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. 发明申请

WO2016000129A1 ADAPTIVE PARTITION MECHANISM WITH ARBITRARY TILE SHAPE FOR TILE BASED RENDERING GPU ARCHITECTURE 审中-公开
标题翻译：具有基于渲染GPU架构的ARBITRARY TILE形状的自适应分割机制
公开(公告)号：WO2016000129A1
公开(公告)日：2016-01-07
申请号：PCT/CN2014/081164
申请日：2014-06-30
申请人： INTEL CORPORATION , YANG, Yi , CHEN, Xiaoming , CHEN, Feng , HAO, Yan
发明人： YANG, Yi , CHEN, Xiaoming , CHEN, Feng , HAO, Yan
IPC分类号： G06T15/00
CPC分类号： G06T15/005 , G06T1/60 , G06T11/40 , G06T15/04 , G06T2200/04
摘要： Methods and apparatus relating to an adaptive partition mechanism with arbitrary tile shape for tile based rendering GPU (Graphics Processing Unit) architecture are described. In an embodiment, the primitive intersection cost value for each atomic tile of an image are determined at least partially based on a vertex element size, a vertex shader length, and a number of the vertices of a primitive of the image. Other embodiments are also disclosed and claimed.
摘要翻译：描述了与基于瓦片的渲染GPU（图形处理单元）架构的具有任意瓦片形状的自适应分区机构有关的方法和装置。在一个实施例中，至少部分地基于图像的原始图元的顶点元素大小，顶点着色器长度和顶点的数量来确定图像的每个原子瓦片的原始交叉点成本值。还公开并要求保护其他实施例。

2. 发明申请

WO2016090606A1 TRUSTED PREDICTIVE ANALYTIC EXECUTION MIDDLEWARE 审中-公开
标题翻译： TRUSTED预测分析执行中间件
公开(公告)号：WO2016090606A1
公开(公告)日：2016-06-16
申请号：PCT/CN2014/093600
申请日：2014-12-11
申请人： INTEL CORPORATION , CHEN, Feng , HAO, Yan , YANG, Yi , CHEN, Xiaoming
发明人： CHEN, Feng , HAO, Yan , YANG, Yi , CHEN, Xiaoming
IPC分类号： G06F21/30
CPC分类号： G06F21/10 , G06F21/74
摘要： A computing system includes technologies for providing trusted predictive analytics services. The computing system provides a common description language for predictive analytics services, and uses cryptographic techniques and digital rights management techniques to protect input data and/or portions of the predictive analytics services.
摘要翻译：计算系统包括用于提供可信任预测分析服务的技术。计算系统为预测分析服务提供通用描述语言，并使用加密技术和数字版权管理技术来保护输入数据和/或部分预测分析服务。

3. 发明申请

WO2016090535A1 GRAPHIC RENDERING QUALITY IMPROVEMENTS THROUGH AUTOMATED DATA TYPE PRECISION CONTROL 审中-公开
标题翻译：通过自动数据类型精确控制的图形渲染质量改进
公开(公告)号：WO2016090535A1
公开(公告)日：2016-06-16
申请号：PCT/CN2014/093296
申请日：2014-12-08
申请人： INTEL CORPORATION , CHEN, Feng , YANG, Yi , CHEN, Xiaoming
发明人： CHEN, Feng , YANG, Yi , CHEN, Xiaoming
IPC分类号： G06T15/10
CPC分类号： G06T15/80 , G06F9/30014 , G06F9/3861 , G06T1/20 , G06T15/005
摘要： One or more system, apparatus, method, and computer readable media is described below for automated data type precision control capable of improving rendering quality on a graphics processor. Perceptible rendering quality is dependent at least in part on number format precision (e.g., FP16 or FP32) employed for shader program variables. In accordance with embodiments, shader variables implemented in lower precision data formats are tracked during shader compile to identify those that might trigger a floating point overflow and/or underflow exception. For shaders including one or more such variable, resources are provided to automatically monitor overflow and/or underflow exceptions during shader execution. In further embodiments, shader code is automatically re-generated based, at least in part, upon occurrences of such exceptions, and an increased number format precision specified for one or more of the tracked shader variables.
摘要翻译：下面描述一种或多种系统，装置，方法和计算机可读介质，用于能够改善图形处理器上的渲染质量的自动数据类型精度控制。可感知的渲染质量至少部分取决于用于着色器程序变量的数字格式精度（例如，FP16或FP32）。根据实施例，在着色器编译期间跟踪以较低精度数据格式实现的着色器变量，以识别那些可能触发浮点溢出和/或下溢异常的变量。对于包括一个或多个此类变量的着色器，提供资源以在着色器执行期间自动监视溢出和/或下溢异常。在另外的实施例中，着色器代码至少部分地基于这种异常的出现以及为一个或多个跟踪的着色器变量指定的增加的数字格式精度而自动重新生成。

