Portable live-action three-dimensional modeling computing power platform

Abstract

The invention discloses a portable live-action three-dimensional modeling computing power platform which comprises a software and hardware all-in-one machine, the software and hardware all-in-one machine comprises a power module, a mainboard module, a display card module and a fan module, a live-action three-dimensional modeling engine scheduling platform is arranged in the computing power platform, and modeling items are automatically scheduled according to the priority of tasks; the scheduling platform automatically allocates the modeling engine for processing according to the emergency degree, complexity and resource occupation condition of the task, so that the demand of manual intervention is reduced, the utilization of computing power resources is optimized, and the processing speed of a live-action three-dimensional modeling project is improved; the cloud management platform monitors the resource pool and the virtual machine in real time, and hardware resources can be scheduled according to the monitoring condition; the software and hardware all-in-one machine has dustproof and shockproof functions, stable operation of equipment in a complex outdoor environment is ensured, the overall structure is light and portable, and a user can easily carry the machine and deploy the machine in different environments for three-dimensional modeling operation.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional modeling computing power platform, and in particular to a portable real-scene three-dimensional modeling computing power platform. Background Art

[0002] At present, with the development of information technology, the demand for real-scene 3D modeling is growing in many fields, such as urban planning, geographic information, architectural design, emergency rescue, etc., especially emergency rescue scenes have higher and higher requirements for the efficiency of real-scene 3D modeling; However, traditional emergency scenario modeling has the following disadvantages: In the real-life 3D modeling of traditional emergency scenarios, it is usually necessary for staff to carry out modeling on mobile workstations, which makes it difficult to complete the overall modeling in a short period of time. At the same time, there may be problems such as multiple mobile workstations being inconvenient to carry, insufficient modeling computing power of mobile workstations, inability to uniformly schedule mobile workstations, and low modeling efficiency and inability to automatically allocate engines. Traditional mobile workstations often cannot cope with such scenarios well. Summary of the invention

[0003] The purpose of the present invention is to provide a portable real-scene 3D modeling computing power platform to solve the problems raised in the above-mentioned background technology that in the real-scene 3D modeling of traditional emergency scenarios, it is usually necessary to rely on staff to carry mobile workstations for modeling, and it is difficult to complete the overall modeling in a short time. At the same time, there may be multiple mobile workstations that are inconvenient to carry, insufficient modeling computing power of mobile workstations, inability to uniformly schedule mobile workstations, low modeling efficiency and inability to automatically allocate engines. Traditional mobile workstations often cannot cope with the problems of such scenarios well.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a portable real-scene three-dimensional modeling computing power platform, including a hardware and software integrated machine, characterized in that the hardware and software integrated machine includes a chassis body, a power module, a mainboard module, a graphics card module, and a fan module. The power module of the hardware and software integrated machine is at the bottom of the chassis body, with a total of 4 power supplies, and a redundant design is adopted. The mainboard module of the hardware and software integrated machine is located above the power module, and the mainboard module integrates CPU, memory, PCIe slot, IO interface and other hardware. The graphics card module of the hardware and software integrated machine is located above the mainboard module, and the graphics card module is connected to the PCIe slot of the mainboard module below and the graphics card expansion board of the graphics card module above through a PCIe split card. 8 graphics cards are fixedly installed on the graphics card expansion board. The fan module of the hardware and software integrated machine is fixed on the inner side of the front panel of the chassis body, and the fan module is equipped with two layers of fans to form two independent air ducts to dissipate heat for the mainboard module and the graphics card module respectively.

[0005] As a preferred technical solution of the present invention, the four corners at the top and the four corners at the bottom of the hardware and software integrated machine are fixedly installed with shock-absorbing corner protection mechanisms, the shock-absorbing corner protection mechanisms include shock-absorbing pads and anti-slip strips, the top of the shock-absorbing pads are fixedly connected to the bottom of the anti-slip strips, and the surface of the shock-absorbing pads is provided with a number of grooves. The hardware and software integrated machine includes a top panel, a front panel, a rear panel and a side panel, the bottom of the top panel is fixedly connected to the tops of the front panel and the rear panel respectively, side panels are fixedly installed on both sides between the front panel and the rear panel, and a power button is fixedly installed on the top of the front panel.

