专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US5822452A System and method for narrow channel compression 失效
标题翻译：窄通道压缩的系统和方法
公开(公告)号：US5822452A
公开(公告)日：1998-10-13
申请号：US641208
申请日：1996-04-30
申请人： Gary Tarolli , Scott Sellers , James E. Margeson, III , Murali Sundaresan
发明人： Gary Tarolli , Scott Sellers , James E. Margeson, III , Murali Sundaresan
IPC分类号： G06T9/00 , H04N7/26 , G06K9/00
CPC分类号： G06T9/002 , H04N19/00
摘要： A system and method for compressing and decompressing a texture image that: (1) compresses each texel to 8 bits, and when decompressed, each texel is of a quality comparable to a 256 color palettized image; (2) increases the efficiency of the decompression system and method by eliminating complex operations, e.g., multiplication; and (3) increases the efficiency of the system and method when switching between textures that use different palettes, when compared to conventional system and methods. The invention compresses a texture image, stores the compressed texture image, and quickly and efficiently decompresses the texture image when determining a value of a pixel. The texture image compression technique utilizes a palletized color space that more closely matches the colors in the texture image while allocating an unequal number of bits to the color channels. Each texel in the texture image is converted to an 8-bit value in the selected color space, and a decompression table is generated that represents the RGB values for the each texel stored in the selected color space. In order to map the texture image to the object, one or more texels that are associated with each pixel are decompressed. The present invention quickly and efficiently decompresses each texel using a hardware decompression unit. The decompression unit does not perform any multiplication operations.
摘要翻译：一种用于压缩和解压缩纹理图像的系统和方法，所述纹理图像：（1）将每个纹素压缩为8位，并且当解压缩时，每个纹素具有与256色调色图像相当的质量; （2）通过消除复杂操作（例如乘法）来提高减压系统和方法的效率; 和（3）当与常规系统和方法相比时，在切换使用不同调色板的纹理之间时，提高了系统和方法的效率。本发明压缩纹理图像，存储压缩的纹理图像，并且在确定像素的值时快速有效地解压纹理图像。纹理图像压缩技术利用与纹理图像中的颜色更接近匹配的码垛颜色空间，同时向颜色通道分配不等位数。纹理图像中的每个纹素被转换为所选颜色空间中的8位值，并且生成表示存储在所选颜色空间中的每个纹素的RGB值的解压缩表。为了将纹理图像映射到对象，与每个像素相关联的一个或多个纹素被解压缩。本发明使用硬件解压缩单元快速有效地解压缩每个纹素。解压缩单元不执行任何乘法运算。

2. 发明申请

US20140049548A1 MEMORY SHARING VIA A UNIFIED MEMORY ARCHITECTURE 有权
标题翻译：通过统一的存储器架构存储共享
公开(公告)号：US20140049548A1
公开(公告)日：2014-02-20
申请号：US13588453
申请日：2012-08-17
申请人： Jayanth N. Rao , Murali Sundaresan
发明人： Jayanth N. Rao , Murali Sundaresan
IPC分类号： G06T11/60 , G06F12/00
CPC分类号： G06T11/60 , G06F12/00 , G06F12/0811 , G06F12/1009 , G06F12/1036 , G06F12/1081 , G06F12/109 , G06F2212/455 , G06F2212/6042 , G06F2212/62 , G06F2212/656 , G06T1/20 , G06T1/60 , Y02D10/13
摘要： A method and system for sharing memory between a central processing unit (CPU) and a graphics processing unit (GPU) of a computing device are disclosed herein. The method includes allocating a surface within a physical memory and mapping the surface to a plurality of virtual memory addresses within a CPU page table. The method also includes mapping the surface to a plurality of graphics virtual memory addresses within an I/O device page table.
摘要翻译：本文公开了一种用于在计算设备的中央处理单元（CPU）和图形处理单元（GPU）之间共享存储器的方法和系统。该方法包括在物理存储器内分配表面并将表面映射到CPU页表内的多个虚拟存储器地址。该方法还包括将表面映射到I / O设备页表中的多个图形虚拟存储器地址。

