Method to transmit processing unit information associated with a split point

Abstract

Systems, methods, and instrumentalities may be disclosed for handling processing unit information associated with a split point. A first device may include a processor. The first device may be configured to determine processing unit information associated with a processing unit of a second device. The processing unit information may be associated with an intermediate data. The processing unit information may include at least an indication of a processing unit type to be used by the second device for processing the intermediate data and / or a processing unit identifier associated with the processing unit of the second device. The device may be configured to send, to the second device, the processing unit information and / or the intermediate data. The device may be configured to receive, from the second device, a processing unit status associated with the intermediate data.

Description

METHOD TO TRANSMIT PROCESSING UNIT INFORMATION ASSOCIATED WITH A SPLIT POINTCROSS-REFERENCE TO RELATED APPLICATIONSBACKGROUND

[0002] Video coding systems may be used to compress digital video signals, e.g., to reduce the storage and / or transmission bandwidth needed for such signals. Video coding systems may include, for example, block-based, wavelet-based, and / or object-based systems.SUMMARY

[0003] Systems, methods, and instrumentalities may be disclosed for handling processing unit information associated with a split point. A wireless transmit / receive unit (WTRU) (e.g., a first device) may include a processor. The first device may be configured to determine processing unit information associated with a processing unit of a second device. The processing unit information may be associated with an intermediate data. The processing unit information may include at least an indication of a processing unit type to be used by the second device for processing the intermediate data and / or a processing unit identifier associated with the processing unit of the second device. The device may be configured to send, to the second device, the processing unit information and / or the intermediate data. The device may be configured to receive, from the second device, a processing unit status associated with the intermediate data.

[0004] The first device may be configured to receive, from the second device, an indication of a hardware capability associated with the second device. The processing unit information may be determined based on the hardware capability associated with the second device. The first device may be configured to send, to the second device, the processing unit information as part of metadata. The metadata may be used by the second device to decode or process the intermediate data, and / or to select or identify the processing unit of the second device. The first device may be configured to send, to the second device, a processing unit recommendation as part of the metadata. The processing unit recommendation may be based on a processing power.

[0005] The metadata may be sent via a different channel than the intermediate data. The first device may be configured to receive, from the second device, an inference result. The inference result may be associated with a score. The processing unit status associated with the intermediate data may include an indication that the processing unit of the second device is not available. The first device may beconfigured to receive, based on the indication that the processing unit of the second device is not available, a reply message and / or an inference result from the second device. The reply message may indicate that the processing unit of the second device is not available and / or may indicate the processing unit information. The processing unit status may include an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

[0006] A method may be performed by a first device. The method may include determining processing unit information associated with a processing unit of a second device. The processing unit information may be associated with an intermediate data. The processing unit information may include at least an indication of a processing unit type to be used by the second device for processing the intermediate data and / or a processing unit identifier associated with the processing unit of the second device. The method may include sending, to the second device, the processing unit information and / or the intermediate data. The method may include receiving, from the second device, a processing unit status associated with the intermediate data.

[0007] The method may include receiving, from the second device, an indication of a hardware capability associated with the second device. The processing unit information may be determined based on the hardware capability associated with the second device. The method may include sending, to the second device, the processing unit information as part of metadata. The metadata may be used by the second device to decode or process the intermediate data and / or to select or identify the processing unit of the second device. The method of may include sending, to the second device, a processing unit recommendation as part of the metadata. The processing unit recommendation may be based on a processing power.

[0008] The metadata may be sent via a different channel than the intermediate data. The method may include receiving, from the second device, an inference result. The inference result may be associated with a score. The processing unit status associated with the intermediate data may include an indication that the processing unit of the second device is not available. The method may include receiving, based on the indication that the processing unit of the second device is not available, a reply message and / or an inference result from the second device. The reply message may indicate that the processing unit of the second device is not available and / or indicate the processing unit information. The processing unit status may include an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

[0009] A wireless transmit / receive unit (WTRU) (e.g., a second device) may include a processor. A second device may be configured to receive, from a first device, processing unit information and / orintermediate data. The processing unit information may be associated with a processing unit of the second device. The processing unit information may be associated with the intermediate data. The processing unit information may include at least an indication of a processing unit type to be used by the second device for processing the intermediate data and / or a processing unit identifier associated with the processing unit of the second device. The second device may be configured to, in response to receiving the processing unit information and / or the intermediate data, determine a processing unit status. The second device may be configured to send, to the first device, the processing unit status.

[0010] The second device may be configured to send, to the first device, an indication of a hardware capability associated with the second device. The indication of the hardware capability may be associated with a processing unit type of the second device. The second device may be configured to receive, from the first device, the processing unit information as part of metadata. The second device may be configured to decode the intermediate data based on the received metadata. The second device may be configured to identify the processing unit of the second device based on the metadata. The second device may be configured to receive, from the first device, a processing unit recommendation as part of the metadata. The processing unit recommendation may be associated with an amount of processing power required to process the intermediate data. The metadata may be received via a different channel than the intermediate data.

[0011] The second device may be configured to send, to the first device, an inference result. The inference result may be associated with a score. The processing unit status associated with the intermediate data may include an indication that the processing unit of the second device is not available. The second device may be configured to send, based on the indication that the processing unit of the second device is not available, a reply message and / or an inference result. The reply message may indicate the unavailability of the processing unit of the second device and / or the processing unit information. The processing unit status may include an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

[0012] A method, performed by a second device, may include receiving, from a first device, processing unit information and / or intermediate data. The processing unit information may be associated with a processing unit of the second device. The processing unit information may be associated with the intermediate data. The processing unit information may include at least an indication of a processing unit type to be used by the second device for processing the intermediate data and / or a processing unit identifier associated with the processing unit of the second device. The method may include, in response to receiving the processing unit information and / or the intermediate data, determining a processing unit status. The method may include sending, to the first device, the processing unit status.

[0013] The method may include sending, to the first device, an indication of a hardware capability associated with the second device. The indication of the hardware capability may be associated with a processing unit type of the second device. The method may include receiving, from the first device, the processing unit information as part of metadata. The method may include decoding the intermediate data based on the received metadata. The method may include identifying the processing unit of the second device based on the metadata. The method may include receiving, from the first device, a processing unit recommendation as part of the metadata. The processing unit recommendation may be associated with an amount of processing power required to process the intermediate data. The metadata may be received via a different channel than the intermediate data.

[0014] The method may include sending, to the first device, an inference result. The inference result may be associated with a score. The processing unit status associated with the intermediate data may include an indication that the processing unit of the second device is not available. The method may include sending, based on the indication that the processing unit of the second device is not available, a reply message and / or an inference result. The reply message may indicate the unavailability of the processing unit of the second device and / or the processing unit information. The processing unit status may include an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

[0015] A computer program product which is stored on a non-transitory computer readable medium may include program code instructions for implementing the steps of a method as described herein when executed by at least one processor. A computer program may include program code instructions for implementing the steps of a method as described herein when executed by a processor. A video data may include information representative of an encoded output generated according to one of the methods as described herein.

[0016] A device (e.g., a WTRU) may be configured with a processor to perform one or more actions. The device may receive a set of processing units and processing unit information associated with each respective processing unit in the set of processing units. The device may determine an amount of processing power required to process intermediate data. The device may select a processing unit from the set of processing units based on the processing unit information and the amount of processing power. The device may send an indication indicating the selected processing unit.

[0017] In examples, the processing unit information may include a processing unit type associated with each respective processing unit in the set of processing units.

[0018] In examples, the processing unit information may include a processing unit identifier associated with each respective processing unit in the set of processing units.

[0019] In examples, the indication may include the processing unit identifier associated with the selected processing unit.

[0020] In examples, the device may receive a status update for a load associated with at least one processing unit in the set of processing units.

[0021] In examples, the device may send a processing unit recommendation as metadata.

[0022] Systems, methods, and instrumentalities described herein may involve a decoder. In some examples, the systems, methods, and instrumentalities described herein may involve an encoder. In some examples, the systems, methods, and instrumentalities described herein may involve a signal (e.g., from an encoder and / or received by a decoder). A computer-readable medium may include instructions for causing one or more processors to perform methods described herein. A computer program product may include instructions which, when the program is executed by one or more processors, may cause the one or more processors to carry out the methods described herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0024] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0025] FIG. 1 C is a system diagram illustrating an example radio access network (RAN) and an example core network (ON) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0026] FIG. 1 D is a system diagram illustrating a further example RAN and a further example ON that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0027] FIG. 2 illustrates an example video encoder.

[0028] FIG. 3 illustrates an example video decoder.

[0029] FIG. 4 illustrates an example of a system in which various aspects and examples may be implemented.

[0030] FIG. 5A depicts an example architecture for split inference between the WTRU and network, with a media data source in the WTRU.

