公开(公告)号：US10796397B2

公开(公告)日：2020-10-06

申请号：US14738679

申请日：2015-06-12

Applicant: INTEL CORPORATION

Inventor： James A. Valerio ,  Abhishek Venkatesh ,  Satyajit Sarangi ,  Michael Apodaca ,  Thomas F. Raoux ,  Hashem Hashemi ,  Rama S. B. Harihara

IPC: G06T1/20 ,  G06F9/30

Abstract: A mechanism is described for facilitating dynamic runtime transformation of graphics processing commands for improved graphics performance on computing devices. A method of embodiments, as described herein, includes detecting a command stream associated with an application, where the command stream includes dispatches. The method may further include evaluating processing parameters relating to each of the dispatches, where evaluating further includes associating a first plan with one or more of the dispatches to transform the command stream into a transformed command stream. The method may further include associating, based on the first plan, a second plan to the one or more of the dispatches, where the second plan represents the transformed command stream. The method may further include executing the second plan, where execution of the second plan includes processing the transformed command stream in lieu of the command stream.

公开(公告)号：US20190324757A1

公开(公告)日：2019-10-24

申请号：US15957695

申请日：2018-04-19

Applicant: Intel Corporation

Inventor： James Valerio ,  Ben Ashbaugh ,  Pradeep Ramani ,  Rebecca David ,  Sabareesh Ganapathy ,  Hashem Hashemi

IPC: G06F9/38 ,  G06F9/30

Abstract: Embodiments described herein provide techniques to maintain high temporal cache locality between independent threads having the same or similar memory access pattern. One embodiment provides a graphics processing unit comprising an instruction execution pipeline including hardware execution logic and a thread dispatcher to process a set of commands for execution and distribute multiple groups of hardware threads to the hardware execution logic to execute the set of commands. The thread dispatcher can be configured to concurrently distribute a first group of the multiple groups of hardware threads to the hardware execution logic and withhold distribution of additional hardware threads for the set of commands until after the first group completes execution.

公开(公告)号：US10146691B2

公开(公告)日：2018-12-04

申请号：US15374630

申请日：2016-12-09

Applicant: INTEL CORPORATION

Inventor： Hashem Hashemi ,  Saurabh Sharma ,  Altug Koker

IPC: G06F12/16 ,  G06F12/0842

Abstract: One embodiment provides for a memory system comprising a cache memory and a cache control circuit to receive a request to perform a partial cache line write to a first cache line of the cache memory, merge the request to perform the partial cache line write with a pending request to write to the first cache line, and process a merged request as a full cache line write.

公开(公告)号：US20160364828A1

公开(公告)日：2016-12-15

申请号：US14738679

申请日：2015-06-12

Applicant: INTEL CORPORATION

Inventor： James A. Valerio ,  Abhishek Venkatesh ,  Satyajit Sarangi ,  Michael Apodaca ,  Thomas F. Raoux ,  Hashem Hashemi ,  Rama S.B. Harihara

IPC: G06T1/20

Abstract: A mechanism is described for facilitating dynamic runtime transformation of graphics processing commands for improved graphics performance on computing devices. A method of embodiments, as described herein, includes detecting a command stream associated with an application, where the command stream includes dispatches. The method may further include evaluating processing parameters relating to each of the dispatches, where evaluating further includes associating a first plan with one or more of the dispatches to transform the command stream into a transformed command stream. The method may further include associating, based on the first plan, a second plan to the one or more of the dispatches, where the second plan represents the transformed command stream. The method may further include executing the second plan, where execution of the second plan includes processing the transformed command stream in lieu of the command stream.

Abstract translation: 描述了一种机制，用于促进图形处理命令的动态运行时转换，以改善计算设备上的图形性能。 如本文所述的实施例的方法包括检测与应用相关联的命令流，其中命令流包括分派。 该方法还可以包括评估与每个调度有关的处理参数，其中评估进一步包括将第一计划与一个或多个调度相关联，以将命令流变换成变换的命令流。 该方法可以进一步包括：基于第一计划，将第二计划与一个或多个调度相关联，其中第二计划表示变换的命令流。 该方法还可以包括执行第二计划，其中第二计划的执行包括处理变换的命令流来代替命令流。