Reducing latency to change operational state of processor from low power state to normal power state

By providing notifications asynchronously after the processor receives the network packet and triggering its state transition in advance, the processor's state transition problems are solved, and efficient state transition and low power consumption are achieved.

CN118984983APending Publication Date: 2024-11-19MICROSOFT TECHNOLOGY LICENSING LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380030560.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-22
Filing Date
2023-02-07
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The prior art has a delay in transitioning from a low-power state to a normal power state, which affects processor performance and results in greater power consumption when power saving features are not used.

Method used

By providing notifications asynchronously after the processor receives a network packet, triggering its transition from a low-power state to a normal power state in advance, receiving notifications using hardware or processors and changing states at a predetermined time instance, reducing the time required for state transition and resource.

Benefits of technology

It effectively reduces the delay of the processor from the low power state to the normal power state, improves the efficiency of the processor and computing system, and reduces power consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118984983A_ABST
    Figure CN118984983A_ABST
Patent Text Reader

Abstract

Techniques are described herein that can reduce the latency in changing an operational state of a processor from a low power state to a normal power state. For example, providing a notification from a hardware system to a processor or receiving a notification at the processor to indicate that a transaction layer packet is to be provided to the processor at a future time may trigger the processor to change an operational state from a low power state to a normal power state. In another example, receiving, at a processor, a transaction layer packet from a hardware system may trigger the processor to change an operational state from a low power state to a normal power state.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0001] Processors such as central processing units (CPUs) incorporated into system on a chip (SoC) circuits often implement power saving features to place the processor in a low power state under certain conditions, thereby reducing the amount of power consumed by the processor. Examples of such power saving features include frequency scaling and C-states. Frequency scaling enables a processor to operate at a relatively lower frequency when the utilization of the processor is relatively low, and to operate at a relatively higher frequency when the utilization of the processor is relatively high.

[0002] A C-state is a predefined control mode that controls the amount of power consumed by a processor. For example, in the C0 (also known as the "operating") state, the processor is fully turned on. In the C1 (also known as the "suspend") state, the processor's main internal clock is stopped via software. In the C1E (also known as the "enhanced suspend") state, the processor's main internal clock is stopped via software, and the processor's operating voltage is reduced. In the C2 (also known as the "stop authorization") state, the processor's main internal clock is stopped via hardware. In the C3 (also known as the "sleep") state, all of the processor's internal clocks are stopped. Other C-states have been defined to provide additional levels of power savings.

[0003] However, if the aforementioned power saving features are utilized, a delay traditionally occurs when the processor exits a low power state, which impairs the performance of the processor. For example, when frequency scaling is used, the utilization threshold that triggers the exit from the low power state may not be reached, or a delay may occur when the utilization threshold is reached. When C-states are used, the transition from one C-state to another C-state may be delayed. A common technique for avoiding delays when exiting a processor from a low power state is to not use the power saving features (e.g., by disabling or disabling the power saving features). However, not utilizing the power saving features results in greater power consumption of the processor. Summary of the invention

[0004] Various methods for reducing the time delay of changing the operating state of a processor from a low power state to a normal power state are described herein. The low power state is configured to cause the processor to consume a first amount of power. For example, the low power state can be achieved by reducing the frequency at which the processor operates, reducing the voltage domain of the processor, and / or turning off components of the processor. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. For example, the normal power state can be achieved by increasing the frequency at which the processor operates, increasing the voltage domain of the processor, and / or turning on processor components that were turned off during the low power state.

[0005] The first example method is implemented by hardware. In the first example method, a network packet is received via a network. Based at least in part on receiving the network packet, before a transaction layer packet based at least in part on the network packet is provided to the processor by hardware, a change in the operating state of the processor from a low power state to a normal power state is triggered by asynchronously providing a notification to the processor at a first time instance. The notification indicates that the transaction layer packet will be provided to the processor at a second time instance after the first time instance in time. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The transaction layer packet is processed in the normal power state by providing the transaction layer packet to the processor at the second time instance.

[0006] A second example method is implemented by a processor. In the second example method, a notification is received from hardware at a first time instance. The notification indicates that a transaction layer packet based at least in part on a network packet will be received by the processor from the hardware at a second time instance after the first time instance in time. Based at least in part on receiving the notification, an operating state of the processor is changed from a low power state to a normal power state. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. A transaction layer packet is received from the hardware at a second time instance. The transaction layer packet is processed in the normal power state based at least in part on receiving the transaction layer packet at the second time instance.

[0007] A third example method is implemented by a processor. In the third example method, a transaction layer packet based at least in part on a network packet is received from a hardware system. Based at least in part on receiving the transaction layer packet, and without regard to the extent to which the processor is utilized, a change in the operating state of the processor from a low power state to a normal power state is triggered. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The transaction layer packet is processed in the normal power state.

[0008] The present invention is provided to introduce in a simplified form a series of concepts that will be further described in the following specific embodiments. The present invention is not intended to identify the key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. In addition, it is noted that the present invention is not limited to the specific embodiments described in the specific embodiments and / or other parts of this document. These embodiments presented herein are for illustrative purposes only. Based on the teachings contained herein, other embodiments will be apparent to those skilled in the art (s). BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments of the invention and, together with the description, further serve to explain the principles involved and to enable one skilled in the relevant art(s) to make and use the disclosed technology.

[0010] Figure 1 is a block diagram of an example latency reduction system according to an embodiment.

[0011] Figure 2 According to the embodiment Figure 1 A block diagram of an example implementation of a second computing device is shown.

[0012] Figure 3 is an example activity diagram for reducing latency in changing an operating state of a processor from a low power state to a normal power state, according to an embodiment.

[0013] Figure 4 and Figure 6 Depicted is a flow chart of an example method for reducing latency in changing an operating state of a processor from a low power state to a normal power state in accordance with an embodiment.

[0014] Figure 5 According to the embodiment Figure 1 A block diagram of an example implementation of a hardware system is shown.

[0015] Figure 7 According to the embodiment Figure 1 A block diagram of an example implementation of a processor system is shown.

[0016] Figure 8 is another example activity diagram for reducing latency in changing an operating state of a processor from a low power state to a normal power state according to an embodiment.

[0017] Fig. 9 Depicted is a flow chart of another example method for reducing latency in changing an operating state of a processor from a low power state to a normal power state in accordance with an embodiment.

[0018] Fig.10 According to the embodiment Figure 1 A block diagram of another example implementation of a processor system is shown.

[0019] Fig.11 is a system diagram of an exemplary mobile device according to an embodiment.

[0020] Fig.12 An example computer is depicted in which embodiments may be implemented.

[0021] The features and advantages of the disclosed technology will become more apparent from the detailed description set forth below when taken in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals always identify corresponding elements. In the accompanying drawings, the same reference numerals generally indicate identical, functionally similar, and / or structurally similar elements. The drawing in which an element first appears is indicated by the leftmost digit(s) in the corresponding reference numeral. DETAILED DESCRIPTION

[0022] I. Introduction

[0023] The following detailed description refers to the accompanying drawings showing exemplary embodiments of the present invention. However, the scope of the present invention is not limited to these embodiments, but is defined by the appended claims. Therefore, embodiments other than the embodiments shown in the accompanying drawings (such as modified versions of the illustrated embodiments) may still be covered by the present invention.

[0024] References in the specification to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the relevant art(s) to implement such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0025] Descriptors such as "first," "second," "third," etc. are used to reference some elements discussed herein. Such descriptors are used to facilitate discussion of example embodiments and do not indicate a required order for the referenced elements unless an affirmative statement is made herein requiring such an order.

[0026] II. Example Embodiments

[0027] The example embodiments described herein can reduce the latency of changing the operating state of a processor from a low power state to a normal power state. The low power state is configured to cause the processor to consume a first amount of power. For example, the low power state can be achieved by reducing the frequency at which the processor operates, reducing the voltage domain of the processor, and / or shutting down components of the processor. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. For example, the normal power state can be achieved by increasing the frequency at which the processor operates, increasing the voltage domain of the processor, and / or turning on processor components that were shut down during the low power state.

[0028] Compared with conventional techniques for disengaging a processor from a low power state, the example techniques described herein have various benefits. For example, the example techniques can reduce the latency associated with disengaging a processor from a low power state. The example techniques can reduce the amount of power consumed by a processor while reducing latency. In a first example, a notification (e.g., a prompt) can be provided to a processor to exit a power saving mode, which can enable the processor to transition to a normal power mode before latency-sensitive services enter the processor. For example, a network packet arriving at a serializer / deserializer (serializer / de-serializer, SerDes) of a hardware component can trigger the hardware component to provide a notification to the processor. Even if the network packet only points to an internal function of a hardware component, the network packet arriving at the hardware component can also trigger the hardware component to provide a notification to the processor. In a second example, the processor can exit a low power state immediately upon receiving a packet and / or without considering the extent to which the processor is being utilized. By reducing latency, the example techniques can improve the efficiency of a processor and / or a computing system including a processor.

[0029] Example techniques can reduce the amount of time and / or resources (e.g., processor cycles, memory, network bandwidth) consumed to change the operating state of a processor from a low power state to a normal power state. For example, by providing a notification (e.g., a prompt) to a processor (or receiving a notification by a processor) indicating that a transaction layer packet will subsequently be provided to the processor, example techniques can enable the processor to avoid consuming time and resources that would otherwise be consumed to change the operating state of the processor after the processor receives the transaction layer packet. For example, providing a notification to a processor (or receiving a notification by a processor) can enable the processor to change its state from a low power state to a normal power state before the processor receives the transaction layer packet. In another example, by immediately changing the operating state of the processor from a low power state to a normal power state when the processor receives the transaction layer packet and / or without regard to the extent to which the processor is being utilized, example techniques can enable the processor to avoid consuming time and resources that would otherwise be consumed to change the operating state of the processor during delays associated with conventional techniques (e.g., while waiting for a utilization threshold to be reached or while waiting for a transition from one C-state to another C-state to occur).

[0030] Figure 11 is a block diagram of an example latency reduction system 100 according to an embodiment. In general, the latency reduction system 100 operates to provide information between a first computing system 102 and a second computing system 106. For example, the latency reduction system 100 may provide information to a user of a first computing device 102 in response to a request (e.g., a hypertext transfer protocol (HTTP) request) received from the user. The information may include a document (a web page, an image, an audio file, a video file, etc.), an output of an executable file, and / or any other suitable type of information. The information is included in (multiple) network packets 116. According to the example embodiments described herein, the latency reduction system 100 reduces the latency of changing the operating state of a processor (e.g., a processor system 110) from a low power state to a normal power state. Details of the technology for reducing the latency of changing the operating state of a processor from a low power state to a normal power state are provided in the following discussion.