[0031] FIG. 5B depicts an example architecture for split inference between the WTRU and network, with a media data source in the network.

[0032] FIG. 5C depicts an example of messages exchanged between the WTRU and the network device to manage a dynamic split point.

[0033] FIG. 6 is a block diagram depicting an example of processing unit information exchanges.

[0034] FIG. 7 depicts an example message exchange between a first device and a second device, with each of the first device or the second device being a WTRU or a network device.

[0035] FIG. 8 depicts an example method of parsing and / or handling a processing unit type and / or processing a unit ID.

[0036] FIG. 9 is a block diagram depicting an example of metadata and / or processing unit information.DETAILED DESCRIPTION

[0037] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings.

[0038] FIG. 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), zero-tail unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0039] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a RAN 104 / 113, a ON 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and / or a “STA”, may be configured to transmit and / or receive wireless signals and may include a user equipment (WTRU), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), avehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a WTRU.

[0040] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a NR NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0041] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0042] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0043] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA,SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 115 / 116 / 117 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink (DL) Packet Access (HSDPA) and / or High-Speed UL Packet Access (HSUPA).

[0044] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0045] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access , which may establish the air interface 116 using New Radio (NR).

[0046] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., a eNB and a gNB).

[0047] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0048] The base station 114b in FIG. 1 A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize acellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0049] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing a NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0050] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or the other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 113 or a different RAT.

[0051] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0052] FIG. 1 B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any subcombination of the foregoing elements while remaining consistent with an embodiment.

[0053] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1 B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0054] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0055] Although the transmit / receive element 122 is depicted in FIG. 1 B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0056] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11 , for example.

[0057] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The nonremovable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0058] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0059] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0060] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and / or Augmented Reality (VR / AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, anaccelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0061] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the UL (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e.g., for transmission) or the downlink (e.g., for reception)).

[0062] FIG. 1 C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0063] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a.

[0064] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, and the like. As shown in FIG. 1 C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0065] The CN 106 shown in FIG. 1 C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0066] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0067] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0068] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0069] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0070] Although the WTRU is described in FIGS. 1 A-1 D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0071] In representative embodiments, the other network 112 may be a WLAN.

[0072] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic in to and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11 z tunneled DLS (TDLS). A WLAN usingan Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an “ad-hoc” mode of communication.

[0073] When using the 802.1 1ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0074] High Throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0075] Very High Throughput (VHT) STAs may support 20MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above described operation for the 80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0076] Sub 1 GHz modes of operation are supported by 802.11af and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.11af and 802.11 ah relative to those used in 802.11 n, and 802.11 ac. 802.11 af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11 ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11 ah may support Meter Type Control / Machine-Type Communications, such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., onlysupport for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0077] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11 n, 802.11 ac, 802.11 af, and 802.11 ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11 ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0078] In the United States, the available frequency bands, which may be used by 802.11 ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11 ah is 6 MHz to 26 MHz depending on the country code.

[0079] FIG. 1 D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0080] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point(CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0081] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0082] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non-standalone configuration, eNode- Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0083] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E- UTRA, routing of user plane data towards User Plane Function (UPF) 184a, 184b, routing of control plane information towards Access and Mobility Management Function (AMF) 182a, 182b and the like. As shown in FIG. 1 D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0084] The CN 115 shown in FIG. 1 D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0085] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b in order to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultrareliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for machine type communication (MTC) access, and / or the like. The AMF 182a, 182b may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0086] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating WTRU IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0087] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet- switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0088] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0089] In view of Figures 1 A-1 D, and the corresponding description of Figures 1 A-1 D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station 114a-b, eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other device(s) described herein, may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0090] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0091] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a nondeployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0092] This application describes a variety of aspects, including tools, features, examples, models, approaches, etc. Many of these aspects are described with specificity and, at least to show the individual characteristics, are often described in a manner that may sound limiting. However, this is for purposes of clarity in description, and does not limit the application or scope of those aspects. Indeed, all of the different aspects may be combined and interchanged to provide further aspects. Moreover, the aspects may be combined and interchanged with aspects described in earlier filings as well.

[0093] The aspects described and contemplated in this application may be implemented in many different forms. FIGS. 5-9 described herein may provide some examples, but other examples are contemplated. The discussion of FIGS. 5-9 does not limit the breadth of the implementations. At leastone of the aspects generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting a bitstream generated or encoded. These and other aspects may be implemented as a method, an apparatus, a computer readable storage medium having stored thereon instructions for encoding or decoding video data according to any of the methods described, and / or a computer readable storage medium having stored thereon a bitstream generated according to any of the methods described.

[0094] In the present application, the terms “reconstructed” and “decoded” may be used interchangeably, the terms “pixel” and “sample” may be used interchangeably, the terms “image,” “picture” and “frame” may be used interchangeably.

[0095] Various methods are described herein, and each of the methods comprises one or more steps or actions for achieving the described method. Unless a specific order of steps or actions is required for proper operation of the method, the order and / or use of specific steps and / or actions may be modified or combined. Additionally, terms such as “first”, “second”, etc. may be used in various examples to modify an element, component, step, operation, etc., such as, for example, a “first decoding” and a “second decoding”. Use of such terms does not imply an ordering to the modified operations unless specifically required. So, in this example, the first decoding need not be performed before the second decoding, and may occur, for example, before, during, or in an overlapping time period with the second decoding.

[0096] Various methods and other aspects described in this application may be used to modify modules, for example, decoding modules, of a video encoder 200 and decoder 300 as shown in FIG. 2 and FIG. 3. Moreover, the subject matter disclosed herein may be applied, for example, to any type, format or version of video coding, whether described in a standard or a recommendation, whether preexisting or future-developed, and extensions of any such standards and recommendations. Unless indicated otherwise, or technically precluded, the aspects described in this application may be used individually or in combination.

[0097] Various numeric values are used in examples described the present application. These and other specific values are for purposes of describing examples and the aspects described are not limited to these specific values.

[0098] FIG. 2 is a diagram showing an example video encoder. Variations of example encoder 200 are contemplated, but the encoder 200 is described below for purposes of clarity without describing all expected variations.

[0099] Before being encoded, the video sequence may go through pre-encoding processing (201 ), for example, applying a color transform to the input color picture (e.g., conversion from RGB 4:4:4 to YCbCr 4:2:0), or performing a remapping of the input picture components in order to get a signal distributionmore resilient to compression (for instance using a histogram equalization of one of the color components). Metadata may be associated with the pre-processing, and attached to the bitstream.

[0100] In the encoder 200, a picture is encoded by the encoder elements as described below. The picture to be encoded is partitioned (202) and processed in units of, for example, coding units (CUs). Each unit is encoded using, for example, either an intra or inter mode. When a unit is encoded in an intra mode, it performs intra prediction (260). In an inter mode, motion estimation (275) and compensation (270) are performed. The encoder decides (205) which one of the intra mode or inter mode to use for encoding the unit, and indicates the intra / inter decision by, for example, a prediction mode flag. Prediction residuals are calculated, for example, by subtracting (210) the predicted block from the original image block.

[0101] The prediction residuals are then transformed (225) and quantized (230). The quantized transform coefficients, as well as motion vectors and other syntax elements, are entropy coded (245) to output a bitstream. The encoder can skip the transform and apply quantization directly to the nontransformed residual signal. The encoder can bypass both transform and quantization, i.e., the residual is coded directly without the application of the transform or quantization processes.

[0102] The encoder decodes an encoded block to provide a reference for further predictions. The quantized transform coefficients are de-quantized (240) and inverse transformed (250) to decode prediction residuals. Combining (255) the decoded prediction residuals and the predicted block, an image block is reconstructed. In-loop filters (265) are applied to the reconstructed picture to perform, for example, deblocking / SAO (Sample Adaptive Offset) filtering to reduce encoding artifacts. The filtered image is stored at a reference picture buffer (280).

[0103] FIG. 3 is a diagram showing an example of a video decoder. In example decoder 300, a bitstream is decoded by the decoder elements as described below. Video decoder 300 generally performs a decoding pass reciprocal to the encoding pass as described in FIG. 2. The encoder 200 also generally performs video decoding as part of encoding video data.

[0104] In particular, the input of the decoder includes a video bitstream, which may be generated by video encoder 200. The bitstream is first entropy decoded (330) to obtain transform coefficients, motion vectors, and other coded information. The picture partition information indicates how the picture is partitioned. The decoder may therefore divide (335) the picture according to the decoded picture partitioning information. The transform coefficients are de-quantized (340) and inverse transformed (350) to decode the prediction residuals. Combining (355) the decoded prediction residuals and the predicted block, an image block is reconstructed. The predicted block may be obtained (370) from intra prediction(360) or motion-compensated prediction (i.e., inter prediction) (375). In-loop filters (365) are applied to the reconstructed image. The filtered image is stored at a reference picture buffer (380).

