This includes devices with peripheral interfaces and their operation methods.
By optimizing the interface connections of peripheral devices through hub devices and DVFS circuits, the problem of degraded communication performance between the host and peripheral devices was solved, and the system achieved efficient and flexible peripheral device interface connections.
Patent Information
- Application Number
- CN202110628738.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2020-08-28
- Filing Date
- 2021-06-04
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2041-06-04
AI Technical Summary
In control systems, performance degrades and limits the freedom to add peripheral devices when the host communicates with peripheral devices, especially in mobile systems where efficiency is low.
By employing hub devices and dynamic voltage-frequency scaling (DVFS) circuitry, the activity schedules of peripheral devices are stored in memory to identify optimal operating conditions and adjust the power consumption of the hub devices to optimize interface connectivity.
It improves system performance and efficiency, supports compatibility with various peripheral devices, and enhances the design and manufacturing freedom of the equipment.
Smart Images

Figure CN114116561B_ABST
Abstract
Description
[0001] Cross-references to related applications
[0002] This application is based on and claims priority to Korean Patent Application No. 10-2020-0109472, filed with the Korean Intellectual Property Office on August 28, 2020, the disclosure of which is incorporated herein by reference in its entirety. Technical Field
[0003] This disclosure relates to a peripheral interface, and more specifically, to a device including a peripheral interface and a method of operating the device. Background Technology
[0004] When the host of a control system communicates directly with the various peripheral devices included in the system, the host's performance may degrade, and this may limit the freedom to add peripheral devices to the system. Therefore, the system can include interface devices between the peripheral devices and the host, and the host can obtain information from the peripheral devices through these interface devices. As the number of peripheral devices included in the system increases, the devices interfaced with these peripheral devices may require high performance, and in the case of mobile systems, these devices may also require high efficiency. Summary of the Invention
[0005] This disclosure provides a device and method for interfacing with peripheral devices while achieving optimal power consumption.
[0006] According to one aspect of this disclosure, an apparatus for providing an interface with a peripheral device is provided, the apparatus comprising: a first interface for receiving a request from a host; a second interface for periodically receiving at least one first sample input from the peripheral device in response to the request from the host; a memory for storing an activity schedule including the processing time of the sample input, wherein the sample input is provided by each of the peripheral devices under each of a plurality of operating conditions corresponding to different power consumptions; and processing circuitry for identifying at least one of the plurality of operating conditions based on the activity schedule and the period of the at least one first sample input.
[0007] According to another aspect of this disclosure, an apparatus is provided, comprising: a host that performs operations based on information provided from a peripheral device; a hub device that provides an interface to the peripheral device; and dynamic voltage-frequency scaling (DVFS) circuitry that adjusts the power consumption of the hub device based on control signals provided from the hub device. The hub device periodically receives at least one sample input from the peripheral device in response to a request from the host, and generates control signals based on the processing time and period of the at least one sample input.
[0008] According to another aspect of this disclosure, a method for connecting to a peripheral device interface is provided, the method comprising: receiving from a host a request indicating periodically receiving at least one sample input from the peripheral device; identifying the processing time and period of the at least one sample input; and identifying at least one operating condition among a plurality of operating conditions corresponding to different power consumptions based on the processing time and period of the at least one sample input. Attached Figure Description
[0009] Embodiments of this disclosure will become clearer from the following detailed description taken in conjunction with the accompanying drawings, in which:
[0010] Figure 1 This is a block diagram of a system according to an exemplary embodiment of the present disclosure;
[0011] Figure 2 This is a timing diagram illustrating the operation of a hub device according to an example embodiment of the present disclosure;
[0012] Figure 3 This is a block diagram of a hub device according to an exemplary embodiment of the present disclosure;
[0013] Figure 4 This is a view of an activity schedule based on an example embodiment of this disclosure;
[0014] Figure 5 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0015] Figure 6 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0016] Figure 7 This is a timing diagram illustrating the operation of a hub device according to an example embodiment of the present disclosure;
[0017] Figure 8A and Figure 8B This is a timing diagram illustrating the operation of a hub device according to an example embodiment of the present disclosure;
[0018] Figure 9 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0019] Figure 10 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0020] Figure 11 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0021] Figure 12This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure;
[0022] Figure 13 This is a block diagram of a hub device according to an exemplary embodiment of the present disclosure; and
[0023] Figure 14 This is a block diagram of a vehicle according to an exemplary embodiment of the present disclosure. Detailed Implementation
[0024] Figure 1 This is a block diagram of system 10 according to an exemplary embodiment of the present disclosure. Figure 1 As shown, system 10 may include a host 11, a hub device 12, a memory 13, a dynamic voltage frequency scaling (DVFS) circuitry 14, a battery 15, and peripheral devices 16. In some embodiments, the battery 15 may be omitted. In some embodiments, at least some of the host 11, hub device 12, memory 13, and DVFS circuitry 14 may be included in a single semiconductor package. In some embodiments, the host 11, hub device 12, memory 13, and DVFS circuitry 14 may be included in a single chip (i.e., a system-on-a-chip (SoC)), and the SoC may be referred to as an application processor (AP).
[0025] System 10 can refer to any system that includes the peripheral device 16 described below. For example, system 10 can be a fixed computing system such as a desktop personal computer (PC) and server, a portable computing system such as a laptop PC, mobile phone, tablet PC and smart wearable device, or a vehicle such as a car, motorcycle or kickboard. System 10 can provide various functions to users of system 10 or other systems through the peripheral device 16.
[0026] Peripheral device 16 can refer to any device designed to provide useful functionality. For example, such as... Figure 1 As shown, the peripheral device 16 may include at least one sensor 16_1, at least one module 16_2, at least one processor 16_3, and at least one input / output device 16_4, and may include at least one switch 16_5 connected to additional peripheral devices. In some embodiments, with Figure 1 Unlike other systems, System 10 may only include... Figure 1 Some of the peripheral devices 16 shown, or may also include Figure 1 Peripheral devices not shown. Each peripheral device 16 can be enabled by the hub device 12, and at least one enabled peripheral device 16 can provide sample input IN to the hub device 12.
[0027] At least one sensor 16_1 can detect the external environment of system 10 and / or the state of system 10, and as a non-limiting example, may include an accelerometer, gyroscope, geomagnetic sensor, proximity sensor, air pressure sensor, temperature sensor, pressure sensor, etc. At least one module 16_2 can process signals provided from outside system 10, and as a non-limiting example, may include a Global Navigation Satellite System (GNSS) module, a wired communication module (e.g., a Universal Serial Bus (USB) module or an Ethernet module), a wireless communication module (e.g., a WiFi module, Bluetooth module, Near Field Communication (NFC) module, or infrared communication module), a storage interface module (e.g., a Secure Digital (SD) card, Multimedia Card (MMC) card, or Universal Flash Memory (UFS)) module, etc. At least one processor 16_3 can process signals and / or data, and as a non-limiting example, may include a communication processor (or modem), codec, etc. At least one input / output device 16_4 may receive input from outside the system 10 or provide output to outside the system 10, and as a non-limiting example, may include a touch screen, keyboard, mouse, display device, audio device (e.g., microphone, speaker, or audio amplifier), etc.