[0031] like Figure 1 As shown, the latency reduction system 100 includes a first computing device 102, a network 104, and a second computing device 106. The communication between the first computing device 102 and the second computing device 106 is implemented on the network 104 using a well-known network communication protocol. The network 104 is a packet-switched network. For example, the network 104 can be a wide area network (e.g., the Internet), a local area network (LAN), another type of network, or a combination thereof.

[0032] The first computing device 102 is a processing system capable of communicating with the second computing system 106. An example of a processing system is a system including at least one processor capable of manipulating data according to an instruction set. For example, the processing system may be a computer, a personal digital assistant, etc. The first computing device 102 is configured to provide a request to the second computing device 106 for information stored on the second computing device 106 (or otherwise accessible via the second computing device 106). For example, a user may use a client (e.g., a web browser, a web crawler, or other type of client) owned by the user or otherwise accessible to the user deployed on the first computing device 102 to initiate a request for executing a computer program (e.g., an application). According to some example embodiments, the first computing device 102 is capable of accessing a domain (e.g., a website) hosted by the second computing device 106, so that the first computing device 102 can access information available via these domains. Such a domain may include a web page, for example, a web page may be provided as a hypertext markup language (HTML) document and objects (e.g., files) linked therein.

[0033] The first computing device 102 may include any client-supported system or device, including but not limited to desktop computers, laptop computers, tablet computers, wearable computers (such as smart watches or head-mounted computers), personal digital assistants, cellular phones, Internet of things (IoT) devices, etc.

[0034] The second computing device 106 is a processing system capable of communicating with the first computing device 102. The second computing device 106 is configured to provide information to a user of the first computing device 102 in response to receiving a request from the user. For example, the second computing device 106 can execute (multiple) computer programs that provide information. The information may include documents (web pages, images, audio files, video files, etc.), output of executable files, or any other suitable type of information. Any one or more of the computer programs may be a cloud computing service. A cloud computing service is a service that is executed at least in part in the cloud. The cloud can be a remote cloud, a local cloud, or a hybrid cloud. It will be appreciated that a local cloud may use a remote cloud service. Examples of cloud computing services include, but are not limited to, Microsoft Azure, developed and distributed by Microsoft Corporation. (or one of them or Word TM ), Google Docs Editors developed and distributed by Google Inc. TM (or Google Sheets TM or Google Docs TM ), and developed and distributed by Apple Inc. (or the Numbers TM or Pages TM According to some example embodiments, the second computing device 106 is configured to host the website(s) so that the website(s) are accessible to a user of the first computing device 102 .

[0035] The second computing device 106 is shown as including a hardware system 108 and a processor system 110. The hardware system 108 is a system including hardware and configured to generate (multiple) transaction layer packets 120 based on receiving (multiple) network packets 116. For example, the hardware system 108 can convert (multiple) network packets 116 into (multiple) transaction layer packets 120. Network packets are packets received via a packet switching network. For example, network packets can be configured according to the network layer (i.e., layer 3) of the Open Systems Interconnection (ISO) model. Transaction layer packets are packets configured according to bus standards. Examples of bus standards include, but are not limited to: Peripheral Component Interconnect (ICI), Peripheral Component Interconnect (ICI), and Transaction Layer Component Interconnect (CLI). TM , PCI TM ) bus standard and Accelerated Graphics Port TM , AGP TM ) bus standard; PCI eXtended PCI (PCI eXtended PCI) developed jointly by International Business Machines Corporation (IBM), Hewlett-Packard Co., Ltd., and Compaq Computer Corporation TM , ) bus standard; and PCI Express, a high-speed PCI bus standard jointly developed by Intel Corporation, Dell Inc., Hewlett-Packard Co., Ltd., and IBM TM , ) bus standard. The transaction layer packet may also be configured according to the Compute Express Link (CXL) open standard developed primarily by Intel Corporation, although the example embodiments are not limited in this regard. In one example, the transaction layer packet may include an interrupt. For example, an interrupt may request that the processor system 110 provide data to the hardware system 108. In another example, the transaction layer packet may include instructions to read data from storage and / or write data to storage.

[0036] The hardware system 108 includes latency reduction logic 122. The latency reduction logic 122 is configured to reduce the latency of changing the operating state of the processor system 110 from a low power state to a normal power state. In one example implementation, the latency reduction logic 122 receives (multiple) network packets 116 via the network 104. Based at least in part on receiving the (multiple) network packets 116, before (multiple) transaction layer packets 120 based at least in part on the (multiple) network packets 116 are provided to the processor system 110 by the latency reduction logic 122, the latency reduction logic 122 triggers the change of the operating state of the processor system 110 from the low power state to the normal power state by asynchronously providing a notification 118 to the processor system 110 at a first time instance. The notification 118 indicates that the (multiple) transaction layer packets 120 will be provided to the processor system 110 at a second time instance after the first time instance in time. The low power state is configured to cause the processor system 110 to consume a first amount of power. The normal power state is configured to cause the processor system 110 to consume a second amount of power greater than the first amount of power. The latency reduction logic 122 causes the transaction layer packet(s) 120 to be processed in the normal power state by providing the transaction layer packet(s) 120 to the processor system 110 at a second time instance.

[0037] The hardware system 108 includes a PCIe WAKE# pin 112, and the latency reduction logic 122 can provide the notification 118 to the processor system 110 via the PCIe WAKE# pin 112. For example, the latency reduction logic 122 can provide the notification 118 to the processor system 110 via an out-of-band connection (i.e., via a connection different from the connection via which the latency reduction logic 122 provides the transaction layer packet(s) 120 to the processor system 110).

[0038] The processor system 110 is a system that includes at least one processor and is configured to process transaction layer packets (eg, the transaction layer packet(s) 120 received from the hardware system 108 ).

[0039] The processor system 110 includes latency reduction logic 124. The latency reduction logic 124 is configured to reduce the latency of changing the operating state of the processor system 110 from a low power state to a normal power state. In a first example implementation, the latency reduction logic 124 receives a notification 118 from the hardware system 108 at a first time instance. According to the implementation, the notification indicates that (multiple) transaction layer packets 120 based at least in part on the (multiple) network packets 116 will be received by the processor system 110 from the hardware system 108 at a second time instance after the first time instance in time. Based at least in part on receiving the notification 118, the operating state of the processor system 110 is changed from the low power state to the normal power state. The low power state is configured to cause the processor system 110 to consume a first amount of power. The normal power state is configured to cause the processor system 110 to consume a second amount of power greater than the first amount of power. If the processor system 110 is already in the normal power state at the first time instance, the latency reduction logic 124 can ignore the notification 118. The latency reduction logic 124 receives the transaction layer packet(s) 120 at a second time instance from the hardware system 108. The latency reduction logic 124 processes the transaction layer packet(s) 120 in the normal power state based at least in part on receiving the transaction layer packet(s) 120 at the second time instance.

[0040] In a second example implementation, latency reduction logic 124 receives transaction layer packet(s) 120 based at least in part on network packet(s) 116 from hardware system 108. Based at least in part on receiving transaction layer packet(s) 120, and without regard to the extent to which processor system 110 is utilized, latency reduction logic 124 triggers a change in the operating state of processor system 110 from a low power state to a normal power state. The low power state is configured to cause processor system 110 to consume a first amount of power. The normal power state is configured to cause processor system 110 to consume a second amount of power greater than the first amount of power. Latency reduction logic 124 processes transaction layer packet(s) 120 in the normal power state.

[0041] The processor system 110 includes a PCIe WAKE# pin 114, and the latency reduction logic 124 can receive the notification 118 from the hardware system 108 via the PCIe WAKE# pin 114. For example, the latency reduction logic 124 can receive the notification 118 from the hardware system 108 via an out-of-band connection (i.e., via a connection different from the connection via which the latency reduction logic 124 receives the transaction layer packet(s) 120 from the hardware system 108). It will be appreciated that the PCIe WAKE# pin 112 and the PCIe WAKE# pin 114 can both be PCIe-compatible general-purpose input / output (GPIO) pins.

[0042] The delay reduction logic 122 and / or the delay reduction logic 124 can be implemented in various ways to reduce the delay of changing the operating state of the processor system 110 from a low power state to a normal power state, including being implemented in hardware, software, firmware, or any combination thereof. For example, the delay reduction logic 122 and / or the delay reduction logic 124 can be implemented as a computer program code that is configured to be executed in one or more processors. In another example, at least a portion of the delay reduction logic 122 and / or the delay reduction logic 124 can be implemented as a hardware logic / electrical circuit. For example, at least a portion of the delay reduction logic 122 and / or the delay reduction logic 124 can be implemented in a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), an application-specific standard product (ASSP), a system on chip (SoC), a complex programmable logic device (CPLD), etc. Each SoC may include an integrated circuit chip. An integrated circuit chip includes one or more of the following: a processor (microcontroller, microprocessor, digital signal processor (DSP) etc.), a memory, one or more communication interfaces, and / or other circuits and / or embedded firmware to perform its functions.

[0043] It will be appreciated that the hardware system 108 need not necessarily include the PCIe WAKE# pin 112 and / or the latency reduction logic 122. Furthermore, the hardware system 108 may include components in addition to or in place of the PCIe WAKE# pin 112 and / or the latency reduction logic 122. It will also be appreciated that the processor system 110 need not necessarily include the PCIe WAKE# pin 114 and / or the latency reduction logic 124. Furthermore, the processor system 110 may include components in addition to or in place of the PCIe WAKE# pin 114 and / or the latency reduction logic 124.

[0044] Figure 2 According to the embodiment as Figure 1 106 is a block diagram of a computing device 200 that illustrates an example implementation of the second computing device 106. Figure 2As shown, the computing device 200 includes a plurality of hardware systems 208A-208N, a Boolean OR gate 226, and a processor system 210. The hardware systems 208A-208N are configured to operate in a manner similar to Figure 1 1. The hardware systems 208A-208N may be configured to receive and process a first portion of the packet 116; the second hardware system 208B may receive and process a second portion of the packet 116 that is different from the first portion; and so on. The hardware systems 208A-208N may each be configured to provide a notification to the processor system 210 upon receipt of a network packet. The first hardware system 208A is shown as generating a notification 218 to indicate that the first hardware system 208A has received a network packet. The hardware systems 208A-208N may each be a PCIe-compatible device and / or may operate in accordance with the NVMe (Non-Volatile Memory Express) open logical device interface specification developed by Intel Corporation, although the example embodiments are not limited in this regard.

[0045] For purposes of illustration, the hardware systems 208A-208N are shown as including corresponding PCIe WAKE# pins 212A-212N. For example, the hardware systems 208A-208N may send their notifications to the processor system 210 via the corresponding PCIe WAKE# pins 212A-212N.

[0046] Boolean OR gate 226 is configured to perform a Boolean OR operation on the outputs of hardware systems 208A-208N. Boolean OR gate 226 forwards notifications received from any one of hardware systems 208A-208N to processor system 210, so that the notifications from any one of hardware systems 208A-208N trigger processor system 210 to change its operating system from a low power state to a normal power state.