[0105] The decoded picture can further go through post-decoding processing (385), for example, an inverse color transform (e.g. conversion from YCbCr 4:2:0 to RGB 4:4:4) or an inverse remapping performing the inverse of the remapping process performed in the pre-encoding processing (201). The post-decoding processing can use metadata derived in the pre-encoding processing and signaled in the bitstream. In an example, the decoded images (e.g., after application of the in-loop filters (365) and / or after post-decoding processing (385), if post-decoding processing is used) may be sent to a display device for rendering to a user.

[0106] FIG. 4 is a diagram showing an example of a system in which various aspects and examples described herein may be implemented. System 400 may be embodied as a device including the various components described below and is configured to perform one or more of the aspects described in this document. Examples of such devices, include, but are not limited to, various electronic devices such as personal computers, laptop computers, smartphones, tablet computers, digital multimedia set top boxes, digital television receivers, personal video recording systems, connected home appliances, and servers. Elements of system 400, singly or in combination, may be embodied in a single integrated circuit (IC), multiple ICs, and / or discrete components. For example, in at least one example, the processing and encoder / decoder elements of system 400 are distributed across multiple ICs and / or discrete components. In various examples, the system 400 is communicatively coupled to one or more other systems, or other electronic devices, via, for example, a communications bus or through dedicated input and / or output ports. In various examples, the system 400 is configured to implement one or more of the aspects described in this document.

[0107] The system 400 includes at least one processor 410 configured to execute instructions loaded therein for implementing, for example, the various aspects described in this document. Processor 410 can include embedded memory, input output interface, and various other circuitries as known in the art. The system 400 includes at least one memory 420 (e.g., a volatile memory device, and / or a non-volatile memory device). System 400 includes a storage device 440, which can include non-volatile memory and / or volatile memory, including, but not limited to, Electrically Erasable Programmable Read-Only Memory (EEPROM), Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash, magnetic disk drive, and / or optical disk drive. The storage device 440 can include an internal storage device, an attached storage device (including detachable and non-detachable storage devices), and / or a network accessible storage device, as non-limiting examples.

[0108] System 400 includes an encoder / decoder module 430 configured, for example, to process data to provide an encoded video or decoded video, and the encoder / decoder module 430 can include its own processor and memory. The encoder / decoder module 430 represents module(s) that may be included in a device to perform the encoding and / or decoding functions. As is known, a device can include one or both of the encoding and decoding modules. Additionally, encoder / decoder module 430 may be implemented as a separate element of system 400 or may be incorporated within processor 410 as a combination of hardware and software as known to those skilled in the art.

[0109] Program code to be loaded onto processor 410 or encoder / decoder 430 to perform the various aspects described in this document may be stored in storage device 440 and subsequently loaded onto memory 420 for execution by processor 410. In accordance with various examples, one or more of processor 410, memory 420, storage device 440, and encoder / decoder module 430 can store one or more of various items during the performance of the processes described in this document. Such stored items can include, but are not limited to, the input video, the decoded video or portions of the decoded video, the bitstream, matrices, variables, and intermediate or final results from the processing of equations, formulas, operations, and operational logic.

[0110] In some examples, memory inside of the processor 410 and / or the encoder / decoder module 430 is used to store instructions and to provide working memory for processing that is needed during encoding or decoding. In other examples, however, a memory external to the processing device (for example, the processing device may be either the processor 410 or the encoder / decoder module 430) is used for one or more of these functions. The external memory may be the memory 420 and / or the storage device 440, for example, a dynamic volatile memory and / or a non-volatile flash memory. In several examples, an external non-volatile flash memory is used to store the operating system of, for example, a television. In at least one example, a fast external dynamic volatile memory such as a RAM is used as working memory for video encoding and decoding operations.

[0111] The input to the elements of system 400 may be provided through various input devices as indicated in block 445. Such input devices include, but are not limited to, (i) a radio frequency (RF) portion that receives an RF signal transmitted, for example, over the air by a broadcaster, (ii) a Component (COMP) input terminal (or a set of COMP input terminals), (iii) a Universal Serial Bus (USB) input terminal, and / or (iv) a High Definition Multimedia Interface (HDMI) input terminal. Other examples, not shown in FIG. 4, include composite video.

[0112] In various examples, the input devices of block 445 have associated respective input processing elements as known in the art. For example, the RF portion may be associated with elements suitable for (i) selecting a desired frequency (also referred to as selecting a signal, or band-limiting asignal to a band of frequencies), (ii) downconverting the selected signal, (iii) band-limiting again to a narrower band of frequencies to select (for example) a signal frequency band which may be referred to as a channel in certain examples, (iv) demodulating the downconverted and band-limited signal, (v) performing error correction, and / or (vi) demultiplexing to select the desired stream of data packets. The RF portion of various examples includes one or more elements to perform these functions, for example, frequency selectors, signal selectors, band-limiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF portion can include a tuner that performs various of these functions, including, for example, downconverting the received signal to a lower frequency (for example, an intermediate frequency or a near-baseband frequency) or to baseband. In one set-top box example, the RF portion and its associated input processing element receives an RF signal transmitted over a wired (for example, cable) medium, and performs frequency selection by filtering, downconverting, and filtering again to a desired frequency band. Various examples rearrange the order of the above-described (and other) elements, remove some of these elements, and / or add other elements performing similar or different functions. Adding elements can include inserting elements in between existing elements, such as, for example, inserting amplifiers and an analog-to-digital converter. In various examples, the RF portion includes an antenna.

[0113] The USB and / or HDMI terminals can include respective interface processors for connecting system 400 to other electronic devices across USB and / or HDMI connections. It is to be understood that various aspects of input processing, for example, Reed-Solomon error correction, may be implemented, for example, within a separate input processing IC or within processor 410 as necessary. Similarly, aspects of USB or HDMI interface processing may be implemented within separate interface ICs or within processor 410 as necessary. The demodulated, error corrected, and demultiplexed stream is provided to various processing elements, including, for example, processor 410, and encoder / decoder 430 operating in combination with the memory and storage elements to process the datastream as necessary for presentation on an output device.

[0114] Various elements of system 400 may be provided within an integrated housing, Within the integrated housing, the various elements may be interconnected and transmit data therebetween using suitable connection arrangement 425, for example, an internal bus as known in the art, including the Inter-IC (I2C) bus, wiring, and printed circuit boards.

[0115] The system 400 includes communication interface 450 that enables communication with other devices via communication channel 460. The communication interface 450 can include, but is not limited to, a transceiver configured to transmit and to receive data over communication channel 460. Thecommunication interface 450 can include, but is not limited to, a modem or network card and the communication channel 460 may be implemented, for example, within a wired and / or a wireless medium.

[0116] Data is streamed, or otherwise provided, to the system 400, in various examples, using a wireless network such as a Wi-Fi network, for example IEEE 802.11 (IEEE refers to the Institute of Electrical and Electronics Engineers). The Wi-Fi signal of these examples is received over the communications channel 460 and the communications interface 450 which are adapted for Wi-Fi communications. The communications channel 460 of these examples is typically connected to an access point or router that provides access to external networks including the Internet for allowing streaming applications and other over-the-top communications. Other examples provide streamed data to the system 400 using a set-top box that delivers the data over the HDMI connection of the input block 445. Still other examples provide streamed data to the system 400 using the RF connection of the input block 445. As indicated above, various examples provide data in a non-streaming manner. Additionally, various examples use wireless networks other than Wi-Fi, for example a cellular network or a Bluetooth® network.

[0117] The system 400 can provide an output signal to various output devices, including a display 475, speakers 485, and other peripheral devices 495. The display 475 of various examples includes one or more of, for example, a touchscreen display, an organic light-emitting diode (OLED) display, a curved display, and / or a foldable display. The display 475 may be for a television, a tablet, a laptop, a cell phone (mobile phone), or other device. The display 475 can also be integrated with other components (for example, as in a smart phone), or separate (for example, an external monitor for a laptop). The other peripheral devices 495 include, in various examples, one or more of a stand-alone digital video disc (or digital versatile disc) (DVD, for both terms), a disk player, a stereo system, and / or a lighting system. Various examples use one or more peripheral devices 495 that provide a function based on the output of the system 400. For example, a disk player performs the function of playing the output of the system 400.

[0118] In various examples, control signals are communicated between the system 400 and the display 475, speakers 485, or other peripheral devices 495 using signaling such as AV. Link, Consumer Electronics Control (CEC), or other communications protocols that enable device-to-device control with or without user intervention. The output devices may be communicatively coupled to system 400 via dedicated connections through respective interfaces 470, 480, and 490. Alternatively, the output devices may be connected to system 400 using the communications channel 460 via the communications interface 450. The display 475 and speakers 485 may be integrated in a single unit with the other components of system 400 in an electronic device such as, for example, a television. In variousexamples, the display interface 470 includes a display driver, such as, for example, a timing controller (T Con) chip.

