruction is the destination operand of the second instruction. An execution unit that can execute a fused instruction in one clock cycle is also disclosed. In one embodiment, the execution unit has two arithmetic logic units (“ALUs”), each of the ALUs performs one of the two operations of the fused instruction. The result of the first ALU is input into the second ALU to produce the desired result.

摘要翻译： 描述用于产生融合指令的系统和方法。 在一个实施例中，作为简单指令（例如，仅执行一个操作）并且是依赖的第一指令和第二指令被融合在一起以创建融合指令。 融合指令具有表示由第一指令执行的操作和由第二指令执行的操作的操作码。 融合指令有三个源操作数和一个目标操作数。 三个源操作数中的两个是第一个指令的两个源操作数，第三个源操作数是不是第一个指令的目标操作数的第二个指令的源操作数。 融合指令的目标操作数是第二条指令的目标操作数。 还公开了可以在一个时钟周期执行融合指令的执行单元。 在一个实施例中，执行单元具有两个算术逻辑单元（“ALU”），每个ALU执行融合指令的两个操作之一。 将第一ALU的结果输入到第二ALU中以产生期望的结果。

公开(公告)号：US07458069B2

公开(公告)日：2008-11-25

申请号：US10752875

申请日：2004-01-06

申请人： Ronny Ronen ,  Alexander Peleg ,  Nathaniel Hoffman

发明人： Ronny Ronen ,  Alexander Peleg ,  Nathaniel Hoffman

IPC分类号： G06F9/45

CPC分类号： G06F9/3001 ,  G06F9/30123 ,  G06F9/3017 ,  G06F9/3853 ,  G06F9/3893

摘要： A system and method for producing a fused instruction is described. In one embodiment, a first instruction and a second instruction that are both simple instructions (e.g., perform only one operation) and are dependent are fused together to create the fused instruction. The fused instruction has an opcode that represents the operation performed by the first instruction and the operation performed by the second instruction. The fused instruction has three source operands and one destination operand. Two of the three source operands are the two source operands of the first instruction, and the third source operand is the source operand of the second instruction that is not the destination operand of the first instruction. The destination operand of the fused instruction is the destination operand of the second instruction. An execution unit that can execute a fused instruction in one clock cycle is also disclosed. In one embodiment, the execution unit has two arithmetic logic units (“ALUs”), each of the ALUs performs one of the two operations of the fused instruction. The result of the first ALU is input into the second ALU to produce the desired result.

摘要翻译： 描述用于产生融合指令的系统和方法。 在一个实施例中，作为简单指令（例如，仅执行一个操作）并且是依赖的第一指令和第二指令被融合在一起以创建融合指令。 融合指令具有表示由第一指令执行的操作和由第二指令执行的操作的操作码。 融合指令有三个源操作数和一个目标操作数。 三个源操作数中的两个是第一个指令的两个源操作数，第三个源操作数是不是第一个指令的目标操作数的第二个指令的源操作数。 融合指令的目标操作数是第二条指令的目标操作数。 还公开了可以在一个时钟周期执行融合指令的执行单元。 在一个实施例中，执行单元具有两个算术逻辑单元（“ALU”），每个ALU执行融合指令的两个操作之一。 将第一ALU的结果输入到第二ALU中以产生期望的结果。

公开(公告)号：US08149242B2

公开(公告)日：2012-04-03

申请号：US11927855

申请日：2007-10-30

申请人： Eric Langyel ,  Pal-Kristian Engstad ,  Mark Evan Cerny ,  Nathaniel Hoffman ,  Jon Olick ,  Motoi Kaneko ,  Yoshinori Washizu

发明人： Eric Langyel ,  Pal-Kristian Engstad ,  Mark Evan Cerny ,  Nathaniel Hoffman ,  Jon Olick ,  Motoi Kaneko ,  Yoshinori Washizu

IPC分类号： G06T1/00

CPC分类号： G06T15/005 ,  G06T2210/52

摘要： There is provided a graphics processing system that includes a main processing unit and a graphics processing unit (GPU). The main processing unit puts rendering commands generated using a graphics library in the queue of a command buffer in a main memory. In this process, the library function offered by the graphics library is converted into the rendering commands, without any rendering attributes retained in the library. The GPU reads and executes the rendering commands stacked in the command buffer, and generates rendering data in a frame buffer.

摘要翻译： 提供了包括主处理单元和图形处理单元（GPU）的图形处理系统。 主处理单元将使用图形库生成的渲染命令放在主存储器中的命令缓冲器的队列中。 在这个过程中，图形库提供的库函数被转换为渲染命令，而不会在库中保留任何渲染属性。 GPU读取并执行堆叠在命令缓冲器中的渲染命令，并在帧缓冲器中生成渲染数据。

公开(公告)号：US20100128038A1

公开(公告)日：2010-05-27

申请号：US12323340

申请日：2008-11-25

申请人： Nathaniel Hoffman ,  Vassily A. Filippov

发明人： Nathaniel Hoffman ,  Vassily A. Filippov

IPC分类号： G06T15/60

CPC分类号： G06T15/506

摘要： A method for use in computer graphics includes establishing a surface that is represented by at least one polygon that includes a plurality of vertices, establishing one or more light sources that are configured to illuminate the surface, for each vertex of the polygon, computing at least one vector quantity that represents an aggregation of a visual attribute and a direction of each of the one or more light sources, and interpolating the computed vector quantities across the polygon to provide at least one interpolated vector quantity value for each of a plurality of pixels included in the polygon. A storage medium stores a computer program, and an apparatus includes a display and a processor based system.