[0006] As a preferred technical solution of the present invention, a mesh cover is fixedly installed on one side of the software and hardware integrated machine, and a plurality of heat dissipation slots are opened in the middle of the top of the software and hardware integrated machine. The opening of the heat dissipation slots and the mesh cover facilitates the contact between the low-temperature gas of the external environment and the software and hardware integrated machine, and heat transfer and heat dissipation and cooling of the software and hardware integrated machine are carried out. Handles are fixedly installed on both sides of the top of the software and hardware integrated machine, and the user can hold the chess hands in his hands to carry the software and hardware integrated machine.

[0007] The workflow of a portable real-scene three-dimensional modeling computing platform of the present invention comprises the following steps: Step 1: Hardware resource construction: Integrate multi-core CPUs, large-capacity memory, multiple GPUs, and storage into a unified hardware resource pool to achieve efficient sharing and dynamic adjustment of computing resources; Step 2: Firecracker virtualization: The underlying system virtualizes hardware resources into multiple virtual machine instances through resource virtualization technology. Each virtual machine runs the modeling task independently. Firecracker virtualization simplifies the virtualization architecture, reduces the resource overhead of traditional virtualization, and has both isolation and efficiency. It also provides performance advantages by optimizing the startup speed of virtual machines. Step 3: Optimize virtual machine performance based on IO_uring: Use the IO_uring asynchronous I / O mechanism to significantly reduce the overhead of system calls and context switches, which is especially suitable for high-concurrency and I / O-intensive tasks and improves the performance of I / O operations. Step 4: Unified management by cloud management platform: The computing power platform has a built-in cloud management platform. Resource pooling technology centrally manages the computing resources of the computing power platform. Through a unified interface, users can call different virtual machine resources through the cloud management platform to complete the allocation and scheduling of modeling tasks. Pooling management makes the use of resources more efficient and facilitates real-time monitoring to ensure the stability of task execution. Step 5. Scheduling of real-scene 3D modeling engines: The computing platform has a built-in real-scene 3D modeling engine scheduling platform, which automatically schedules modeling projects according to task priority. The scheduling platform automatically allocates modeling engines for processing based on the urgency, complexity, and resource usage of the task.

[0008] As a preferred technical solution of the present invention, the hardware resource construction in the step one is specifically as follows: S1: hardware resource preparation: motherboard, CPU, memory, hard disk, GPU, I / O devices, which are used to provide necessary computing resources; S2: hardware assembly: based on the general x86 server architecture, the I / O devices in S1 include a 10 Gigabit network card, which provides network services for the portable real-life 3D modeling computing power platform. The hard disk in S1 uses a high-speed solid-state hard disk as the shared storage of the portable real-life 3D modeling computing power platform, and the computing power, network, and storage are integrated on one device; S3: appearance design: the chassis is made of alloy material, and the overall appearance of the chassis is a rectangular parallelepiped. A dustproof net is installed on the front of the chassis, and power, network cable, USB, HDMI, and VGA interfaces are reserved on the back. Two alloy handles are installed on the top of the chassis to make the physical machine easy to carry.

[0009] As a preferred technical solution of the present invention, the Firecracker virtualization in step 2 is specifically as follows: S1, KVM initialization: enable KVM, the host machine provides hardware-level virtualization support, and allows each micro virtual machine to run independently; S2, Firecracker binary startup: start the Firecracker binary file, initialize the micro virtual machine management process, which is responsible for managing the life cycle of the virtual machine, including creating, starting, pausing and destroying the micro virtual machine; S3, configure the virtual machine: modify the configuration file to define the resource parameters of the virtual machine, including the number of CPU cores, memory size, and I / O settings; S4, device simulation selection: by minimizing the simulation of hardware devices, reducing overhead and increasing the startup speed, the supported devices are limited to basic functions, such as virtio storage devices and virtio network devices; S5, virtio driver initialization: use the virtio driver to configure block storage devices and network interfaces for the virtual machine to ensure that the I / O operations of the micro virtual machine are completed through efficient virtualization drivers; S6, memory initialization: when starting the micro virtual machine, allocate a specified physical memory space for it through Linux's memory mapping technology, and ensure that the memory of each micro virtual machine does not interfere with each other; S7, Seccomp BPF security mechanism: Use Seccomp BPF system call filter to limit the system call scope of micro virtual machines to the host system, intercept illegal or unauthorized system calls during runtime, and enhance security; S8, cgroup resource limitation: Use Linux's cgroup mechanism to limit the CPU and memory resources of each micro virtual machine to prevent the micro virtual machine from occupying more resources than expected. Cgroup can also control the use of I / O and network bandwidth to ensure fair resource allocation; S9, ESRTful API management: Use the RESTful API interface to manage the virtual machine life cycle. The API supports creating, starting, pausing, and destroying virtual machines, and provides resource monitoring and snapshot management functions.