[0047] The processor system 210 is configured to operate in a manner similar to Figure 1 For example, based at least in part on receiving a notification (e.g., notification 218) from any of hardware systems 208A-208N via Boolean OR gate 226, processor system 210 changes its operating state from a low power state to a normal power state.

[0048] For purposes of illustration, the processor system 210 is shown as including the PCIe WAKE# pin 214. For example, the processor system 210 may receive notification from the Boolean OR gate 226 via the PCIe WAKE# pin 214.

[0049] Figure 3is an example activity diagram 300 for reducing latency in changing an operating state of a processor system 310 from a low power state to a normal power state, according to an embodiment. Figure 3 A first computing system 302 and a second computing system 306 are depicted. The first computing system 302 includes first hardware 324. The second computing system 306 includes second hardware 308, a processor system 310, and third hardware 326. Activities 330, 332, 334, 336, 338, 340, 342, and 344 will now be described with reference to the first hardware 324, the second hardware 308, the processor system 310, and the third hardware 326.

[0050] In activity 330 , first hardware 324 provides the network packet to second hardware 308 .

[0051] In activity 332, the second hardware 308 provides a notification to the processor system 310 (e.g., based on receiving the network packet in activity 330). The notification indicates that (multiple) transaction layer packets will be provided to the processor system 310 at a future (e.g., subsequent) time. By providing the notification to the processor system 310, the second hardware 308 can trigger the processor system 310 to change the operating state of the processor system 310 from a low-power state to a normal power state. In the low-power state, the processor system 310 operates in a manner that consumes a relatively small amount of power. For example, in the low-power state, selected portions of the functions of the processor system 310 can be turned off, the frequency of the clock signal of the processor system 310 can be reduced (e.g., the operating frequency of the processor system 310 can be reduced), and / or the voltage of the clock signal used for the processor system 310 can be reduced. In the normal power state, the processor system 310 operates in a manner that consumes a relatively large amount of power. For example, in the normal power state, portions of the functions of the processor system 310 that were turned off in the low power state may be turned on, the frequency of the clock signal of the processor system 310 may be increased (e.g., the operating frequency of the processor system 310 may be increased), and / or the voltage of the clock signal used for the processor system 310 may be increased.

[0052] In activity 334, processor system 310 changes its state from the low-power state to the normal power state based at least in part on receiving the notification from second hardware 308. Processor system 310 can ensure that its state is changed from the low-power state to the normal power state at or before a future time. For example, the notification can specify a future time at which (multiple) transaction layer packets will be provided to processor system 310. According to this example, processor system 310 can schedule turning on aspects of its functionality, increasing the frequency of a clock signal, and / or increasing the voltage of a clock signal at a sufficiently early time to ensure that the transition from the low-power state to the normal power state is completed before the future time.

[0053] In activity 336, the second hardware 308 processes the network packet. For example, the second hardware 308 can decrypt the network packet and / or decompress the network packet.

[0054] In activity 338, the second hardware 308 generates (multiple) transaction layer packets based on the network packet. For example, the second hardware 308 can divide the network packet into (multiple) parts and send them according to the bus standard (such as The second hardware 308 may format the portion(s) according to the bus standard to generate corresponding transaction layer packet(s). The second hardware 308 may perform any of a variety of operations on the transaction layer packet(s) to prepare the transaction layer packet(s) for transmission to another entity, such as the third hardware 326. For example, the second hardware 308 may encode the transaction layer packet(s) and / or encrypt the transaction layer packet(s).

[0055] In activity 340, the second hardware 308 provides the transaction layer packet(s) to the processor system 310. It will be appreciated that upon completion of activity 340, but prior to receipt of the transaction layer packet(s) by the processor system 310, the operating state of the processor system 310 may be changed from the low power state to the normal power state in activity 334. For example, activity 334 may be completed while any one or more of activities 336, 338, and / or 340 are being performed.

[0056] In activity 342, processor system 310 processes transaction layer packet(s). For example, processor system 310 may decrypt transaction layer packet(s) and / or decode transaction layer packet(s). Decoding each transaction layer packet may include identifying a header of the packet, a body of the packet, prefix(es) of the packet, suffix(es) of the packet, and the like.

[0057] In activity 344, the processor system 310 forwards the transaction layer packet(s) to the third hardware 326. By forwarding the transaction layer packet(s) to the third hardware 326, the processor system 310 may enable the third hardware 326 to process the transaction layer packet(s). It will be appreciated that the third hardware 326 and the second hardware 308 may be the same, although example embodiments are not limited in this respect.

[0058] In some example embodiments, one or more of the activities 330, 332, 334, 336, 338, 340, 342, and / or 344 of the activity diagram 300 may not be performed. Furthermore, activities in addition to or in place of the activities 330, 332, 334, 336, 338, 340, 342, and / or 344 may be performed.

[0059] Figure 4 400 is a flowchart of an example method for reducing the latency of changing the operating state of a processor from a low power state to a normal power state according to an embodiment. For example, flowchart 400 may be composed of Figure 1 The hardware system 108 shown is executed. For the purpose of illustration, reference is made to the example implementation of the hardware system 108. Figure 5 Flowchart 400 is described with reference to hardware system 500 shown in FIG. 5 . Hardware system 500 may be any suitable type of hardware system, including but not limited to a network interface controller (NIC), an accelerator, a storage device (e.g., a memory such as a solid-state drive (SSD)), or a graphical processing unit (GPU). Figure 5 As shown, hardware system 500 includes latency reduction logic 522. Latency reduction logic 522 includes state controller 552, packet conversion logic 554, time determination logic 556, and time selection logic 558. Further structural and operational embodiments will be apparent to those skilled in the relevant art(s) based on the discussion regarding flowchart 400.

[0060] like Figure 4 As shown, the method of flowchart 400 begins at step 402. In step 402, a network packet is received via a network. In one example implementation, state controller 552 receives network packet 516.

[0061] At step 404, a change in the operating state of the processor from a low power state to a normal power state is triggered by asynchronously providing a notification to the processor at a first time instance. The change in the operating state is triggered at least in part based on receiving a network packet at step 402. The change in the operating state is penalized before a transaction layer packet based at least in part on the network packet is provided to the processor. For example, in the case where an expected transaction layer packet is provided to the processor, the processor may be penalized to change the operating state of the processor. The notification indicates that the transaction layer packet will be provided to the processor at a second time instance after the first time instance in time. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. In an example implementation, the state controller 552 triggers a change in the operating state of the processor by asynchronously providing a notification 518 to the processor at a first time instance. For example, the state controller 552 can trigger the change as a result of receiving a network packet 516. The notification 518 indicates that the transaction layer packet 520 will be provided to the processor at a second time instance.

[0062] Triggering a change in the operating state of the processor at step 404 may reduce latency associated with changing the state of the processor from a low power state to a normal power state. Triggering a change in the operating state of the processor at step 404 may improve efficiency of the processor and / or a computing system including the processor. Triggering a change in the operating state of the processor at step 404 may enable the processor to reduce power consumption without delaying exiting from a low power state to a normal power state.

[0063] In one example embodiment, the notification indicates an amount of time between a first time instance at which the notification is asynchronously provided to the processor and a second time instance at which the transaction layer packet is to be provided to the processor. For example, the notification may include a first timestamp indicating the first time instance and a second timestamp indicating the second time instance. In another example, the notification specifies a difference between the first time instance and the second time instance without including the first timestamp indicating the first time instance and / or the second timestamp indicating the second time instance.

[0064] In another example embodiment, triggering a change in the operating state of the processor at step 404 includes triggering the processor to increase the frequency at which the processor operates (i.e., the operating frequency) by asynchronously providing a notification to the processor at a first time instance. For example, the processor may be triggered to increase the operating frequency from a first frequency (e.g., 0.7 GHz) to a second frequency (e.g., 2.0 GHz) greater than the first frequency. In another example, increasing the operating frequency may include increasing the rate at which a clock used by the processor to perform operations operates (e.g., oscillates).

[0065] In yet another example embodiment, triggering a change in the operating state of the processor at step 404 includes triggering the processor to increase a voltage of a clock used by the processor to perform operations by asynchronously providing a notification to the processor at a first time instance. For example, the processor may be triggered to increase the voltage of the clock from a first voltage to a second voltage greater than the first voltage.

[0066] In yet another example embodiment, triggering a change in the operating state of the processor at step 404 includes triggering the processor to switch a portion of the processor from an off state to an on state by asynchronously providing a notification to the processor at a first time instance. For example, the processor may be triggered to turn on a voltage that was turned off while the processor was in a low power state. In another example, the processor may be triggered to reverse clock gating performed by the processor in a low power state to turn off the portion of the processor. Clock gating is a power saving technique that turns off circuit(s) and / or portion(s) thereof to reduce dynamic power consumption.

[0067] In another example embodiment, triggering a change in the operating state of the processor at step 404 includes asynchronously providing a notification to the processor via a peripheral component interconnect express (PCIe) WAKE# pin of the hardware system at a first time instance.

[0068] In yet another example embodiment, triggering a change in the operating state of the processor at step 404 includes asynchronously providing a notification to the processor via a first connection at a first time instance, the first connection being included in a plurality of connections connecting a plurality of corresponding hardware systems to the processor via a Boolean OR gate.

[0069] At step 406, the transaction layer packet is processed in the normal power state by providing a transaction layer packet based at least in part on the network packet to the processor at a second time instance. For example, the transaction layer packet may be provided to the processor via a PCIe connection. The PCIe connection is based on The state controller 552 may forward the network packet 516 to the packet conversion logic 554 to enable the packet conversion logic 554 to generate the transaction layer packet 520 based at least in part on the network packet 516. For example, the packet conversion logic 554 may convert the network packet 516 into one or more transaction layer packets including the transaction layer packet 520. According to this example, the packet conversion logic 554 may process the network packet 516 (e.g., by decrypting and / or decompressing the network packet 516) before converting the network packet 516 into one or more transaction layer packets. The packet conversion logic 554 may provide the transaction layer packet 520 to the processor in response to generating the transaction layer packet 520.

[0070] In some example embodiments, one or more steps 402, 404, and / or 406 of flowchart 400 may not be performed. Furthermore, steps in addition to or in place of steps 402, 404, and / or 406 may be performed. For example, in one example embodiment, the notification is provided to the processor asynchronously at step 404 before the hardware system completes processing of the network packet. The processing of the network packet includes generating a transaction layer packet based at least in part on the network packet. The processing of the network packet may include other types of processing, such as decrypting the network packet and / or decompressing the network packet, although example embodiments are not limited in this regard.