[0119] The display 475 and speakers 485 can alternatively be separate from one or more of the other components, for example, if the RF portion of input 445 is part of a separate set-top box. In various examples in which the display 475 and speakers 485 are external components, the output signal may be provided via dedicated output connections, including, for example, HDMI ports, USB ports, or COMP outputs.

[0120] The examples may be carried out by computer software implemented by the processor 410 or by hardware, or by a combination of hardware and software. As a non-limiting example, the examples may be implemented by one or more integrated circuits. The memory 420 may be of any type appropriate to the technical environment and may be implemented using any appropriate data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory, as non-limiting examples. The processor 410 may be of any type appropriate to the technical environment, and can encompass one or more of microprocessors, general purpose computers, special purpose computers, and processors based on a multi-core architecture, as non-limiting examples.

[0121] Various implementations involve decoding. “Decoding”, as used in this application, can encompass all or part of the processes performed, for example, on a received encoded sequence in order to produce a final output suitable for display. In various examples, such processes include one or more of the processes typically performed by a decoder, for example, entropy decoding, inverse quantization, inverse transformation, and differential decoding.

[0122] As further examples, in one example “decoding” refers only to entropy decoding, in another example “decoding” refers only to differential decoding, and in another example “decoding” refers to a combination of entropy decoding and differential decoding. Whether the phrase “decoding process” is intended to refer specifically to a subset of operations or generally to the broader decoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0123] Various implementations involve encoding. In an analogous way to the above discussion about “decoding”, “encoding” as used in this application can encompass all or part of the processes performed, for example, on an input video sequence in order to produce an encoded bitstream. In various examples, such processes include one or more of the processes typically performed by an encoder, for example, partitioning, differential encoding, transformation, quantization, and entropy encoding.

[0124] As further examples, in one example “encoding” refers only to entropy encoding, in another example “encoding” refers only to differential encoding, and in another example “encoding” refers to a combination of differential encoding and entropy encoding. Whether the phrase “encoding process” is intended to refer specifically to a subset of operations or generally to the broader encoding process will be clear based on the context of the specific descriptions and is believed to be well understood by those skilled in the art.

[0125] Note that syntax elements as used herein, for example, coding syntax on host sender, message type, split points etc., are descriptive terms. As such, they do not preclude the use of other syntax element names.

[0126] When a figure is presented as a flow diagram, it should be understood that it also provides a block diagram of a corresponding apparatus. Similarly, when a figure is presented as a block diagram, it should be understood that it also provides a flow diagram of a corresponding method / process.

[0127] The implementations and aspects described herein may be implemented in, for example, a method or a process, an apparatus, a software program, a data stream, or a signal. Even if only discussed in the context of a single form of implementation (for example, discussed only as a method), the implementation of features discussed can also be implemented in other forms (for example, an apparatus or program). An apparatus may be implemented in, for example, appropriate hardware, software, and firmware. The methods may be implemented in, for example, a processor, which refers to processing devices in general, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. Processors also include communication devices, such as, for example, computers, cell phones, portable / personal digital assistants ("PDAs"), and other devices that facilitate communication of information between end-users.

[0128] Reference to “one example” or “an example” or “one implementation” or “an implementation”, as well as other variations thereof, means that a particular feature, structure, characteristic, and so forth described in connection with the example is included in at least one example. Thus, the appearances of the phrase “in one example” or “in an example” or “in one implementation” or “in an implementation”, as well any other variations, appearing in various places throughout this application are not necessarily all referring to the same example.

[0129] Additionally, this application may refer to “determining” various pieces of information. Determining the information can include one or more of, for example, estimating the information, calculating the information, predicting the information, or retrieving the information from memory. Obtaining may include receiving, retrieving, constructing, generating, and / or determining.

[0130] Further, this application may refer to “accessing” various pieces of information. Accessing the information can include one or more of, for example, receiving the information, retrieving the information (for example, from memory), storing the information, moving the information, copying the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0131] Additionally, this application may refer to “receiving” various pieces of information. Receiving is, as with “accessing”, intended to be a broad term. Receiving the information can include one or more of, for example, accessing the information, or retrieving the information (for example, from memory). Further, “receiving” is typically involved, in one way or another, during operations such as, for example, storing the information, processing the information, transmitting the information, moving the information, copying the information, erasing the information, calculating the information, determining the information, predicting the information, or estimating the information.

[0132] It is to be appreciated that the use of any of the following 7”, “and / or”, and “at least one of’, for example, in the cases of “A / B”, “A and / or B” and “at least one of A and B”, is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of both options (A and B). As a further example, in the cases of “A, B, and / or C” and “at least one of A, B, and C”, such phrasing is intended to encompass the selection of the first listed option (A) only, or the selection of the second listed option (B) only, or the selection of the third listed option (C) only, or the selection of the first and the second listed options (A and B) only, or the selection of the first and third listed options (A and C) only, or the selection of the second and third listed options (B and C) only, or the selection of all three options (A and B and C). This may be extended, as is clear to one of ordinary skill in this and related arts, for as many items as are listed.

[0133] Also, as used herein, the word “signal” refers to, among other things, indicating something to a corresponding decoder. In this way, in an example the same parameter is used at both the encoder side and the decoder side. Thus, for example, an encoder can transmit (explicit signaling) a particular parameter to the decoder so that the decoder can use the same particular parameter. Conversely, if the decoder already has the particular parameter as well as others, then signaling may be used without transmitting (implicit signaling) to simply allow the decoder to know and select the particular parameter. By avoiding transmission of any actual functions, a bit savings is realized in various examples. It is to be appreciated that signaling may be accomplished in a variety of ways. For example, one or more syntax elements, flags, and so forth are used to signal information to a corresponding decoder in various examples. While the preceding relates to the verb form of the word “signal”, the word “signal” can also be used herein as a noun.

[0134] As will be evident to one of ordinary skill in the art, implementations may produce a variety of signals formatted to carry information that may be, for example, stored or transmitted. The information can include, for example, instructions for performing a method, or data produced by one of the described implementations. For example, a signal may be formatted to carry the bitstream of a described example. Such a signal may be formatted, for example, as an electromagnetic wave (for example, using a radio frequency portion of spectrum) or as a baseband signal. The formatting may include, for example, encoding a data stream and modulating a carrier with the encoded data stream. The information that the signal carries may be, for example, analog or digital information. The signal may be transmitted over a variety of different wired or wireless links, as is known. The signal may be stored on, or accessed or received from, a processor-readable medium.

[0135] Many examples are described herein. Features of examples may be provided alone or in any combination, across various claim categories and types. Further, examples may include one or more of the features, devices, or aspects described herein, alone or in any combination, across various claim categories and types. For example, features described herein may be implemented in a bitstream or signal that includes information generated as described herein. The information may allow a decoder to decode a bitstream, the encoder, bitstream, and / or decoder according to any of the embodiments described. For example, features described herein may be implemented by creating and / or transmitting and / or receiving and / or decoding a bitstream or signal. For example, features described herein may be implemented a method, process, apparatus, medium storing instructions, medium storing data, or signal. For example, features described herein may be implemented by a TV, set-top box, cell phone, tablet, or other electronic device that performs decoding. The TV, set-top box, cell phone, tablet, or other electronic device may display (e.g. using a monitor, screen, or other type of display) a resulting image (e.g., an image from residual reconstruction of the video bitstream). The TV, set-top box, cell phone, tablet, or other electronic device may receive a signal including an encoded image and perform decoding.

[0136] A WTRU as used herein may refer to user equipment (UE).

[0137] FIGS. 5A and 5B depict example architectures (e.g., 3GPP SA4 AI4media) for split inferences of a model (e.g., an artificial intelligence and / or machine learning (AI / ML model) composed of n layers (1..n) between the network and a WTRU). A first inference may process a first portion (e.g., a first part) of the model (e.g., layers 1..k), and / or a second inference may process a second portion (e.g., a second part) of the model (e.g., layers k+1..n).

[0138] The example architecture as depicted in FIGS. 5A and 5B may include delivery and access functions of intermediate data between the WTRU and the network (e.g., for the two different scenariosas illustrated in FIGS. 5A-5B). FIG. 5A depicts an example split inference between the WTRU and the network, with a media data source in the WTRU. FIG. 5B depicts an example split inference between the WTRU and the network, with a media data source in the network.

[0139] In an example, as illustrated in FIG. 5A, a media data source may originate from a WTRU associated with a network. If / when a media data source originates from the WTRU, a first portion of the inference may be performed by the WTRU and a second portion of the inference may be performed by the network. The resulting output data may be sent back to the WTRU (e.g., from the network).