[0010] As a preferred technical solution of the present invention, the virtual machine performance optimization based on IO_uring in the step three is specifically as follows: S1, initializing the IO_uring structure: initializing an io_uring instance, allocating a submission queue and a completion queue, the buffer is shared, the user space and the kernel implement asynchronous I / O transmission through this structure, defining the depth of the submission queue and the completion queue, and ensuring appropriate memory allocation and concurrent processing capabilities; S2, operation of the submission queue: obtaining a new queue entry from the submission queue to describe the I / O operation to be submitted, the operation type includes read and write, file operation, setting the type of I / O operation as needed, and defining related parameters such as file descriptors and data buffers for each operation; S3, submitting an I / O request: after filling all I / O operations into the submission queue, submit them to the kernel at one time, and improve efficiency by reducing the system call for each request; S4, processing the completion queue: checking the I / O operations processed by the kernel through the completion queue Operation, the user process blocks and waits, or periodically checks whether there are new completion events in the completion queue, reads the operation result from the completion queue, and checks whether it is successful. If completed, execute S5 subsequent operations, otherwise continue to wait for I / O completion; S5, resource cleanup: After all I / O operations are completed, release resources and destroy the io_uring instance and its associated queues and buffers.

[0011] As a preferred technical solution of the present invention, the unified management of the cloud management platform in step 4 is specifically S1, virtual machine resource scheduling: the cloud management platform obtains an authentication token by sending a POST request to the Firecracker server. The permissions of this token are consistent with the management user permissions in the Firecracker service, ensuring that the platform has the permissions to create, destroy, start, and suspend management operations on virtual machines; S2, resource pooling: the CPU, memory, GPU, and hard disk hardware resources of the computing power platform are divided into different resource pools. Each resource pool is allocated to different departments according to business needs. The resource pool further allocates the allocated resources to virtual machines for computing tasks, which are divided into first resources: the overall hardware resources allocated to the resource pool, and second resources: the hardware resources allocated to a certain virtual machine in the first resource; S3, resource monitoring: the platform obtains real-time data from the Firecracker service, monitors the usage of resource pools and virtual machine resources, that is, the usage of first resources and second resources, and can adjust the first resources and second resources on demand on the cloud management platform to maximize resource utilization.

[0012] As a preferred technical solution of the present invention, the real-scene 3D modeling engine scheduling in step five is specifically as follows: S1, information entry: real-scene 3D production project and corresponding engineering information entry, setting the processing priority of real-scene 3D production project and engineering, and submitting the tasks required for processing for each engineering; S2, task calculation: determine whether the task requires the resource engine to calculate it. If the resource engine is required to calculate, execute step S53; if the resource engine is not required to calculate, execute step S4; S3, task processing: automatically process tasks according to priority, generate task completion results, and execute step S5; S4, exception handling: remind humans to handle task nodes or abnormal situations; S5, task judgment: determine whether the task completion result is qualified. If the task completion result is qualified, continue to execute the next stage task. If the task completion result is unqualified, execute step S4.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. The computing power platform has a built-in real-scene 3D modeling engine scheduling platform, which automatically schedules modeling projects according to the priority of the task. The scheduling platform automatically allocates modeling engines for processing according to the urgency, complexity and resource occupancy of the task, reducing the need for manual intervention. This not only optimizes the utilization of computing power resources, but also greatly improves the processing speed of real-scene 3D modeling projects; 2. The integrated hardware and software machine adopts an independent appearance design and has dust-proof and shock-proof functions to ensure stable operation of the equipment in complex outdoor environments. The overall structure is lightweight and portable, allowing users to easily carry and deploy it in different environments for 3D modeling operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A three-dimensional diagram of the hardware and software integrated machine of the present invention; Figure 2 It is a work flow chart of the present invention; Figure 3 A flowchart for building hardware resources for the present invention; Figure 4 It is a flowchart of Firecracker virtualization of the present invention; Figure 5 A flowchart of virtual machine performance optimization based on IO_uring of the present invention; Figure 6 A flowchart of the unified management of the virtual machine platform of the present invention; Figure 7 A flowchart of the real-scene 3D modeling engine scheduling of the present invention; Figure 8 The real-scene 3D modeling engine scheduling flow chart of the present invention; Fig. 9 It is a side view of the hardware and software integrated machine of the present invention; Fig.10 It is a cross-sectional view of the hardware and software integrated machine of the present invention.