[0071] In a first aspect of this embodiment, the method of flowchart 400 also includes: determining the amount of time that the hardware system will consume to complete processing of the network packet. In an example implementation, the time determination logic 556 determines the amount of time that the packet conversion logic 554 will consume to complete processing of the network packet 516. For example, the time determination logic 556 can monitor how long it takes for the packet conversion logic 554 to complete processing of the network packet. According to this example, the time determination logic 556 can determine the amount of time that will be consumed to complete processing of the network packet 516 based on historical measurements indicating how long the packet conversion logic 554 has spent in the past to complete processing of the network packet. The time determination logic 556 can generate a time estimate 560 to indicate the amount of time that the packet conversion logic 554 will consume to complete processing of the network packet 516. According to the first aspect, the method of flowchart 400 also includes: selecting a first time instance at which the notification is provided to the processor based at least in part on the amount of time. For example, the first time instance can be selected based at least in part on the difference between the first time instance and the second time instance that are equal to the amount of time that the hardware system will consume to complete processing of the network packet. In one example implementation, time selection logic 558 selects the first time instance based at least in part on the amount of time as indicated by time estimate 560. Time selection logic 558 may generate time indicator 562 to indicate the first time instance, which may enable state controller 552 to determine the first time instance to provide notification 518 to the processor.

[0072] In a second aspect of the embodiment, the method of flowchart 400 further includes completing processing of the network packet to generate a transaction layer packet. In one example implementation, packet conversion logic 554 completes processing of network packet 516 to generate transaction layer packet 520. According to the second aspect, the transaction layer packet is provided to the processor at a second time instance based at least in part on completing processing of the network packet.

[0073] It will be appreciated that hardware system 500 may not include one or more of state controller 552, packet conversion logic 554, time determination logic 556, and / or time selection logic 558. Furthermore, hardware system 500 may include components in addition to or in place of state controller 552, packet conversion logic 554, time determination logic 556, and / or time selection logic 558.

[0074] Figure 6 A flowchart 600 is depicted of another example method for reducing the latency of changing the operating state of a processor system from a low power state to a normal power state according to an embodiment. For example, the flowchart 600 may be composed of Figure 1For purposes of illustration, reference is made to an example implementation of the processor system 110. Figure 7 The flowchart 600 is described with reference to the processor system 700 shown in FIG. Figure 7 As shown, processor system 700 includes latency reduction logic 724. Latency reduction logic 724 includes state controller 772, attribute selection logic 774, and packet processing logic 776. Based on the discussion regarding flowchart 600, further structural and operational embodiments will be apparent to those skilled in the relevant art(s).

[0075] like Figure 6 As shown, the method of flowchart 600 begins at step 602. In step 602, a notification is received from a hardware system at a first time instance. The notification indicates that a transaction layer packet based at least in part on a network packet will be received by a processor system from the hardware system at a second time instance that is later in time than the first time instance. The hardware system can be any suitable type of hardware system, including but not limited to a network interface controller (NIC), an accelerator, a memory (e.g., a memory such as a solid state drive (SSD)), or a graphics processing unit (GPU). In an example implementation, state controller 772 receives notification 718 at a first time instance. Notification 718 indicates that a transaction layer packet 720 based at least in part on a network packet will be received by processor system 700 from the hardware system at a second time instance that is later in time than the first time instance.

[0076] In one example implementation, a notification is received from a hardware system at step 602 via a peripheral component interconnect express (PCIe) WAKE# pin of a processor system at a first time instance.

[0077] In another example implementation, a notification is received at step 602 from a hardware system at a first time instance via a first connection, the first connection being included in a plurality of connections connecting a plurality of respective hardware systems to a processor system via a Boolean OR gate.

[0078] At step 604, based at least in part on receiving the notification, the operating state of the processor system is changed from a low power state to a normal power state. The low power state is configured to cause the processor system to consume a first amount of power. The normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. In an example implementation, the state controller 772 changes the operating state of the processor system 700 from a low power state to a normal power state based at least in part on receiving the notification 718. The low power state is configured to cause the processor system 700 to consume a first amount of power. The normal power state is configured to cause the processor system 700 to consume a second amount of power greater than the first amount of power.

[0079] Receiving the notification at step 602 and / or changing the operating state of the processor system at step 604 may reduce latency associated with changing the state of the processor system from a low power state to a normal power state. Receiving the notification at step 602 and / or changing the operating state of the processor system at step 604 may improve efficiency of the processor system and / or a computing system including the processor system. Receiving the notification at step 602 and / or changing the operating state of the processor system at step 604 may enable the processor system to reduce power consumption without delaying exiting from a low power state to a normal power state.

[0080] In an example embodiment, the operating state of the processor system is changed at step 604 prior to receiving the transaction layer packet from the hardware system at the second time instance.

[0081] In another example embodiment, changing the operating state of the processor system at step 604 includes increasing the frequency at which the processor system operates, increasing the voltage of a clock used by the processor system to perform operations, and / or switching a portion of the processor system from an off state to an on state.

[0082] At step 606, a transaction layer packet is received from the hardware system at a second time instance. In one example implementation, the packet processing logic 776 receives a transaction layer packet 720 from the hardware system at a second time instance.

[0083] At step 608, a transaction layer packet is processed in the normal power state (e.g., based at least in part on receiving the transaction layer packet at the second time instance). For example, processing the transaction layer packet may include decrypting the transaction layer packet and / or decoding the transaction layer packet. In one example implementation, the packet processing logic 776 processes the transaction layer packet 720 in the normal power state based at least in part on receiving the transaction layer packet 720 at the second time instance.

[0084] In one example embodiment, processing the transaction layer packet at step 608 includes instructing the hardware system to perform a specified task based at least in part on receiving the transaction layer packet. For example, the specified task may include processing a specified image and displaying a specified image. In another example, the specified task may include processing a specified audio file and playing a specified audio file.

[0085] In some example embodiments, one or more steps 602, 604, 606, and / or 608 of flowchart 600 may not be performed. Furthermore, steps in addition to or in place of steps 602, 604, 606, and / or 608 may be performed. For example, in one example embodiment, the notification indicates an amount of time between a first time instance at which the processor system receives the notification from the hardware system and a second time instance at which the processor system will receive a transaction layer packet from the hardware system. According to this embodiment, the method of flowchart 600 also includes: selecting an attribute of the processor system from a plurality of attributes of the processor system to be changed based at least in part on the ability of the processor system to change the attribute of the processor system from a first value to a second value within the amount of time between the first time instance and the second time instance. In one example implementation, attribute selection logic 774 selects an attribute of the processor system 700 to be changed from a plurality of attributes of the processor system 700. For example, state controller 772 may generate a time estimate 778 indicating an amount of time between the first time instance and the second time instance. Attribute selection logic 774 may analyze time estimate 778 to determine the amount of time. The attribute selection logic 774 may determine the amount of time consumed by the processor system 700 to change each of the plurality of attributes. The attribute selection logic 774 may also determine which of the plurality of attributes may be changed simultaneously. Based on the determined amount of time consumed by the processor system 700 to change each of the plurality of attributes, and also based on which of the plurality of attributes may be changed simultaneously, the attribute selection logic 774 may determine which of the plurality of attributes the processor system 700 is able to change within the amount of time indicated by the time estimate 778. The attribute selection logic 774 may select the attribute to be changed of the processor system 700 from the attribute(s) that the processor system 700 is able to change within the amount of time indicated by the time estimate 778. Further in accordance with this embodiment, changing the operating state of the processor system at step 604 includes changing the selected attribute of the processor system from a first value to a second value.

[0086] In one aspect of this embodiment, selecting the attributes includes: selecting a first subset of the plurality of attributes and not selecting a second subset of the plurality of attributes based at least in part on the processor system being able to change each attribute in the first subset from a corresponding first value to a corresponding second value within an amount of time between the first time instance and the second time instance. According to this aspect, changing the operating state of the processor system at step 604 includes changing each attribute in the first subset from a corresponding first value to a corresponding second value.

[0087] It will be appreciated that the processor system 700 may not include one or more of the state controller 772, the attribute selection logic 774, and / or the packet processing logic 776. Furthermore, the processor system 700 may include components in addition to or in place of the state controller 772, the attribute selection logic 774, and / or the packet processing logic 776.

[0088] Figure 8 is another example activity diagram 800 for reducing latency in changing an operating state of a processor system 810 from a low power state to a normal power state, according to an embodiment. Figure 8 A first computing system 802 and a second computing system 806 are depicted. The first computing system 802 includes first hardware 824. The second computing system 806 includes second hardware 808, a processor system 810, and third hardware 826. Activities 830, 834, 836, 838, 840, 842, and 844 will now be described with reference to the first hardware 824, the second hardware 808, the processor system 810, and the third hardware 826.

[0089] In activity 830 , the first hardware 824 provides the network packet to the second hardware 808 .

[0090] In activity 836, the second hardware 808 processes the network packet. For example, the second hardware 808 can decrypt the network packet and / or decompress the network packet.

[0091] In activity 838, the second hardware 808 generates (multiple) transaction layer packets based on the network packet. For example, the second hardware 808 can divide the network packet into (multiple) parts and generate (multiple) transaction layer packets according to the bus standard (such as The second hardware 808 may format the portion(s) according to the bus standard to generate corresponding transaction layer packet(s). The second hardware 808 may perform any of a variety of operations on the transaction layer packet(s) to prepare the transaction layer packet(s) for transmission to another entity, such as the third hardware 826. For example, the second hardware 808 may encode the transaction layer packet(s) and / or encrypt the transaction layer packet(s).

[0092] In activity 840 , the second hardware 808 provides the transaction layer packet(s) to the processor system 810 .

[0093] In activity 834, the processor system 810 changes its state from the low power state to the normal power state based at least in part on receiving the transaction layer packet(s) from the second hardware 808. The processor system 810 can change its state from the low power state to the normal power state without regard to the extent to which the processor system 810 is utilized. For example, the processor system 810 can change its state independently of whether the utilization of the processor system 810 is greater than or equal to a utilization threshold. The utilization of the processor system 810 can indicate a number of processor cycles of the processor system 810 consumed in a specified time period, a number of tasks executed by the processor system 810 in a specified time period, and / or a proportion of resources of the processor system 810 consumed at a certain moment or in a specified time period (e.g., the proportion is greater than a proportion threshold at the moment, or the proportion is greater than a proportion threshold for a duration greater than a duration threshold).

[0094] In the low power state, the processor system 810 operates in a manner that consumes a relatively small amount of power. For example, in the low power state, selected portions of the functionality of the processor system 810 may be turned off, the frequency of a clock signal to the processor system 810 may be reduced (e.g., the operating frequency of the processor system 810 may be reduced), and / or the voltage of the clock signal for the processor system 810 may be reduced. In the normal power state, the processor system 810 operates in a manner that consumes a relatively large amount of power. For example, in the normal power state, portions of the functionality of the processor system 810 that were turned off in the low power state may be turned on, the frequency of a clock signal to the processor system 810 may be increased (e.g., the operating frequency of the processor system 810 may be increased), and / or the voltage of the clock signal for the processor system 810 may be increased.