3. 发明授权

US07337339B1 Multi-level power monitoring, filtering and throttling at local blocks and globally 有权
标题翻译：在本地区域和全球进行多级电源监控，过滤和调节
公开(公告)号：US07337339B1
公开(公告)日：2008-02-26
申请号：US11162578
申请日：2005-09-15
申请人： Jack H. Choquette , Kevin B. Normoyle , Elias Atmeh , Scott D. Sellers , Murali Sundaresan , Manuel Gautho
发明人： Jack H. Choquette , Kevin B. Normoyle , Elias Atmeh , Scott D. Sellers , Murali Sundaresan , Manuel Gautho
IPC分类号： G06F1/26 , G06F1/32
CPC分类号： G06F1/3203 , G06F1/3287 , Y02D10/171 , Y02D50/20
摘要： Power management for a multi-processor chip includes a centralized global power manager that monitors global power for the whole chip, and local power managers. Local power managers manage power for local blocks such as processor cores, caches, and memory controllers. When a local block executes an instruction or accesses memory, an event is generated and looked up in a local power estimate table. A local power estimate for that event is sent to the global power manager, which sums all local power estimates received from all local blocks. An exponential moving average (EMA) is generated and compared to a global power threshold. When global power is over the threshold, local targets are sent to power managers that generate and monitor local power averages that must remain under the local target. The local block is throttled by the local power manager to reduce power when the local target is exceeded.
摘要翻译：多处理器芯片的电源管理包括一个集中的全球电源管理器，用于监控整个芯片的全球电源以及本地电源管理器。本地电源管理器管理本地块（如处理器内核，高速缓存和内存控制器）的电源。当本地块执行指令或访问存储器时，在本地功率估计表中生成并查找事件。该事件的局部功率估计被发送到全局功率管理器，其总和从所有本地块接收的所有本地功率估计。生成指数移动平均值（EMA），并与全局功率阈值进行比较。当全球电力超过阈值时，本地目标将发送给能够管理并产生并必须保持在本地目标下的局部功率平均值的电源管理员。本地电源管理器节流本地电源，以便在超出当地目标时降低电力。

4. 发明授权

US09373182B2 Memory sharing via a unified memory architecture 有权
公开(公告)号：US09373182B2
公开(公告)日：2016-06-21
申请号：US13588453
申请日：2012-08-17
申请人： Jayanth N. Rao , Murali Sundaresan
发明人： Jayanth N. Rao , Murali Sundaresan
IPC分类号： G06F15/16 , G06T11/60 , G06F12/00 , G06T1/60 , G06F12/10
CPC分类号： G06T11/60 , G06F12/00 , G06F12/0811 , G06F12/1009 , G06F12/1036 , G06F12/1081 , G06F12/109 , G06F2212/455 , G06F2212/6042 , G06F2212/62 , G06F2212/656 , G06T1/20 , G06T1/60 , Y02D10/13
摘要： A method and system for sharing memory between a central processing unit (CPU) and a graphics processing unit (GPU) of a computing device are disclosed herein. The method includes allocating a surface within a physical memory and mapping the surface to a plurality of virtual memory addresses within a CPU page table. The method also includes mapping the surface to a plurality of graphics virtual memory addresses within an I/O device page table.

