17901363. APPARATUS AND METHOD WITH LARGE-SCALE COMPUTING simplified abstract (Samsung Electronics Co., Ltd.)

APPARATUS AND METHOD WITH LARGE-SCALE COMPUTING

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

HYUNG-DAL Kwon of Hwaseong-si (KR)

Jaejin Lee of Seoul (KR)

Jinpyo Kim of Seoul (KR)

BYUNGWOO Bang of Seoul (KR)

Heehoon Kim of Daejeon (KR)

Daeyoung Park of Seoul (KR)

SUNGHOON Son of Suwon-si (KR)

SEUNG WOOK Lee of Suwon-si (KR)

WOOSEOK Chang of Hwaseong-si (KR)

Wookeun Jung of Seoul (KR)

JAE HOON Jung of Seoul (KR)

Jae-Eon Jo of Suwon-si (KR)

APPARATUS AND METHOD WITH LARGE-SCALE COMPUTING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17901363 titled 'APPARATUS AND METHOD WITH LARGE-SCALE COMPUTING

Simplified Explanation

The patent application describes a method and device for large-scale computing using a neural network. The device includes a processing device, a sensor, and a processor.

• The processing device performs operations related to a neural network.
• The sensor measures the electrical characteristic, operating frequency, and temperature of the processing device.
• The processor calculates the workload to be allocated to the processing device based on its operating mode, electrical characteristic, operating frequency, and temperature.
• The processor controls the electrical characteristic, operating frequency, and temperature based on the workload and operating mode.

Potential Applications

This technology has potential applications in various fields, including:

• Artificial intelligence and machine learning: The device can optimize the workload allocation and control the processing device's characteristics to enhance the performance of neural networks.
• Data centers: The technology can be used to efficiently manage and allocate computing resources in large-scale data centers, improving overall efficiency and reducing energy consumption.
• High-performance computing: The device can be utilized in high-performance computing systems to optimize resource allocation and improve computational efficiency.

Problems Solved

The technology addresses several problems in large-scale computing:

• Workload optimization: By calculating and allocating the workload based on various factors, the device ensures efficient utilization of computing resources and prevents overloading or underutilization.
• Thermal management: By monitoring and controlling the temperature of the processing device, the technology helps prevent overheating and potential damage to the hardware.
• Energy efficiency: By dynamically adjusting the electrical characteristic and operating frequency, the device optimizes energy consumption and reduces power usage.

Benefits

The technology offers several benefits:

• Improved performance: By optimizing workload allocation and controlling device characteristics, the technology enhances the performance and efficiency of large-scale computing systems.
• Enhanced reliability: By monitoring and managing the temperature of the processing device, the technology improves the reliability and longevity of the hardware.
• Energy savings: By dynamically adjusting electrical characteristics and operating frequency, the technology reduces energy consumption and contributes to overall energy savings in computing systems.

Original Abstract Submitted

A computing method and device for large-scale computing is provided. The computing device includes at least one processing device configured to perform an operation related to a neural network, a sensor configured to sense an electrical characteristic of the at least one processing device, an operating frequency of the at least one processing device, and a temperature of the at least one processing device, and a processor configured to calculate a workload to be allocated to the at least one processing device based on an operating mode of the at least one processing device, the electrical characteristic of the at least one processing device, the operating frequency of the at least one processing device, and the temperature of the at least one processing device, and control the electrical characteristic, the operating frequency, and the temperature based on the operating mode and the workload.