[0095] In activity 842, the processor system 810 processes the transaction layer packet(s). For example, the processor system 810 may decrypt the transaction layer packet(s) and / or decode the transaction layer packet(s).

[0096] In activity 844, the processor system 810 forwards the transaction layer packet(s) to the third hardware 826. By forwarding the transaction layer packet(s) to the third hardware 826, the processor system 810 may enable the third hardware 826 to process the transaction layer packet(s). It will be appreciated that the third hardware 826 and the second hardware 808 may be the same, although example embodiments are not limited in this respect.

[0097] In some example embodiments, one or more of the activities 830, 834, 836, 838, 840, 842, and / or 844 of the activity diagram 800 may not be performed. Furthermore, activities in addition to or in place of activities 830, 834, 836, 838, 840, 842, and / or 844 may be performed.

[0098] Fig. 9 A flowchart 900 is depicted of another example method for reducing the latency of changing the operating state of a processor system from a low power state to a normal power state according to an embodiment. For example, the flowchart 900 may be composed of Figure 1 For illustrative purposes, reference is made to another example implementation of the processor system 110. Fig.10 Flowchart 900 is described with reference to processor system 1000 shown in FIG. Fig.10 As shown, processor system 1000 includes latency reduction logic 1024. Latency reduction logic 1024 includes state controller 1072 and packet processing logic 1076. Based on the discussion regarding flowchart 900, further structural and operational embodiments will be apparent to persons skilled in the relevant art(s).

[0099] like Fig. 9 As shown, the method of flowchart 900 begins at step 902. In step 902, a transaction layer packet is received from a hardware system. The transaction layer packet is based at least in part on a network packet. The hardware system can be any suitable type of hardware system, including but not limited to a network interface controller (NIC), an accelerator, a memory (e.g., a memory such as a solid state drive (SSD)), or a graphics processing unit (GPU). In one example implementation, state controller 1072 receives transaction layer packets 1020 based at least in part on network packets from a hardware system.

[0100] At step 904, a change in the operating state of the processor system from a low power state to a normal power state is triggered without regard to the extent to which the processor system is utilized. The triggering of the change in the operating state may be based at least in part on receiving a transaction layer packet. The low power state is configured to cause the processor system to consume a first amount of power. The normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. In an example implementation, the state controller 1072 triggers a change in the operating state of the processor system 1000 from a low power state to a normal power state without regard to the extent to which the processor system 1000 is utilized.

[0101] Triggering a change in the operating state of the processor system at step 904 may reduce latency associated with changing the state of the processor system from a low power state to a normal power state. Triggering a change in the operating state of the processor system at step 904 may improve efficiency of the processor system and / or a computing system including the processor system. Triggering a change in the operating state of the processor system at step 904 may enable the processor system to reduce power consumption without delaying exiting from a low power state to a normal power state.

[0102] In an example embodiment, changing the operating state of the processor system includes increasing the frequency at which the processor system operates, increasing the voltage of a clock used by the processor system to perform operations, and / or switching a portion of the processor system from an off state to an on state.

[0103] In another example embodiment, triggering a change in the operating state of the processor system at step 904 is performed before the processor system decodes the transaction layer packet.

[0104] At step 906, the transaction layer packet is processed in the normal power state. In one example implementation, the packet processing logic 10776 processes the transaction layer packet 1020 in the normal power state.

[0105] In one example embodiment, processing the transaction layer packet at step 906 includes instructing the hardware system to perform a specified task based at least in part on receiving the transaction layer packet. For example, the specified task may include processing a specified image and displaying a specified image. In another example, the specified task may include processing a specified audio file and playing a specified audio file.

[0106] In some example embodiments, one or more steps 902, 904, and / or 906 of flowchart 900 may not be performed. Furthermore, steps in addition to or in place of steps 902, 904, and / or 906 may be performed.

[0107] It will be appreciated that processor system 1000 may not include one or more of state controller 1072 and / or packet processing logic 1076. Furthermore, processor system 1000 may include components in addition to or in place of state controller 1072 and / or packet processing logic 1076.

[0108] Fig.111 is a system diagram of an exemplary mobile device 1100 including various optional hardware components and software components as shown in 1102. Any component 1102 in the mobile device can communicate with any other component, although not all connections are shown for ease of illustration. The mobile device 1100 can be any of a variety of computing devices (e.g., a cellular phone, a smart phone, a handheld computer, a personal digital assistant (PDA), etc.), and can allow wireless two-way communication with one or more mobile communication networks 1104 (such as a cellular network or a satellite network) or with a local area network or a wide area network.

[0109] The mobile device 1100 may include a processor 1110 (e.g., a signal processor, a microprocessor, an ASIC, or other control and processing logic circuit) for performing tasks such as signal encoding, data processing, input / output processing, power control, and / or other functions. An operating system 1112 may control the allocation and use of the components 1102 and support for one or more applications 1114 (also referred to as applications). The applications 1114 may include common mobile computing applications (e.g., email applications, calendars, contact managers, web browsers, messaging applications) and any other computing applications (e.g., word processing applications, mapping applications, media player applications).

[0110] The mobile device 1100 may include a memory 1120. The memory 1120 may include a non-removable memory 1122 and / or a removable memory 1124. The non-removable memory 1122 may include a RAM (random access memory), a ROM (read-only memory), a flash memory, a hard disk, or other well-known memory storage technologies. The removable memory 1124 may include a flash memory or a Subscriber Identity Module (SIM) card well-known in the GSM communication system, or other well-known memory storage technologies such as "smart cards". The memory 1120 may store data and / or code for running the operating system 1112 and the application 1114. Example data may include web pages, text, images, sound files, video data, or other data sets to be sent to or received from one or more web servers or other devices via one or more wired networks or wireless networks. The memory 1120 may store a subscriber identifier (such as an International Mobile Subscriber Identity (IMSI)) and an equipment identifier (such as an International Mobile Equipment Identifier (IMEI)). This identifier may be sent to a network server to identify the user and device.

[0111] The mobile device 1100 may support one or more input devices 1130 (such as a touch screen 1132, a microphone 1134, a camera 1136, a physical keyboard 1138, and / or a trackball 1140) and one or more output devices 1150 (such as a speaker 1152 and a display 1154). A touch screen (such as touch screen 1132) may detect input in different ways. For example, a capacitive touch screen detects a touch input when an object (e.g., a fingertip) distorts or interrupts the current flowing through the surface. As another example, a touch screen may use an optical sensor to detect a touch input when a light beam from the optical sensor is interrupted. Physical contact with the screen surface is not necessary for some touch screens to detect input. For example, the touch screen 1132 may support finger hover detection using capacitive sensing, which is well known in the art. Other detection techniques may be used, including (but not limited to) camera-based detection and ultrasonic-based detection. To implement finger hovering, the user's finger is typically within a predetermined spacing distance above the touch screen, such as between 0.1 inches and 0.25 inches, or between 0.25 inches and 0.5 inches, or between 0.5 inches and 0.75 inches, or between 0.75 inches and 1 inch, or between 1 inch and 1.5 inches, etc.

[0112] The mobile device 1100 may include latency reduction logic 1192. The latency reduction logic 1192 is configured to reduce the latency of changing the operating state of the processor 1110 from a low power state to a normal power state according to any one or more of the techniques described herein. The latency reduction logic 1192 may be incorporated into (a plurality of) suitable components 1102. For example, the latency reduction logic 1192 may be partially or fully incorporated into the processor 1110, the non-removable memory 1122, the operating system 1112, etc.

[0113] Other possible output devices (not shown) may include piezoelectric output devices or other tactile output devices. Some devices may provide more than one input / output function. For example, touch screen 1132 and display 1154 may be combined in a single input / output device. Input device 1130 may include a natural user interface (Natural User Interface, NUI). NUI is any interface technology that enables a user to interact with a device in a "natural" way, without being subject to artificial constraints imposed by input devices such as a mouse, keyboard, remote control, etc. Examples of NUI methods include methods that rely on speech recognition, touch and stylus recognition, gesture recognition on and near the screen, air gestures, head and eye tracking, voice and speech, vision, touch, gestures, and machine intelligence. Other examples of NUI include motion gesture detection using accelerometers / gyroscopes, facial recognition, 3D display, head eye gaze tracking, immersive augmented reality and virtual reality systems (all of which provide more natural interfaces) and technologies for sensing brain activity using electric field sensing electrodes (EEG (electroencephalogram, electroencephalogram) and related methods). Thus, in one specific example, the operating system 1112 or the applications 1114 may include voice recognition software that allows a user to operate the mobile device 1100 via voice commands as part of a voice control interface. Additionally, the mobile device 1100 may include input devices and software that allow user interaction via the user's spatial gestures, such as detecting and interpreting gestures to provide input to a gaming application.

[0114] Wireless modem(s) 1170 may be coupled to antenna(s) (not shown) and may support bidirectional communications between processor 1110 and external devices as is well known in the art. Modem(s) 1170 are shown generically and may include a modem for communicating with mobile communication network 1104 and / or other radio-based modems (e.g., The wireless modem 1170 may be a cellular modem 1176 configured to communicate with a wireless modem 1174 and / or Wi-Fi 1172. At least one of the wireless modems 1170 is typically configured to communicate with one or more cellular networks, such as a GSM network for data and voice communications within a single cellular network, between cellular networks, or between a mobile device and a public switched telephone network (PSTN).

[0115] The mobile device may also include at least one input / output port 1180, a power source 1182, a satellite navigation system receiver 1184 (such as a global positioning system (GPS) receiver), an accelerometer 1186, and / or a physical connector 1190 (which may be a USB (universal serial bus) port, an IEEE 1394 (Firewire) port, and / or an RS-232 port). As will be appreciated by those skilled in the art, the components 1102 shown are not required or all-inclusive, as any components may be deleted and other components may be added.

[0116] Although the operations of some disclosed methods are described in a particular order for ease of presentation, it should be understood that such description encompasses rearrangement unless the specific language set forth herein requires a particular ordering. For example, the operations described in sequence may be rearranged or performed simultaneously in some cases. In addition, for simplicity, the accompanying drawings may not illustrate the various ways in which the disclosed methods may be used in conjunction with other methods.

[0117] Delay reduction logic 122, delay reduction logic 124, delay reduction logic 522, state controller 552, packet conversion logic 554, time determination logic 556, time selection logic 558, delay reduction logic 724, state controller 772, attribute selection logic 774, packet processing logic 776, delay reduction logic 1024, state controller 1072, packet processing logic 1076, activity diagram 300, flowchart 400, flowchart 600, activity diagram 800 and / or flowchart 900 can be implemented in hardware, software, firmware or any combination thereof.