5. 发明申请

US20140359220A1 Scatter/Gather Capable System Coherent Cache 有权
标题翻译：散射/收集能力系统相干缓存
公开(公告)号：US20140359220A1
公开(公告)日：2014-12-04
申请号：US14122256
申请日：2013-05-31
申请人： Altug Koker , Thomas A. Piazza , Murali Sundaresan
发明人： Altug Koker , Thomas A. Piazza , Murali Sundaresan
IPC分类号： G06F12/08
CPC分类号： G06F12/0804 , G06F12/0808 , G06F12/0811 , G06F12/0822 , G06F12/0831 , G06F12/0846 , G06F12/0853 , G06F12/0875 , G06F12/128 , G06F2212/621
摘要： In accordance with some embodiments, a scatter/gather memory approach may be enabled that is exposed or backed by system memory and uses conventional tags and addresses. Thus, such a technique may be more amenable to conventional software developers and their conventional techniques.
摘要翻译：根据一些实施例，可以启用由系统存储器公开或支持并使用常规标签和地址的分散/收集存储器方法。因此，这种技术可能更适合于常规软件开发人员及其常规技术。

6. 发明授权

US07987473B1 Accelerated class check 有权
标题翻译：加速班级检查
公开(公告)号：US07987473B1
公开(公告)日：2011-07-26
申请号：US11227419
申请日：2005-09-14
申请人： Gil Tene , Murali Sundaresan , Michael A. Wolf
发明人： Gil Tene , Murali Sundaresan , Michael A. Wolf
IPC分类号： G06F9/42
CPC分类号： G06F8/315 , G06F9/3001 , G06F9/30032 , G06F9/3004 , G06F9/30087 , G06F9/345 , G06F9/355 , G06F9/3834 , G06F9/3842 , G06F9/3857 , G06F9/3863 , G06F9/461
摘要： Determining a class of an object is disclosed. A pointer of the object is obtained. One or more bits that are not implemented as address bits are extracted from the pointer. The one or more bits are interpreted as an identifier of the class of the object. The class of the object is determined to correspond to the identifier.
摘要翻译：公开了确定对象的类别。获取对象的指针。从指针中提取未实现为地址位的一个或多个位。一个或多个位被解释为对象的类的标识符。确定对象的类对应于标识符。

7. 发明授权

US08843944B2 Accelerated class check 有权
标题翻译：加速班级检查
公开(公告)号：US08843944B2
公开(公告)日：2014-09-23
申请号：US13157170
申请日：2011-06-09
申请人： Gil Tene , Murali Sundaresan , Michael A. Wolf
发明人： Gil Tene , Murali Sundaresan , Michael A. Wolf
IPC分类号： G06F9/54 , G06F9/46 , G06F9/30 , G06F9/38 , G06F9/345 , G06F9/355
CPC分类号： G06F8/315 , G06F9/3001 , G06F9/30032 , G06F9/3004 , G06F9/30087 , G06F9/345 , G06F9/355 , G06F9/3834 , G06F9/3842 , G06F9/3857 , G06F9/3863 , G06F9/461
摘要： Determining a class of an object is disclosed. A pointer of the object is obtained. One or more bits that are not implemented as address bits are extracted from the pointer. The one or more bits are interpreted as an identifier of the class of the object. The class of the object is determined to correspond to the identifier.
摘要翻译：公开了确定对象的类别。获取对象的指针。从指针中提取未实现为地址位的一个或多个位。一个或多个位被解释为对象的类的标识符。确定对象的类对应于标识符。

