In-chip hardware interconnection structure, chip, server and method

By introducing the connection between the hub and hardware resources into the chip, synchronous interconnection is achieved, and the problem of poor signal transmission timeliness in multi-core joint and synchronous debugging is solved, and the level signal is directly transmitted, improving efficiency and lightweight design.

CN117290278BActive Publication Date: 2024-11-19HEXIN TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311311960.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-10
Publication Date
2024-11-19
Estimated Expiration
2043-10-10

AI Technical Summary

Technical Problem

In the prior art, the hardware solutions for multi-core joint and synchronous debugging have poor signal transmission timeliness and cannot directly transmit level signals due to bus bandwidth problems.

Method used

The hardware interconnection structure in chip is adopted, and the connection between the hub and the hardware resources is achieved through the connection between the hub, synchronous interconnection between the hardware resources is avoided, bus interconnection is directly transmitted, and level signals are not required, and signal encoding and bus asynchronous bridge are not required.

Benefits of technology

It improves the timeliness of signal transmission, reduces the size and weight of the chip, simplifies design, and is suitable for synchronous debugging of large-scale chips.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117290278B_ABST
    Figure CN117290278B_ABST
Patent Text Reader

Abstract

The present application provides an intra-chip hardware interconnection structure, chip, server and method, wherein the intra-chip hardware interconnection structure includes: at least one hub and multiple hardware resources; each of the hardware resources is connected to the hub via a preset number of connecting lines; the hub is configured with at least one resource pool, and the resource pool is related to each of the hardware resources having a synchronous relationship. In the intra-chip hardware interconnection structure of the present application, each hardware resource is connected to the hub via a preset number of connecting lines, and the hub is configured with at least one resource pool to achieve synchronous interconnection between hardware resources through the resource pool. Since there is no need to rely on bus interconnection, there is no need to encode the signal before transmitting it, and the level signal can be transmitted directly. In addition, there is no need for bus asynchronous bridges, signal encoding and other units, so that the chip can be smaller and lighter. At the same time, compared with the signal transmission of the bus, the timeliness is also better.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intra-chip hardware interconnection structure, chip, server and method. Background Art

[0002] The CPU (full name in English: Central Processing Unit, Chinese: Central Processing Unit) core contains Debug&Trace (literally translated as troubleshooting and tracing) hardware resources. After the chip is returned from the manufacturer, it can provide chip designers with a large number of continuous, microscopic integrated circuit electronic signals, which is a key means of locating chip hardware. Chip designers can set trigger conditions at the location of the fault. With the help of on-chip Debug&Trace hardware resources, they can provide circuit changes over a period of time, and accurately capture the conditions before and after the fault. As the scale of chips becomes larger and larger, each chip often contains many CPU cores, and multi-core joint and synchronous debugging has become an increasingly serious problem.

[0003] At present, the solutions to achieve multi-core joint and synchronous debugging mainly include hardware and software solutions. Among them, the hardware solution needs to rely on the CPU inter-core bus for communication, and the level signal needs to be transmitted through the process of encoding, bus bridge, bus, and decoding.

[0004] In the current hardware solution, due to the bus bandwidth problem, there are problems such as poor signal transmission timeliness and inability to directly transmit level signals. Summary of the invention

[0005] The present application provides an intra-chip hardware interconnection structure, chip, server and method to solve the problem that in the current hardware solution for realizing multi-core combination and synchronous debugging, due to the bus bandwidth problem, the signal transmission timeliness is poor and the level signal cannot be directly transmitted.

[0006] The first aspect of the present application provides a hardware interconnection structure within a chip, including:

[0007] at least one hub and a plurality of hardware resources;

[0008] Each of the hardware resources is connected to the hub via a preset number of connection lines;

[0009] At least one resource pool is configured in the hub, and the resource pool is associated with each of the hardware resources having a synchronization relationship.

[0010] Further, in the above-mentioned in-chip hardware interconnection structure, the number of hardware resources is greater than a preset number threshold; there are at least three hubs; the hubs are divided into primary hubs and multi-level hubs; there are multiple primary hubs;

[0011] Each of the hardware resources is connected to a matching primary hub via a preset number of connection lines;

[0012] Each of the primary hubs is connected to the multi-stage hub via a preset number of connection lines.

