CN112862104B - Hybrid quantum computer architecture and method for executing computing tasks thereof - Google Patents
Hybrid quantum computer architecture and method for executing computing tasks thereof Download PDFInfo
- Publication number
- CN112862104B CN112862104B CN202110359265.0A CN202110359265A CN112862104B CN 112862104 B CN112862104 B CN 112862104B CN 202110359265 A CN202110359265 A CN 202110359265A CN 112862104 B CN112862104 B CN 112862104B
- Authority
- CN
- China
- Prior art keywords
- quantum
- computer
- classical
- quantum computer
- interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004891 communication Methods 0.000 claims abstract description 67
- 238000004364 calculation method Methods 0.000 claims abstract description 40
- 230000001133 acceleration Effects 0.000 claims description 17
- 230000000903 blocking effect Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000013468 resource allocation Methods 0.000 claims description 15
- 230000003068 static effect Effects 0.000 claims description 6
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002096 quantum dot Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Multi Processors (AREA)
- Optical Communication System (AREA)
Abstract
A hybrid quantum computer architecture and method of performing computational tasks, the hybrid quantum computer architecture comprising: classical computer clusters, quantum computer clusters, and communication links. The classical computer cluster comprises at least one classical computer, wherein each classical computer is provided with a first interface for connection with a quantum computer. A quantum computer cluster comprising at least one quantum computer, wherein each quantum computer is provided with a second interface for connection with a classical computer. The classical computer cluster is used for calling the first interface according to the calculation requirement so as to send the distributed calculation tasks to the quantum computer cluster through the first interface; the second interface is used for receiving the calculation tasks distributed by the classical computer and feeding back calculation results to the first interface. The communication link is disposed between the classical computer and the quantum computer for transmitting data between the classical computer cluster and the quantum computer cluster.
Description
Technical Field
The disclosure belongs to the technical field of computers, and relates to a hybrid quantum computer architecture and a method for executing a computing task thereof.
Background
Today is the primary stage of quantum computer technology development, and how to implement quantum computing is itself the focus of its technology development. From the characteristic of the accelerated computing of the quantum computing, the quantum computing does not have the capability of general computing or is difficult to realize in a short period, so that whether the quantum computing can be directly connected with the existing classical computing or in what form is connected with the existing classical computing to form more powerful quantum computing capability, and no clear development route is available. Moreover, quantum computers, because of the harsh operating conditions, are often not integrated with classical computers or co-located in the same operating environment.
Disclosure of Invention
First, the technical problem to be solved
The present disclosure provides a hybrid quantum computer architecture and a method of performing computing tasks thereof to at least partially solve the following technical problems: at present, when a quantum computer is used, the quantum computer is in an isolated state, and the computing resources between a classical computer and the quantum computer cannot be integrated.
(II) technical scheme
One aspect of the present disclosure provides a hybrid quantum computer architecture. The hybrid quantum computer architecture includes: classical computer clusters, quantum computer clusters, and communication links. The classical computer cluster comprises at least one classical computer, and a first interface for connecting with a quantum computer is arranged on each classical computer in the at least one classical computer. A quantum computer cluster comprising at least one quantum computer, each of said at least one quantum computer being provided with a second interface for connection with said classical computer. The classical computer cluster is used for calling the first interface according to the calculation requirement so as to send the distributed calculation tasks to the quantum computer cluster through the first interface; the second interface is used for receiving the calculation tasks distributed by the classical computer and feeding back calculation results to the first interface. The communication link is disposed between the classical computer and the quantum computer for transmitting data between the classical computer cluster and the quantum computer cluster.
According to an embodiment of the present disclosure, the above-described quantum computer includes: the quantum computing unit is used for realizing quantum computing; and a quantum computer servo electrically connected with the quantum computer unit and used for receiving the calculation tasks distributed by the classical computer cluster through the second interface, converting the calculation tasks into input and control signals of the quantum computer unit and feeding back the calculation results of the quantum computer unit to the second interface.
According to an embodiment of the disclosure, the quantum computing unit and the quantum computer server are connected in a one-to-one, one-to-many or many-to-one manner.