[0028] The host 11 can control the system 10 and may be referred to as a host processor, host device, etc. In some embodiments, the host 11 may include at least one core that executes a series of instructions and can execute a program composed of instructions. The program may include multiple subroutines, and the subroutines may be referred to as subroutines, routines, procedures, functions, etc. In some embodiments, the host 11 may include at least one intellectual property (IP) core designed through logic synthesis and / or a field-programmable gate array (FPGA). Hereinafter, it is assumed that the host 11 includes at least one core for executing a program; however, it should be noted that the exemplary embodiments of this disclosure are not limited thereto.
[0029] like Figure 1 As shown, host 11 can execute hub driver 11_2. For example, host 11 can run an operating system (OS), and the OS can include hub driver 11_2. Hub driver 11_2 can provide an interface to hub device 12 with applications running on the OS. Hub driver 11_2 can generate request REQs for peripheral device 16 independently or according to instructions from the application, and host 11 can provide the request REQs to hub device 12. In addition, host 11 can receive output data OUT, including information related to peripheral device 16, from hub device 12, and hub driver 11_2 can utilize output data OUT independently or provide output data OUT to the application. In some embodiments, host 11 may include a dedicated hardware block designed to perform the functions of hub driver 11_2.
[0030] Hub device 12 can be located between peripheral device 16 and host 11, and interface peripheral device 16 with host 11. Hub device 12 can communicate with peripheral device 16 and receive sample input IN from peripheral device 16. For example, hub device 12 can communicate with multiple peripheral devices connected to a bus (e.g., Peripheral Component Rapid Interconnect (PCIe)), or can communicate with peripheral devices via a dedicated communication channel. Additionally, hub device 12 can communicate with host 11, receive requests REQ from host 11, and provide output data OUT to host 11. For example, hub device 12 can be connected to a bus such as Advanced Extensible Interface (AXI) along with host 11, and can receive requests REQ from host 11 or provide output data OUT to host 11 via the bus. Hub device 12 can enable at least one of peripheral devices 16 based on a request REQ, and can generate output data OUT based on sample input IN provided from the enabled peripheral device. In some embodiments, hub device 12 and host 11 may be included in a single semiconductor package, or may be implemented as separate semiconductor packages mounted on an on-board surface. When peripheral device 16 includes only sensors, hub device 12 may be referred to as a sensor hub, and when peripheral device 16 includes sensors and other peripheral devices, hub device 12 may be referred to as a context hub.
[0031] Hub device 12 can receive a clock signal CLK and a power supply voltage VDD from DVFS circuit 14, and can provide a control signal CTR to DVFS circuit 14. For example, hub device 12 can operate synchronously with the clock signal CLK and can operate based on the power supplied by the power supply voltage VDD. The performance and power consumption of hub device 12 can depend on the magnitude of the power supply voltage VDD and the frequency of the clock signal CLK. For example, as the magnitude of the power supply voltage VDD increases and the frequency of the clock signal CLK increases, the performance of hub device 12 can improve, while the power consumption of hub device 12 can increase. Therefore, the performance and power consumption of hub device 12 can vary according to the frequency of the clock signal CLK and the magnitude of the power supply voltage VDD. In addition, multiple operating conditions of hub device 12 corresponding to combinations of the frequency of the clock signal CLK and the magnitude of the power supply voltage VDD can be defined, and multiple operating conditions can correspond to different performance and / or power consumption. In the following, for ease of description, exemplary embodiments of this disclosure will be described primarily with reference to operating conditions corresponding to the frequency of the clock signal CLK.
[0032] As described below with reference to the accompanying drawings, hub device 12 can estimate optimal power consumption based on the processing time and cycle of sample input IN, and can generate a control signal CTR corresponding to the estimated optimal power consumption, and provide the control signal CTR to DVFS circuit 14. Therefore, hub device 12 can achieve interface connection to peripheral device 16 with optimal power consumption, and can improve the performance and efficiency of system 10. Furthermore, even if the peripheral device 16 included in system 10 changes, hub device 12 can still estimate the optimal power consumption for interface connection to peripheral device 16. In addition, due to the high compatibility of hub device 12 with peripheral device 16, various peripheral devices depending on the user of hub device 12 (e.g., the manufacturer of system 10) can be easily supported. Therefore, hub device 12 or devices including hub device 12 (e.g., devices including hub device 12 and host 11) can be freely designed and manufactured, thus significantly increasing the productivity of hub device 12 or devices including hub device 12.
[0033] Hub device 12 can access memory 13, and hub device 12 can interface with peripheral device 16 by storing data in memory 13 or retrieving data stored in memory 13. Memory 13 may include volatile storage devices such as static random access memory (SRAM) or dynamic random access memory (DRAM), or may include non-volatile storage devices such as flash memory or resistive random access memory (RRAM). In some embodiments, as will be referenced below... Figure 3 and Figure 4 As described, memory 13 can store an uptime (i.e., active time) table. In some embodiments, with Figure 1 Unlike other devices, memory 13 can be included in hub device 12. Furthermore, in some embodiments, memory 13 can be accessed by host 11.
[0034] DVFS circuit 14 can provide power supply voltage VDD and clock signal CLK to hub device 12, and receive control signal CTR from hub device 12. For example... Figure 1As shown, the DVFS circuit 14 may include a clock management unit (CMU) 14_2 and a power management unit (PMU) 14_4. CMU 14_2 can generate a clock signal CLK based on a control signal CTR and adjust the frequency of the clock signal CLK. For example, CMU 14_2 may include an oscillator that generates the clock signal CLK based on the control signal CTR. CMU 14_2 may also be referred to as a clock generator or clock generator circuit. PMU 14_4 can generate a power supply voltage VDD based on the control signal CTR and adjust the magnitude of the power supply voltage VDD. For example, PMU 14_4 may include a switching regulator that generates the power supply voltage VDD based on the voltage supplied by battery 15 according to the control signal CTR. PMU 14_4 may also be referred to as a power management integrated circuit (PMIC).
[0035] Figure 2 This is a timing diagram illustrating the operation of a hub device according to an exemplary embodiment of the present disclosure. Specifically, as examples of different operating conditions, Figure 2 The timing diagram shows Figure 1 Examples of the operation of hub device 12 at different frequencies of clock signal CLK. Figure 2 In this context, it is assumed that the first frequency f1 of the clock signal CLK is higher than the second frequency f2 (f1 > f2), and the reference frequency is... Figure 1 To describe Figure 2 The timing diagram.
[0036] The request REQ provided by host 11 can instruct hub device 12 to periodically receive and process sample input IN. For example, as Figure 2 As shown, hub device 12 can receive and process first sample inputs IN1 to third sample inputs IN3 from the first to third peripheral devices included in peripheral devices 16 in each cycle T. Therefore, hub device 12 may need to complete the reception and / or processing of first sample inputs IN1 to third sample inputs IN3 within cycle T. As will be referred to below Figure 7 As described, the first sample input IN1 to the third sample input IN3 can each correspond to a different period.
