公开(公告)号：US20180032431A1

公开(公告)日：2018-02-01

申请号：US15219997

申请日：2016-07-26

Applicant: Joydeep Ray ,  James A. Valerio ,  Abhishek R. Appu

Inventor： Joydeep Ray ,  James A. Valerio ,  Abhishek R. Appu

IPC: G06F12/06 ,  G06F9/38

CPC classification number: G06F12/0646 ,  G06F9/34 ,  G06F9/3824 ,  G06F9/3887

Abstract: A graphics processor may be assigned a number of banks in a shared local memory to reduce the number of bank conflicts. In some cases, the number of banks may be higher than the single instruction multiple data slot number times the number of messages per cycle. The actual number of banks may be set to the next higher relatively prime number of 2n and 3 where n is 0-5.

公开(公告)号：US20180285120A1

公开(公告)日：2018-10-04

申请号：US15477030

申请日：2017-04-01

Applicant: Joydeep Ray ,  Altug Koker ,  Balaji Vembu ,  Murali Ramadoss ,  Guei-Yuan Lueh ,  James A. Valerio ,  Prasoonkumar Surti ,  Abhishek R. Appu ,  Vasanth Ranganathan ,  Kalyan Bhairavabhatla ,  Arthur D. Hunter, JR. ,  Wei-Yu Chen ,  Subramaniam M. Maiyuran

Inventor： Joydeep Ray ,  Altug Koker ,  Balaji Vembu ,  Murali Ramadoss ,  Guei-Yuan Lueh ,  James A. Valerio ,  Prasoonkumar Surti ,  Abhishek R. Appu ,  Vasanth Ranganathan ,  Kalyan Bhairavabhatla ,  Arthur D. Hunter, JR. ,  Wei-Yu Chen ,  Subramaniam M. Maiyuran

IPC: G06F9/38 ,  G06F9/345 ,  G06F9/30 ,  G06F12/084 ,  G06T1/60 ,  G06T1/20 ,  G09G5/36

CPC classification number: G09G5/363 ,  G06F9/461 ,  G06F12/0811 ,  G06F12/084 ,  G06F12/0875 ,  G06F2212/1024 ,  G06F2212/1028 ,  G06F2212/455 ,  G09G5/001 ,  G09G2340/02 ,  G09G2350/00 ,  G09G2352/00 ,  G09G2360/08 ,  G09G2360/121

Abstract: A mechanism is described for facilitating using of a shared local memory for register spilling/filling relating to graphics processors at computing devices. A method of embodiments, as described herein, includes reserving one or more spaces of a shared local memory (SLM) to perform one or more of spilling and filling relating to registers associated with a graphics processor of a computing device.

公开(公告)号：US5546538A

公开(公告)日：1996-08-13

申请号：US167523

申请日：1993-12-14

Applicant: David A. Cobbley ,  James A. Valerio ,  Frederick J. Pollack

Inventor： David A. Cobbley ,  James A. Valerio ,  Frederick J. Pollack

IPC: G06F3/033 ,  G06F3/048 ,  G06F3/16 ,  G06F17/28 ,  G06K9/22 ,  G10L15/22 ,  H04M1/725 ,  G06F13/00

CPC classification number: G06F3/16 ,  G06F17/28 ,  G06F3/0488 ,  G06K9/00429 ,  G10L15/22 ,  H04M1/72519 ,  H04M2250/70

Abstract: A computer arrangement that offloads computationally intensive tasks from portable computer devices to larger servers is disclosed. A portable computer device that relies on handwriting or speech for input is equipped with a wireless communication subsystem. When a user writes on the display or speaks into the portable computer device, the central processing unit passes the handwriting or speech information to the wireless communication subsystem. While the user is still inputting information, the wireless communication subsystem transmits received information to a communication server. The communication server routes the handwriting or speech information to a server that performs handwriting or speech recognition to translate the information into encoded text. The communication server then transmits the encoded text information back to the portable computer device.

Abstract translation: 公开了将计算密集型任务从便携式计算机设备卸载到较大服务器的计算机装置。 依靠手写或语音输入的便携式计算机装置装备有无线通信子系统。 当用户在显示器上写入或者说便携式计算机设备时，中央处理单元将手写或语音信息传递到无线通信子系统。 当用户仍在输入信息时，无线通信子系统将接收的信息发送到通信服务器。 通信服务器将手写或语音信息路由到执行手写或语音识别的服务器，以将信息翻译成编码文本。 然后，通信服务器将经编码的文本信息发送回便携式计算机设备。