[0140] In an example, as illustrated in FIG. 5B, the media data source may originate from a network. The media data source may be received by the WTRU from the network. If / when the media data source is received from the network or from the network via the WTRU, a first portion of the AI / ML model may be performed by the network (e.g., on the network side) and a second portion may be performed by the WTRU (e.g., on the WTRU).

[0141] The WTRU and / or the network may select a type of processing unit the model (e.g., AI / ML model) will run on (e.g., if / when selecting the model to run). The type of processing unit may be at least one of a CPU, a TPU, a GPU, an FPGA, and / or the like.

[0142] A first portion of the AI / ML model may be compiled and / or loaded into a machine learning framework. The machine learning framework may be configured and / or able to infer the input media data. The resulting intermediate data may be transmitted towards a second portion of the AI / ML model (e.g., to finalize the inference).

[0143] A message may be defined to wrap data exchange within the AI / ML partitioned pipeline. The message may include (e.g., be made of) information followed by intermediate data. The information may assist a remote node (e.g., the network) in handling the intermediate data (e.g., by indicating one or more of: a model to use, a split point to set, a number of intermediate data to copy, or how the intermediate data may have been encoded).

[0144] The information and intermediate data may be transported via a data structure. An example data structure (e.g., for transporting the information and / or intermediate data) may include at least one of: a model identifier (e.g., ModeLRefID), an indication if a split point is changed from a previous message (e.g., ChangeOfSplitPoint), a split point used by the WTRU (e.g., SplitPointID), a next split point used by the WTRU (e.g., NextSplitPointID), a length of intermediate data (e.g., IntermediateDataLength), an array dimension of intermediate data (e.g., IntermediateDataDim), an indication if data is compressed and / or a compression algorithm used (e.g., EncodingMethod), a sequential identifier of input data (e.g., SequenceNumber), a timestamp of the intermediate data (e.g., TimeStamp), or intermediate data (e.g.,IntermediateData). An example data structure (e.g., for transporting the information and intermediate data) may be represented as follows:Current IntermediateDataWrapper:Struct IntermediateDataWrapper {I nt ModeLRefID; # Model Identifier bit ChangeOfSplitPoint; # 1 if the splitpoint is changed from the previous messageInt SplitPointID; # Split point used by the WTRUInt NextSplitpointID; # Next split point used by the WTRU (e.g., optional)Int IntermediateDataLength; # Length of Intermediate DataDim IntermediateDataDim; # Array dimension of intermediate data byte EncodingMethod; # Indicate if data are compressed and by which algorithm int SequenceNumber; # Sequential identifier of input data double TimeStamp; # Timestamp of the intermediate dataByte lntermediateData[] # Intermediate Data};

[0145] In an in-band intermediate data information transport example, the transport information may be transported in-band (e.g., together) with the intermediate data (e.g., on the same channel).

[0146] In examples, information may be transported out-of-band (e.g., separate) from the intermediate data (e.g., on another channel).

[0147] FIG. 5C depicts an example of dynamic split point management. Messages may be exchanged between a WTRU and a network device (e.g., an operator, an AI / ML application provider, and / or the like), to manage a dynamic split point. A local decision module (e.g., in the WTRU) may be used to set the best split point based on the requirements (e.g., bandwidth, latency, energy, and / or the like), local information, and / or a split point range.

[0148] A local decision module included as part of (e.g., located on) a first device (e.g., a WTRU, a network device, and / or the like) or a decision module (e.g., a remote decision module) included as part of a second device (e.g., a WTRU, a network device, and / or the like) may determine where to split (e.g., determine the optimal split point) based on requirements (e.g., latency or prediction score) and / or the current conditions (e.g., available bandwidth, energy level, available processing unit, and / or the like.).

[0149] The conditions may change. To maintain the requirements as initially defined (e.g., if conditions change), the local decision module and / or the decision module (e.g., a remote decision module) may determine to change processing units (e.g., to a processing unit of the other device, for example to change to a processing unit on the second device from a processing unit on the first device). An indication including information instructing to change a processing unit may be transmitted (e.g., from the first device to the second device).

[0150] A first device may determine (e.g., compute) the processing power required to process the intermediate data to be sent to a second device. The first device may transmit information (e.g., a processing unit recommendation) to the second device based on the determined processing power. The transmitted information may include (e.g., comprise) processing unit information such as the type (e.g., a processing unit type, such as TPU, GPU, CPU, FPGA, and / or the like) and / or one or more processing unit identifiers.

[0151] The first device may request and / or receive (e.g., from the second device) a list of processing units (e.g., at the second device) and their respective capabilities. The first device may determine and / or select one or more processing units (e.g., from the list of processing units) based on (e.g., that meet) the requirements (e.g., bandwidth, latency, energy, and / or the like). The first device may transmit the identifier(s) of the selected processing unit(s) (e.g., to the second device).

[0152] A second device may provide the real-time status of one or more processing units (e.g., a processing unit in the list of processing units) to the first device. For example, the second device may send a load of the respective processing unit(s) (e.g., to the first device).

[0153] Processing unit information may be transmitted from the first device to the second device.

[0154] A first device may provide processing unit information (e.g., as metadata) to transmit to a second device. The second device (e.g., receiving the processing unit information) may process (e.g., compute) the processing unit information to determine and / or select a processing unit to process data (e.g., an AI / ML model or AI / ML model subset).

[0155] The processing unit information may include one or more of: processing unit capabilities, a processing unit type, a processing unit identifier, a processing capabilities identifier, parameter numbers (e.g., a number of parameters), parameter precision (e.g., precision of parameter(s), multiply-accumulate (MAC) operations (e.g., Kilo), temporary memory (e.g., MB), or a processing unit real-time status.

[0156] The processing unit information may include processing unit capabilities. Processing unit capabilities may describe the capabilities required for a processing unit to process intermediate datatransmitted from a first device to the second device. Processing unit capabilities may include a processing unit speed, random access memory (RAM), cache memory, and / or energy consumption.

[0157] The processing unit speed (e.g., flops per clock cycle) may define the number of operations per clock cycle required by a processing unit to compute the intermediate data. RAM is an amount of memory that may be used to handle the intermediate data (e.g., the minimal memory required to handle the intermediate data). Cache memory may be an amount of memory used to run the inference on the intermediate data (e.g., the minimal cache (e.g., L1 / L2) memory required to run the inference on the intermediate data). Energy consumption may be an estimated energy consumption for processing the intermediate data.

[0158] The processing unit information may include a processing unit type. A processing unit type may be one or more of: CPU, GPU, TPU, FPGA Vision Processing Unit (VPU), or Quantum Processing Unit (QPU).

[0159] The processing unit information may include a processing unit identifier. A process unit identifier may identify the processing unit associated with the processing unit capabilities. A first device may request and / or may receive a list of processing unit(s) with their respective capabilities (e.g., from a second device). The first device may determine processing unit capabilities (e.g., for each processing unit), select a processing unit (e.g., from the list of processing unit(s)), and / or send the processing unit identifier (e.g., associated with the selected processing unit). A processing unit identifier may be sent with intermediate data to the second device. In examples, “GPU IDO” ,“GPU ID1”, “GPU ID3”, “GPU ID4” , “CPU IDO”, or a process unit list number [1 ,2, 3, 4] may be sent and / or received.

[0160] The processing unit information may include a processing unit real-time status. A processing unit real-time status may describe the live status of the respective processing unit (e.g., the processing unit load and / or the occupied memory).

[0161] The processing unit information may include processing unit status (e.g., received by the first device from the second device).

[0162] The processing unit information may include a processing unit type. The processing unit information may define the processing unit type (e.g., CPU, GPU, TPU, FPGA Vision Processing Unit (VPU) or Quantum Processing Unit (QPU).

[0163] The processing unit information may include a processing capabilities identifier. The processing capabilities identifier may be used to indicate the allocated and / or recommended processing capabilities (e.g., of the processing unit). Processing capabilities may be negotiated at the configuration stage.Processing capabilities and / or settings may be stored (e.g., at the configuration stage). Processing capabilities may be identified with a processing capabilities identifier.

[0164] The processing unit information may include a parameters number (e.g., a number of parameters). The number of parameters may indicate a (e.g., total) number of parameters in the neural network.

[0165] The processing unit information may include the parameters precision. Parameters precision may be indicated as bits (e.g., number of bits) for storing a (e.g., one) parameter. In examples, a first indicator (e.g., “I”) may be used for indicating an integer parameter. In examples, a second indicator (e.g., “F”) may be used to indicate a floating-point number. In examples, if the proposed method uses a 16-bit integer to represent a parameter, the 16-bit integer may be reported as 16 (I) or 161 or 16lnt.