[0013] Furthermore, in the above-mentioned in-chip hardware interconnection structure, each hardware resource having a deep synchronization relationship is connected to the same primary hub; the deep synchronization relationship is a synchronization relationship in which the number of events synchronously processed by each hardware resource is greater than a preset event number threshold.

[0014] Furthermore, in the above-mentioned on-chip hardware interconnection structure, the hardware resources include: off-chip hardware and on-chip hardware; the on-chip hardware includes at least a processor core;

[0015] The off-chip hardware is connected to the external interface of the primary hub via the preset number of connection lines;

[0016] The hardware in the chip is connected to the internal interface of the primary hub via the preset number of connection lines.

[0017] Further, in the above-mentioned intra-chip hardware interconnection structure, the multi-level hub is configured with multiple resource pools;

[0018] Each resource pool is associated with each hardware resource having a synchronization relationship, and the maximum number of hardware resources involved in the resource pool is the total number of all hardware resources.

[0019] Furthermore, in the above-mentioned in-chip hardware interconnection structure, the number of the hub is one; the number of the hardware resources is at least three;

[0020] The hardware resources are divided into a plurality of hardware resource sets according to a synchronization relationship; a plurality of resource pools are configured in the hub; and the resource pools correspond to the hardware resource sets.

[0021] Further, in the above-mentioned in-chip hardware interconnection structure, the number of hubs is two; the preset number is four; the number of hardware resources is at least four;

[0022] Each of the hardware resources is divided into two hardware resource sets according to a synchronization relationship;

[0023] The hardware resources corresponding to one of the hardware resource sets are connected to one of the hubs via a preset number of connection lines;

[0024] The hardware resources corresponding to another hardware resource set are connected to another hub via a preset number of connection lines.

[0025] A second aspect of the present application provides a chip, wherein the hardware connection structure within the chip is the hardware interconnection structure within the chip as described in any one of the first aspects.

[0026] A third aspect of the present application provides a server, comprising: a mainboard and the chip as described in the second aspect; the chip is arranged on the mainboard.

[0027] A fourth aspect of the present application provides a synchronization test method, based on the server described in the third aspect, the method comprising:

[0028] generating a synchronization test signal in response to a synchronization test instruction input by a user;

[0029] Sending a synchronous test signal to a target hardware resource to be tested and other hardware resources; the synchronous test signal is transmitted from the target hardware resource to other hardware resources via a hub; the other hardware resources have a synchronous relationship with the target hardware resource;

[0030] Receiving integrated circuit electronic signals uploaded by target hardware resources and other hardware resources;

[0031] A synchronization test result is determined based on the integrated circuit electronic signal.

[0032] A fifth aspect of the present application provides a synchronization test device, based on the server described in the third aspect, the device comprising:

[0033] A response module, used for generating a synchronization test signal in response to a synchronization test instruction input by a user;

[0034] A sending module, used for sending a synchronous test signal to a target hardware resource to be tested and other hardware resources; the synchronous test signal is transmitted from the target hardware resource to other hardware resources via a hub; the other hardware resources have a synchronous relationship with the target hardware resource;

[0035] A receiving module, used to receive integrated circuit electronic signals uploaded by target hardware resources and other hardware resources;

[0036] The determination module is used to determine the synchronization test result according to the integrated circuit electronic signal.

[0037] In a sixth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the synchronization test method described in the fourth aspect.

[0038] The seventh aspect of the present application provides a computer program product, including a computer program, which implements the synchronization test method described in the fourth aspect when executed by a processor.

[0039] The present application provides an intra-chip hardware interconnection structure, chip, server and method, wherein the intra-chip hardware interconnection structure includes: at least one hub and multiple hardware resources; each of the hardware resources is connected to the hub via a preset number of connecting lines; the hub is configured with at least one resource pool, and the resource pool is related to each of the hardware resources having a synchronous relationship. In the intra-chip hardware interconnection structure of the present application, each hardware resource is connected to the hub via a preset number of connecting lines, and the hub is configured with at least one resource pool to achieve synchronous interconnection between hardware resources through the resource pool. Since there is no need to rely on bus interconnection, there is no need to encode the signal before transmitting it, and the level signal can be transmitted directly. In addition, there is no need for bus asynchronous bridges, signal encoding and other units, so that the chip can be smaller and lighter. At the same time, compared with the signal transmission of the bus, the timeliness is also better. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] Figure 1 A schematic diagram of the hardware interconnection structure within a chip provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a resource pool in a hub provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a hardware interconnection structure within a chip provided in another embodiment of the present application;

