FIELD: computer equipment.
SUBSTANCE: invention relates to means for distributing the computing resources of a multi-core data package processing system. Processing queues and utilization of CPU cores are traced. If the average processing queue size is less than a predetermined lower threshold, scaling unit blocks the addition of data packages into the processing queues. Emptying of the processing queue for each processing core of the processor is checked. After the processing queue has been emptied, the number of processing cores of the processor is reduced for each processing core of the processor. If at least one of the average size of the processing queue exceeds the first predetermined upper threshold, scaling unit directs all data from the processing queue to the memory buffer, increases the number of processing cores of the processor.
EFFECT: technical result is to optimize the utilization of the processing cores by dynamically scaling the number of cores, which leads to optimizing the use of computing resources of the data package processing system and reducing power consumption of the data package processing system.
8 cl, 9 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR WORKING MULTIPLE VIRTUAL COMPUTERS CONTROL IN VIRTUAL NETWORK SYSTEM OF INFORMATION PROTECTION | 2015 |
|
RU2619716C1 |
ARCHITECTURE OF ON-CHIP INTERCONNECTIONS | 2015 |
|
RU2625558C2 |
METHOD OF DISTRIBUTING ACCEPTABLE PACKAGES, QUEUE SELECTOR, PACKAGE PROCESSING DEVICE AND INFORMATION MEDIA | 2015 |
|
RU2643626C1 |
SMALL-SIZED HIGH-PERFORMANCE COMPUTING MODULE BASED ON A MULTIPROCESSOR SYSTEM-ON-A-CHIP | 2021 |
|
RU2778213C1 |
PHYSICAL LAYER OF HIGH-EFFICIENCY INTERCONNECTION | 2013 |
|
RU2579140C1 |
PHYSICAL LAYER OF HIGH-EFFICIENCY INTERCONNECTION | 2013 |
|
RU2599971C2 |
METHOD FOR PARALLEL PROCESSING OF INFORMATION IN A HETEROGENEOUS MULTIPROCESSOR SYSTEM ON A CHIP (SOC) | 2022 |
|
RU2790094C1 |
COMPUTING DEVICE OF SOFTWARE AND HARDWARE COMPLEX | 2016 |
|
RU2618367C1 |
SPECIALIZED COMPUTING SYSTEM DESIGNED FOR INFERENCE IN DEEP NEURAL NETWORKS BASED ON STREAM PROCESSORS | 2022 |
|
RU2793084C1 |
INTELLIGENT ELECTRONIC DEVICES FOR SUBSTATION AUTOMATION SYSTEM AND METHOD FOR DESIGN AND CONTROL THEREOF | 2009 |
|
RU2504913C2 |
Authors
Dates
2019-10-15—Published
2017-10-05—Filed