[0166] The processing unit information may include multiply-accumulate (MAC) operations (e.g., Kilo). MAC operations may be a number of MAC operations (e.g., per pixel or in general) in the worst case for the inference stage. A MAC operation may add the product of two numbers to an accumulator. The processing unit information may include temporary memory (e.g., MB). Temporary memory may denote the memory used to store the output feature map for (e.g., all) intermediate layers (e.g., forward pass).

[0167] A second device may provide a processing unit real-time status (e.g., to the first device). A processing unit real-time status may include one or more of: a processing unit load, overall processing unit loads, a selected processing unit type, or a selected processing unit identifier.

[0168] A processing unit load may identify the load of the processing unit (e.g., in percentage from 0% to 100%). Overall processing unit loads may identify the load of the overall processing units (e.g., GPUs from 1 to 4). In examples, the load of the overall processing units may be represented in a percentage (e.g., from 0% to 100%). A selected processing unit type may define the current processing unit type being used for processing the model part (e.g., the AI / ML model part). A selected processing unit identifier may identify the current processing unit being used for processing the model part (e.g., the AI / ML model part). The selected processing unit identifier may belong to the list of candidate processing units shared between the devices (e.g., “GPU IDO”, “GPU ID1”, “GPU ID3”, “GPU ID4”, “CPU IDO” or a process unit list number [1 ,2, 3, 4]).

[0169] FIG. 6 is a block diagram depicting an example of a processing unit information exchange.

[0170] A processing unit message and / or metadata may include processing unit information. The processing unit message may be used by a local decision module (e.g., hosted by a first device) and an AI / ML model manager (e.g., hosted by a second device) to exchange information (e.g., about the first devices and / or second devices capabilities, such as processing capabilities). The exchanged informationmay be compiled by the local decision module of the first device. The exchanged information may be used by the local decision module to determine an appropriate processing unit (e.g., a processing unit most capable to handle intermediate data).

[0171] The metadata associated with the intermediate data may include indications for the AI / ML processing module (e.g., on the second device) to decode and process intermediate data.

[0172] Feature(s) associated with control data for providing processing unit information (e.g., before, during split inference) are provided herein.

[0173] A first device may send a message to a second device to receive and / or obtain (e.g., get) status information about the second device’s processing usage and / or requirements. An AI / ML model manager on the second device (e.g., as depicted in FIG. 6) may process (e.g., handle) the message. The AI / ML model manager may respond with information about the processing unit (e.g., CPU, GPU, TPU, FPGA, VPU, and / or the like) usage and / or availability on the second device. The first device may receive the information about the processing unit and / or availability on the device. The local decision module may process (e.g., handle) the response. The local decision module may compile the information included in the response. The local decision module may determine and / or select the best split point and / or the best processing unit(s) to use (e.g., on the first device and / or on the second device). In examples, the decision module (e.g., the remote decision module) may determine and / or select the best processing unit(s) and / or a set of split points to use (e.g., on the first device and / or on the second device). In examples, the second device may send an indication of a selected best processing unit and / or a set of split points to the first device.

[0174] Processing unit(s) (e.g., an identified processing unit) on the second device may be communicated to the first device in metadata or may be associated (e.g., directly associated) with the intermediate data (e.g., in the form of 2 bytes that may describe the type and the ID of the processing unit to be used).

[0175] The messages exchanged between first device and second device may include the following example structure:ProcessingUnit message:{ Host_sender: <Host_name>,MessageType: <Message_type> ModeLRefID: < Model_ReflD> SplitPoints: [{<SplitPointlD>,<ProcessingUnitType>,<ProcessingUnitlD>,<ArchitectureType>} ]Processingllnitlnfos: [ { ProcessingUnitType: < ProcessingUnitType >, ProcessingUnitID: < ProcessingUnitID >, ProcessingUnitLoad: < ProcessingUnitLoad>}, ...{ProcessingUnitID: < ProcessingUnitID >, ProcessingUnitLoad: < ProcessingUnitLoad > }}

[0176] Where, for example:<Host_name>: may be “network” or “WTRU.”<Message_Type>: may be “request” or “answer.”<Model_ReflD>: may be a unique model identifier.SplitPoints: may be a list of split points with the requested processing unit if the message type is “request”, or list of split points with updated configuration if the message type is “answer.” <SplitPointlD> may be the Unique identifier of a split point.<ProcessingUnitType> may be “CPU,” “GPU,” ‘TPU,” or “FPGA.”<ProcessingUnitlD> may be “GPU IDO” ,“GPU ID1”, “GPU ID3”, “GPU ID4” , “CPU IDO”, “TPU”, or “FPGA.”<ArchitectureType> may be the main type of split point architecture (e.g., CNN, FC, ...), that may influence the choice of the processing unit.<ProcessingUnitLoad> may be the load of the processing unit (e.g., in percentage from 0% to 100%).

[0177] FIG. 7 depicts an example message exchange between a first device and a second device (e.g., the second device including an AI / ML model manager operating thereon). In examples, messages may be exchanged by performing one or more of the following as described herein.

[0178] As illustrated in FIG. 7, at 1 , a first device using a processing unit request may request information from a second device. The processing unit request may include one or more of: a request for information associated with a split point, a request including information associated with a processing unit, a request including information associated with processing unit capabilities, or a request including information associated with a processing unit real-time status.

[0179] In examples, a request for information associated with a split point may include the first device communicating a list of split points on which information may be expected. An example request for information associated with a split point may include one or more of the following: Host_name (e.g., “WTRU”), Message_type (e.g., “request”), or SplitPoints (e.g., [ {SplitPointIDI }, ..., {SplitPointIDn} ]).

[0180] In examples, a request for information associated with a processing unit (e.g., associated with a split point) may include the first device communicating a list of split points with a proposed processing unit. The request for information associated with a processing unit may include one or more of the following: Host_name (e.g., “WTRU”), Message_type (e.g., “request”), or SplitPoints (e.g., [ {SplitPointIDI , ProcessingUnitTypel }, ..., {SplitPointIDn .ProcessingUnitTypen } ]).

[0181] In examples, a request including information associated with processing unit capabilities may include one or more of the following: Hostjiame (e.g., “WTRU”), Message_type (e.g., “request”), or processing unit capabilities (e.g., as described herein).

[0182] In examples, a request including information associated with a processing unit real-time status may include one or more of the following: Hostjiame (e.g., “WTRU”), Message_type (e.g., “request”), or processing unit real-time status (e.g., as described herein).

[0183] An AI / ML model manager (e.g., of the second device) may receive (e.g., collect) a request. The request may include an indication of requested information on split point(s) and / or processing unit(s). As illustrated in FIG. 7, at 2, the AI / ML model manager may determine, get, or compute a response comprising the requested information (e.g., an answer based on the requested information).

[0184] At 3, the AI / ML model manager may answer the request (e.g., provide the requested information). The answer may include one or more of: information on split points, information on processing units (e.g., associated with a split point), information on processing unit capabilities, or information on a processing unit real-time status.

[0185] In examples, a response including information associated with split points may include one or more of the following: Hostjiame (e.g., “network”), Message_type (e.g., “answer”), or SplitPoints (e.g., [ {SplitPointIDI , ProcessingUnitTypel , ArchitectureTypel }, ..., {SplitPointIDn, ProcessingUnitTypen, ArchitectureTypen } ]).

[0186] In examples, a response including information associated with processing units (e.g., associated with a split point) may include one or more of the following: Hostjiame (e.g., “network”), Message_type (e.g., “answer”), or SplitPoints (e.g., [ {SplitPointIDI, ProcessingUnitTypel , ProcessingUnitIDI , ArchitectureTypel }, ..., {SplitPointIDn, ProcessingUnitTypen, ProcessingUnitIDn, ArchitectureTypen } ]).

[0187] In examples, a response including information associated with processing unit capabilities may include one or more of the following: Hostjiame (e.g., “network”), Message_type (e.g., “answer”), or ProcessingUnitlnfos: [ { ProcessingUnitType: ProcessingUnitTypel , ProcessingUnitID: ProcessingUnitlDi>, ProcessingUnitSpeed:< ProcessingUnitSpeed>, ProcessingUnitRAM:<ProcessingUnitRAM >, ProcessingUnitCache:< ProcessingUnitCacheLI , ProcessingUnitCachel_2>, ProcessingUnitEnergyConsumption:< ProcessingUnitEnergyConsumption > }, ... } ]).

[0188] In examples, a response including information associated with the processing unit real-time status may include one or more of the following: Host_name (e.g., “network”), Message_type (e.g., “answer”), or Processing Unit Real Time Status (e.g., [ { ProcessingUnitType: ProcessingUnitTypel , ProcessingUnitID: ProcessingUnitIDI, ProcessingUnitLoad: ProcessingUnitLoadl }...]).