[0037] Reference Figure 2 In the upper part, when the clock signal CLK has a first frequency f1, the first sample input IN1 to the third sample input IN3 can be processed from time t11 to time t12. In this document, the time during which the hub device 12 processes the sample inputs can be referred to as the active time (i.e., normal operating time), and as... Figure 2As shown, the first sample input IN1 to the third sample input IN3 can be processed during the first active time ACT1. From time t12 to time t13 (i.e., during the first idle time IDL1), sample inputs can be left unprocessed, and the first sample input IN1 to the third sample input IN3 can be processed again starting from time t13.
[0038] Reference Figure 2 In the lower part, when the clock signal CLK has a second frequency f2, the first sample input IN1 to the third sample input IN3 can be processed from time t21 to time t22 (i.e., during the second active time ACT2). Since the second frequency f2 is less than the first frequency f1, the time required to process the first sample input IN1 to the third sample input IN3 (i.e., the second active time ACT2) can be longer than the first active time ACT1 (ACT2 > ACT1). From time t22 to time t23 (i.e., during the second idle time IDL2), the sample inputs can be left unprocessed, and the first sample input IN1 to the third sample input IN3 can be processed again starting from time t23. Because all the first sample input IN1 to the third sample input IN3 are processed at the second frequency f2 of the clock signal CLK within the period T, the hub device 12 can reduce the power consumed by the hub device 12 by generating a control signal CTR to make the clock signal CLK have a second frequency f2.
[0039] Figure 3 This is a block diagram of a hub device 30 according to an exemplary embodiment of the present disclosure. As referenced above... Figure 1 The above, Figure 3 The hub device 30 can receive requests (REQ) and sample inputs (IN), generate output data (OUT) and control signals (CTR), and access memory 20. For example... Figure 3 As shown, hub device 30 may include a first interface 31, a second interface 32, and processing circuitry 33. In the following, it is assumed that... Figure 3 Hub device 30 and Figure 1 The peripheral device 16 communicates with the host 11.
[0040] The first interface 31 can form a communication channel with the peripheral device 16 and receive sample input IN from the peripheral device 16. For example, the first interface 31 can implement the physical layer using the communication protocol with the peripheral device 16. The second interface 32 can form a communication channel with the host 11, receive request REQ from the host 11, and provide output data OUT to the host 11. For example, the second interface 32 can implement the physical layer using the communication protocol with the host 11.
[0041] The processing circuit 33 can receive sample input IN from the peripheral device 16 via the first interface 31, and can receive request REQ from the host 11 via the second interface 32. Additionally, the processing circuit 33 can provide output data OUT to the host 11 via the second interface IF2. In some embodiments, the processing circuit 33 may include at least one core that executes a series of instructions, and can execute a program composed of instructions. Furthermore, in some embodiments, the processing circuit 33 may include at least one IP core designed by logic synthesis and / or FPGA. Figure 3 As shown, the processing circuit 33 can execute multiple subroutines, namely, at least one peripheral device driver 33_2, at least one algorithm 33_4, a table manager 33_6, and a DVFS controller 33_8. Hereinafter, it is assumed that the processing circuit 33 includes at least one core that executes a program comprising multiple subroutines; however, it should be noted that the exemplary embodiments of this disclosure are not limited thereto. That is, in some embodiments, the processing circuit 33 may include at least one dedicated hardware module designed to perform at least one function of at least one of the peripheral device driver 33_2, at least one algorithm 33_4, a table manager 33_6, and a DVFS controller 33_8. Hereinafter, the processing circuit 33 performing an operation by executing a subroutine can be simply expressed as the subroutine performing the operation.
[0042] At least one peripheral device driver 33_2 can perform operations specifically for at least one peripheral device included in peripheral device 16, and can provide an interface independent of peripheral device 16 for other subroutines of processing circuit 33. For example, peripheral device driver 33_2 can convert sample input IN provided from peripheral device 16 into data with a common format.
[0043] At least one algorithm 33_4 can generate output data OUT based on the sample input IN. For example, at least one algorithm 33_4 can convert the sample input IN into output data OUT that can be recognized by the host 11, or it can generate data including useful information by processing the sample input IN. In the latter case, since the sample input IN is received periodically, at least one algorithm 33_4 can periodically generate data based on the sample input IN, and thus will refer to the following... Figure 8A As described, data generated by at least one algorithm 33_4 can be manipulated in the same way as sample input IN received from peripheral device 16, and therefore at least one algorithm 33_4 can be referred to as a virtual peripheral device.
[0044] Table manager 33_6 can manage the activity schedule 22 stored in memory 20. For example, table manager 33_6 can identify scan modes and can generate and store the activity schedule 22 in the memory 20 under scan modes. The activity schedule 22 can include the time required to process the sample input IN of each peripheral device 16 under each of a plurality of operating conditions as entries, and can be referenced by DVFS controller 33_8, which will be described below. (The following references...) Figure 4 Example describing the activity schedule 22.
[0045] The DVFS controller 33_8 can identify the optimal operating conditions of the hub device 30 based on the processing time and cycle of the sample input IN, and can generate the control signal CTR provided to the DVFS circuit 14 based on the identified operating conditions. The following will refer to... Figure 5 Examples describing the operation of the DVFS controller 33_8.
[0046] Figure 4 This is a view of an activity schedule 40 according to an example embodiment of this disclosure. (Refer to the above...) Figure 3 The activity schedule 40 can be stored in the memory 20 and referenced by the processing circuit 33. In the following text, reference will be made to... Figure 3 To describe Figure 4 And assume Figure 3 The memory 20 stores Figure 4 The activity schedule is 40.
[0047] Activity schedule 40 can include the processing time of sample inputs under each of multiple operating conditions as entries. For example, as Figure 4 As shown, the activity schedule 40 may include m*n activity times ACT11 to ACTnm (where m and n are integers greater than 1) as entries corresponding to combinations of first operating conditions CON1 to m-th operating conditions CONm and first sample input IN1 to n-th sample input INn. The first operating conditions CON1 to m-th operating conditions CONm may correspond to different power consumption and performance, and as... Figure 4 As shown, the first operating condition CON1 can correspond to the highest power consumption and performance. Additionally, the m-th operating condition CONm can correspond to the lowest power consumption and performance. Furthermore, each of the first sample input IN1 to the n-th sample input INn can be provided from a peripheral device, or can correspond to... Figure 3 At least one of the algorithms 33_4.
[0048] For the dynamic voltage-frequency scaling of hub device 30, and Figure 4The activity schedule 40 shown is different; an input pattern table that stores operating conditions corresponding to sample input patterns can be used. However, when peripheral devices are changed, the input pattern table can be completely modified, and when a peripheral device is added, data corresponding to multiple input patterns can be added to the input pattern table. On the other hand, because Figure 4 The activity schedule 40 stores the processing time corresponding to each peripheral device, so when the peripheral device changes, only the corresponding entries can be deleted and / or added, thus making it easier to manage the activity schedule 40.