[0118] For example, any one or more of the latency reduction logic 122, latency reduction logic 124, latency reduction logic 522, state controller 552, packet conversion logic 554, time determination logic 556, time selection logic 558, latency reduction logic 724, state controller 772, attribute selection logic 774, packet processing logic 776, latency reduction logic 1024, state controller 1072, packet processing logic 1076, activity diagram 300, flowchart 400, flowchart 600, activity diagram 800 and / or flowchart 900 may be at least partially implemented as computer program code configured to be executed in one or more processors.

[0119] In another example, any one or more of the delay reduction logic 122, the delay reduction logic 124, the delay reduction logic 522, the state controller 552, the packet conversion logic 554, the time determination logic 556, the time selection logic 558, the delay reduction logic 724, the state controller 772, the attribute selection logic 774, the packet processing logic 776, the delay reduction logic 1024, the state controller 1072, the packet processing logic 1076, the activity diagram 300, the flowchart 400, the flowchart 600, the activity diagram 800 and / or the flowchart 900 may be at least partially implemented as a hardware logic / electrical circuit. Such a hardware logic / electrical circuit may include one or more hardware logic components. Examples of hardware logic components include, but are not limited to, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on chip (SoCs), complex programmable logic devices (CPLDs), etc. For example, an SoC may include an integrated circuit chip. An integrated circuit chip includes one or more of the following: a processor (e.g., a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or other circuits and / or embedded firmware to perform its functions.

[0120] III. Further Discussion of Some Example Embodiments

[0121] (A1) A method for reducing the processor ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) of an example hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12, 1250) includes a memory ( Fig.11 , 1120; Fig.12 , 1204, 1208, 1210) and a processing system ( Fig.11 , 1110; Fig.12 , 1202). The processing system is configured to: at least partially based on the network ( Figure 1 ,104)Received network packet ( Figure 1 , 116; Figure 5 , 516), in a transaction layer packet based at least in part on a network packet ( Figure 1 , 120; Figure 5 , 520) is provided to the processor by the hardware system by asynchronously providing a notification to the processor at a first time instance ( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518) to trigger ( Figure 3 , 332; Figure 4 , 404) a change in the operating state of the processor from a low power state to a normal power state. The notification indicates that the transaction layer packet will be provided to the processor at a second time instance after the first time instance in time. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The processing system is further configured to cause ( Figure 3 , 340; Figure 4 , 406) transaction layer packets are processed under normal power state.

[0122] (A2) In the example hardware system of A1, wherein the notification indicates an amount of time between a first time instance at which the notification is asynchronously provided to the processor and a second time instance at which the transaction layer packet is to be provided to the processor.

[0123] (A3) In the example hardware system of any of A1-A2, the processor system is configured to: asynchronously provide a notification to the processor before the hardware system completes processing of the network packet.

[0124] (A4) In the example hardware system of any of items A1-A3, the processor system is further configured to: determine an amount of time it will take the hardware system to complete processing of the network packet; and select a first time instance in which a notification is provided to the processor based at least in part on the amount of time.

[0125] (A5) In the example hardware system of any of A1-A4, the processor system is configured to: complete processing of the network packet to generate a transaction layer packet; and provide the transaction layer packet to the processor at a second time instance based at least in part on the completed processing of the network packet.

[0126] (A6) In the example hardware system of any of A1-A5, the processor system is configured to trigger the processor to increase the frequency at which the processor operates by asynchronously providing a notification to the processor at a first time instance.

[0127] (A7) In the example hardware system of any of A1-A6, the processor system is configured to trigger the processor to increase a voltage of a clock used by the processor to perform an operation by asynchronously providing a notification to the processor at a first time instance.

[0128] (A8) In the example hardware system of any of A1-A7, the processor system is configured to trigger the processor to switch a portion of the processor from an off state to an on state by asynchronously providing a notification to the processor at a first time instance.

[0129] (A9) In the example hardware system of any one of items A1-A8, it also includes: a peripheral component interconnect express (PCIe) WAKE# pin; wherein the processor system is configured to: asynchronously provide a notification to the processor via the PCIe WAKE# pin at a first time instance.

[0130] (A10) In the example hardware system of any one of items A1-A9, the processor system is configured to: asynchronously provide a notification to the processor via a first connection at a first time instance, the first connection being included in a plurality of connections that connect a plurality of corresponding hardware systems to the processor via a Boolean "OR" gate.

[0131] (B1) A method for reducing the number of processor systems ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) of a first example computing system ( Figure 1 , 106; Figure 2 , 200; Figure 3 , 300; Fig.11 , 1102; Fig.12 , 1200) includes a memory ( Fig.11 , 1120; Fig.12, 1204, 1208, 1210) and a processor system coupled to the memory. The processor system is configured to, at a first time instance, receive data from the hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12 , 1250)Receive( Figure 3 , 332; Figure 6 , 602) Notification( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518). The notification indication is based at least in part on the network packet ( Figure 1 , 116; Figure 5 , 516) transaction layer grouping ( Figure 1 , 120; Figure 5 , 520) will be received by the processor system from the hardware system at a second time instance after the first time instance in time. The processor system is also configured to: change the operating state of the processor system from the low power state ( Figure 3 , 334; Figure 6 , 604) is a normal power state. The low power state is configured to cause the processor system to consume a first amount of power. The normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. The processor system is also configured to receive ( Figure 3 , 340; Figure 6 , 606) transaction layer packet. The processor system is further configured to: based at least in part on receiving the transaction layer packet at the second time instance, process ( Figure 3 , 342; Figure 6 , 608) transaction layer grouping.

[0132] (B2) In the example computing system of B1, the processor system is configured to: change the operating state of the processor system from the low power state to the normal power state before receiving the transaction layer packet from the hardware system at the second time instance.

[0133] (B3) In an example computing system of any of items B1-B2, wherein the notification indicates an amount of time between a first time instance at which the processor system receives the notification from the hardware system and a second time instance at which the processor system will receive a transaction layer packet from the hardware system; and wherein the processor system is configured to: select an attribute of the processor system from a plurality of attributes of the processor system to be changed based at least in part on the processor system being able to change the attribute of the processor system from a first value to a second value within the amount of time between the first time instance and the second time instance; and change an operating state of the processor system from a low power state to a normal power state by changing the selected attribute of the processor system from the first value to the second value.

[0134] (B4) In the example computing system of any of items B1-B3, the processor system is configured to: change the operating state of the processor system by increasing the frequency at which the processor system operates, based at least in part on receiving the notification.

[0135] (B5) In the example computing system of any of items B1-B4, the processor system is configured to: change the operating state of the processor system by increasing the voltage of a clock used by the processor system to perform operations, at least in part based on receiving the notification.

[0136] (B6) In the example computing system of any of items B1-B5, the processor system is configured to: change the operating state of the processor system by switching a portion of the processor system from an off state to an on state based at least in part on receiving the notification.

[0137] (B7) In the example computing system of any of items B1-B6, wherein the processor system includes: a peripheral component interconnect express (PCIe) WAKE# pin; and wherein the processor system is configured to: receive a notification from the hardware system via the PCIe WAKE# pin at a first time instance.

[0138] (B8) In the example computing system of any of items B1-B7, the processor system is configured to: receive a notification from a hardware system via a first connection at a first time instance, the first connection being included in a plurality of connections that connect a plurality of corresponding hardware systems to the processor system via a Boolean OR gate.

[0139] (B9) In the example computing system of any of items B1-B8, the processor system is configured to: instruct the hardware system to perform a specified task based at least in part on receiving a transaction layer packet.

[0140] (C1) A method for reducing the number of processor systems ( Figure 1 , 110; Figure 2 , 210; Figure 8 , 810; Fig.10 , 1000; Fig.11 , 1110; Fig.12 , 1202) of a second example computing system ( Figure 1 , 106; Figure 2 , 200; Figure 8 , 806; Fig.11 , 1102; Fig.12 , 1200) includes a memory ( Fig.11 , 1120; Fig.12 , 1204, 1208, 1210) and a processor system coupled to the memory. The processor system is configured to receive data from the hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 8 , 808; Fig.12 , 1250)Receive( Figure 8 , 840; Fig. 9 , 902) based at least in part on a network packet ( Figure 1 , 116) transaction layer grouping ( Figure 1 , 120; Fig.10 , 1020). The processor system is further configured to: trigger (based at least in part on receiving the transaction layer packet, and regardless of the extent to which the processor system is utilized) Figure 8 , 834; Fig. 9 , 904) a change in the operating state of the processor system from a low power state to a normal power state. The low power state is configured to cause the processor system to consume a first amount of power. The normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. The processor system is also configured to process ( Figure 8 , 842; Fig. 9 , 906) transaction layer grouping.

[0141] (C2) In the example computing system of C1, the processor system is configured to trigger a change in the operating state of the processor system by increasing a frequency at which the processor system operates.

[0142] (C3) In the example computing system of any of items C1-C2, the processor system is configured to trigger a change in the operating state of the processor system by increasing a voltage of a clock used by the processor system to perform operations.

[0143] (C4) In the example computing system of any of items C1-C3, the processor system is configured to trigger a change in the operating state of the processor system by switching a portion of the processor system from an off state to an on state.

[0144] (C5) In the example computing system of any of items C1-C4, wherein the processor system is configured to: trigger a change in an operating state of the processor system from a low power state to a normal power state before the processor system decodes the transaction layer packet.

[0145] (C6) In the example computing system of any of C1-C5, the processor system is configured to: instruct the hardware system to perform a specified task based at least in part on receiving the transaction layer packet.

[0146] (D1) A method of reducing the processor ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) of the operating state from a low power state to a normal power state. The method is composed of a hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12 , 1250) is implemented. The method includes: via a network ( Figure 1 , 104) receive ( Figure 3 , 330; Figure 4 , 402) network packet ( Figure 1 , 116; Figure 5 , 516). The method further includes: based at least in part on receiving the network packet, in a transaction layer packet ( Figure 1 , 120; Figure 5 , 520) is provided to the processor by the hardware system by asynchronously providing a notification to the processor at a first time instance ( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518) to trigger ( Figure 3 , 332; Figure 4 , 404) a change in the operating state of the processor from a low power state to a normal power state. The notification indicates that the transaction layer packet will be provided to the processor at a second time instance after the first time instance in time. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The method further includes causing ( Figure 3 , 340; Figure 4 , 406) transaction layer packets are processed under normal power state.

[0147] (D2) In the method of D1, wherein the notification indicates an amount of time between a first time instance at which the notification is asynchronously provided to the processor and a second time instance at which the transaction layer packet is to be provided to the processor.

[0148] (D3) In the method of any of D1-D2, wherein asynchronously providing the notification to the processor includes: asynchronously providing the notification to the processor before the hardware system completes processing of the network packet.