[0015] In the figure: 1. Hardware and software integrated machine; 101. Top panel; 102. Front panel; 103. Side panel; 104. Rear panel; 2. Shock-absorbing corner guard mechanism; 21. Shock-absorbing pad; 22. Anti-slip strip; 23. Groove; 3. Handle; 4. Net cover; 5. Heat sink; 6. Power button; 7. Fan module; 8. Graphics card module; 9. Motherboard module; 10. Power supply module; 11. Chassis body; 12. Graphics card expansion board. DETAILED DESCRIPTION

[0016] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] See also Figure 1-10 The present invention provides a portable real-scene three-dimensional modeling computing platform, including a hardware and software integrated machine 1, characterized in that the hardware and software integrated machine 1 includes a chassis body 11, a power module 10, a mainboard module 9, a graphics card module 8, and a fan module 7. The power module 10 of the hardware and software integrated machine 1 is at the bottom of the chassis body 11, with a total of 4 power supplies, and a redundant design is adopted. The mainboard module 9 of the hardware and software integrated machine 1 is located above the power module 10, and the mainboard module 9 integrates CPU, memory, PCIe slot, IO interface and other hardware. The graphics card module 8 of the hardware and software integrated machine 1 is located above the mainboard module 9, and the graphics card module 8 is connected to the PCIe slot of the mainboard module 9 below and the graphics card expansion board 12 of the graphics card module 8 above through a PCIe split card. The 8 graphics cards are fixedly installed on the graphics card expansion board 12. The fan module 7 of the hardware and software integrated machine is fixed on the inner side of the front panel of the chassis body 11, and the fan module 7 is installed with two layers of fans to form two independent air ducts to dissipate heat for the mainboard module 9 and the graphics card module 8 respectively.

[0018] The four corners at the top and the four corners at the bottom of the hardware and software integrated machine 1 are fixedly installed with shock-absorbing corner protection mechanisms 2, the shock-absorbing corner protection mechanisms 2 include shock-absorbing pads 21 and anti-slip strips 22, the top of the shock-absorbing pads 21 is fixedly connected to the bottom of the anti-slip strips 22, and the surface of the shock-absorbing pads 21 is provided with a plurality of grooves 23. The hardware and software integrated machine 1 includes a top panel 101, a front panel 102, a rear panel 104 and a side panel 103, the bottom of the top panel 101 is fixedly connected to the tops of the front panel 102 and the rear panel 104 respectively, the side panels 103 are fixedly installed on both sides between the front panel 102 and the rear panel 104, and the top of the front panel 102 is fixedly installed with a power button 6.

[0019] A mesh cover 4 is fixedly installed on one side of the software and hardware integrated machine 1, and a plurality of heat dissipation slots 5 are opened in the middle of the top of the software and hardware integrated machine 1. The opening of the heat dissipation slots 5 and the mesh cover 4 facilitates the contact between the low-temperature gas of the external environment and the software and hardware integrated machine 1, and heat transfer and heat dissipation and cooling of the software and hardware integrated machine 1 are performed. Handles 3 are fixedly installed on both sides of the top of the software and hardware integrated machine 1, which is convenient for carrying when going out for work.

[0020] The workflow of a portable real-scene three-dimensional modeling computing platform of the present invention comprises the following steps: Step 1: Hardware resource construction: Integrate multi-core CPUs, large-capacity memory, multiple GPUs, and storage into a unified hardware resource pool to achieve efficient sharing and dynamic adjustment of computing resources; Step 2: Firecracker virtualization: The underlying system virtualizes hardware resources into multiple virtual machine instances through resource virtualization technology. Each virtual machine runs the modeling task independently. Firecracker virtualization simplifies the virtualization architecture, reduces the resource overhead of traditional virtualization, and has both isolation and efficiency. It also provides performance advantages by optimizing the startup speed of virtual machines. Step 3: Optimize virtual machine performance based on IO_uring: Use the IO_uring asynchronous I / O mechanism to significantly reduce the overhead of system calls and context switches, which is especially suitable for high-concurrency and I / O-intensive tasks and improves the performance of I / O operations. Step 4: Unified management by cloud management platform: The computing power platform has a built-in cloud management platform. Resource pooling technology centrally manages the computing resources of the computing power platform. Through a unified interface, users can call different virtual machine resources through the cloud management platform to complete the allocation and scheduling of modeling tasks. Pooling management makes the use of resources more efficient and facilitates real-time monitoring to ensure the stability of task execution. Step 5. Scheduling of real-scene 3D modeling engines: The computing platform has a built-in real-scene 3D modeling engine scheduling platform, which automatically schedules modeling projects according to task priority. The scheduling platform automatically allocates modeling engines for processing based on the urgency, complexity, and resource usage of the task.