[0049] Figure 5 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. As referenced above... Figure 1 The hub device 54 can be located between the host 52 and the peripheral device 56, and enables the peripheral device 56 to interface with the host 52.
[0050] Reference Figure 5 In operation S20, host 52 can send a request REQ to hub device 54. (See above reference.) Figure 1 The request REQ can instruct the activation of at least one of the peripheral devices 56, and can instruct the periodic reception and processing of sample input IN provided from the peripheral device 56.
[0051] In operation S30, hub device 54 can identify the processing time and cycle of sample input IN. For example, hub device 54 can identify the cycle of sample input IN based on request REQ received from host 52, and can identify the processing time of sample input IN corresponding to request REQ by referring to the activity schedule.
[0052] In operation S40, hub device 54 can identify at least one operating condition. For example, hub device 54 can identify at least one operating condition based on the processing time and cycle of the sample input IN identified in operation S30. (Refer to the above...) Figure 2 As described, the identified at least one operating condition may correspond to one of a plurality of operating conditions that allows processing of the sample input IN to be completed within a cycle. Hub device 54 can select one of the identified at least one operating condition and can operate under the selected operating condition by generating a control signal CTR. The following will refer to... Figure 6 Describe an example of operation S40.
[0053] In operation S50, peripheral device 56 can periodically send sample input IN to hub device 54. For example, hub device 54 can periodically receive sample input IN from peripheral device 56 by communicating with peripheral device 56 based on request REQ. The periodicity of sample input IN can be maintained even if the operating conditions identified in operation S40 change.
[0054] In operation S60, hub device 54 can generate output data OUT. For example, hub device 54 can generate output data OUT by converting or processing sample input IN received in operation S50. The output data OUT can correspond to a response to the request REQ sent by host 52 in operation S20.
[0055] In operation S70, hub device 54 can send output data OUT to host 52. In some embodiments, as will be referred to below. Figure 9 and Figure 10 As described, hub device 54 can detect the loss of processing of sample input IN based on the transmission of output data OUT, and when the loss of processing of sample input IN is detected, hub device 54 can change the operating conditions identified in operation S40.
[0056] Figure 6 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. Specifically, Figure 6 The flowchart shows Figure 5 An example of operation S40, and as referenced above. Figure 5 As described, it can be found Figure 6 In operation S40', at least one operating condition is identified. For example... Figure 6 As shown, operation S40' may include multiple operations S41 to S47. In some embodiments, operation S40' may be performed by... Figure 3 The processing circuit 33 executes the DVFS controller 33_8, and will be referred to below. Figure 3 and Figure 5 describe Figure 6 .
[0057] Reference Figure 6 In operation S41, the minimum cycle of the sample input can be identified. For example, processing circuit 33 can identify... Figure 5 The smallest cycle identified in operation S30. See below for reference. Figure 7 As described, it may be necessary to complete the processing of sample inputs within the minimum period required to identify the worst-case scenario, and therefore this minimum period can be used to identify the operating conditions.
[0058] In operation S42, operating conditions can be selected. For example, processing circuit 33 can select one of a plurality of operating conditions included in activity schedule 22. In some embodiments, processing circuit 33 can select the operating condition corresponding to the highest power and performance from the plurality of operating conditions (e.g., Figure 4 CON1 in the text refers to operating conditions corresponding to the lowest power and performance (e.g., ...). Figure 4 CONm in the sequence selects the operation conditions.
[0059] In operation S43, the sum of the processing times for the sample inputs can be calculated. For example, processing circuit 33 can identify the sample inputs from activity schedule 22 under the operating conditions selected in operation S42. Figure 3 The processing time corresponding to the sample input identified in operation S30 can be calculated, and the sum of the identified processing times can be calculated. For example, refer to Figure 4 In the activity schedule 40, when the first sample input IN1 and the second sample input IN2 are enabled by the request REQ of the host 11, the processing circuit 33 can select the second operating condition CON2 and calculate the sum of the activity times ACT12 and ACT22.
[0060] In operation S44, the sum of processing times can be compared with the minimum cycle. For example, processing circuit 33 can compare the minimum cycle identified in operation S41 with the sum of processing times calculated in operation S43. Figure 6 As shown, when the sum of processing times is less than the minimum cycle, operation S45 can be executed subsequently, and when the sum of processing times is greater than or equal to the minimum cycle, operation S46 can be executed subsequently.
[0061] When the sum of processing times is less than the minimum cycle, the operating conditions can be added to the list in operation S45. For example, when the sum of the processing times of the sample input is less than the minimum cycle under the selected operating conditions, the processing circuit 33 can determine that the hub device 30 can normally perform the operation corresponding to the request REQ from the host 11, and can add the selected operating conditions to the list. Figure 6 As shown, after operation S45, a new operation condition can be selected in operation S42, so the list can include at least one available operation condition for the request REQ for host 11 from among multiple operation conditions. Therefore, at least one operation condition can be identified.
[0062] When the sum of processing times is greater than or equal to the minimum cycle time, the operating condition corresponding to the minimum power consumption can be identified in operation S46. For example, processing circuit 33 can identify the operating condition corresponding to the minimum power consumption from the list of operating conditions included. Figure 6In the example, the processing circuit 33 can select multiple operating conditions in descending order of power consumption and performance, so in operation S46, the processing circuit 33 can identify the operating condition that was last added to the list.
[0063] In operation S47, operating conditions can be set. For example, processing circuit 33 can generate a control signal CTR corresponding to the operating conditions identified in operation S46, and can provide the control signal CTR to DVFS circuit 14. DVFS circuit 14 can provide power supply voltage VDD and clock signal CLK to hub device 30 based on control signal CTR, and hub device 30 can operate under the identified operating conditions.
[0064] Figure 7 This is a timing diagram illustrating the operation of a hub device according to an exemplary embodiment of the present disclosure. Specifically, as examples of different operating conditions, Figure 7 The timing diagram shows Figure 1 Examples of the operation of hub device 12 at different frequencies of clock signal CLK. For example... Figure 7 As shown, the first sample input IN1 to the third sample input IN3 can each correspond to different periods, namely, the first period T1 to the third period T3 (T1 < T2 < T3). Figure 7 In this context, it is assumed that the first frequency f1 is higher than the second frequency f2 (f1 > f2). In the following text, reference will be made to... Figure 1 To describe Figure 7 And omission and Figure 2 The description is the same as the description.