[0149] (D4) In the method of any one of items D1-D3, it also includes: determining the amount of time it will take for the hardware system to complete processing of the network data packet; and selecting a first time instance at which a notification will be provided to the processor based at least in part on the amount of time.

[0150] (D5) In the method of any one of D1-D4, it also includes: completing processing of the network packet to generate a transaction layer packet; wherein the transaction layer packet is provided to the processor at a second time instance at least partially based on the completion of the processing of the network packet.

[0151] (D6) In the method of any one of D1-D5, wherein triggering a change in the operating state of the processor includes: triggering the processor to increase the frequency at which the processor operates by asynchronously providing a notification to the processor at a first time instance.

[0152] (D7) In the method of any one of D1-D6, wherein triggering a change in the operating state of the processor includes: triggering the processor to increase a voltage of a clock used by the processor to perform operations by asynchronously providing a notification to the processor at a first time instance.

[0153] (D8) In the method of any one of D1-D7, wherein triggering a change in the operating state of the processor includes: triggering the processor to switch a portion of the processor from an off state to an on state by asynchronously providing a notification to the processor at a first time instance.

[0154] (D9) In the method of any one of items D1-D8, wherein triggering a change in the operating state of the processor from a low power state to a normal power state includes: asynchronously providing a notification to the processor via a Peripheral Component Interconnect Express (PCIe) WAKE# pin of the hardware system at a first time instance.

[0155] (D10) In the method of any one of items D1-D9, wherein triggering a change in the operating state of the processor from a low power state to a normal power state includes: asynchronously providing a notification to the processor via a first connection at a first time instance, the first connection being included in a plurality of connections that connect a plurality of corresponding hardware systems to the processor via a Boolean "OR" gate.

[0156] (E1) A method for reducing the number of processor systems ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) from a low power state to a normal power state. The method is implemented by a processor system. The method includes: at a first time instance, from a hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12 , 1250)Receive( Figure 3 , 332; Figure 6 , 602) Notification( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518). The notification indication is based at least in part on the network packet ( Figure 1 , 116; Figure 5 , 516) transaction layer grouping ( Figure 1 , 120; Figure 5 , 520) will be received by the processor system from the hardware system at a second time instance after the first time instance in time. The method also includes: at least in part based on receiving the notification, changing the operating state of the processor system from a low power state ( Figure 3 , 334; Figure 6 , 604) is a normal power state, wherein the low power state is configured to cause the processor system to consume a first amount of power, wherein the normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. The method further includes: receiving ( Figure 3 , 340; Figure 6 , 606) a transaction layer packet. The method further includes: processing ( Figure 3 , 342; Figure 6 , 608) transaction layer grouping.

[0157] (E2) In the method of E1, wherein changing the operating state of the processor system includes: changing the operating state of the processor system from a low power state to a normal power state before receiving the transaction layer packet from the hardware system at the second time instance.

[0158] (E3) In the method of any of items E1-E2, wherein the notification indicates the amount of time between a first time instance at which the processor system receives the notification from the hardware system and a second time instance at which the processor system will receive a transaction layer packet from the hardware system; wherein the method further comprises: selecting an attribute of the processor system from a plurality of attributes of the processor system to be changed based at least in part on the ability of the processor system to change the attribute of the processor system from a first value to a second value within the amount of time between the first time instance and the second time instance; and wherein changing the operating state of the processor system comprises: changing the operating state of the processor system from a low power state to a normal power state by changing the selected attribute of the processor system from a first value to a second value.

[0159] (E4) In the method of any one of items E1-E3, changing the operating state of the processor system includes: increasing the frequency at which the processor system operates.

[0160] (E5) In the method of any one of items E1-E4, changing the operating state of the processor system includes: increasing the voltage of a clock used by the processor system to perform operations.

[0161] (E6) In the method of any one of items E1-E5, changing the operating state of the processor system includes: switching a portion of the processor system from an off state to an on state.

[0162] (E7) In the method of any of items E1-E6, wherein receiving the notification from the hardware system includes: receiving the notification from the hardware system via a peripheral component interconnect express (PCIe) WAKE# pin of the processor system at a first time instance.

[0163] (E8) In the method of any one of items E1-E7, wherein receiving a notification from a hardware system includes: receiving a notification from the hardware system via a first connection at a first time instance, the first connection being included in a plurality of connections that connect a plurality of corresponding hardware systems to a processor system via a Boolean OR gate.

[0164] (E9) In the method of any of E1-E8, wherein processing the transaction layer packet includes: instructing the hardware system to perform a specified task based at least in part on receiving the transaction layer packet.

[0165] (F1) A method for reducing the number of processor systems ( Figure 1 , 110; Figure 2 , 210; Figure 8 , 810; Fig.10 , 1000; Fig.11 , 1110; Fig.12, 1202) changes from a low power state to a normal power state. The method is implemented by a processor system. The method includes: from a hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 8 , 808; Fig.12 , 1250)Receive( Figure 8 , 840; Fig. 9 , 902) based at least in part on a network packet ( Figure 1 , 116) transaction layer grouping ( Figure 1 , 120; Fig.10 , 1020). The method further includes: triggering (based at least in part on receiving the transaction layer packet and without regard to the degree to which the processor system is utilized Figure 8 , 834; Fig. 9 , 904) changing the operating state of the processor system from a low power state to a normal power state. The low power state is configured to cause the processor system to consume a first amount of power. The normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power. The method further includes: processing ( Figure 8 , 842; Fig. 9 , 906) transaction layer grouping.

[0166] (F2) In the method of F1, triggering a change in the operating state of the processor system includes: increasing the frequency at which the processor system operates.

[0167] (F3) In the method of any one of F1-F2, triggering a change in the operating state of the processor system includes: increasing a voltage of a clock used by the processor system to perform operations.

[0168] (F4) In the method of any one of F1-F3, triggering a change in the operating state of the processor system includes: switching a portion of the processor system from an off state to an on state.

[0169] (F5) In the method of any one of F1-F4, triggering a change in the operating state of the processor system includes: triggering a change in the operating state of the processor system from a low power state to a normal power state before the processor system decodes the transaction layer packet.

[0170] (F6) In the method of any of F1-F5, processing the transaction layer packet includes: instructing the hardware system to perform a specified task based at least in part on receiving the transaction layer packet.

[0171] (G1) A first example computer program product ( Fig.11 , 1124; Fig.12, 1218, 1222) includes a computer-readable storage medium having recorded thereon instructions for causing a processor-based system ( Figure 1 , 106; Figure 2 , 200; Figure 8 , 806; Fig.11 , 1102; Fig.12 , 1200) can reduce the number of processors included in a processor-based system by performing operations ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) changes its operating state from a low power state to a normal power state. The operation includes: via a network ( Figure 1 , 104) A hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12 , 1250) receives the network packet ( Figure 1 , 116; Figure 5 , 516). The operations also include: receiving the network packet at the hardware system at least in part, in a transaction layer packet ( Figure 1 , 120; Figure 5 , 520) is provided to the processor by the hardware system by asynchronously providing a notification to the processor at a first time instance ( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518) to trigger ( Figure 3 , 332; Figure 4 , 404) a change in an operating state of the processor from a low power state to a normal power state. The notification indicates that a transaction layer packet will be provided to the processor at a second time instance after the first time instance in time. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The operations also include causing ( Figure 3 , 340; Figure 4 , 406) The transaction layer packet is processed by the processor in a normal power state.

[0172] (H1) A second example computer program product (FIG. 16, 1618, 1622) includes a computer-readable storage medium having recorded thereon instructions for causing a processor-based system ( Figure 1 , 106; Figure 2 , 200; Figure 3 , 300; Fig.11 , 1102; Fig.12 , 1200) can reduce the number of processors included in a processor-based system by performing operations ( Figure 1 , 110; Figure 2 , 210; Figure 3 , 310; Figure 7 , 700; Fig.11 , 1110; Fig.12 , 1202) changes from a low power state to a normal power state. The operation includes: at a first time instance, at a processor, from a hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 3 , 308; Figure 5 , 500; Fig.12 , 1250)Receive( Figure 3 , 332; Figure 6 , 602) Notification( Figure 1 , 118; Figure 2 , 218; Figure 5 , 518). The notification indication is based at least in part on the network packet ( Figure 1 , 116; Figure 5 , 516) transaction layer grouping ( Figure 1 , 120; Figure 5 , 520) will be received by the processor from the hardware system at a second time instance after the first time instance in time. The operation also includes: at least in part based on receiving the notification at the processor, changing the operating state of the processor from a low power state ( Figure 3 , 334; Figure 6 , 604) is a normal power state. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The operations also include: receiving at the processor from the hardware system at a second time instance ( Figure 3 , 340; Figure 6 , 606) a transaction layer packet. The operations also include: processing ( Figure 3 , 342; Figure 6 , 608)'s transaction layer grouping.

[0173] (I1) A third example computer program product (FIG. 16, 1618, 1622) includes a computer-readable storage medium having recorded thereon instructions for causing a processor-based system ( Figure 1 , 106; Figure 2 , 200; Figure 8 , 806; Fig.11 , 1102; Fig.12 , 1200) can reduce the number of processors included in a processor-based system by performing operations ( Figure 1 , 110; Figure 2 , 210; Figure 8 , 810; Fig.10 , 1000; Fig.11 , 1110; Fig.12 , 1202) changes its operating state from a low power state to a normal power state. The operation includes: the processor changes the hardware system ( Figure 1 , 108; Figure 2 , 208A-208N; Figure 8 , 808; Fig.12 , 1250)Receive( Figure 8 , 840; Fig. 9 , 902) based at least in part on a network packet ( Figure 1 , 116) transaction layer grouping ( Figure 1 , 120; Fig.10 , 1020). The operations further include: triggering (based at least in part on the processor receiving the transaction layer packet and without regard to the degree to which the processor is utilized) Figure 8 , 834; Fig. 9 , 904) the operating state of the processor changes from a low power state to a normal power state. The low power state is configured to cause the processor to consume a first amount of power. The normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power. The operation also includes: processing by the processor in the normal power state ( Figure 8 , 842; Fig. 9 , 906) transaction layer grouping.

[0174] IV. Example Computer System

[0175] Fig.12 An example computer 1200 is depicted in which embodiments may be implemented. Figure 1 The first computing device 102 and / or the second computing device 106 shown, Figure 2 The computing device 200 shown, Figure 3 The first computing device 302 and / or the second computing device 306 shown, and / or Figure 8Any one or more of the illustrated first computing device 802 and / or second computing device 806 may be implemented using computer 1200 (including one or more features and / or alternative features of computer 1200). Computer 1200 may be a general-purpose computing device in the form of, for example, a conventional personal computer, a mobile computer, or a workstation, or computer 1200 may be a special-purpose computing device. The description of computer 1200 provided herein is provided for purposes of illustration and not for limitation. As known to those skilled in the relevant art(s), embodiments may be implemented in other types of computer systems.