[0044] Figure 4 A schematic diagram of a hardware interconnection structure within a chip provided in yet another embodiment of the present application;

[0045] Figure 5 A schematic diagram of a resource pool in a hub provided in yet another embodiment of the present application;

[0046] Figure 6 A flowchart of a synchronization test method provided in an embodiment of the present application.

[0047] Explanation of symbols:

[0048] 10. Hub; 11. Primary hub; 13. Multi-level hub; 20. Hardware resources.

[0049] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0050] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0051] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0052] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail. At present, the solutions for realizing multi-core joint and synchronous debugging mainly include two solutions: hardware and software. In the software solution, the CPU core needs to initiate a corresponding interrupt to the software, or the software waits in a polling state, and the software controls the operation and stop of multiple CPUs. Although the solution has strong solving ability, it has poor timeliness and accuracy, and cannot accurately and timely locate.

[0053] In the hardware solution, some technologies need to rely on the bus between cores for communication. There is a master and a slave in the CPU core. The master has the ability to encode and can encode some trigger signals into corresponding messages and transfer them to the bus through the bus bridge. The slave has the ability to decode and can translate the messages transmitted by the bus into corresponding triggers, which also requires some bus bridge transitions. Therefore, the level signal cannot be directly transmitted in this solution. If you want to complete similar functions, you need to encode it into at least two messages.

[0054] In addition, due to the influence of bus bandwidth, this technical solution has certain timeliness issues and uncertain propagation delay. At the same time, this technical solution needs to include modules such as Master, Slave, Encoder, Decoder, and Bridge, which occupy more resources. For systems without a bus, this solution is less applicable and requires more additional development work.

[0055] Therefore, in the current hardware solution for realizing multi-core joint and synchronous debugging, due to the problem of bus bandwidth, there are problems such as poor timeliness of signal transmission and inability to directly transmit level signals.

[0056] Therefore, in view of the problem that the signal transmission timeliness is poor and the level signal cannot be directly transmitted in the prior art, the inventor found in the research that in order to solve this problem, based on the idea of ​​not relying on the bus and improving the signal transmission efficiency, it is possible to consider directly connecting the hardware resources in pairs. However, as the chip scale increases and the number of hardware resources increases, it is difficult to achieve the interconnection between the hardware resources in pairs through direct connection, and there is a problem of too many connections. Therefore, the inventor thought of connecting each hardware resource to the HUB to achieve synchronous interconnection between the hardware resources.

[0057] Specifically, the hardware interconnection structure within the chip includes:

[0058] At least one hub and multiple hardware resources.

[0059] Each hardware resource is connected to the hub via a preset number of connection lines.

[0060] At least one resource pool is configured in the hub, and the resource pool is associated with each hardware resource having a synchronization relationship.

[0061] In the hardware interconnection structure within the chip of the present application, each hardware resource is connected to the hub through a preset number of connecting lines, and the hub is configured with at least one resource pool to achieve synchronous interconnection between hardware resources through the resource pool. Since there is no need to rely on bus interconnection, there is no need to encode the signal before transmitting it, and the level signal can be transmitted directly. In addition, there is no need for bus asynchronous bridges, signal encoding and other units, so that the chip can be smaller and lighter. At the same time, compared with the signal transmission of the bus, the timeliness is also better.

[0062] Based on the above creative findings, the inventor proposed the technical solution of the present application.

[0063] The embodiments of the present application are introduced below in conjunction with the drawings in the specification.

[0064] Figure 1 A schematic diagram of the hardware interconnection structure within a chip provided in an embodiment of the present application, Figure 2 A schematic diagram of a resource pool in a hub 10 provided in an embodiment of the present application, such as Figure 1 and Figure 2 As shown, in this embodiment, the hardware interconnection structure in the chip includes:

[0065] At least one hub 10 and a plurality of hardware resources 20 .