4. 发明申请

WO2014134771A1 ENERGY AWARE INFORMATION PROCESSING FRAMEWORK FOR COMPUTATION AND COMMUNICATION DEVICES (CCD) COUPLED TO A CLOUD 审中-公开
标题翻译：用于与云组合的计算和通信设备（CCD）的能量知识信息处理框架
公开(公告)号：WO2014134771A1
公开(公告)日：2014-09-12
申请号：PCT/CN2013/072125
申请日：2013-03-04
申请人： INTEL CORPORATION , YANG, Rongzhen , YIN, Hujun , CHEN, Feng , WU, Johnson, Z , HAO, Yan, Mars , YANG, Yi
发明人： YANG, Rongzhen , YIN, Hujun , CHEN, Feng , WU, Johnson, Z , HAO, Yan, Mars , YANG, Yi
IPC分类号： G06F9/50
CPC分类号： G06F9/5094 , G06F9/4893 , Y02D10/22
摘要： An energy aware framework for computation and communication devices (CCDs) is disclosed. CCDs may support applications, which may participate in energy aware optimization. Such applications may be designed to support execution modes, which may be associated with different computation and communication demands or requirements. An optimization block may collect computation requirement values (CRVM), communication demand values (CDVM), and such other values of each execution mode to perform a specific task(s). The optimization block may collect computation energy cost information (CECIM) and multi-radio communication energy cost information (MCECIM) for each execution mode. Also, the optimization block may collect the workload values of a cloud-side processing device. The optimization block may determine power estimation values (PEV), based on the energy cost values (CECIM), (MCECIM), CRVM, and CDVM. The optimization block may then determine the execution mode or the apparatus best suited to perform the tasks.
摘要翻译：公开了一种用于计算和通信设备（CCD）的能量感知框架。 CCD可以支持可能参与能量感知优化的应用。这样的应用可以被设计为支持可能与不同计算和通信需求或需求相关联的执行模式。优化块可以收集计算需求值（CRVM），通信需求值（CDVM）以及每个执行模式的其他值以执行特定的任务。优化块可以针对每个执行模式收集计算能量成本信息（CECIM）和多无线电通信能量成本信息（MCECIM）。此外，优化块可以收集云端处理设备的工作负载值。优化块可以基于能量成本值（CECIM），（MCECIM），CRVM和CDVM来确定功率估计值（PEV）。然后，优化块可以确定执行模式或者最适于执行任务的装置。

5. 发明申请

WO2013071485A1 SCHEDULING THREAD EXECUTION BASED ON THREAD AFFINITY 审中-公开
标题翻译：基于线程调度螺纹执行
公开(公告)号：WO2013071485A1
公开(公告)日：2013-05-23
申请号：PCT/CN2011/082215
申请日：2011-11-15
申请人： INTEL CORPORATION , CHEN, Feng , HAO, Yan , FU, Jin
发明人： CHEN, Feng , HAO, Yan , FU, Jin
IPC分类号： G06F9/46
CPC分类号： G06F9/46 , G06F9/4881 , G06F9/5033 , G06T15/00
摘要： In accordance with some embodiments, spatial and temporal locality between threads executing on graphics processing units may be analyzed and tracked in order to improve performance. In some applications where a large number of threads are executed and those threads use common resources such as common data, affinity tracking may be used to improve performance by reducing the cache miss rate and to more effectively use relatively small-sized caches.
摘要翻译：根据一些实施例，可以分析和跟踪在图形处理单元上执行的线程之间的空间和时间局部性，以便提高性能。在一些执行大量线程并且这些线程使用公共资源（例如公共数据）的应用中，可以使用亲和度跟踪来降低高速缓存未命中率并更有效地使用相对小尺寸的高速缓存。