[0065] Reference Figure 7 In the upper part, when the clock signal CLK has a first frequency f1, the first sample input IN1 to the third sample input IN3 can be processed from time t31 to time t32. The first sample input IN1 can have a first period T1, which is the shortest period among the first period T1 to the third period T3, so the first sample input IN1 can be processed at each of time t32 and time t33. The second sample input IN2 can have a second period T2 that is longer than the first period T1, and the second sample input IN2 can be processed after the first sample input IN1. The third sample input IN3 can have a third period T3, which is the longest period among the first period T1 to the third period T3, so the third sample input IN3 can be processed after the first sample input IN1. Figure 7 As shown in the upper part, all first sample inputs IN1 to third sample inputs IN3 can be processed from time t31 to time t32 (i.e., within the first period T1), so no loss of processing of first sample inputs IN1 to third sample inputs IN3 occurs.
[0066] Reference Figure 7 In the lower part, when the clock signal CLK has a second frequency f2, the first sample input IN1 to the third sample input IN3 can be processed from time t41 to time t42. Therefore, the first sample input IN1 can be processed again at time t42, and the period T1' from time t41 to time t42 can be longer than the first period T1 (T1' > T1). Therefore, the processing of the first sample input IN1 may be delayed, and when operating synchronously with the clock signal CLK having a second frequency f2, the hub device 12 may generally be unable to respond to the request REQ from the host 11. When unlike Figure 7 As shown in the lower part, when processing the first sample input IN1 in each first cycle T1, the processing of the second sample input IN2 and / or the third sample input IN3 can be stopped or omitted. Therefore, the hub device 12 may generally be unable to respond to the request REQ from the host 11. The hub device 12 can be as described above. Figure 6 The process involves identifying the smallest period within the sample input period in order to exclude it from... Figure 7 The operating conditions shown at the bottom are identified, and the sum of the processing times for the sample inputs is less than the minimum cycle.
[0067] Figure 8A and Figure 8B This is a timing diagram illustrating the operation of a hub device according to an example embodiment of the present disclosure. Specifically, Figure 8A The timing diagram illustrates an example of the operation of processing data generated based on sample input IN received from a peripheral device, and Figure 8B The sequence diagram illustrates an example of operations that include background processes. Figure 8A and Figure 8B In this context, it is assumed that the first frequency f1 is higher than the second frequency f2 (f1 > f2). In the following text, reference will be made to... Figure 3 describe Figure 8A and Figure 8B And omission and Figure 2 The same description about Figure 8A and Figure 8B The description.
[0068] Reference Figure 8A The processing time of the data generated based on the sample input IN can be used to identify operating conditions. For example, as mentioned above... Figure 3 As stated, at least one algorithm 33_4 can generate data including useful information based on the sample input IN. Figure 8AIn the example, at least one algorithm 33_4 can generate first data f(IN1) based on a first sample input IN1, and can generate second data g(IN2, IN3) based on a second sample input IN2 and a third sample input IN3. The processing circuit 33 can determine the time spent generating the first data f(IN1) and the second data g(IN2, IN3), as well as the processing time from the first sample input IN1 to the third sample input IN3. In some embodiments, the activity schedule 22 can include the time spent generating the first data f(IN1) and the second data g(IN2, IN3) under each of a plurality of operating conditions, as well as the processing time from the first sample input IN1 to the third sample input IN3, and the processing circuit 33 can identify the time spent generating the first data f(IN1) and the second data g(IN2, IN3) by referring to the activity schedule 22.
[0069] Reference Figure 8A At the upper part, when the clock signal CLK has a first frequency f1, it can process the first sample input IN1 to the third sample input IN3, and can generate the first data f(IN1) and the second data g(IN2, IN3) from time t51 to time t52. That is, during the first active time ACT1, it can process the first sample input IN1 to the third sample input IN3, and can generate the first data f(IN1) and the second data g(IN2, IN3). (Refer to...) Figure 8A In the lower part, when the clock signal CLK has a second frequency f2, the first sample input IN1 to the third sample input IN3 can be processed, and the first data f(IN1) and the second data g(IN2, IN3) can be generated from time t61 to time t62. That is, during the second activity time ACT2, the first sample input IN1 to the third sample input IN3 can be processed, and the first data f(IN1) and the second data g(IN2, IN3) can be generated. The second activity time ACT2 can be longer than the first activity time ACT1 (ACT2 > ACT1).
[0070] Reference Figure 8B The execution time of a background operation can be used to identify operating conditions. For example, the processing circuit 33 can periodically execute background operations, and as a non-limiting example, background operations may include operations for switching sample inputs, monitoring operations, interrupt handling operations, etc. The execution time of a background operation can also vary depending on the operating conditions. In some embodiments, the memory 20 can store the execution time of a background operation in each of a plurality of operating conditions, and the processing circuit 33 can access the memory 20 to identify the execution time of the background operation. In this document, the time required to execute a background operation may be referred to as background time.
[0071] Reference Figure 8B At the top, when the clock signal CLK has a first frequency f1, it can process the first sample input IN1 to the third sample input IN3, and can perform background operations from time t71 to time t72. That is, during the first activity time ACT1, it can process the first sample input IN1 to the third sample input IN3, and can perform background operations. (Refer to...) Figure 8B In the lower part, when the clock signal CLK has a second frequency f2, the first sample input IN1 to the third sample input IN3 can be processed, and background operations can be performed from time t81 to time t82. That is, during the second activity time ACT2, the first sample input IN1 to the third sample input IN3 can be processed, and background operations can be performed. The second activity time ACT2 can be longer than the first activity time ACT1 (ACT2 > ACT1).
[0072] Figure 9 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. Figure 9 As shown, operation S80 may include multiple operations S81, S82, and S83, and the operating conditions in operation S80 may be changed based on the loss of processing of the sample input IN. In some embodiments, operation S80 may be... Figure 3 The processing circuit 33 executes the DVFS controller 33_8, and can be executed in... Figure 5 The operation S70 is repeated. This will be discussed in the following text. Figure 3 and Figure 5 describe Figure 9 .
[0073] In operation S81, the loss of processing of sample input IN can be detected. For example, processing circuit 33 can detect the loss of processing of sample input IN while operating under operating conditions identified and set based on the processing time and period of sample input IN. The loss of processing of sample input IN may occur for various reasons. For example, processing circuit 33 may handle temporary operations with high priority, such as interrupt handling operations, and the processing of sample input may be delayed due to the time required to execute temporary operations, so processing circuit 33 may generally be unable to respond to the request REQ of host 11. In this document, the loss of processing of sample input IN can be simply referred to as the loss of sample input IN.
[0074] In operation S82, it can be determined whether a sample input IN has been lost. For example... Figure 9 As shown, when a sample input IN is lost, that is, when a loss of sample input IN is detected in operation S81, operation S83 can be executed subsequently. On the other hand, when no loss of sample input IN occurs, operation S80 can be terminated.
[0075] When a sample input IN is lost, the operating conditions can be changed in operation S83. For example, when a sample input IN is lost, the processing circuit 33 can determine that the current operating conditions are unsuitable, and therefore can change the operating conditions by identifying operating conditions corresponding to higher power consumption and performance. The processing circuit 33 can generate a control signal CTR corresponding to the changed operating conditions, and can provide the control signal CTR to the DVFS circuit 14.