摘要翻译： 一种用于计算机图形学的方法包括建立一个表面，该表面由至少一个多边形表示，该多边形包括多个顶点，为多边形的每个顶点建立配置成照亮表面的一个或多个光源，至少计算 一个矢量数量，其表示视觉属性和一个或多个光源中的每一个的方向的聚集，并且内插所述多边形的所计算的向量量，以对包括的多个像素中的每个像素提供至少一个内插向量数值 在多边形。 存储介质存储计算机程序，并且装置包括显示器和基于处理器的系统。

公开(公告)号：US20100128037A1

公开(公告)日：2010-05-27

申请号：US12323306

申请日：2008-11-25

申请人： Nathaniel Hoffman ,  Vassily A. Filippov

发明人： Nathaniel Hoffman ,  Vassily A. Filippov

IPC分类号： G06T15/50

CPC分类号： G06T15/506

摘要： A method for use in computer graphics includes establishing a surface that is represented by at least one polygon that includes a plurality of vertices, establishing one or more light sources that are configured to illuminate the surface, and computing an aggregate light source position for each vertex of the polygon, wherein the computation for each vertex includes averaging directions from the vertex to the one or more light sources. A storage medium stores a computer program, and an apparatus includes a display and a processor based system.

摘要翻译： 一种用于计算机图形学的方法包括建立由包括多个顶点的至少一个多边形表示的表面，建立被配置为照亮表面的一个或多个光源，以及计算每个顶点的聚集光源位置 的多边形，其中每个顶点的计算包括从顶点到一个或多个光源的平均方向。 存储介质存储计算机程序，并且装置包括显示器和基于处理器的系统。

公开(公告)号：US08355022B2

公开(公告)日：2013-01-15

申请号：US12323306

申请日：2008-11-25

申请人： Nathaniel Hoffman ,  Vassily A. Filippov

发明人： Nathaniel Hoffman ,  Vassily A. Filippov

IPC分类号： G06T15/50 ,  G06T15/60

CPC分类号： G06T15/506

摘要： A method for use in computer graphics includes establishing a surface that is represented by at least one polygon that includes a plurality of vertices, establishing one or more light sources that are configured to illuminate the surface, and computing an aggregate light source position for each vertex of the polygon, wherein the computation for each vertex includes averaging directions from the vertex to the one or more light sources. A storage medium stores a computer program, and an apparatus includes a display and a processor based system.

摘要翻译： 一种用于计算机图形学的方法包括建立由包括多个顶点的至少一个多边形表示的表面，建立被配置为照亮表面的一个或多个光源，以及计算每个顶点的聚集光源位置 的多边形，其中每个顶点的计算包括从顶点到一个或多个光源的平均方向。 存储介质存储计算机程序，并且装置包括显示器和基于处理器的系统。

公开(公告)号：US20090002380A1

公开(公告)日：2009-01-01

申请号：US11927855

申请日：2007-10-30

申请人： Eric Langyel ,  Pal-Kristian Engstad ,  Mark Evan Cerny ,  Nathaniel Hoffman ,  Jon Olick ,  Motoi Kaneko ,  Yoshinori Washizu

发明人： Eric Langyel ,  Pal-Kristian Engstad ,  Mark Evan Cerny ,  Nathaniel Hoffman ,  Jon Olick ,  Motoi Kaneko ,  Yoshinori Washizu

IPC分类号： G06T1/00 ,  G06T1/60

CPC分类号： G06T15/005 ,  G06T2210/52

摘要： There is provided a graphics processing system that includes a main processing unit and a graphics processing unit (GPU). The main processing unit puts rendering commands generated using a graphics library in the queue of a command buffer in a main memory. In this process, the library function offered by the graphics library is converted into the rendering commands, without any rendering attributes retained in the library. The GPU reads and executes the rendering commands stacked in the command buffer, and generates rendering data in a frame buffer.