[0021] The hardware resource construction in step 1 is specifically as follows: S1: Hardware resource preparation: motherboard, CPU, memory, hard disk, GPU, I / O devices, used to provide necessary computing resources; S2: Hardware assembly: Based on the general x86 server architecture, the I / O devices in S1 include a 10 Gigabit network card, which provides network services for the portable real-life 3D modeling computing power platform. The hard disk in S1 uses a high-speed solid-state hard disk as the shared storage of the portable real-life 3D modeling computing power platform, and computing power, network, and storage are integrated into one device; S3: Appearance design: The chassis is made of alloy material, and the overall appearance of the chassis is a rectangular block. A dustproof net is installed on the front of the chassis, and power, network cable, USB, HDMI, and VGA interfaces are reserved on the back. Two alloy handles are installed on the top of the chassis to make the physical machine easy to carry.

[0022] The Firecracker virtualization in step 2 is as follows: S1, KVM initialization: Enable KVM, the host provides hardware-level virtualization support, allowing each micro virtual machine to run independently; S2, Firecracker binary startup: Start the Firecracker binary file and initialize the micro virtual machine management process, which is responsible for managing the life cycle of the virtual machine, including creating, starting, pausing and destroying micro virtual machines; S3, Configure the virtual machine: Modify the configuration file to define the resource parameters of the virtual machine, including the number of CPU cores, memory size, and I / O settings; S4, Device simulation selection: By minimizing the simulation of hardware devices, reducing overhead and increasing startup speed, the supported devices are limited to basic functions, such as virtio storage devices and virtio network devices; S5, Virtio driver initialization: Use the virtio driver to configure block storage devices and network interfaces for the virtual machine to ensure that the I / O operations of the micro virtual machine are completed through efficient virtualization drivers; S6, Memory initialization: When starting the micro virtual machine, allocate the specified physical memory space for it through Linux's memory mapping technology, and ensure that the memory of each micro virtual machine does not interfere with each other; S7, Seccomp BPF security mechanism: Use Seccomp BPF system call filter limits the scope of system calls made by micro-virtual machines to the host system, intercepts illegal or unauthorized system calls during runtime, and enhances security; S8, cgroup resource limitation: Use Linux's cgroup mechanism to limit the CPU and memory resources of each micro-virtual machine to prevent the micro-virtual machine from occupying more resources than expected. Cgroup can also control the use of I / O and network bandwidth to ensure fair resource allocation; S9, ESRTful API management: Use the RESTful API interface to manage the virtual machine life cycle. The API supports the creation, start, suspension, and destruction of virtual machines, and provides resource monitoring and snapshot management functions.

[0023] The IO_uring-based virtual machine performance optimization in step three is specifically as follows: S1. Initialize the IO_uring structure: initialize an io_uring instance, allocate the submission queue and completion queue, the buffer is shared, the user space and the kernel implement asynchronous I / O transmission through this structure, define the depth of the submission queue and the completion queue, and ensure appropriate memory allocation and concurrent processing capabilities; S2. Operation of the submission queue: get a new queue entry from the submission queue to describe the I / O operation to be submitted. The operation types include read, write, and file operations. Set the type of I / O operation as needed, and define related parameters for each operation such as file descriptors and data buffers; S3. Submit I / O requests: After filling all I / O operations into the submission queue, submit them to the kernel at one time, and improve efficiency by reducing the system calls for each request; S4. Processing of the completion queue: check the I / O processed by the kernel through the completion queue Operation, the user process blocks and waits, or periodically checks whether there are new completion events in the completion queue, reads the operation result from the completion queue, and checks whether it is successful. If completed, executes S5 subsequent operations, otherwise continues to wait for I / O completion; S5, resource cleanup: After all I / O operations are completed, release resources and destroy the io_uring instance and its associated queues and buffers.