8. 发明授权

US08839274B2 Accelerated class check 有权
标题翻译：加速班级检查
公开(公告)号：US08839274B2
公开(公告)日：2014-09-16
申请号：US13227111
申请日：2011-09-07
申请人： Gil Tene , Cliff N. Click, Jr. , Murali Sundaresan , Michael A. Wolf
发明人： Gil Tene , Cliff N. Click, Jr. , Murali Sundaresan , Michael A. Wolf
IPC分类号： G06F9/54 , G06F9/30 , G06F9/44
CPC分类号： G06F9/4428 , G06F9/3016 , G06F9/30167 , G06F9/4488 , G06F9/449 , G06F9/455
摘要： Handling a virtual method call includes extracting, from a pointer to an object, an identifier associated with the class of the object, the pointer to the object being associated with the virtual method call, and the identifier being embedded within the pointer; using the identifier to obtain a virtual method table, including locating a first entry in a class identifier table mapping a plurality of class identifiers to a corresponding plurality of class data, the first entry being associated with the identifier and comprising the virtual method table or a pointer used to obtain the virtual method table; locating a second entry in the virtual method table, the second entry being associated with the virtual method call; and jumping to an address associated with the second entry to execute code at the address.
摘要翻译：处理虚拟方法调用包括从对象的指针提取与对象的类相关联的标识符，与虚拟方法调用相关联的对象的指针，以及嵌入在指针内的标识符; 使用所述标识符来获得虚拟方法表，包括将映射多个类标识符的类标识符表中的第一条目定位到对应的多个类数据，所述第一条目与所述标识符相关联，并且包括所述虚方法表或指针用于获取虚拟方法表; 在虚拟方法表中定位第二条目，第二条目与虚拟方法调用相关联; 并跳转到与第二条目相关联的地址，以在该地址处执行代码。

9. 发明授权

US08037482B1 Accelerated class check 有权
标题翻译：加速班级检查
公开(公告)号：US08037482B1
公开(公告)日：2011-10-11
申请号：US11296652
申请日：2005-12-06
申请人： Gil Tene , Cliff N. Click, Jr. , Murali Sundaresan , Michael A. Wolf
发明人： Gil Tene , Cliff N. Click, Jr. , Murali Sundaresan , Michael A. Wolf
IPC分类号： G06F9/42
CPC分类号： G06F9/4428 , G06F9/3016 , G06F9/30167 , G06F9/4488 , G06F9/449 , G06F9/455
摘要： Reaching a determination associated with a class of an object is disclosed. An identifier associated with the class of the object is extracted from a pointer to the object. The extracted identifier is compared to a comparison value. At least in part using a result of the comparison a determination is reached.
摘要翻译：公开了与对象类别相关联的确定。从对象的指针中提取与对象的类相关联的标识符。将提取的标识符与比较值进行比较。至少部分地使用比较的结果来确定。

10. 发明申请

US20110321064A1 ACCELERATED CLASS CHECK 有权
标题翻译：加速类检查
公开(公告)号：US20110321064A1
公开(公告)日：2011-12-29
申请号：US13227111
申请日：2011-09-07
申请人： Gil Tene , Cliff N. Click, JR. , Murali Sundaresan , Michael A. Wolf
发明人： Gil Tene , Cliff N. Click, JR. , Murali Sundaresan , Michael A. Wolf
IPC分类号： G06F9/42
CPC分类号： G06F9/4428 , G06F9/3016 , G06F9/30167 , G06F9/4488 , G06F9/449 , G06F9/455
摘要： Handling a virtual method call includes extracting, from a pointer to an object, an identifier associated with the class of the object, the pointer to the object being associated with the virtual method call, and the identifier being embedded within the pointer; using the identifier to obtain a virtual method table, including locating a first entry in a class identifier table mapping a plurality of class identifiers to a corresponding plurality of class data, the first entry being associated with the identifier and comprising the virtual method table or a pointer used to obtain the virtual method table; locating a second entry in the virtual method table, the second entry being associated with the virtual method call; and jumping to an address associated with the second entry to execute code at the address.
摘要翻译：处理虚拟方法调用包括从对象的指针提取与对象的类相关联的标识符，与虚拟方法调用相关联的对象的指针，以及嵌入在指针内的标识符; 使用所述标识符来获得虚拟方法表，包括将映射多个类标识符的类标识符表中的第一条目定位到对应的多个类数据，所述第一条目与所述标识符相关联，并且包括所述虚方法表或指针用于获取虚拟方法表; 在虚拟方法表中定位第二条目，第二条目与虚拟方法调用相关联; 并跳转到与第二条目相关联的地址，以在该地址处执行代码。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式