[0066] Each hardware resource 20 is connected to the hub 10 via a preset number of connection lines.

[0067] At least one resource pool is configured in the hub 10, and the resource pool is associated with each hardware resource 20 having a synchronization relationship.

[0068] Hub 10 is called HUB in English. It is a multi-port repeater and a pure hardware network underlying device. The main function of hub 10 is to regenerate, shape and amplify the received signal to expand the transmission distance of the network, and at the same time concentrate all nodes on the node centered on it.

[0069] The hardware resources 20 may be a CPU core, chip external devices, bus, audio processing circuit, video processing circuit, L2 memory, etc. The L2 memory is a temporary memory located between the CPU and the memory. Its capacity is smaller than the memory but the exchange speed is faster. The data in the cache is a small part of the memory, but this small part is about to be accessed by the CPU in a short time. When the CPU calls a large amount of data, it can bypass the memory and call directly from the cache, thereby speeding up the reading speed.

[0070] like Figure 1 As shown, each hardware resource 20 is connected to the hub 10 via a preset number of connecting lines, wherein the number of connecting lines (connecting arrows in the figure) is not shown, and the number of connecting lines can be a multiple of 2, such as 4, 8, 12, etc., and can also be set according to actual needs. At the same time, the number of connecting lines corresponding to each hardware resource 20 is the same.

[0071] In the figure, the hardware resources 20 are exemplarily represented by hardware resources a, hardware resources b, hardware resources c to hardware resources n. In actual applications, there is no limit on the number of hardware resources 20. The number of hardware resources 20 connected to the hub 10 and the number of hardware resources 20 existing in the chip can be the same or different.

[0072] Meanwhile, the figure shows only one hub 10 for example, and there may be multiple hubs 10, and hubs may be divided into multiple categories according to their functions. When the number of hardware resources 20 is large, the hub 10 may be divided into a primary hub and a multi-level hub, the hardware resources 20 are connected to the primary hub 10, and the primary hub 10 is connected to the multi-level hub 10.

[0073] Figure 2 The resource pool in the hub 10 is exemplarily shown in the figure. The hub 10 can be configured with multiple resource pools, and each resource pool is related to the synchronization relationship between the hardware resources 20 during configuration. For example, when processing an event such as reading data, hardware resource a and hardware resource b need to be processed synchronously, then hardware resource a and hardware resource b can be divided into the same resource pool.

[0074] Similarly, resource pool 2 and resource pool n can also be divided in the above manner, and different resource pools are isolated from each other and will not interfere with each other.

[0075] Exemplarily, when a new event occurs in hardware resource b in resource pool 2 , it will be broadcast to hardware resource b and hardware resource c in resource pool 2 through hub 10 , but will not be broadcast to hardware resource a in resource pool 1 .

[0076] In actual applications, the number of resource pools may be set according to the number of hardware resources 20 , which can generally meet actual application requirements and may also be adjusted accordingly according to actual applications, which is not limited in this embodiment.

[0077] Optionally, in this embodiment, there is one hub 10 and there are at least three hardware resources 20.

[0078] Each hardware resource 20 is divided into a plurality of hardware resource sets according to a synchronization relationship. A plurality of resource pools are configured in the hub 10. The resource pools correspond to the hardware resource sets.

[0079] In this embodiment, there is only one hub 10 , which is applicable to a situation where the number of hardware resources 20 is small. If the number of hardware resources 20 is large, the number of hubs 10 needs to be increased accordingly.

[0080] The synchronization relationship is that when each hardware resource 20 processes various events, multiple hardware resources 20 need to be coordinated for processing. For example, when performing certain data collection, multiple hardware resources 20 may be required to coordinate. For example, if some data processed by a hardware resource 20 needs to be transferred to a certain hardware resource 20 for further processing, then the two hardware resources 20 have a synchronization relationship. The synchronization relationship can also be debugging the corresponding multiple hardware resources 20 during synchronous debugging.

[0081] Hardware resource collection such as Figure 2 As shown in , the hardware resources a and hardware resources b corresponding to resource pool 1 are one hardware resource set, the hardware resources a, hardware resources b and hardware resources c corresponding to resource pool 2 are another hardware resource set, and the hardware resources b, hardware resources c and hardware resources n corresponding to resource pool n are another hardware resource set.