[0024] The unified management of the virtual machine platform in step 4 is specifically S1. Virtual machine resource scheduling: the platform obtains the authentication token by sending a POST request to the Firecracker server. The permissions of this token are consistent with the management user permissions in the Firecracker service, ensuring that the platform has the permissions to create, destroy, start, and pause management operations on virtual machines; S2. Resource pooling: the CPU, memory, GPU, and hard disk hardware resources of the computing power platform are divided into different resource pools. Each resource pool is allocated to different departments according to business needs. The resource pool further allocates the allocated resources to virtual machines for computing tasks, which are divided into the first resource: the overall hardware resources allocated to the resource pool, and the second resource: the hardware resources allocated to a certain virtual machine in the first resource; S3. Resource monitoring: the platform obtains real-time data from the Firecracker service, monitors the usage of resource pools and virtual machine resources, that is, the usage of first resources and second resources, and can adjust the first resources and second resources on demand on the cloud management platform to maximize resource utilization.

[0025] The real-life 3D modeling engine scheduling in step 5 is specifically as follows: S1. Information entry: real-life 3D production projects and corresponding engineering information are entered, the processing priority of real-life 3D production projects and engineering projects is set, and the tasks required to be processed for each engineering project are submitted; S2. Task calculation: determine whether the task requires a resource engine to calculate it. If the resource engine is required to calculate it, execute step S53; if the resource engine is not required to calculate it, execute step S4; S3. Task processing: automatically process tasks according to priority, generate task completion results, and execute step S5; S4. Exception handling: remind humans to handle task nodes or abnormal situations; S5. Task judgment: determine whether the task completion result is qualified. If the task completion result is qualified, continue to execute the next stage of the task. If the task completion result is unqualified, execute step S4.

[0026] In the present invention, the computing power platform adopts an independent appearance design, with dustproof and shockproof functions, ensuring that the equipment can run stably in complex outdoor environments. The overall structure is lightweight and portable, allowing users to easily carry and deploy it in different environments for 3D modeling operations; secondly, the present invention integrates multi-core CPUs, large-capacity memory, and multiple GPU cards to form a unified hardware resource pool. The underlying system virtualizes hardware resources into multiple virtual machine instances through resource virtualization technology. Each virtual machine independently runs modeling tasks, simplifies the virtualization architecture, reduces the resource overhead of traditional virtualization, and has both isolation and efficiency. It also provides performance advantages by optimizing the startup speed of virtual machines; then, the IO_uring asynchronous I / O mechanism is adopted to significantly reduce the overhead of system calls and context switches. , especially suitable for high-concurrency and I / O-intensive tasks, improving the performance of I / O operations; then, resource pooling technology centrally manages the computing resources of the computing power platform. Through a unified interface, users call different virtual machine resources through the cloud management platform to complete the allocation and scheduling of modeling tasks. Pooling management makes the use of resources more efficient and facilitates real-time monitoring to ensure the stability of task execution; finally, the computing power platform has a built-in real-scene 3D modeling engine scheduling platform, which automatically schedules modeling projects according to the priority of the task. The scheduling platform automatically allocates the modeling engine for processing according to the urgency, complexity and resource occupancy of the task, reducing the need for manual intervention. This not only optimizes the utilization of computing power resources, but also greatly improves the processing speed of real-scene 3D modeling projects. The hardware parameters are as follows:

[0027] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A portable real-scene 3D modeling computing platform, comprising a hardware and software integrated machine (1), characterized in that: The hardware and software integrated machine (1) comprises a chassis body (11), a power module (10), a motherboard module (9), a graphics card module (8), and a fan module (7). The power module (10) of the hardware and software integrated machine (1) is located at the bottom of the chassis body (11), and has a total of four power supplies, which adopt a redundant design. The motherboard module (9) of the hardware and software integrated machine (1) is located above the power module (10). The motherboard module (9) integrates hardware such as a CPU, memory, PCIe slot, and IO interface. The hardware and software integrated machine (1) The graphics card module (8) is located above the mainboard module (9); the graphics card module (8) is connected to the PCIe slot of the mainboard module (9) below and the graphics card expansion board (12) of the graphics card module (8) above via a PCIe split card; eight graphics cards are fixedly mounted on the graphics card expansion board (12); the fan module (7) of the hardware and software integrated machine is fixed to the inner side of the front panel of the chassis body (11); the fan module (7) is equipped with two layers of fans to form two independent air ducts to dissipate heat for the mainboard module (9) and the graphics card module (8) respectively.