[0189] Feature(s) associated with metadata for providing processing unit information may be provided herein.

[0190] A first device may provide processing unit information as metadata (e.g., to transmit to a second device). A device receiving the information (e.g., the second device) may get or compute the processing information to select which processing unit will process data (e.g., an AI / ML model or an AI / ML model subset).

[0191] The processing information may include a processing unit type (e.g., ProcessingUnitType) and / or a processing unit ID (e.g., ProcessingUnitID).

[0192] A processing unit type (e.g., ProcessingUnitType) is a parameter that may be transmitted (e.g., as 8 bits / 1 byte). In examples, processing unit type values may include one or more of: 0x00 (e.g., CPU), 0x01 (e.g., GPU), 0x02 (e.g., TPU), or 0x03 (e.g., FPGA). It should be appreciated that the example processing unit type values described herein may not be an exhaustive list as one or more processing units may be provided (e.g., VPU, QPU, and / or the like).

[0193] A processing unit ID (e.g., ProcessingUnitID) is a parameter that may be transmitted (e.g., as 8 bits / 1 byte). In examples, a processing unit ID (e.g., ProcessingUnitID) may be used to send information in addition to the processing unit type (e.g., ProcessingUnitType) parameter. For example, 256 entities of the selected (e.g., chosen) processing unit type (e.g., ProcessingUnitType) may be possible. For example, ProcessingUnitType = 0x01 and ProcessingUnitID = 0x02 (e.g., the selected processing unit of a second device may compile and / or load the split model for “GPU:2”).

[0194] A processing unit type and / or a processing unit ID (e.g., ProcessingUnitType and / or ProcessingUnitID) may be parameters (e.g., they are not required). The second device may use the processing unit type and / or the processing unit ID if / when the processing unit type and / or the processing unit ID are present. The second device may not set the recommended processing unit type and / or processing unit ID if the recommended processing unit is not available (e.g., if / when the second device receives the processing unit type and / or processing unit ID from the first device).

[0195] An intermediate data wrapper including processing unit information may be used. The intermediate data wrapper may include one or more of the following: a model identifier, whether the split point is changed from a previous message, a next split point (e.g., used by the first device), a length of intermediate data, an array dimension of intermediate data, an indication if data is compressed, an indication if a compression algorithm used, a sequential identifier of input data, a timestamp of intermediate data, a processing unit type, a processing unit ID, or intermediate data. In examples, the intermediate data wrapper including processing unit information may be represented as follows:Struct IntermediateDataWrapper {I nt ModeLRefID; # Model Identifier bit ChangeOfSplitPoint; # 1 if the splitpoint is changed from the previous messageInt SplitPointID; # Split point used by the first deviceInt NextSplitpointID; # Next split point used by the first device (optional)Int IntermediateDataLength; # Length of Intermediate DataDim IntermediateDataDim; # Array dimension of intermediate data byte EncodingMethod; # Indicate if data are compressed and by which algorithm int SequenceNumber; # Sequential identifier of input data double TimeStamp; # Timestamp of the intermediate dataByte ProcessingUnitType; # 0: CPU, 1 : GPU, 2 : TPU, 3 : FPGAByte ProcessingUnitID; # 0: GPU IDO, 1 : GPU ID1 , 2 : GPU ID2, 3 : GPU ID3Byte lntermediateData[] # Intermediate Data};

[0196] Feature(s) associated with processing unit type metadata (e.g., for selecting the required processing unit) may be provided herein.

[0197] FIG. 8 depicts an example method of parsing and / or handling a processing unit type and a processing unit ID.

[0198] A first split model may be running on a processing unit (e.g., on a first device). The first split model may produce intermediate data resulting from an inference. The intermediate data may be transmitted through the network to a second device. The second device may complete (e.g., may end) the inference process. The second device may send an inference result (e.g., a score) to the first device.

[0199] The intermediate data may be sent with information that indicates (e.g., to the second device) how to handle the intermediate data. The processing unit type and / or a processing unit ID may be transmitted (e.g., in addition to the intermediate data and / or in addition to (e.g., any) existing information). The second device may parse the intermediate data and / or existing information.

[0200] As illustrated in FIG. 8, at 1 , the processing unit type value may be read.

[0201] At 2, the second device may determine if / whether the processing unit type is present. If the processing unit type is present, the example method proceeds to 3. If the processing unit type is not present, the example method proceeds to 5. At 5, the second device may remain on the current processing unit (e.g., the current processing unit type and / or the current processing unit ID).

[0202] At 3, the second device may read the processing unit ID.

[0203] At 4, the second device may determine whether the processing unit ID is present. If the processing unit ID is not present, the example method proceeds to 6 where the second device may use the default processing unit (e.g., I D=0) . If the processing unit ID is present, the example method proceeds to 7.

[0204] At 7, the second device may apply the (e.g., new) processing unit type and processing unit ID for the split model. The AI / ML model may be loaded on the (e.g., new) processing unit. The second device may send a message (e.g., a response to the first device). The message may indicate if / whether the (e.g., new) processing unit is in use. The message may be associated with (e.g., include) the (e.g., final) inference result or may be sent to the first device as a separate message.

[0205] FIG. 9 is a block diagram depicting an example of metadata and / or processing unit information (e.g., how the intermediate data and associated information may be transmitted from one device to another, such as from a first device to a second device).

[0206] In examples, an application may run on a first device. The application may rely on an AI / ML service. The AI / ML service may implement a distributed inference method. The distributed inference method may include an AI / ML model. The AI / ML model may include one or more layers (e.g., n layers (1..n)) between a second device and the first device. A first AI / ML inference engine may process a first part of the AI / ML model (e.g., partition M1 (e.g., layers 1..k)) and the second AI / ML inference engine may process the second part of the AI / ML model (e.g., partition M2 (e.g., layers k+1..n). M1 may run on the first device and M2 may run on the second device.

[0207] A decision module (e.g., located on the first device), may be designated as a local decision module. The decision model (e.g., the local decision model) may ingest (e.g., receive) input data, suchas private information, a split point range, and / or requirements (e.g., bandwidth, latency, energy, and / or the like).

[0208] The decision module (e.g., the local decision model) may send a message to the AI / ML model manager (e.g., on a second device). The message may request information on the hardware capabilities of the second device. The message may be sent on a regular basis (e.g., periodically) or at a (e.g., any) time.

[0209] The second device may send a response (e.g., an answer message) that includes the hardware capabilities.

[0210] The decision module (e.g., the local decision module on the first device) may compile the received information (e.g., private and / or local information, split point range, requirements, and / or second device hardware capabilities).

[0211] The decision module (e.g., local decision module) may deliver a split point to a split function module.

[0212] The split function module may manage the split of the AI / ML model. The split function module may update the model (e.g., that runs in the AI / ML inference engine).

[0213] In addition to the split point, the decision module (e.g., local decision module) may deliver processing unit information to the AI / ML processing module (e.g., of the first device). The processing unit information (e.g., dedicated to the second device) may be sent to the intermediate data delivery module.

[0214] The processing unit information may include information about the type of processing unit to be used (e.g., locally) on the first device and / or the type of processing unit to be used on the second device.

[0215] The decision module (e.g., local decision module) may run (e.g., continuously run) and evaluate inputs. The decision module may deliver a (e.g., new) split point and / or (e.g., new) processing unit information (e.g., if needed).

[0216] The AI / ML inference engine (e.g., of the first device) may process M1 from the input data and may deliver intermediate data (e.g., intended to the second device) for processing M2.

[0217] The intermediate data may be sent to the intermediate data delivery function which may prepare a transmission (e.g., to the second device). Preparing may include serialization, encoding, packaging, and / or encapsulating the data.

[0218] The intermediate data delivery function may associate the intermediate data with information for the second device to decode and process. The information for the second device to decode andprocess may be enriched with bytes (e.g., 2 bytes): a processing unit type (e.g., ProcessingUnitType) and / or a processing unit ID (e.g., ProcessingllnitlD).

[0219] A processing unit type (e.g., ProcessingUnitType) may define the type of processing unit that the second device may (e.g., should) use for processing the intermediate data.

[0220] A processing unit ID (e.g., ProcessingUnitID) may define the identifier of the processing unit (e.g., if / when there are multiple processing units (e.g., devices) of the same type, e.g., GPU:0, GPU:2, and / or the like).

[0221] As depicted in FIG. 9, the metadata may include the information data utilized by the second device to decode and / or process the intermediate data. The metadata may be transmitted in-band (e.g., together with the intermediate data) or out-of-band (e.g., on a channel that is separate from the channel on which the intermediate data is transmitted).

[0222] The intermediate data and the metadata may be read by the intermediate data access function (e.g., on the second device).

[0223] The split point information may be transmitted to the AI / ML split function module. The AI / ML split function module may manage the splitting of the AI / ML model (e.g., if needed).