[0082] The hardware resource sets may contain the same hardware resources 20 or different hardware resources 20. The principle of division is whether there is collaboration between the hardware resources 20 when processing one or some events, that is, whether there is a synchronization relationship.

[0083] Optionally, in this embodiment, there are two hubs 10, the preset number is four, and the number of hardware resources 20 is at least four.

[0084] The hardware resources 20 are divided into two hardware resource sets according to a synchronization relationship.

[0085] The hardware resource 20 corresponding to one of the hardware resource sets is connected to one of the hubs 10 via a preset number of connection lines.

[0086] The hardware resource 20 corresponding to another hardware resource set is connected to another hub 10 via a preset number of connection lines.

[0087] In actual applications, generally, each hardware resource 20 has a certain association. If each hardware resource 20 can be completely divided into two hardware resource sets, the method of this embodiment can be adopted to divide each hardware resource 20 into two hardware resource sets according to a synchronization relationship. Each hardware resource set corresponds to a hub 10, so that the hardware resources 20 that do not have a synchronization relationship are isolated from each other.

[0088] At the same time, in this embodiment, since two hubs 10 are used, the number of hardware resources 20 is relatively small, and four connecting lines can be used, so that the number of events that can be transmitted simultaneously reaches four, improving the event transmission efficiency without increasing the number of lines.

[0089] Figure 3 A schematic diagram of the hardware interconnection structure within a chip provided in another embodiment of the present application is shown in FIG. Figure 3 As shown, the chip hardware interconnection structure provided by this embodiment includes:

[0090] The number of the hardware resources 20 is greater than a preset number threshold, there are at least three hubs 10, the hubs 10 are divided into primary hubs 10 and multi-level hubs 10, and there are multiple primary hubs 10.

[0091] Each hardware resource 20 is connected to a matching primary hub 11 via a preset number of connection lines.

[0092] Each primary hub 11 is connected to the multi-stage hub 13 via a preset number of connection lines.

[0093] In this embodiment, the preset quantity threshold can be set according to actual application, for example, it can be set to 100, 150, etc.

[0094] The primary hub 11 is a hub directly connected to the hardware resources 20, and the multi-level hub 13 is a hub connected to the hub. At the same time, if the number of hardware resources 20 is too large, the multi-level hub 13 can also be divided into a secondary hub, a tertiary hub, etc., and the entire hardware resources 20 can be interconnected by connecting the primary hub 11 to the secondary hub and the secondary hub to the tertiary hub.

[0095] The matching relationship between each hardware resource 20 and the primary hub 11 may be determined according to the synchronization relationship between each hardware resource 20 .

[0096] Optionally, in this embodiment, each hardware resource 20 having a deep synchronization relationship is connected to the same primary hub 11. A deep synchronization relationship is a synchronization relationship in which the number of events synchronously processed by each hardware resource 20 is greater than a preset event number threshold.

[0097] There may be hardware resources 20 with greater collaboration between the hardware resources 20, or there may be hardware resources 20 that only collaborate occasionally. Therefore, the hardware resources 20 with greater collaboration, i.e., those with a deep synchronization relationship, can be connected to the same primary hub 11 to improve the event propagation efficiency and event processing efficiency when events are generated.

[0098] The preset event quantity threshold can be set according to actual applications, for example, to 30, 50, etc.

[0099] Optionally, in this embodiment, the hardware resources 20 include: off-chip hardware and on-chip hardware. The on-chip hardware at least includes a processor core.

[0100] The off-chip hardware is connected to the external interface of the primary hub 11 via a preset number of connection lines.

[0101] The hardware in the chip is connected to the internal interface of the primary hub 11 through a preset number of connection lines.

[0102] In this embodiment, the off-chip hardware may be a flash memory (full name in English: flash memory), a read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), etc. The on-chip hardware may be a processor core, an audio processing circuit or a video processing circuit developed in actual applications, etc.

[0103] The primary hub 11 may use a common interface as an external interface for connecting to off-chip hardware.

[0104] Optionally, in this embodiment, a plurality of resource pools are configured in the multi-stage hub 13 .

