# US 2020/0402196 A1 · Asynchronous execution mechanism

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0402196 A1
- Document ID: US20200402196A1
- Status: Published application
- Kind: A1
- Application number: 16/449,034
- Filed: 2019-06-21
- Published: 2020-12-24
- Earliest claimed: 2019-06-21
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Saurabh Sharma; Michael Apodaca; Aditya Navale; Travis Schluessler; Vamsee Vardhan Chivukula; Abhishek Venkatesh; Subramaniam Maiyuran
- Web page: https://patentgrep.com/patent/US20200402196A1

## CPC

- G06T 1/20: Processor architectures; Processor configuration, e.g. pipelining
- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06T 2210/52: Parallel processing
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

An apparatus to facilitate asynchronous execution at a processing unit. The apparatus includes one or more processors to detect independent task passes that may be executed out of order in a pipeline of the processing unit, schedule a first set of processing tasks to be executed at a first set of processing elements at the processing unit and schedule a second set of tasks to be executed at a second set of processing elements, wherein execution of the first set of tasks at the first set of processing elements is to be performed simultaneous and in parallel to execution of the second set of tasks at the second set of processing elements.

## Claims

### Claim 1

An apparatus to facilitate asynchronous execution at a processing unit, comprising:
one or more processors to detect independent task passes that may be executed out of order in a pipeline of the processing unit, schedule a first set of processing tasks to be executed at a first set of processing elements at the processing unit and schedule a second set of tasks to be executed at a second set of processing elements, wherein execution of the first set of tasks at the first set of processing elements is to be performed simultaneous and in parallel to execution of the second set of tasks at the second set of processing elements.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the one or more processors further schedule the first and second set of processing tasks at a third set of processing elements.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the one or more processors transmit the first set of tasks to a first queue and transmit the second set of tasks to a second queue.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the one or more processors transmit the first set of tasks to a first command streamer at the processing unit and transmit the second set of tasks to a second command streamer.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the one or more processors receives information specifying independent tasks.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the information comprises a directed acyclic graph.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the directed acyclic graph comprises a plurality of nodes representing units of tasks and a plurality of edges representing resource dependency between operations.

### Claim 8 (depends on 4)

The apparatus of claim 4, wherein the one or more processors generate a directed acyclic graph.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the one or more processors identify whether a first task pass has a first bottleneck at the first set of processing elements and second pass has a second bottleneck at the second set of processing elements.

### Claim 10 (depends on 2)

The apparatus of claim 2, wherein the one or more processors schedule the first task pass and the second task pass in parallel based on identifying the first bottleneck and the second bottleneck.

### Claim 11

A method to facilitate asynchronous execution at a processing unit, comprising:
detecting independent task passes that may be executed out of order in a pipeline of the processing unit;
scheduling a first set of processing tasks to be executed at a first set of processing elements at the processing unit; and
scheduling a second set of tasks to be executed at a second set of processing elements, wherein execution of the first set of tasks at the first set of processing elements is to be performed simultaneous and in parallel to execution of the second set of tasks at the second set of processing elements.

### Claim 12 (depends on 11)

The method of claim 11, further comprising scheduling the first and second set of processing tasks at a third set of processing elements.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
transmitting the first set of tasks to a first command streamer at the processing unit; and
transmitting the second set of tasks to a second command streamer.

### Claim 14 (depends on 11)

The method of claim 11, further comprising receiving a directed acyclic graph comprising a plurality of nodes representing units of tasks and a plurality of edges representing resource dependency between operations.

### Claim 15 (depends on 11)

The method of claim 11, further comprising generating a directed acyclic graph comprising a plurality of nodes representing units of tasks and a plurality of edges representing resource dependency between operations.

### Claim 16

At least one computer readable medium having instructions stored thereon, which when executed by one or more processors, cause the processors to:
detect independent task passes that may be executed out of order in a pipeline of the processing unit;
schedule a first set of processing tasks to be executed at a first set of processing elements at the processing unit; and
schedule a second set of tasks to be executed at a second set of processing elements, wherein execution of the first set of tasks at the first set of processing elements is to be performed simultaneous and in parallel to execution of the second set of tasks at the second set of processing elements.

### Claim 17 (depends on 16)

The computer readable medium of claim 16, having instructions stored thereon, which when executed by one or more processors, further cause the processors to schedule the first and second set of processing tasks at a third set of processing elements.

### Claim 18 (depends on 17)

The computer readable medium of claim 17, having instructions stored thereon, which when executed by one or more processors, further cause the processors to:
transmit the first set of tasks to a first command streamer at the processing unit; and
transmit the second set of tasks to a second command streamer.

### Claim 19 (depends on 16)

The computer readable medium of claim 16, having instructions stored thereon, which when executed by one or more processors, further cause the processors to receive a directed acyclic graph comprising a plurality of nodes representing units of tasks and a plurality of edges representing resource dependency between operations.

### Claim 20 (depends on 16)

The computer readable medium of claim 16, having instructions stored thereon, which when executed by one or more processors, further cause the processors to identify whether a first task pass has a first bottleneck at the first set of processing elements and second pass has a second bottleneck at the second set of processing elements.