[0224] The processing unit information (e.g., processing unit type and / or processing unit ID) may be transmitted to the AI / ML inference engine. The processing unit information may be used by the AI / ML framework to compile and / or load the split model. In examples, the AI / ML framework may be Tensorflow and / or Pytorch. If the designated processing unit is not available, the processing unit information may be transmitted back to the first device (e.g., with the inference result).

[0225] The intermediate data may be sent to the AI / ML inference engine (e.g., to finalize the inference process in processing the second part M2 of the model). The inference result may be transmitted to the result delivery module.

[0226] The result delivery module may prepare the inference result. Preparing may include packaging or encapsulating (e.g., the inference result).

[0227] The processing unit status may be transmitted (e.g., with the inference result). If the processing unit status is transmitted (e.g., with the inference result), the processing unit status may indicate (e.g., to the first device and its local decision module) if / whether the selection of the processing unit was relevant.

[0228] Although features and elements are described herein in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable mediumfor execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

CLAIMS1. A first device comprising: a processor configured to: determine processing unit information associated with a processing unit of a second device, wherein the processing unit information is associated with an intermediate data, and wherein the processing unit information comprises at least an indication of a processing unit type to be used by the second device for processing the intermediate data and a processing unit identifier associated with the processing unit of the second device; send, to the second device, the processing unit information and the intermediate data; and receive, from the second device, a processing unit status associated with the intermediate data.

2. The first device of claim 1 , wherein the processor is further configured to receive, from the second device, an indication of a hardware capability associated with the second device, wherein the processing unit information is determined based on the hardware capability associated with the second device.

3. The first device of any one of claims 1 -2, wherein the processor is further configured to send, to the second device, the processing unit information as part of metadata.

4. The first device of claim 3, wherein the metadata is to be used by the second device to decode or process the intermediate data.

5. The first device of any one of claims 3-4, wherein the metadata is to be used by the second device to select or identify the processing unit of the second device.

6. The first device of any one of claims 3-5, wherein the processor is further configured to send, to the second device, a processing unit recommendation as part of the metadata, and wherein the processing unit recommendation is based on a processing power.

7. The first device of any one of claims 3-6, wherein the metadata is sent via a different channel than the intermediate data.

8. The first device of any one of claims 1 -7, wherein the processor is further configured to receive, from the second device, an inference result, wherein the inference result is associated with a score.

9. The first device of any one of claims 1 -7, wherein the processing unit status associated with the intermediate data comprises an indication that the processing unit of the second device is not available.

10. The first device of claim 9, wherein the processor is further configured to receive, based on the indication that the processing unit of the second device is not available, a reply message and an inference result from the second device, wherein the reply message indicates the processing unit of the second device is not available and the processing unit information.

11. The first device of any one of claims 1-10, wherein the processing unit status comprises an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

12. A method performed by a first device comprising: determining processing unit information associated with a processing unit of a second device, wherein the processing unit information is associated with an intermediate data, and wherein the processing unit information comprises at least an indication of a processing unit type to be used by the second device for processing the intermediate data and a processing unit identifier associated with the processing unit of the second device; sending, to the second device, the processing unit information and the intermediate data; and receiving, from the second device, a processing unit status associated with the intermediate data.

13. The method of claim 12, wherein the method further comprises receiving, from the second device, an indication of a hardware capability associated with the second device, wherein the processing unit information is determined based on the hardware capability associated with the second device.

14. The method of any one of claims 12-13, wherein the method further comprises sending, to the second device, the processing unit information as part of metadata.

15. The method of claim 14, wherein the metadata is to be used by the second device to decode or process the intermediate data.

16. The method of any one of claims 14-15, wherein the metadata is to be used by the second device to select or identify the processing unit of the second device.

17. The method of any one of claims 14-16, wherein the method further comprises sending, to the second device, a processing unit recommendation as part of the metadata, and wherein the processing unit recommendation is based on a processing power.

18. The method of any one of claims 14-17, wherein the metadata is sent via a different channel than the intermediate data.

19. The method of any one of claims 12-18, wherein the method further comprises receiving, from the second device, an inference result, wherein the inference result is associated with a score.

20. The method of any one of claims 12-18, wherein the processing unit status associated with the intermediate data comprises an indication that the processing unit of the second device is not available.

21. The method of claims 20, wherein the method further comprises receiving, based on the indication that the processing unit of the second device is not available, a reply message and an inference result from the second device, wherein the reply message indicates the processing unit of the second device is not available and the processing unit information.

22. The method of any one of claims 12-21 , wherein the processing unit status comprises an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

23. A second device comprising a processor configured to: receive, from a first device, processing unit information and intermediate data, wherein the processing unit information is associated with a processing unit of the second device, wherein the processing unit information is associated with the intermediate data, and wherein theprocessing unit information comprises at least an indication of a processing unit type to be used by the second device for processing the intermediate data and a processing unit identifier associated with the processing unit of the second device; in response to receiving the processing unit information and the intermediate data, determine a processing unit status; and send, to the first device, the processing unit status.

24. The second device of claim 23, wherein the processor is further configured to send, to the first device, an indication of a hardware capability associated with the second device, wherein the indication of the hardware capability is associated with a processing unit type of the second device.

25. The second device of any one of claims 23-24, wherein the processor is further configured to receive, from the first device, the processing unit information as part of metadata.

26. The second device of claim 25, wherein the processor is further configured to decode the intermediate data based on the received metadata.

27. The second device of any one of claims 25-26, wherein the processor is further configured to identify the processing unit of the second device based on the metadata.

28. The second device of any one of claims 25-27, wherein the processor is further configured to receive, from the first device, a processing unit recommendation as part of the metadata, wherein the processing unit recommendation is associated with an amount of processing power required to process the intermediate data.

29. The second device of any one of claims 25-28, wherein the metadata is received via a different channel than the intermediate data.

30. The second device of any one of claims 23-29, wherein the processor is further configured to send, to the first device, an inference result, wherein the inference result is associated with a score.

31. The second device of any one of claims 23-29, wherein the processing unit status associatedwith the intermediate data comprises an indication that the processing unit of the second device is not available.

32. The second device of claim 31 , wherein the processor is further configured to send, based on the indication that the processing unit of the second device is not available, a reply message and an inference result, wherein the reply message indicates the unavailability of the processing unit of the second device and the processing unit information.

33. The second device of any one of claims 23-32, wherein the processing unit status comprises an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

34. A method performed by a second device comprising: receiving, from a first device, processing unit information and intermediate data, wherein the processing unit information is associated with a processing unit of the second device, wherein the processing unit information is associated with the intermediate data, and wherein the processing unit information comprises at least an indication of a processing unit type to be used by the second device for processing the intermediate data and a processing unit identifier associated with the processing unit of the second device; in response to receiving the processing unit information and the intermediate data, determining a processing unit status; and sending, to the first device, the processing unit status.

35. The method of claim 34, wherein the method further comprises sending, to the first device, an indication of a hardware capability associated with the second device, wherein the indication of the hardware capability is associated with a processing unit type of the second device.

36. The method of any one of claims 34-35, wherein the method further comprises receiving, from the first device, the processing unit information as part of metadata.

37. The method of claim 36, wherein the method further comprises decoding the intermediate data based on the received metadata.

38. The method of any one of claims 36-37, wherein the method further comprises identifying theprocessing unit of the second device based on the metadata.

39. The method of any one of claims 36-38, wherein the method further comprises receiving, from the first device, a processing unit recommendation as part of the metadata, wherein the processing unit recommendation is associated with an amount of processing power required to process the intermediate data.

40. The method of any one of claims 36-39, wherein the metadata is received via a different channel than the intermediate data.

41. The method of any one of claims 34-40, wherein the method further comprises sending, to the first device, an inference result, wherein the inference result is associated with a score.

42. The method of any one of claims 34-40, wherein the processing unit status associated with the intermediate data comprises an indication that the processing unit of the second device is not available.

43. The method of claim 42, wherein the method further comprises sending, based on the indication that the processing unit of the second device is not available, a reply message and an inference result, wherein the reply message indicates the unavailability of the processing unit of the second device and the processing unit information.

44. The method of any one of claims 34-43, wherein the processing unit status comprises an indication of at least one of: a processing unit load, the processing unit type, or the processing unit identifier.

45. A computer program product which is stored on a non-transitory computer readable medium and comprises program code instructions for implementing the steps of a method according to at least one of claims 12 to 22 or claims 34 to 44 when executed by at least one processor.

46. A computer program comprising program code instructions for implementing the steps of a method according to at least one of claims 12 to 22 or claims 34 to 44 when executed by a processor.

47. A video data comprising information representative of an encoded output generated according to one of the methods of any of claims 12 to 22 or claims 34 to 44.

Images