[0105] Each resource pool is associated with each hardware resource 20 having a synchronization relationship, and the maximum number of hardware resources 20 involved in the resource pool is the total number of all hardware resources 20 .

[0106] Since the multi-level hub 13 is connected to the primary hub 11, it can cover all the hardware resources 20 connected to the primary hub 11, so that a larger resource pool can be further configured to include all the hardware resources 20. At the same time, the hardware resources 20 connected to a primary hub 11 can be synchronously interconnected with the hardware resources 20 connected to another primary hub 11, thereby improving the overall signal transmission efficiency of all the hardware resources 20.

[0107] Figure 4 A schematic diagram of the hardware interconnection structure within a chip provided by another embodiment of the present application, Figure 5 A schematic diagram of a resource pool in a hub provided in another embodiment of the present application is shown in FIG. Figure 4 and Figure 5 As shown in the figure, HUB refers to the hub, HUB (level 1) refers to the primary hub, and HUB (level 2) refers to the multi-level hub. Channel refers to the connection line, which can also be called the signal transmission channel. 4channel means 4 connection lines.

[0108] Pool_0 refers to the first resource pool, Pool_1 refers to the second resource pool, Pool_2 refers to the third resource pool, and Pool_n refers to the n+1th resource pool. Pool_0 and Pool_1 are the resource pools in the first primary hub arranged from top to bottom, supporting a maximum of X hardware resources, of which Pool_0 has 4 hardware resources and Pool_1 has 6 hardware resources. Pool_2 and Pool_n are the resource pools in the multi-level hub, supporting a maximum of X*Y hardware resources, of which Pool_2 has 2 hardware resources and Pool_n has X*Y hardware resources. In the figure, the primary hub is exemplarily connected to a maximum of X hardware resources, and the maximum number of primary hubs is Y. "00", "01" to "YX" represent hardware resources.

[0109] Figure 4 For the hardware connection structure within the entire chip, "00", "01", etc. not only represent the CPU core, but also can be off-chip hardware, buses, audio processing circuits and video processing circuits developed in actual applications. These hardware are interconnected through the HUB. Each hardware resource, such as "00", "01", etc., has "4" (or other number) independent lines to the HUB. Similarly, there are "4" independent lines from the HUB to each hardware resource. There are also 4 pairs of connection lines in different directions between the HUB (level 1) and the HUB (level 2). The hardware resource "00" can send four different events to the HUB (level 1) at the same time, and can also receive four different events from the HUB (level 1).

[0110] For each HUB, the implementation principle is the same. They are all units that can configure resource pools. They support several resource pools, and the number of hardware resources in each resource pool can be configured. Figure 5 As shown, in resource pool Pool_0,

[0111] The four hardware resources "00", "02", ..., "03" are grouped together. When an event occurs on channel_0 of "00", it can be broadcasted to all other hardware resources such as "02", ..., "03" through the HUB.

[0112] In pool_2, all hardware resources are included, such as "00", ..., "0x". When a channel of one hardware resource sends an event, other members can obtain it. Although the maximum number of events that can be propagated in a single resource pool is 4, there are many logical links in the entire chip at the same time.

[0113] Each hardware resource has a hardware resource identifier, which can be used to divide resource pools. For example, Figure 5 The labels of the resource pools in the .

[0114] Therefore, in this embodiment, when multiple hardware resources such as CPU cores need to be debugged together, if one of the members fails, the members in the same resource pool can be debugged quickly and synchronously. For example, when a read instruction error occurs in CPU0, while the Trace resource in CPU0 collects the fault data, it can notify CPU1, L2 and other hardware resources to collect the corresponding fault data synchronously and quickly.

[0115] At the same time, the on-chip hardware interconnection structure of this embodiment can be applied to the Power architecture. Each hardware resource in the Power architecture has an on-chip logic analyzer, and a large number of timing changes before and after the fault can be collected through the on-chip logic analyzer, thereby more accurately achieving signal synchronization and more accurately locating the fault.

[0116] The hardware interconnection structure within the chip of this embodiment has the following effects:

[0117] It does not need to rely on interconnection buses, nor does it require bus asynchronous bridges, signal encoding and other units. It can directly transmit level information without additional encoding. At the same time, it does not need to design different Master and Slave according to different bus types, does not occupy bus bandwidth, and does not have to bear the risk of bus delay.