[0076] Figure 10 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. Specifically, Figure 10 The flowchart shows Figure 9 An example of operation S80. See the above reference. Figure 9 As mentioned above, in Figure 10 In operation S80', the operating conditions can be changed based on the loss of sample input IN. For example... Figure 10 As shown, operation S80' may include multiple operations S81' to S83', and operation S83' may include operations S83_1 and S83_2. In the following text, the terms related to... will be omitted. Figure 9 The same description about Figure 10 The description.
[0077] Reference Figure 10 During operation S81', the transmission of output data OUT can be monitored. For example, processing circuit 33 can provide output data OUT to host 11 via inter-process communication (TPC). Processing circuit 33 can monitor the transmission of output data OUT by monitoring IPC, and when the transmission of output data OUT corresponding to sample input IN is lost, processing circuit 33 can determine that sample input IN has been lost.
[0078] In operation S82', it can be determined whether the transmission of output data OUT has been lost. For example... Figure 10 As shown, when the transmission of output data OUT is lost, that is, when the sample input IN is lost, operation S83' can be executed subsequently. On the other hand, when the transmission of output data OUT is not lost, operation S80' can be terminated.
[0079] When a loss of output data OUT occurs, an offset can be added to the sum of processing times in operation S83_1. For example, processing circuit 33 can add the offset to the sum of processing times. Figure 6 The sum of the processing times of the sample inputs calculated in operation S43 can be used to identify operating conditions based on the extended sum of processing times. In some embodiments, the processing circuit 33 can add a representation of the above reference. Figure 8BThe value describing the execution time of the background operation is added to the sum of the processing times of the sample input.
[0080] In operation S83_2, operating conditions can be identified. For example, processing circuit 33 can execute based on the sum of the processing times extended in operation S83_1. Figure 6 Operation S40'. That is, the processing circuit 33 can compare the sum of the extended processing times with the minimum cycle, and can identify at least one operating condition based on the comparison result. Furthermore, the processing circuit 33 can select the operating condition corresponding to the minimum power consumption from the identified at least one operating condition, and can change the current operating condition to the selected operating condition.
[0081] Figure 11 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. Figure 11 As shown, operation S10 may include multiple operations S11 to S13, and an activity schedule may be generated in operation S10. In some embodiments, operation S10 may be performed by... Figure 3 The processing circuit 33 executes the table manager 33_6. In some embodiments, it can be... Figure 5 Operation S10 is performed before operation S20, and can be performed, for example, during the manufacturing of a system including hub device 30 and peripheral devices (e.g., Figure 1 The system (10) performs operation S10 during the process. In the following text, reference will be made to... Figure 3 and Figure 5 describe Figure 11 .
[0082] In operation S11, it can be determined whether a scan mode is set. For example, during the manufacturing process of a system including hub device 30, hub device 30 can be set to scan mode. (See above reference...) Figure 1 The user of hub device 30 (or the device including hub device 30 and host) (i.e., the manufacturer of the system including hub device 30 and peripheral devices) can set hub device 30 (or the device including hub device 30 and host) to scan mode during the manufacturing process of the system. Scan mode can correspond to an operating mode that generates an activity schedule by scanning peripheral devices. Figure 11 As shown, when the hub device 30 is set to scan mode, operation S12 can be performed subsequently, while when the hub device 30 is not set to scan mode, operation S10 can be terminated.
[0083] When hub device 30 is set to scan mode, each peripheral device can be tested in operation S12. For example, processing circuitry 33 can mutually exclusively enable peripheral devices under each of a plurality of operating conditions, and the processing time of sample input IN can be detected by testing the enabled peripheral devices. In some embodiments, peripheral device testing can be performed in response to a request REQ provided by the host, and the host (or an application executed by the host) can generate an activity schedule using hub device 30. Reference will be made below. Figure 12 Describe an example of operation S12.
[0084] In operation S13, an activity schedule 22 can be generated and stored in memory 20. For example, processing circuit 33 can generate an activity schedule 22 that includes the processing time detected in operation S12, and can store the activity schedule 22 in memory 20. In some embodiments, processing circuit 33 can provide the generated activity schedule to the host, and the host can store the generated activity schedule in non-volatile memory, and can load the stored activity schedule into memory 20 after system startup.
[0085] Figure 12 This is a flowchart of a method for connecting to a peripheral device interface according to an exemplary embodiment of this disclosure. Specifically, Figure 12 The flowchart shows Figure 11 Example of operation S12. See the above reference. Figure 11 As mentioned above, it can be found in Figure 12 In operation S12', each peripheral device is tested. For example... Figure 12 As shown, operation S12' may include multiple operations S12_1 to S12_8. In some embodiments, operation S12' may be performed by... Figure 3 The processing circuit 33 executes the table manager 33_6. In the following text, reference will be made to... Figure 3 and Figure 11 describe Figure 12 .
[0086] In operation S12_1, a peripheral device can be selected. For example, processing circuit 33 can select each peripheral device sequentially. In operation S12_2, the selected peripheral device can be enabled. For example, processing circuit 33 can periodically receive sample input IN from the enabled peripheral device.
[0087] In operation S12_3, operating conditions can be selected and set. For example, processing circuit 33 can sequentially select each of a plurality of operating conditions and can generate a control signal CTR corresponding to the selected operating condition. In operation S12_4, idle time can be measured during a unit time period. For example, processing circuit 33 can measure the idle time excluding the time required to process sample input IN (i.e., activity time) during a 1-second period. In some embodiments, with Figure 12 Unlike other circuits, processing circuit 33 can measure the time required to process sample input IN (i.e., activity time) per unit time period.
[0088] In operation S12_5, the processing time of the sample input IN can be calculated. For example, the processing circuit 33 can calculate the processing time of the sample input IN based on the following Equation 1.
[0089] [Equation 1]
[0090] ACT = T * (1 - idle_time)
[0091] In Equation 1, ACT can represent the processing time of the sample input IN, T can represent the period of the sample input IN, and idle_time can represent the idle time measured in 1 second.
[0092] In operation S12_6, it can be determined whether the peripheral device test is complete. For example, the test can be determined to be complete when the total time required to process the sample input IN provided from the selected peripheral device in each of several operating conditions is calculated. Figure 12 As shown, when the test is determined to be completed, operation S12_7 can be executed subsequently, while when the test is not completed, that is, when there are still operating conditions for testing the selected peripheral device, operations S12_3 to S12_5 can be executed again.
[0093] When the test is complete, the selected peripheral device can be disabled in operation S12_7. For example, processing circuit 33 may no longer receive or process sample input IN from the selected peripheral device. In operation S12_8, it can be determined whether the scan of the peripheral device is complete. For example, processing circuit 33 can determine that the scan is complete when all tests for each peripheral device are completed. Figure 12 As shown, operation S12' can be terminated when the scan is complete, while operations S12_1 to S12_7 can be subsequently executed when the scan is not complete, i.e., when there are still peripheral devices to be tested. Finally, when operation S12' is completed, the processing time of the sample input provided by the peripheral device under each of the multiple operating conditions can be obtained.