6. 发明申请

WO2017201676A1 SELF-ADAPTIVE WINDOW MECHANISM 审中-公开
标题翻译：自适应窗口机制
公开(公告)号：WO2017201676A1
公开(公告)日：2017-11-30
申请号：PCT/CN2016/083192
申请日：2016-05-24
申请人： INTEL CORPORATION , CHEN, Feng , YANG, Yi , CHEN, Zhenyang
发明人： CHEN, Feng , YANG, Yi , CHEN, Zhenyang
IPC分类号： G06N3/08
CPC分类号： G06N3/08 , G06N3/0454
摘要： A mechanism is described for facilitating training of Convolutional Neural Network (CNN) logic. A method of embodiments, as described herein, includes performing a sensitivity scan on an input image using a self-adaptive bi-direction mask (SABM) window structure and a normalized sensitivity map, wherein the SABM window structure is based on the input image and training Convolutional Neural Network (CNN) logic based on the results of the sensitivity scan.
摘要翻译：描述了用于促进卷积神经网络（CNN）逻辑的训练的机制。如本文所述，实施例的方法包括使用自适应双向掩模（SABM）窗口结构和归一化灵敏度图对输入图像执行灵敏度扫描，其中SABM窗口结构基于输入图像并且根据灵敏度扫描的结果训练卷积神经网络（CNN）逻辑。

7. 发明申请

WO2006092079A1 MINING FOR PERFORMANCE DATA FOR SYSTEMS WITH DYNAMIC COMPILERS 审中-公开
标题翻译：采用动态编译器进行系统性能数据采集
公开(公告)号：WO2006092079A1
公开(公告)日：2006-09-08
申请号：PCT/CN2005/000258
申请日：2005-03-03
申请人： INTEL CORPORATION , YANG, Rongzhen , CHEN, Feng
发明人： YANG, Rongzhen , CHEN, Feng
IPC分类号： G06F9/45
CPC分类号： G06F11/3612 , G06F9/45516
摘要： In an example data mining process, performance data for instructions that execute in a data processing system is obtained. The performance data may comprise instruction addresses and corresponding performance information. A dump that comprises the instructions and corresponding instruction addresses may also be obtained. Common code segments in the dump may be automatically identified. A common code segment may comprise an ordered set of multiple instructions that appears multiple times in the dump. Aggregate performance data for the code segments may be generated, based at least in part on (a) the instruction addresses associated with the common code segments in the dump, and (b) the instruction addresses and the corresponding performance information performance data. Other embodiments are described and claimed.
摘要翻译：在示例数据挖掘过程中，获得在数据处理系统中执行的指令的性能数据。性能数据可以包括指令地址和对应的性能信息。还可以获得包括指令和对应指令地址的转储。可以自动识别转储中的公共代码段。公共代码段可以包括在转储中出现多次的多个指令的有序集合。可以至少部分地基于（a）与转储中的公共代码段相关联的指令地址，以及（b）指令地址和相应的性能信息性能数据来生成代码段的总体性能数据。描述和要求保护其他实施例。

8. 发明申请

WO2013101179A1 WRITE MECHANISM FOR STORAGE CLASS MEMORY 审中-公开
标题翻译：存储类存储器的写入机制
公开(公告)号：WO2013101179A1
公开(公告)日：2013-07-04
申请号：PCT/US2011/068086
申请日：2011-12-30
申请人： INTEL CORPORATION , CHEN, Feng , MESNIER, Michael P.
发明人： CHEN, Feng , MESNIER, Michael P.
IPC分类号： G06F12/00 , G06F12/16 , G06F13/16 , G06F9/06
CPC分类号： G06F3/0656 , G06F3/0611 , G06F3/0679 , G06F12/0238 , G06F12/0246 , G06F12/1009 , G06F12/14 , G06F12/1433 , G06F2212/7205
摘要： Storage class memory may be used in an architecture to achieve high performance, high reliability, high compatibility. In some embodiments, reads may be handled in a conventional way used in a memory based model. However writes do not use a memory based model but instead correspond to a storage based model. The hybrid nature can be achieved by setting the storage class memory to be write protected so that all writes must go through a software based block device interface. In some embodiments, the software based block device interface prevents erroneous writes to the storage class memory.
摘要翻译：存储类内存可用于架构，以实现高性能，高可靠性，高兼容性。在一些实施例中，读取可以以基于存储器的模型中使用的常规方式来处理。但是，写入不使用基于内存的模型，而是对应于基于存储的模型。可以通过将存储类存储器设置为写保护来实现混合性质，以便所有写操作都必须通过基于软件的块设备接口。在一些实施例中，基于软件的块设备接口防止对存储类存储器的错误写入。