[0118] When the number of CPUs or hardware resources increases, there is no need to interconnect them, so there is no risk of a large number of wiring.

[0119] The signal transmission requirements between hardware resources and HUB are lower and the transmission time efficiency is better.

[0120] In a miniaturized and lightweight chip architecture, it is simple and easy to implement, does not have too high development costs, and does not consume too many silicon resources. At the same time, it is suitable for complex chips or simple chips.

[0121] The hardware interconnection structure in the chip in this embodiment is a simple and effective interconnection, which is relatively fast and accurate when transmitting a small amount of signals between chips, and does not cause routing problems. Among them, the HUB is the core component, with the HUB as the center.

[0122] At the same time, although the number of signals between two hardware resources is fixed, based on the idea of ​​grouping, the number of logical links that can coexist in the entire chip is greatly increased.

[0123] In addition, this embodiment further provides a chip, and the hardware connection structure in the chip is the hardware interconnection structure in the chip in any of the above embodiments.

[0124] Figure 6 A flowchart of a synchronization test method provided by an embodiment of the present application is shown in FIG. Figure 6 As shown, this embodiment also provides a synchronous testing method based on a server including the above chip, the server including: a mainboard and a chip, the chip being arranged on the mainboard. The method includes the following steps:

[0125] Step S101 : generating a synchronization test signal in response to a synchronization test instruction input by a user.

[0126] Step S102, sending a synchronous test signal to the target hardware resource to be tested and other hardware resources. The synchronous test signal is transmitted from the target hardware resource to the other hardware resources via the hub. The other hardware resources have a synchronous relationship with the target hardware resource.

[0127] Step S103, receiving integrated circuit electronic signals uploaded by the target hardware resources and other hardware resources.

[0128] Step S104, determining a synchronization test result according to the integrated circuit electronic signal.

[0129] In the synchronous testing method of this embodiment, during the synchronous testing, the control signal - the synchronous testing signal is transmitted to other hardware resources via the target hardware resources and the hub, so that other hardware resources that need to be synchronously tested can quickly and synchronously collect data with the target hardware resources and upload the integrated circuit electronic signals, thereby improving the efficiency of the synchronous testing.

[0130] The target hardware resources and other hardware resources can upload integrated circuit electronic signals through the bus, and perform corresponding analysis on the integrated circuit electronic signals through the analysis application to determine the synchronization test results.

[0131] In this embodiment, a synchronization test device is also provided, the device comprising:

[0132] The response module is used to generate a synchronization test signal in response to a synchronization test instruction input by a user.

[0133] The sending module is used to send a synchronous test signal to the target hardware resource to be tested and other hardware resources. The synchronous test signal is transmitted from the target hardware resource to the other hardware resources via the hub. The other hardware resources have a synchronous relationship with the target hardware resource.

[0134] The receiving module is used to receive integrated circuit electronic signals uploaded by the target hardware resources and other hardware resources.

[0135] The determination module is used to determine the synchronization test result according to the integrated circuit electronic signal.

[0136] The file transmission device provided in this embodiment can execute Figure 6 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 6 The method embodiments shown are similar and will not be described in detail here.

[0137] According to an embodiment of the present application, the present application also provides a server, a computer-readable storage medium and a computer program product for implementing the method embodiment.

[0138] The server includes a mainboard and the aforementioned chip, wherein the chip includes a processing component and a memory, and the mainboard is also provided with a power component, a multimedia component, an input / output (I / O) interface, a sensor component, and a communication component.

[0139] The processing component generally controls the overall operation of the server, such as operations associated with display, data communication, and recording operations. The processing component may include one or more processors to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component may include one or more modules to facilitate interaction between the processing component and other components. For example, the processing component may include a multimedia module to facilitate interaction between the multimedia component and the processing component.

[0140] The memory is configured to store various types of data to support operations on the server. Examples of such data include instructions for any application or method operating on the server. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0141] The power supply assembly provides power to the various components of the server. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the server.