[0094] Figure 13This is a block diagram of a hub device 70 according to an exemplary embodiment of the present disclosure. Specifically, Figure 13 The block diagram illustrates a hub device 70 connected to a peripheral device interface based on a machine learning model 62. For example... Figure 13 As shown, similar to Figure 3 The hub device 30, and the hub device 70 may include a first interface 71, a second interface 72, and processing circuitry 73. Furthermore, the hub device 70 may communicate with a neural processing unit (NPU) 60 that executes a machine learning model 62. In some embodiments, with Figure 13 Unlike other devices, the NPU 60 can be included in the hub device 70.
[0095] The processing circuit 73 can interface with a peripheral device using a machine learning model 62 trained with multiple samples. In some embodiments, the machine learning model 62 may have a state trained with multiple samples as input. By providing sample input IN to the machine learning model 62, the processing circuit 73 can receive execution from the machine learning model 62. Figure 8B The processing circuit 73 can obtain processing times corresponding to multiple operating conditions by providing the machine learning model 62 with the processing time of the sample input IN calculated under one operating condition in scan mode, and can generate an activity schedule based on the obtained processing times. Additionally, in some embodiments, the machine learning model 62 can learn the sample input IN, and the processing time and / or period of the sample input IN, and can output scores corresponding to multiple operating conditions. The processing circuit 73 can identify operating conditions based on the scores provided from the machine learning model 62, and in this case, the processing time of the sample input IN can be omitted. Figure 3 The activity schedule.
[0096] NPU 60 can refer to any device that executes machine learning model 62. In some embodiments, NPU 60 can be a dedicated hardware block designed to execute machine learning model 62, or it can be a software block executed by the processing circuitry 73 of hub device 70, a processor included in the host, or another processor. Machine learning model 62 can be any model trained with multiple samples, such as a model based on artificial neural networks, decision trees, support vector machines, regression analysis, Bayesian networks, genetic algorithms, etc. Figure 13As shown, when machine learning model 62 is based on an artificial neural network, as a non-limiting example, the artificial neural network may include a convolutional neural network (CNN), a region convolutional neural network (R-CNN), a region proposal network (RPN), a recurrent neural network (RNN), a stack-based deep neural network (S-DNN), a state-space dynamic neural network (S-SDNN), a deconvolutional network, a deep trust network (DBN), a restricted Boltzmann machine (RBM), a fully convolutional network, a long short-term memory (LSTM) network, or a classification network.
[0097] Figure 14 This is a block diagram of a vehicle 100 according to an exemplary embodiment of the present disclosure. Figure 14 As shown, vehicle 100 may include propulsion device 120, electronic device 140, auxiliary device 160 and drive device 180.
[0098] The propulsion device 120 may include an engine / motor 121, an energy source 122, a transmission 123, wheels / tires 124, a suspension 125, and shock absorbers 126. The engine / motor 121 may include any combination of an internal combustion engine, an electric motor, a steam engine, and a Stirling engine. In some embodiments, when the vehicle 100 is a gas-electric hybrid vehicle, the engine / motor 121 may include a gasoline engine and an electric motor. The energy source 122 may be an energy source that at least partially supplies electricity to the engine / motor 121, and the engine / motor 121 may convert the energy source 122 into kinetic energy.
[0099] In a non-limiting example, energy source 122 may include at least one of gasoline, diesel, propane, compressed gas-based fuel, ethanol, solar panels, batteries, and power sources. In some embodiments, energy source 122 may include at least one of a fuel tank, a battery, a capacitor, and a flywheel. Additionally, energy source 122 may supply energy to other components of vehicle 100 and engine / motor 121.
[0100] The transmission 123 can transmit mechanical power from the engine / motor 121 to the wheel / tire 124. For example, the transmission 123 may include at least one of a gearbox, a clutch, a differential, and a drive shaft. When the transmission 123 includes a drive shaft, the drive shaft may include at least one axle coupled to the wheel / tire 124. The wheel / tire 124 may have various structures for bicycles, motorcycles, four-wheeled vehicles, etc., and may be in contact with the road surface.
[0101] The suspension 125 is a device that supports the weight of the vehicle 100 and can adjust the ground clearance between the vehicle 100 and the road surface, and can control vibrations from the road surface that are transmitted to the vehicle 100. The shock absorber 126 can control spring vibrations transmitted from the road surface during driving and can help the spring return to its original state. For example, the shock absorber 126 can control the spring's elasticity by generating a damping force to stop the spring's vibrations. In some embodiments, the shock absorber 126 may be included in the suspension 125.
[0102] Electronic device 140 may include controller 141, hub device 142, storage device 143, user interface 144, at least one sensor 145, and power supply 146. Controller 141 can control vehicle 100 and may also be referred to as electronic control unit (ECU). For example, controller 141 can control the movement of vehicle 100 by controlling propulsion device 120 and drive device 180, and can control auxiliary device 160. Controller 141, acting as the host, can indirectly communicate with peripheral devices (i.e., components included in electronic device 140, and at least some of the components included in propulsion device 120, auxiliary device 160, and drive device 180) via hub device 142. Hub device 142 can connect between controller 141 and peripheral devices, and interface peripheral devices with controller 141. As described above with reference to the accompanying drawings, hub device 142 can identify optimal operating conditions and therefore can have optimal performance and power consumption.
[0103] Storage device 143 can store data and may include, for example, a non-volatile semiconductor storage device, a volatile semiconductor storage device, or a disk drive. User interface 144 may include input devices for receiving user input and output devices for providing output signals to the user. For example, input devices may include a keypad, dome switch, touchpad, scroll wheel, scroll wheel switch, microphone, etc. Additionally, output devices may include speakers and / or buzzers for outputting audio signals, display devices and / or light-emitting diodes (LEDs) for outputting video signals, etc.
[0104] At least one sensor 145 may include a sensor for detecting the state of vehicle 100. For example, at least one sensor 145 may include a motion sensor such as a geomagnetic sensor, an accelerometer, or a gyroscope sensor, and may include a GPS sensor for estimating the position of vehicle 100. Additionally, at least one sensor 145 may include a sensor for detecting the state around vehicle 100. For example, at least one sensor 145 may include a RADAR sensor (which detects the presence and / or velocity of objects around vehicle 100 using radio signals), and may also include a LIDAR sensor (which detects the presence and / or velocity of objects around vehicle 100 using lasers). Furthermore, at least one sensor 145 may include at least one image sensor (or a camera module including an image sensor) for capturing images of the environment surrounding vehicle 100.
[0105] The power source 146 can provide power to at least some of the components of the vehicle 100. For example, the power source 146 may include a generator that generates electricity through the drive of the vehicle 100, and may include a battery for storing electricity.
