Apparatus and method for providing workload distribution of threads among multiple compute units
Abstract
In some examples, thermal aware optimization logic determines a characteristic (e.g., a workload or type) of a wavefront (e.g., multiple threads). For example, the characteristic indicates whether the wavefront is compute intensive, memory intensive, mixed, and/or another type of wavefront. The thermal aware optimization logic determines temperature information for one or more compute units (CUs) in one or more processing cores. The temperature information includes predictive thermal information indicating expected temperatures corresponding to the one or more CUs and historical thermal information indicating current or past thermal temperatures of at least a portion of a graphics processing unit (GPU). The logic selects the one or more compute units to process the plurality of threads based on the determined characteristic and the temperature information. The logic provides instructions to the selected subset of the plurality of CUs to execute the wavefront.
- Inventors:
- Issue Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1860144
- Patent Number(s):
- 11194634
- Application Number:
- 16/220,827
- Assignee:
- Advanced Micro Devices, Inc. (Santa Clara, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- DOE Contract Number:
- AC52-07NA27344; B620717
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 12/14/2018
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Rao, Karthik, Das, Shomit N., An, Xudong, and Huang, Wei. Apparatus and method for providing workload distribution of threads among multiple compute units. United States: N. p., 2021.
Web.
Rao, Karthik, Das, Shomit N., An, Xudong, & Huang, Wei. Apparatus and method for providing workload distribution of threads among multiple compute units. United States.
Rao, Karthik, Das, Shomit N., An, Xudong, and Huang, Wei. Tue .
"Apparatus and method for providing workload distribution of threads among multiple compute units". United States. https://www.osti.gov/servlets/purl/1860144.
@article{osti_1860144,
title = {Apparatus and method for providing workload distribution of threads among multiple compute units},
author = {Rao, Karthik and Das, Shomit N. and An, Xudong and Huang, Wei},
abstractNote = {In some examples, thermal aware optimization logic determines a characteristic (e.g., a workload or type) of a wavefront (e.g., multiple threads). For example, the characteristic indicates whether the wavefront is compute intensive, memory intensive, mixed, and/or another type of wavefront. The thermal aware optimization logic determines temperature information for one or more compute units (CUs) in one or more processing cores. The temperature information includes predictive thermal information indicating expected temperatures corresponding to the one or more CUs and historical thermal information indicating current or past thermal temperatures of at least a portion of a graphics processing unit (GPU). The logic selects the one or more compute units to process the plurality of threads based on the determined characteristic and the temperature information. The logic provides instructions to the selected subset of the plurality of CUs to execute the wavefront.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2021},
month = {12}
}
Works referenced in this record:
Balanced Data-Intensive Computing
patent-application, July 2011
- Szalay, Sandor; White, Alainna; Vandenberg, Jan
- US Patent Application 12/970533; 20110167229
Apparatus and Method for Efficient Estimation of the Energy Dissipation of Processor Based Systems
patent-application, July 2015
- Ghose, Kanad
- US Patent Application 14/663572; 20150192978
Temperature-based thread scheduling
patent-application, May 2006
- Bodas, Devadatta; Nakajima, Jun
- US Patent Application 11/096976; 20060095913
Scalable Work Load Management of Multi-Core Computer Systems
patent-application, November 2012
- Marchand, Benoit; Zhou, Xinliang
- US Patent Application 13/453099; 20120297395
Thermally-Aware Throttling in a Three Dimensional Processor Stack
patent-application, March 2017
- Huang, Wei; Arora, Manish; Eckert, Yasuko
- US Patent Application 14/862044; 20170083065
Cache-Aware Adaptive Thread Scheduling And Migration
patent-application, March 2016
- Wang, Ren; Tai, Tsung-Yuan C.; Diefenbaugh, Paul S.
- US Patent Application 14/496216; 20160092363
Circuits and Methods Providing Thread Assignment for a Multi-Core Processor
patent-application, August 2018
- Kumar, Akash; , Ankita
- US Patent Application 15/435630; 20180239641
Parallel processing apparatus for video compression
patent-application, September 2008
- Huang, Jonathan Jiann-Jang; Yu, Tsaifa; Tu, Kuei-Chung
- US Patent Application 11/716197; 20080219349