skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Monitor support on accelerated processing device

Patent ·
OSTI ID:1632546

A technique for implementing synchronization monitors on an accelerated processing device (“APD”) is provided. Work on an APD includes workgroups that include one or more wavefronts. All wavefronts of a workgroup execute on a single compute unit. A monitor is a synchronization construct that allows workgroups to stall until a particular condition is met. Responsive to all wavefronts of a workgroup executing a wait instruction, the monitor coordinator records the workgroup in an “entry queue.” The workgroup begins saving its state to a general APD memory and, when such saving is complete, the monitor coordinator moves the workgroup to a “condition queue.” When the condition specified by the wait instruction is met, the monitor coordinator moves the workgroup to a “ready queue,” and, when sufficient resources are available on a compute unit, the APD schedules the ready workgroup for execution on a compute unit.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC52-07NA27344; B620717
Assignee:
Advanced Micro Devices, Inc. (Sunnyvale, CA)
Patent Number(s):
10,558,418
Application Number:
15/661,843
OSTI ID:
1632546
Resource Relation:
Patent File Date: 07/27/2017
Country of Publication:
United States
Language:
English

References (28)

Out-of-Order Cache Returns patent-application June 2018
Integrated Heterogeneous Processing Units patent-application November 2017
Compute cluster preemption within a general-purpose graphics processing unit patent August 2018
Low Power and Low Latency GPU Coprocessor for Persistent Computing patent-application May 2018
Software Mechanisms for Managing Task Scheduling on an Accelerated Processing Device (APD) patent-application June 2013
Parallel Computing Architecture for Use with a Non-Greedy Scheduling Algorithm patent-application October 2018
Software Only Inter-Compute Unit Redundant Multithreading for GPUs patent-application December 2014
Automatic Load Balancing for Heterogeneous Cores patent-application November 2012
System and Method for Page-Conscious GPU Instruction patent-application February 2016
Monitors: an operating system structuring concept journal October 1974
Parallel processor system for processing natural concurrencies and method therefor patent June 1991
Method and Apparatus for Efficient Submission of Workload to a High Performance Graphics Sub-System patent-application September 2017
Managing Coherent Memory between an Accelerated Processing Device and a Central Processing Unit patent-application October 2013
System and Method for Hardware Scheduling of Conditional Barriers and Impatient Barriers patent-application September 2014
Scheduling and Execution of Compute Tasks patent-application July 2013
System and Method for Hardware Scheduling of Indexed Barriers patent-application September 2014
Scheduling and Execution of Compute Tasks patent-application July 2013
Creating SIMD Efficient Code by Transferring Register State Through Common Memory patent-application May 2014
Conditional Atomic Operations at a Processor patent-application December 2016
Stall Prediction Thread Management patent-application August 2007
Partitioning Resources of a Processor patent-application June 2013
Structured multiprogramming journal July 1972
Experience with processes and monitors in Mesa journal February 1980
Graphic Processing System and Method Thereof patent-application September 2016
Prediction-based power management strategy for GPU compute workloads patent April 2019
Adaptive scheduling for task assignment among heterogeneous processor cores patent January 2019
System and Method of Data Processing patent-application May 2015
Policies for Shader Resource Allocation in a Shader Core patent-application June 2013

Similar Records

Performance for GPU exceptions
Patent · Tue Feb 15 00:00:00 EST 2022 · OSTI ID:1632546

Enhanced atomics for workgroup synchronization
Patent · Tue Mar 29 00:00:00 EDT 2022 · OSTI ID:1632546

UPC++ as_eager Working Group Draft, Revision 2020.6.2
Technical Report · Mon Aug 09 00:00:00 EDT 2021 · OSTI ID:1632546