摘要翻译： 提供了包括主处理单元和图形处理单元（GPU）的图形处理系统。 主处理单元将使用图形库生成的渲染命令放在主存储器中的命令缓冲器的队列中。 在这个过程中，图形库提供的库函数被转换为渲染命令，而不会在库中保留任何渲染属性。 GPU读取并执行堆叠在命令缓冲器中的渲染命令，并在帧缓冲器中生成渲染数据。

公开(公告)号：US06370559B1

公开(公告)日：2002-04-09

申请号：US09354004

申请日：1999-07-13

申请人： Nathaniel Hoffman

发明人： Nathaniel Hoffman

IPC分类号： G06F752

CPC分类号： G06F7/5324 ,  G06F9/30014 ,  G06F9/30025 ,  G06F9/30036 ,  G06F2207/3828

摘要： A method and apparatus for performing N bit by 2*N (or 2*N−1) bit signed multiplication using two N bit multiply instructions. According to one aspect of the invention, a method for performing signed multiplication of A times B (where B has N bits and A has N*2 bits) is described. In this method, Ahigh and Alow respectively represent the most and least significant halves of A. According to this method, Alow is logically shifted right by one bit to generate Alow>>1. Then, Alow>>1 is multiplied by B using signed multiplication to generate a first partial result. In addition, a second partial result is generated by performing signed multiplication of Ahigh times B. One or both of the first and second partial results is shifted to align the first and second partial results for addition, and then the addition is performed to generate a final result representing A multiplied by B.

摘要翻译： 一种使用两个N位乘法指令执行N比特乘以2 * N（或2 * N-1）比特带符号乘法的方法和装置。 根据本发明的一个方面，描述了执行A次B（其中B具有N位且A具有N * 2位）的有符号乘法的方法。 在这种方法中，Ahigh和Alow分别表示A中最大和最不重要的一半。根据该方法，Alow在逻辑上向右移位一位以产生Alow >> 1。 然后，使用带符号乘法将Alow >> 1乘以B，以产生第一部分结果。 另外，通过执行Ahigh次数B的有符号乘法来生成第二部分结果。移位第一和第二部分结果中的一个或两个以对齐第一和第二部分结果以进行相加，然后执行相加以产生 最终结果代表A乘以B.

公开(公告)号：US6052769A

公开(公告)日：2000-04-18

申请号：US52881

申请日：1998-03-31

申请人： Thomas R. Huff ,  Shreekant Thakkar ,  Nathaniel Hoffman

发明人： Thomas R. Huff ,  Shreekant Thakkar ,  Nathaniel Hoffman

IPC分类号： G06F9/30 ,  G06F9/315 ,  G06F15/80

CPC分类号： G06F9/30032 ,  G06F9/30036 ,  G06F9/30163

摘要： A method comprises decoding a single instruction having a first operand identifying a plurality of bytes of packed data and a second operand identifying a corresponding plurality of byte masks. Each of the plurality of byte masks identified by the second operand of the single decoded instruction are analyzed, wherein select bytes of the plurality of bytes identified by the first operand are moved to an implicitly defined location based, at least in part, on the analysis of the individual byte masks identified by the second operand of the single decoded instruction.

摘要翻译： 一种方法包括解码具有标识多个打包数据字节的第一操作数的单个指令和识别对应的多个字节掩码的第二操作数。 分析由单一解码指令的第二操作数标识的多个字节掩码中的每一个，其中由第一操作数识别的多个字节中的选择字节被至少部分地基于分析移动到隐含定义的位置 由单个解码指令的第二个操作数标识的单个字节掩码。

公开(公告)号：US6014684A

公开(公告)日：2000-01-11

申请号：US822846

申请日：1997-03-24

申请人： Nathaniel Hoffman

发明人： Nathaniel Hoffman

IPC分类号： G06F7/52 ,  G06F9/30 ,  G06F9/302

CPC分类号： G06F7/5324 ,  G06F9/30014 ,  G06F9/30025 ,  G06F9/30036 ,  G06F2207/3828

摘要： A method and apparatus for performing N bit by 2*N (or 2*N-1) bit signed multiplication using two N bit multiply instructions. According to one aspect of the invention, a method for performing signed multiplication of A times B (where B has N bits and A has N*2 bits) is described. In this method, A.sub.high and A.sub.low respectively represent the most and least significant halves of A. According to this method, A.sub.low is logically shifted right by one bit to generate A.sub.low >>1. Then, A.sub.low >>1 is multiplied by B using signed multiplication to generate a first partial result. In addition, a second partial result is generated by performing signed multiplication of A.sub.high times B. One or both of the first and second partial results is shifted to align the first and second partial results for addition, and then the addition is performed to generate a final result representing A multiplied by B.

摘要翻译： 一种使用两个N位乘法指令执行N比特乘以2 * N（或2 * N-1）比特带符号乘法的方法和装置。 根据本发明的一个方面，描述了执行A次B（其中B具有N位且A具有N * 2位）的有符号乘法的方法。 在这种方法中，Ahigh和Alow分别表示A中最大和最不重要的一半。根据该方法，Alow在逻辑上向右移位一位以产生Alow >> 1。 然后，使用带符号乘法将Alow >> 1乘以B，以产生第一部分结果。 另外，通过执行Ahigh次数B的有符号乘法来生成第二部分结果。移位第一和第二部分结果中的一个或两个以对齐第一和第二部分结果以进行相加，然后执行相加以产生 最终结果代表A乘以B.