[0176] like Fig.12 As shown, computer 1200 includes a processing unit 1202, a system memory 1204, and a bus 1206 that couples various system components including the system memory 1204 to the processing unit 1202. Bus 1206 represents any one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. System memory 1204 includes read-only memory (ROM) 1208 and random access memory (RAM) 1210. Basic input / output system (BIOS) 1212 is stored in ROM 1208.

[0177] The computer 1200 also has one or more of the following drives: a hard disk drive 1214 for reading and writing a hard disk, a disk drive 1216 for reading and writing a removable disk 1218, and an optical drive 1220 for reading and writing a removable optical disk 1222 such as a CD ROM, DVD ROM or other optical media. The hard disk drive 1214, the disk drive 1216, and the optical drive 1220 are connected to the bus 1206 via a hard disk drive interface 1224, a disk drive interface 1226, and an optical drive interface 1228, respectively. The drives and their associated computer-readable storage media provide non-volatile storage of computer-readable instructions, data structures, program modules, and other data for the computer. Although a hard disk, a removable disk, and a removable optical disk are described, other types of computer-readable storage media such as flash memory cards, digital video disks, random access memory (RAM), read-only memory (ROM), etc. may also be used to store data.

[0178] A plurality of program modules may be stored on a hard disk, a magnetic disk, an optical disk, a ROM or a RAM. These programs include an operating system 1230 , one or more application programs 1232 , other program modules 1234 and program data 1236 . The application 1232 or program module 1234 may include, for example, computer program logic for implementing any one or more (e.g., at least a portion) of the following as described herein: latency reduction logic 122, latency reduction logic 124, latency reduction logic 522, state controller 552, packet conversion logic 554, time determination logic 556, time selection logic 558, latency reduction logic 724, state controller 772, attribute selection logic 774, packet processing logic 776, latency reduction logic 1024, state controller 1072, packet processing logic 1076, activity diagram 300 (including any activity of activity diagram 300), flowchart 400 (including any step of flowchart 400), flowchart 600 (including any step of flowchart 600), activity diagram 800 (including any activity of activity diagram 800), and / or flowchart 900 (including any step of flowchart 900).

[0179] A user may enter commands and information into the computer 1200 through input devices such as a keyboard 1238 and a pointing device 1240. Other input devices (not shown) may include a microphone, a joystick, a game controller, a satellite dish, a scanner, a touch screen, a camera, an accelerometer, a gyroscope, etc. These and other input devices are often connected to the processing unit 1202 through a serial port interface 1242 coupled to the bus 1206, but may be connected through other interfaces such as a parallel port, a game port, or a universal serial bus (USB).

[0180] A display device 1244 (eg, a monitor) is also connected to the bus 1206 via an interface, such as a video adapter 1246. In addition to the display device 1244, the computer 1200 may also include other peripheral output devices (not shown), such as speakers and printers.

[0181] The computer 1200 is connected to a network 1248 (eg, the Internet) through a network interface or adapter 1250, a modem 1252, or other means for establishing communications over the network. The modem 1252 (which may be internal or external) is connected to the bus 1206 via the serial port interface 1242.

[0182] As used herein, the terms "computer program medium" and "computer readable storage medium" are used to generally refer to media (e.g., non-transitory media) such as a hard disk associated with hard disk drive 1214, removable disk 1218, removable optical disk 1222, and other media such as flash memory cards, digital video disks, random access memory (RAM), read-only memory (ROM), etc. A computer-readable storage medium is not a signal, such as a carrier signal or a propagating signal. For example, a computer-readable storage medium may not include a signal. Accordingly, a computer-readable storage medium itself does not constitute a signal. Such a computer-readable storage medium is distinguished from a communication medium and does not overlap with a communication medium (does not include a communication medium). A communication medium embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier. The term "modulated data signal" means a signal that sets or changes one or more of its characteristics in a manner that encodes information in the signal. By way of example and not limitation, communication media include wireless media (such as acoustic media, RF media, infrared media, and other wireless media) and wired media. Example embodiments are also directed to such communication media.

[0183] As described above, computer programs and modules (including application programs 1232 and other program modules 1234) can be stored on a hard disk, disk, optical disk, ROM or RAM. Such computer programs can also be received via network interface 1250 or serial port interface 1242. When executed or loaded by an application, such computer programs enable computer 1200 to implement the features of the embodiments discussed herein. Accordingly, such computer programs represent controllers of computer 1200.

[0184] Example embodiments are also directed to a computer program product comprising software (e.g., computer-readable instructions) stored on any computer-usable medium. When executed in one or more data processing devices, such software causes (multiple) data processing devices to operate as described herein. Embodiments may employ any computer-usable or computer-readable medium known now or in the future. Examples of computer-readable media include, but are not limited to, storage devices such as RAM, hard disk drives, floppy disks, CD ROMs, DVD ROMs, compact disks, magnetic storage devices, optical storage devices, storage devices based on MEMS (Micro ElectroMechanical System, micro-electromechanical systems), storage devices based on nanotechnology, and the like.

[0185] It will be appreciated that the disclosed technology is not limited to any particular computer or hardware type. Certain details of suitable computers and hardware are well known and need not be set forth in detail in this disclosure.

[0186] V. Conclusion

[0187] Although the subject matter has been described in language specific to structural features and / or actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as examples of implementing the claims, and other equivalent features and actions are intended to fall within the scope of the claims.

Claims

1. A hardware system for reducing the delay of changing the operating state of a processor from a low power state to a normal power state, the hardware system comprising: Memory; as well as a processor system coupled to the memory, the processor system being configured to: triggering a change in the operating state of the processor from the low-power state to the normal power state by asynchronously providing a notification to the processor at a first time instance before providing a transaction layer packet based at least in part on the network packet to the processor by the hardware system based at least in part on the network packet, the notification indicating that the transaction layer packet will be provided to the processor at a second time instance that is temporally subsequent to the first time instance, wherein the low-power state is configured to cause the processor to consume a first amount of power, and wherein the normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power; as well as The transaction layer packet is caused to be processed in the normal power state by providing the transaction layer packet to the processor at the second time instance.

2. The hardware system of claim 1, wherein the notification indicates an amount of time between the first time instance at which the notification is asynchronously provided to the processor and the second time instance at which the transaction layer packet is to be provided to the processor.

3. The hardware system according to any one of claims 1 to 2, wherein the processor system is configured as: The notification is provided to the processor asynchronously prior to completion of processing of the network packet by the hardware system.

4. The hardware system according to any one of claims 1 to 3, wherein the processor system is further configured to: determining an amount of time consumed to complete processing of the network packet by the hardware system; and The first time instance at which the notification is provided to the processor is selected based at least in part on the amount of time.

5. The hardware system of any one of claims 1 to 4, wherein the processor system is configured to perform at least one of the following by asynchronously providing the notification to the processor at a first time instance: triggering the processor to increase the frequency at which the processor operates; triggering the processor to increase a voltage of a clock used to perform operations by the processor; Triggering the processor switches a portion of the processor from an off state to an on state.

6. The hardware system according to any one of claims 1 to 5, further comprising: Peripheral Component Interconnect Express (PCIe) WAKE# pin; The processor system is configured to: The notification is provided asynchronously to the processor via the PCIe WAKE# pin at the first time instance.

7. The hardware system according to any one of claims 1 to 6, wherein the processor system is configured to: At the first time instance, the notification is asynchronously provided to the processor via a first connection, the first connection being included in a plurality of connections connecting a plurality of respective hardware systems to the processor via a Boolean OR gate.

8. A method of reducing a delay in changing an operating state of a processor system from a low power state to a normal power state, the method being implemented by the processor system, the method comprising: receiving a notification from a hardware system at a first time instance, the notification indicating that a transaction layer packet will be received by the processor system from the hardware system at a second time instance that is subsequent in time to the first time instance, the transaction layer packet being based at least in part on a network packet; based at least in part on receiving the notification, changing the operating state of the processor system from the low power state to the normal power state, wherein the low power state is configured to cause the processor system to consume a first amount of power, wherein the normal power state is configured to cause the processor system to consume a second amount of power greater than the first amount of power; receiving the transaction layer packet from the hardware system at the second time instance; as well as The transaction layer packet is processed in the normal power state based at least in part on receiving the transaction layer packet at the second time instance.

9. The method of claim 8, wherein changing the operating state of the processor system comprises: The operating state of the processor system is changed from the low power state to the normal power state before the transaction layer packet is received from the hardware system at the second time instance.

10. The method of any one of claims 8 to 9, wherein the notification indicates an amount of time between a first time instance at which the notification is received by the processor system from the hardware system and a second time instance at which the transaction layer packet is to be received by the processor system from the hardware system; The method further comprises: selecting the property of the processor system from a plurality of properties of the processor system to be changed based at least in part on the processor system being able to change the property of the processor system from a first value to a second value within the amount of time between the first time instance and the second time instance; and Wherein changing the operating state of the processor system comprises: The operating state of the processor system is changed from the low power state to the normal power state by changing the selected attribute of the processor system from the first value to the second value.

11. The method according to any one of claims 8 to 10, wherein changing the operating state of the processor system comprises at least one of the following: increasing the frequency at which the processor system operates; increasing a voltage of a clock used by the processor system to perform operations; Switching a portion of the processor system from an off state to an on state.

12. The method of any one of claims 8 to 11, wherein receiving the notification from the hardware system comprises: The notification is received from the hardware system via a peripheral component interconnect express (PCIe) WAKE# pin of the processor system at the first time instance.

13. The method of any one of claims 8 to 12, wherein receiving the notification from the hardware system comprises: At the first time instance, the notification is received from the hardware system via a first connection included in a plurality of connections connecting a plurality of corresponding hardware systems to the processor system via a Boolean OR gate.

14. A computer program product comprising a computer-readable storage medium having recorded thereon instructions for enabling a processor-based system to reduce a latency of changing an operating state of a processor included in the processor-based system from a low power state to a normal power state by performing operations comprising: receiving, by the processor, from a hardware system a transaction layer packet based at least in part on a network packet; triggering a change in the operating state of the processor from the low power state to the normal power state based at least in part on receipt of the transaction layer packet by the processor and without regard to the extent to which the processor is utilized, wherein the low power state is configured to cause the processor to consume a first amount of power, wherein the normal power state is configured to cause the processor to consume a second amount of power greater than the first amount of power; as well as The transaction layer packet is processed by the processor in the normal power state.

15. The computer program product of claim 14, wherein the operations comprise: Prior to decoding of the transaction layer packet by the processor system, the change of the operating state of the processor system from the low power state to the normal power state is triggered.