2. A portable real-scene 3D modeling computing platform according to claim 1, characterized in that: The four corners at the top and the four corners at the bottom of the hardware and software integrated machine (1) are all fixedly installed with a shock-absorbing corner protection mechanism (2), the shock-absorbing corner protection mechanism (2) comprises a shock-absorbing pad (21) and an anti-slip strip (22), the top of the shock-absorbing pad (21) is fixedly connected to the bottom of the anti-slip strip (22), and a plurality of grooves (23) are provided on the surface of the shock-absorbing pad (21), the hardware and software integrated machine (1) comprises a top panel (101), a front panel (102), a rear panel (104) and a side panel (103), the bottom of the top panel (101) is respectively fixedly connected to the top of the front panel (102) and the top of the rear panel (104), the side panels (103) are fixedly installed on both sides between the front panel (102) and the rear panel (104), and a power button (6) is fixedly installed on the top of the front panel (102).

3. The portable real-scene 3D modeling computing platform according to claim 1, characterized in that: A mesh cover (4) is fixedly mounted on one side of the hardware and software integrated machine (1), a plurality of heat dissipation slots (5) are provided in the middle of the top of the hardware and software integrated machine (1), and handles (3) are fixedly mounted on both sides of the top of the hardware and software integrated machine (1).

4. The workflow of a portable real-scene 3D modeling computing platform according to any one of claims 1 to 3 is characterized in that: The following steps are involved: Step 1: Hardware resource construction: Integrate multi-core CPUs, large-capacity memory, multiple GPUs, and storage into a unified hardware resource pool to achieve efficient sharing and dynamic adjustment of computing resources; Step 2: Firecracker virtualization: The underlying system virtualizes hardware resources into multiple virtual machine instances through resource virtualization technology. Each virtual machine runs the modeling task independently. Firecracker virtualization simplifies the virtualization architecture, reduces the resource overhead of traditional virtualization, and has both isolation and efficiency. It also provides performance advantages by optimizing the startup speed of virtual machines. Step 3: Optimize virtual machine performance based on IO_uring: Use the IO_uring asynchronous I / O mechanism to significantly reduce the overhead of system calls and context switches, which is especially suitable for high-concurrency and I / O-intensive tasks and improves the performance of I / O operations. Step 4: Unified management by cloud management platform: The computing power platform has a built-in cloud management platform. Resource pooling technology centrally manages the computing resources of the computing power platform. Through a unified interface, users can call different virtual machine resources through the cloud management platform to complete the allocation and scheduling of modeling tasks. Pooling management makes the use of resources more efficient and facilitates real-time monitoring to ensure the stability of task execution. Step 5. Scheduling of real-scene 3D modeling engines: The computing platform has a built-in real-scene 3D modeling engine scheduling platform, which automatically schedules modeling projects according to task priority. The scheduling platform automatically allocates modeling engines for processing based on the urgency, complexity, and resource usage of the task.

5. The workflow of a portable real-scene 3D modeling computing platform according to claim 4 is characterized in that: The hardware resource construction in step 1 is specifically as follows: S1: hardware resource preparation: motherboard, CPU, memory, hard disk, GPU, I / O device, used to provide necessary computing resources; S2: Hardware assembly: Based on the general x86 server architecture, the I / O devices in S1 include a 10 Gigabit network card, which provides network services for the portable real-life 3D modeling computing platform. The hard disk in S1 uses a high-speed solid-state hard disk as the shared storage of the portable real-life 3D modeling computing platform. The computing power, network, and storage are integrated into one device; S3: Appearance design: The chassis is made of alloy material, and the overall appearance of the chassis is a rectangular block. A dustproof net is installed on the front of the chassis, and power, network cable, USB, HDMI, and VGA interfaces are reserved on the back. Two alloy handles are installed on the top of the chassis to make the physical machine easy to carry.

