# US 2024/0004829 A1 · Graphics processing integrated circuit package

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

- Number: US 2024/0004829 A1
- Document ID: US20240004829A1
- Status: Published application
- Kind: A1
- Application number: 18/350,902
- Filed: 2023-07-12
- Published: 2024-01-04
- Earliest claimed: 2017-04-09
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Altug Koker; Farshad Akhbari; Feng Chen; Dukhwan Kim; Narayan Srinivasa; Nadathur Rajagopalan Satish; Liwei Ma; Jeremy Bottleson; Eriko Nurvitadhi; Joydeep Ray; Ping T. Tang; Michael S. Strickland; Xiaoming Chen; Tatiana Shpeisman; Abhishek R. Appu
- Web page: https://patentgrep.com/patent/US20240004829A1

## CPC

- G06F 15/8007: {single instruction multiple data [SIMD] multiprocessors}
- G06F 9/3004: {to perform operations on memory}
- G06F 13/00: Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units (interface circuits for specific input/output devices G06F3/00 {; multiprogram control therefor G06F9/46}; multiprocessor systems G06F15/16 )
- G06F 13/4027: {using bus bridges (G06F13/4022 takes precedence)}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/048: Activation functions
- G06N 3/063: using electronic means
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06T 1/20: Processor architectures; Processor configuration, e.g. pipelining
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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 integrated circuit (IC) package apparatus is disclosed. The IC package includes one or more processing units and a bridge, mounted below the one or more processing unit, including one or more arithmetic logic units (ALUs) to perform atomic operations.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

An integrated circuit (IC) package comprising:
one or more graphics processing units (GPUs), the one or more GPUs including one or more cores to run one or more applications; and
circuitry including sensor routing and registration;
wherein the circuitry is to:
determine which of one or more sensor capabilities of one or more sensors coupled with the IC package are required for an application, the one or more sensors including a first sensor having a first sensor capability; and
disable the first sensor upon determining that the first sensor capability is not required for the application.

### Claim 22 (depends on 21)

The IC package of claim 21, wherein the circuitry is further to disable a first perception capability of the IC package upon determining that the first sensor capability is not required for the application.

### Claim 23 (depends on 22)

The IC package of claim 22, wherein the disablement of the first perception capability includes powering off a portion of the one or more GPUs.

### Claim 24 (depends on 22)

The IC package of claim 22, wherein the disablement of the first perception capability includes load balancing for the one or more GPUs.

### Claim 25 (depends on 22)

The IC package of claim 22, wherein, upon the disablement of the first perception capability, the one or more GPUs reassign compute resources for the first perception capability to a different usage of the one or more GPUs.

### Claim 26 (depends on 21)

The IC package of claim 21, wherein the application includes an autonomous driving application.

### Claim 27 (depends on 26)

The IC package of claim 26, wherein the one or more sensors include one or more of:
a camera;
a radar sensor; and
a Light Detection and Ranging (LiDAR) sensor.

### Claim 28

A system comprising:
a processor integrated circuit (IC) including one or more processors;
a memory IC including memory for storage of data, including data for one or more applications; and
a graphics processing unit (GPU) package including:
one or more graphics processing units (GPUs), the one or more GPUs including one or more cores to run one or more applications; and
circuitry including sensor routing and registration;
wherein the circuitry is to:
determine which of one or more sensor capabilities of one or more sensors coupled with the IC package are currently in use for an application, the one or more sensors including a first sensor having a first sensor capability; and
disable the first sensor upon determining that the first sensor capability is not in current use for the application.

### Claim 29 (depends on 28)

The system of claim 28, wherein the circuitry is further to disable a first perception capability of the IC package upon determining that the first sensor capability is not in use for the application.

### Claim 30 (depends on 29)

The system of claim 29, wherein the disablement of the first perception capability includes powering off a portion of the one or more GPUs.

### Claim 31 (depends on 29)

The system of claim 29, wherein the disablement of the first perception capability includes load balancing for the one or more GPUs.

### Claim 32 (depends on 29)

The system of claim 29, wherein, upon the disablement of the first perception capability, the one or more GPUs reassign compute resources for the first perception capability to a different usage of the one or more GPUs.

### Claim 33 (depends on 28)

The system of claim 28, wherein the system is at least a portion of an autonomous vehicle, and wherein the application includes an autonomous driving application.

### Claim 34 (depends on 33)

The system of claim 33, wherein the one or more sensors include one or more of:
a camera;
a radar sensor; and
a Light Detection and Ranging (LiDAR) sensor.

### Claim 35

One or more non-transitory computer-readable storage mediums having stored thereon executable computer program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
processing an application on a computing system, processing the application including processing by one or more graphics processing units (GPUs) of the computing system;
determining which of one or more sensor capabilities of one or more sensors are required for the application running on one or more graphics processing units (GPUs), the one or more sensors including a first sensor having a first sensor capability; and
disabling the first sensor upon determining that the first sensor capability is not in current use for the application.

### Claim 36 (depends on 35)

The one or more storage mediums of claim 35, wherein the executable computer program instructions further include instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
disabling a first perception capability performed by the one or more GPUs upon determining that the first sensor capability is not in use for the application.

### Claim 37 (depends on 36)

The one or more storage mediums of claim 36, wherein the disablement of the first perception capability includes powering off a portion of the one or more GPUs.

### Claim 38 (depends on 36)

The one or more storage mediums of claim 36, wherein the disablement of the first perception capability includes load balancing for the one or more GPUs.

### Claim 39 (depends on 36)

The one or more storage mediums of claim 36, wherein the executable computer program instructions further include instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
upon the disablement of the first perception capability, reassigning compute resources for the first perception capability to a different usage of the one or more GPUs.

### Claim 40 (depends on 36)

The one or more storage mediums of claim 36, wherein processing the application includes processing an autonomous driving application.