[0106] Auxiliary equipment 160 may include headlights 161, taillights 162, turn indicators (vehicle hazard lights) 163, interior lighting 164, windshield wipers 165, and air conditioning 166. Headlights 161 may be located at the front of vehicle 100, and taillights 162 may be located at the rear of vehicle 100. Turn indicators 163 may be located at the front, rear, and sides of vehicle 100, and interior lighting 164 may be located in the driver's area. Windshield wipers 165 may reciprocate on the front and / or rear windows of vehicle 100, and air conditioning 166 may include air conditioning and / or a heater.
[0107] The drive unit 180 may include a braking unit 181, a steering unit 182, and a throttle valve 183. The braking unit 181 may be implemented as a combination of mechanisms configured to decelerate the vehicle 100. For example, the braking unit 181 may use friction to reduce the rotational speed of the wheels / tires 124. The steering unit 182 may be implemented as a combination of mechanisms configured to adjust the travel direction of the vehicle 100. The throttle valve 183 may be implemented as a combination of mechanisms configured to control the operating speed of the engine / motor 121. For example, the throttle valve 183 may control the amount of fuel-air mixture flowing into the engine / motor 121 and control power and thrust.
[0108] As is common in the art, embodiments can be described and illustrated around blocks that perform desired functions. These blocks, which may be referred to herein as units or modules, are physically implemented by analog and / or digital circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuitry, etc., and may optionally be driven by firmware and / or software. For example, the circuitry may be specifically implemented in one or more semiconductor chips, or on a substrate support such as a printed circuit board. The circuitry constituting a block may be implemented by dedicated hardware or by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware for performing some functions of the block and a processor for performing other functions of the block. Without departing from the scope of this disclosure, each block of an embodiment may be physically divided into two or more interactive and discrete blocks. Similarly, without departing from the scope of this disclosure, the blocks of an embodiment may be physically combined into more complex blocks. One aspect of an embodiment may be implemented by instructions stored in a non-transitory storage medium and executed by a processor.
[0109] Although this disclosure has been specifically shown and described with reference to embodiments thereof, it will be understood that various changes in form and detail may be made therein without departing from the spirit and scope of the appended claims.
Claims
1. A device configured to provide an interface with a peripheral device, the device comprising: The first interface is configured to receive requests from the host. The second interface is configured to periodically receive at least one first sample input from the peripheral device in response to a request from the host. The memory is configured to store an activity schedule including the processing time of sample inputs, which are provided by each of the peripheral devices under each of a plurality of operating conditions corresponding to different power consumption. as well as The processing circuitry is configured to identify at least one of the plurality of operating conditions based on the activity schedule and the period of the at least one first sample input.
2. The apparatus of claim 1, wherein, The processing circuit is further configured to: The sum of the processing times for the at least one first sample input is calculated based on the activity schedule. Identify the minimum period from the periods of the at least one first sample input, and The at least one operating condition is identified based on the sum of the processing times and the minimum cycle.
3. The apparatus of claim 2, wherein, The processing circuit is further configured to: identify the at least one operating condition such that the sum of the processing times is less than the minimum period.
4. The device according to claim 2, wherein, The processing circuit is further configured to: Identify the background time of background operations, and Identify at least one operating condition such that the sum of the background time and the processing time is less than the minimum period.
5. The device according to claim 4, wherein, The processing circuit is also configured to identify the background time based on the output of a machine learning model trained on multiple samples through sample input.
6. The device according to claim 2, wherein, The first interface is further configured to: send output data generated by processing the at least one first sample input to the host, and The processing circuit is further configured to: detect the loss of processing of the at least one first sample input based on the transmission of the output data, and change the at least one operating condition based on the detected loss.
7. The device according to claim 6, wherein, The processing circuit is also configured to add an offset to the sum of the processing times when the loss is detected.
8. The device according to claim 2, wherein, The processing circuit is further configured to identify, from the at least one operating condition, the operating condition corresponding to the minimum power consumption.
9. The device according to claim 1, wherein, The processing circuit is also configured to generate the activity schedule by testing the peripheral device in a scan mode, and to store the generated activity schedule in the memory.
10. The device according to claim 9, wherein, The processing circuit is also configured to: mutually exclusively enable each of the peripheral devices in the scanning mode, and under each of the plurality of operating conditions, measure the processing time of a second sample input of the enabled peripheral device to generate the activity schedule.
11. The device according to claim 10, wherein, The processing circuit is also configured to generate the activity schedule based on the period of the second sample input and the total time spent processing the second sample input within a unit time period.
12. The device according to claim 9, wherein, The processing circuit is also configured to: measure the processing time of the sample input of the peripheral device in the scanning mode, and generate the activity schedule based on the output of a machine learning model trained on multiple samples of the processing time.
13. The device according to claim 1, wherein, The activity schedule also includes: processing time for sample inputs generated based on each of the plurality of operating conditions and each of the algorithms; and The processing circuit is further configured to: By processing the at least one first sample input based on the algorithm, at least one third sample input is periodically generated, and The at least one operating condition is identified based on the activity schedule, the period of the at least one first sample input, and the period of the at least one third sample input.
14. The device according to claim 1, wherein, The multiple operating conditions correspond to multiple dynamic voltage-frequency scaling (DVFS) levels.
15. A device including an interface with a peripheral device, comprising: The host is configured to perform operations based on information provided from peripheral devices; A hub device is configured to provide an interface for the peripheral device; as well as A dynamic voltage-frequency scaling (DVFS) circuit is configured to adjust the power consumption of the hub device based on control signals provided from the hub device, wherein... The hub device is configured to periodically receive at least one sample input from the peripheral device in response to a request from the host, and to generate the control signal based on the processing time and period of the at least one sample input. The hub device is further configured to: Calculate the sum of the processing times for the at least one sample input. Identify the minimum period within the period of the at least one sample input, and The control signal is generated based on the sum of the processing times and the minimum period.
16. The apparatus of claim 15, further comprising: The memory is configured to store an activity schedule including the processing time of sample inputs, the sample inputs being provided by each of the peripheral devices under each of a plurality of operating conditions corresponding to different power consumptions, wherein... The hub device is also configured to identify the processing time of the at least one sample input from the activity schedule.
17. A method for connecting to an interface with a peripheral device, the method comprising: The host receives a request instructing the periodic receipt of at least one sample input from the peripheral device; Identify the processing time and cycle of the at least one sample input; as well as Based on the processing time and period of the at least one sample input, identify at least one operating condition from a plurality of operating conditions corresponding to different power consumptions. Identifying the at least one operating condition includes: Calculate the sum of the processing times for the at least one sample input; Identify the minimum period within the period of the at least one sample input; and The at least one operating condition is identified based on the sum of the processing times and the minimum cycle.
18. The method according to claim 17, wherein, Identifying the at least one operating condition includes: identifying the at least one operating condition based on the sum of the processing times and the minimum cycle time. This ensures that the sum of the processing times is less than the minimum cycle time.
Citation Information
Patent Citations
Manufacturing method of remolding rice including cactus pear powder and remolding rice including cactus pear powder
KR1020200109472A
Mobile device including context hub and operation method thereof
US20190250691A1
