17936788. Work Graph Scheduler Implementation simplified abstract (ADVANCED MICRO DEVICES, INC.)

Work Graph Scheduler Implementation

Organization Name

ADVANCED MICRO DEVICES, INC.

Inventor(s)

Matthäus G. Chajdas of Munich (DE)

Michael J. Mantor of Orlando FL (US)

Rex Eldon Mccrary of Orlando FL (US)

Christopher J. Brennan of Boxborough MA (US)

Robert Martin of Boxborough MA (US)

Dominik Baumeister of Munich (DE)

Fabian Robert Sebastian Wildgrube of Munich (DE)

Work Graph Scheduler Implementation - A simplified explanation of the abstract

This abstract first appeared for US patent application 17936788 titled 'Work Graph Scheduler Implementation

Simplified Explanation

The abstract describes a hierarchical scheduler implemented in a processor, such as a graphics processing unit, with a global scheduler and multiple local schedulers coupled to processors. The global scheduler stores work items in a shared cache and instructs local schedulers to retrieve and schedule these work items for execution by the processors.

• The patent describes a hierarchical scheduler system for processors, including a global scheduler and multiple local schedulers.
• Each local scheduler is connected to a group of processors and has its own local cache.
• The global scheduler stores work items in a shared cache and directs local schedulers to retrieve and schedule these work items for execution.
• The local schedulers operate independently of each other in scheduling work items for execution.

Potential Applications

This technology can be applied in graphics processing units, data centers, and high-performance computing systems where efficient task scheduling is crucial.

Problems Solved

This technology solves the problem of efficiently scheduling work items for execution across multiple processors in a hierarchical manner, improving overall system performance and resource utilization.

Benefits

The benefits of this technology include improved system performance, optimized resource utilization, and better task scheduling efficiency in multi-processor systems.

Potential Commercial Applications

Potential commercial applications of this technology include graphics processing units, cloud computing services, scientific computing clusters, and any system requiring efficient task scheduling across multiple processors.

Possible Prior Art

One possible prior art could be the use of hierarchical scheduling systems in operating systems or parallel computing environments to manage tasks across multiple processing units efficiently.

How does this technology compare to traditional single-level scheduling systems?

This article does not provide a direct comparison between hierarchical scheduling and traditional single-level scheduling systems in terms of performance, resource utilization, and scalability.

What are the potential challenges in implementing this hierarchical scheduler in real-world systems?

The article does not address the potential challenges or limitations in implementing this hierarchical scheduler in practical applications, such as scalability issues, overhead costs, or compatibility with existing hardware and software systems.

Original Abstract Submitted

Systems, apparatuses, and methods for implementing a hierarchical scheduler. In various implementations, a processor includes a global scheduler, and a plurality of independent local schedulers with each of the local schedulers coupled to a plurality of processors. In one implementation, the processor is a graphics processing unit and the processors are computation units. The processor further includes a shared cache that is shared by the plurality of local schedulers. Each of the local schedulers also includes a local cache used by the local scheduler and processors coupled to the local scheduler. To schedule work items for execution, the global scheduler is configured to store one or more work items in the shared cache and convey an indication to a first local scheduler of the plurality of local schedulers which causes the first local scheduler to retrieve the one or more work items from the shared cache. Subsequent to retrieving the work items, the local scheduler is configured to schedule the retrieved work items for execution by the coupled processors. Each of the plurality of local schedulers is configured to schedule work items for execution independent of scheduling performed by other local schedulers.