公开(公告)号：US20140253567A1

公开(公告)日：2014-09-11

申请号：US13699658

申请日：2011-12-14

申请人： Simon Moy ,  Shihao Wang ,  Zhengqian Qiu

发明人： Simon Moy ,  Shihao Wang ,  Zhengqian Qiu

IPC分类号： G06T1/20

CPC分类号： G06T1/20 ,  G06F9/5011 ,  G06F2209/507 ,  Y02D10/22

摘要： The invention relates to a method for hiding texture latency in an MVP processor, which comprises the following steps of: allowing the MVP processor to start running a main rendering program; segmenting registers of various MVP kernel instances in the MVP processor according to the length set, acquiring a plurality of register sets with same length, and binding the register sets to the dies at the beginning of the running of the kernel instance; allowing a shader thread to give up a processing time slot occupied by the shader thread after sending a texture detail request, and setting a PC (Program Counter) value in the case of return; and returning texture detail and allowing the shader thread to restart running. The invention also relates to a method for managing registers of grahic processing threads in the MVP processor.

摘要翻译： 本发明涉及一种在MVP处理器中隐藏纹理延迟的方法，包括以下步骤：允许MVP处理器开始运行主渲染程序; 根据长度设置，在MVP处理器中分割各种MVP内核实例的寄存器，获取具有相同长度的多个寄存器组，并且在内核实例的运行开始时将寄存器组绑定到管芯; 允许着色线程在发送纹理细节请求之后放弃着色器线程占用的处理时隙，并在返回时设置PC（程序计数器）值; 并返回纹理细节，并允许着色器线程重新启动。 本发明还涉及用于管理MVP处理器中的外加处理线程的寄存器的方法。

公开(公告)号：US09613389B2

公开(公告)日：2017-04-04

申请号：US13699658

申请日：2011-12-14

申请人： Simon Moy ,  Shihao Wang ,  Zhengqian Qiu

发明人： Simon Moy ,  Shihao Wang ,  Zhengqian Qiu

IPC分类号： G06T1/20 ,  G06F9/50

CPC分类号： G06T1/20 ,  G06F9/5011 ,  G06F2209/507 ,  Y02D10/22

摘要： A method for hiding texture latency in a multi-thread virtual pipeline (MVP) processor including the steps of: allowing the MVP processor to start running a main rendering program; segmenting registers of various MVP kernel instances in the MVP processor according to the length set, acquiring a plurality of register sets with the same length, binding the register sets to chipsets of the processor at the beginning of the running of the kernel instance; allowing a shader thread to give up a processing time slot occupied by the shader thread after sending a texture detail request, and setting a Program Counter (PC) value in the case of return; and returning texture detail and allowing the shader thread to restart running.

公开(公告)号：US20120173847A1

公开(公告)日：2012-07-05

申请号：US13395694

申请日：2009-11-05

申请人： Simon Moy ,  Shihao Wang ,  Wing Yee Lo

发明人： Simon Moy ,  Shihao Wang ,  Wing Yee Lo

IPC分类号： G06F9/38

CPC分类号： G06F9/3851 ,  G06F9/3009 ,  G06F9/3893 ,  G06F9/5083

摘要： A parallel processor and a method for concurrently processing threads in the parallel processor are disclosed. The parallel processor comprises: a plurality of thread processing engines for processing threads distributed to the thread processing engines, and the plurality of thread processing engines being connected in parallel; a thread management unit for obtaining, judging the statuses of the plurality of thread processing engines, and distributing the threads in a waiting queue among the plurality of thread processing engines.

摘要翻译： 公开了并行处理器和并行处理器中的线程处理方法。 所述并行处理器包括：多个线程处理引擎，用于处理分配给所述线程处理引擎的线程，并且所述多个线程处理引擎并联连接; 线程管理单元，用于获得，判断多个线程处理引擎的状态，以及在多个线程处理引擎中的等待队列中分配线程。

公开(公告)号：US20120233616A1

公开(公告)日：2012-09-13

申请号：US13395502

申请日：2009-12-28

申请人： Simon Moy ,  Shihao Wang ,  Wing Yee Lo ,  Kaimin Feng ,  Hua Bai

发明人： Simon Moy ,  Shihao Wang ,  Wing Yee Lo ,  Kaimin Feng ,  Hua Bai

IPC分类号： G06F9/46

CPC分类号： G06F9/4881 ,  G06F2209/483

摘要： A stream data processing method is provided, which includes the steps as follows: obtaining from data a program pointer indicating a task to which the pointer belongs, and configures a thread processing engine according to the program pointer; processing simultaneously the data of the different durations of the task or the data of different tasks by a plurality of thread engines; decides whether there is data still not processed, and if yes, returns to the first step; and if no, exits this data processing. A processor for processing a stream data is also provided.

摘要翻译： 提供了一种流数据处理方法，其包括以下步骤：从数据获取指示指针所属任务的程序指针，并根据程序指针配置线程处理引擎; 通过多个线程引擎同时处理任务的不同持续时间的数据或不同任务的数据; 决定是否还有数据尚未处理，如果是，则返回到第一步; 如果否，退出此数据处理。 还提供了一种用于处理流数据的处理器。