9. 发明申请

WO2022133814A1 OMNI-SCALE CONVOLUTION FOR CONVOLUTIONAL NEURAL NETWORKS 审中-公开
公开(公告)号：WO2022133814A1
公开(公告)日：2022-06-30
申请号：PCT/CN2020/138664
申请日：2020-12-23
申请人： INTEL CORPORATION , YAO, Anbang , LIU, Bo , LU, Ming , CHEN, Feng , CHEN, Yurong
发明人： YAO, Anbang , LIU, Bo , LU, Ming , CHEN, Feng , CHEN, Yurong
IPC分类号： G06K9/00
摘要： Omni-scale convolution for convolutional neural networks is disclosed. An example of an apparatus includes one or more processors to process data, including processing for a convolutional neural network (CNN); and a memory to store data, including CNN data, wherein processing of input data by the CNN includes implementing omni-scale convolution in one or more convolutional layers of the CNN, implementation of the omni-scale convolution into a convolutional layer of the one or more convolutional layers including at least applying multiple dilation rates in a plurality of kernels of a kernel lattice of the convolutional layer, and applying a cyclic pattern for the multiple dilation rates in the plurality of kernels of the convolutional layer.

10. 发明申请

WO2014008073A1 SOUNDING REFERENCE SIGNAL (SRS) MECHANISM FOR INTRACELL DEVICE-TO-DEVICE (D2D) COMMUNICATION 审中-公开
标题翻译：用于INTRACELL设备到设备（D2D）通信的声音参考信号（SRS）机制
公开(公告)号：WO2014008073A1
公开(公告)日：2014-01-09
申请号：PCT/US2013/048018
申请日：2013-06-27
申请人： INTEL CORPORATION , HE, Hong , HAN, Seunghee , HEO, Youn Hyoung , FWU, Jong-Kae , CHOI, Hyung-Nam , FONG, Mo-Han , ZHANG, Yujian , PHUYAL, Umesh , YANG, Rongzhen , CHEN, Feng , YIN, Hujun , CHEN, Xiaogang
发明人： HE, Hong , HAN, Seunghee , HEO, Youn Hyoung , FWU, Jong-Kae , CHOI, Hyung-Nam , FONG, Mo-Han , ZHANG, Yujian , PHUYAL, Umesh , YANG, Rongzhen , CHEN, Feng , YIN, Hujun , CHEN, Xiaogang
IPC分类号： H04W48/16 , H04B7/24
CPC分类号： H04L1/1861 , H04L1/0025 , H04L1/0026 , H04L1/1628 , H04L1/1812 , H04L1/1854 , H04L1/1887 , H04L5/0048 , H04L5/0053 , H04L5/0055 , H04L5/0073 , H04L5/14 , H04W4/70 , H04W24/10 , H04W28/0205 , H04W28/08 , H04W36/22 , H04W48/12 , H04W52/0206 , H04W52/0209 , H04W52/0212 , H04W52/0245 , H04W52/383 , H04W68/00 , H04W72/005 , H04W72/0413 , H04W72/042 , H04W72/0446 , H04W72/046 , H04W88/08 , H04W92/02 , Y02D70/00 , Y02D70/1222 , Y02D70/1224 , Y02D70/1242 , Y02D70/1262 , Y02D70/1264 , Y02D70/142 , Y02D70/144 , Y02D70/146 , Y02D70/164 , Y02D70/21 , Y02D70/22 , Y02D70/23 , Y02D70/24 , Y02D70/25 , Y02E40/62
摘要： Technology for device discovery using a device-to-device (D2D) sounding reference signal (SRS) and device discovery using D2D SRS in a channel measurement group (CMG) is disclosed. In an example, a user equipment (UE) configured for device discovery via a node using the D2D SRS can include a transceiver module. The transceiver module can send a radio resource control (RRC) device discovery request to a node, scan D2D SRS subframes of proximity UEs using D2D SRS triggering, and send feedback to the node of detected D2D SRS information of the proximity UEs. The proximity UE can be located within a same cell as the UE.
摘要翻译：公开了使用设备到设备（D2D）探测参考信号（SRS）的设备发现技术和在信道测量组（CMG）中使用D2D SRS的设备发现。在一个示例中，被配置用于经由使用D2D SRS的节点进行设备发现的用户设备（UE）可以包括收发器模块。收发器模块可以向节点发送无线电资源控制（RRC）设备发现请求，使用D2D SRS触发来扫描D2D SRS邻近UE的子帧，并向接收UE的检测到的D2D SRS信息的节点发送反馈。邻近UE可以位于与UE相同的小区内。

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