[0142] The multimedia component includes a touch display screen. In some embodiments, the touch display screen may include a liquid crystal display (LCD) and a touch panel (TP). The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0143] The I / O interface provides an interface between the processing component and the peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0144] The sensor assembly includes one or more sensors for providing various aspects of status assessment for the server. For example, the sensor assembly can detect the on / off state of the server, the relative positioning of components, such as the display and keypad of the server, and the sensor assembly can also detect changes in the position of the server or a component of the server, the presence or absence of user contact with the server, the server orientation or acceleration / deceleration, and temperature changes of the server. The sensor assembly may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly may also include a light sensor for use in imaging applications. In some embodiments, the sensor assembly may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0145] The communication component is configured to facilitate wired or wireless communication between the server and other devices. The server can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.

[0146] At the same time, this embodiment also provides a computer product. When the instructions in the computer product are executed by the processor of the electronic device, the electronic device can execute the file transmission method of the above embodiment.

[0147] Those skilled in the art will readily come up with other implementations of the embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modifications, uses or adaptations of the embodiments of the present application, which follow the general principles of the embodiments of the present application and include common knowledge or customary technical means in the art that are not disclosed in the embodiments of the present application.

[0148] It should be understood that the embodiments of the present application are not limited to the precise structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the embodiments of the present application is limited only by the appended claims.

[0149] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A hardware interconnection structure within a chip, characterized in that: include: at least one hub and a plurality of hardware resources; Each of the hardware resources is connected to the hub via a preset number of connection lines; At least one resource pool is configured in the hub, and the resource pool is related to each of the hardware resources having a synchronization relationship, and the hardware resources having a synchronization relationship are divided into the same resource pool; wherein different resource pools are isolated from each other; When the number of the hardware resources is greater than a preset number threshold, the number of the hubs is at least three; the hubs are divided into primary hubs and multi-level hubs; the number of the primary hubs is multiple; Each of the hardware resources is connected to a matching primary hub via a preset number of connection lines; Each of the primary hubs is connected to the multi-stage hub via a preset number of connection lines; Each hardware resource having a deep synchronization relationship is connected to the same primary hub; the deep synchronization relationship is a synchronization relationship in which the number of events synchronously processed by each hardware resource is greater than a preset event number threshold.

2. The chip hardware interconnection structure according to claim 1, characterized in that: The hardware resources include: off-chip hardware and on-chip hardware; the on-chip hardware includes at least a processor core; The off-chip hardware is connected to the external interface of the primary hub via the preset number of connection lines; The hardware in the chip is connected to the internal interface of the primary hub via the preset number of connection lines.

3. The chip hardware interconnection structure according to claim 1, characterized in that: The multi-level hub is configured with multiple resource pools; Each resource pool is associated with each hardware resource having a synchronization relationship, and the maximum number of hardware resources involved in the resource pool is the total number of all hardware resources.

4. The chip hardware interconnection structure according to claim 1, characterized in that: The number of the hub is one; the number of the hardware resources is at least three; The hardware resources are divided into a plurality of hardware resource sets according to a synchronization relationship; a plurality of resource pools are configured in the hub; and the resource pools correspond to the hardware resource sets.

5. The chip hardware interconnection structure according to claim 1, characterized in that: The number of hubs is two; the preset number is four; the number of hardware resources is at least four; Each of the hardware resources is divided into two hardware resource sets according to a synchronization relationship; The hardware resources corresponding to one of the hardware resource sets are connected to one of the hubs via a preset number of connection lines; The hardware resources corresponding to another hardware resource set are connected to another hub via a preset number of connection lines.

6. A chip, characterized in that: The hardware connection structure within the chip is the hardware interconnection structure within the chip as described in any one of claims 1 to 5.

7. A server, characterized in that: include: A main board and a chip as claimed in claim 6; the chip is arranged on the main board.

8. A synchronous testing method, characterized in that: Based on the server according to claim 7, the method comprises: generating a synchronization test signal in response to a synchronization test instruction input by a user; Sending a synchronous test signal to a target hardware resource to be tested and other hardware resources; the synchronous test signal is transmitted from the target hardware resource to other hardware resources via a hub; the other hardware resources have a synchronous relationship with the target hardware resource; Receiving integrated circuit electronic signals uploaded by target hardware resources and other hardware resources; A synchronization test result is determined based on the integrated circuit electronic signal.