6. The workflow of a portable real-scene 3D modeling computing platform according to claim 4 is characterized by: The Firecracker virtualization in step 2 is specifically as follows: S1, KVM initialization: enable KVM, the host machine provides hardware-level virtualization support, and allows each micro virtual machine to run independently; S2, Firecracker binary startup: start the Firecracker binary file and initialize the micro virtual machine management process, which is responsible for managing the life cycle of the virtual machine, including creating, starting, pausing and destroying the micro virtual machine; S3, configure the virtual machine: modify the configuration file to define the resource parameters of the virtual machine, including the number of CPU cores, memory size, and I / O settings; S4, device simulation selection: by minimizing the simulation of hardware devices, reducing overhead and increasing the startup speed, the supported devices are limited to basic functions, such as virtio storage devices and virtio network devices; S5, virtio driver initialization: use the virtio driver to configure block storage devices and network interfaces for the virtual machine to ensure that the I / O operations of the micro virtual machine are completed through efficient virtualization drivers; S6, memory initialization: when starting the micro virtual machine, allocate the specified physical memory space for it through Linux's memory mapping technology, and ensure that the memory of each micro virtual machine does not interfere with each other; S7, Seccomp BPF security mechanism: use Seccomp BPF system call filter limits the scope of system calls made by micro-virtual machines to the host system, intercepts illegal or unauthorized system calls during runtime, and enhances security; S8, cgroup resource limitation: Use Linux's cgroup mechanism to limit the CPU and memory resources of each micro-virtual machine to prevent the micro-virtual machine from occupying more resources than expected. Cgroup can also control the use of I / O and network bandwidth to ensure fair resource allocation; S9, ESRTful API management: Use the RESTful API interface to manage the virtual machine life cycle. The API supports the creation, start, suspension, and destruction of virtual machines, and provides resource monitoring and snapshot management functions.

7. The workflow of a portable real-scene 3D modeling computing platform according to claim 4 is characterized by: The virtual machine performance optimization based on IO_uring in step 3 is specifically as follows: S1, initializing the IO_uring structure: initializing an io_uring instance, allocating a submission queue and a completion queue, the buffer is shared, the user space and the kernel implement asynchronous I / O transmission through this structure, defining the depth of the submission queue and the completion queue, and ensuring appropriate memory allocation and concurrent processing capabilities; S2, operation of the submission queue: obtaining a new queue entry from the submission queue to describe the I / O operation to be submitted, the operation type includes read and write, and file operation, setting the type of I / O operation as needed, and defining related parameters such as file descriptors and data buffers for each operation; S3, submitting an I / O request: after filling all I / O operations into the submission queue, submit them to the kernel at one time, and improve efficiency by reducing the system call for each request; S4, processing of the completion queue: check the I / O operations processed by the kernel through the completion queue, the user process blocks and waits, or regularly checks whether there are new completion events in the completion queue, reads the operation results from the completion queue, and checks whether they are successful. If completed, execute S5 subsequent operations, otherwise continue to wait for I / O completion; S5, resource cleanup: after all I / O operations are completed, release resources and destroy the io_uring instance and its associated queues and buffers.

8. The workflow of a portable real-scene 3D modeling computing platform according to claim 4 is characterized by: The unified management of the cloud management platform in step 4 is specifically as follows: S1. Virtual machine resource scheduling: the cloud management platform obtains an authentication token by sending a POST request to the Firecracker server. The permissions of this token are consistent with the management user permissions in the Firecracker service, ensuring that the platform has the permissions to create, destroy, start, and suspend management operations on virtual machines; S2. Resource pooling: the CPU, memory, GPU, and hard disk hardware resources of the computing power platform are divided into different resource pools. Each resource pool is allocated to different departments according to business needs. The resource pool further allocates the allocated resources to virtual machines for computing tasks, which are divided into first resources: the overall hardware resources allocated to the resource pool, and second resources: the hardware resources allocated to a certain virtual machine in the first resource; S3. Resource monitoring: the platform obtains real-time data from the Firecracker service, monitors the usage of resource pools and virtual machine resources, that is, the usage of first resources and second resources, and can adjust the first resources and second resources on demand on the cloud management platform to maximize resource utilization.

9. The workflow of a portable real-scene 3D modeling computing platform according to claim 4 is characterized by: The real-life 3D modeling engine scheduling in step five is specifically as follows: S1. Information entry: real-life 3D production projects and corresponding engineering information are entered, the processing priority of real-life 3D production projects and engineering projects is set, and the tasks required to be processed for each engineering project are submitted; S2. Task calculation: determine whether the task requires a resource engine to calculate it. If the resource engine is required to calculate it, execute step S3; if the resource engine is not required to calculate it, execute step S4; S3. Task processing: automatically process tasks according to priority, generate task completion results, and execute step S5; S4. Exception handling: remind humans to handle task nodes or abnormal situations; S5. Task judgment: determine whether the task completion result is qualified. If the task completion result is qualified, continue to execute the next stage of the task. If the task completion result is unqualified, execute step S4.

Images