According to an embodiment of the disclosure, the classical computer is in a blocking state when the first interface is invoked, and when the classical computer is in the blocking state, the result returned from the quantum computer cluster through the communication link must be waited for, and the program executed by the classical computer can be executed continuously. Alternatively, the classical computer may be in a non-blocking state when the first interface is called, the classical computer calls the first interface based on a parallel running process or thread, the quantum computer executes the assigned calculation task, the main program of the classical computer continues to execute the predetermined task without being affected by the parallel running process or thread, and when receiving the calculation result returned from the quantum computer cluster through the communication link, the parallel running process or thread notifies the main program to use the calculation result.
According to an embodiment of the present disclosure, the setting form of the first interface in the classical computer includes one or more of the following forms: dynamic/static link libraries, or device files.
According to an embodiment of the present disclosure, the setting form of the above-mentioned second interface in the quantum computer includes one or more of the following forms: dynamic/static link libraries, device files, or dedicated hardware control logic.
According to an embodiment of the present disclosure, the communication link comprises a physical communication line or comprises a physical communication line and a line switch. The circuit switch is used for communication interconnection of physical communication lines. The physical communication line includes: ethernet, cable, optical fiber, wireless WIFI, USB direct-connection bus, RS232 direct-connection bus, RS485 direct-connection bus or GPIB direct-connection bus. The circuit-switching device includes: network switches or routers.
A second aspect of the present disclosure provides a method of performing a computational task by the hybrid quantum computer described above. The method comprises the following steps: the classical computer cluster receives the complete task/program of the target calculation; the classical computer cluster determines whether a first computing task/program which can be accelerated by the quantum computer cluster exists in the execution process of the complete task/program of the target computing; in the case that the first computing task/program exists, calling a first interface in the classical computer cluster to send the first computing task/program to the quantum computer cluster through a communication link to perform availability inquiry; the quantum computer cluster or the classical computer cluster determines whether available quantum computing units exist and whether resource allocation in the available quantum computing units meets the condition of calculation acceleration; in case it is determined that there are available quantum computing units and that the resource allocation in the available quantum computing units fulfils the condition of computational acceleration, the above-mentioned available quantum computing units execute the first computational task/program and feed back the computational result to the above-mentioned classical computer cluster via the second interface.
According to an embodiment of the present disclosure, the above method further includes: in case it is determined that there is no first computing task/program that can be accelerated by the quantum computer cluster, that there is no available quantum computing unit, or that the resource allocation in all available quantum computing units does not meet the condition of the computational acceleration, the above-mentioned classical computer cluster performs the above-mentioned first computing task/program with the computing resources of the classical computer, or gives a feedback result refusing to perform the above-mentioned first computing task/program, so that an instruction for a re-operation or intervention is issued by the task issuer.
According to an embodiment of the present disclosure, the above method further includes: further determining, if the first computing task/program is determined to be present, whether the first computing task/program has a call authority to the first interface and a use authority to a quantum computer in the quantum computer cluster; and when the first computing task/program has a calling authority for the first interface and a using authority for the quantum computers in the quantum computer cluster, calling the first interface in the classical computer cluster, and sending the first computing task/program to the quantum computer cluster via a communication link for availability inquiry.
(III) beneficial effects
From the above technical solution, it can be seen that the hybrid quantum computer architecture and the method for executing the computing task provided by the present disclosure have the following beneficial effects:
the method comprises the steps that interfaces are respectively arranged on a classical computer and a quantum computer, and a communication link is arranged between the classical computer and the quantum computer, the interfaces pack remote equipment into local equipment, after a first interface on the classical computer is called, a first calculation task/program assigned by the classical computer is subjected to data conversion according to the requirements of the remote quantum computer, adjustment and transmission are carried out according to the type of the communication link, and return data are waited to be received so as to report the return data to the classical computer; the second interface on the quantum computer converts the data transmitted by the remote classical computer through the communication link into the standard input which can be understood by the local quantum computer servo, packages the return value, and transmits the return value to the remote classical computer through the communication link, thus realizing the effective communication between the classical computer and the quantum computer, forming a mixed computer architecture with stronger performance under the condition that the classical computer and the quantum computer are only rarely changed, and being beneficial to improving the operation force and the operation efficiency.
Drawings
Fig. 1 is a schematic structural diagram of a hybrid quantum computer architecture according to an embodiment of the present disclosure.
Fig. 2 is a schematic structural diagram of a hybrid quantum computer architecture according to another embodiment of the present disclosure.
Fig. 3 is a schematic structural diagram of a hybrid quantum computer architecture according to yet another embodiment of the present disclosure.
Fig. 4 is a schematic structural diagram of a hybrid quantum computer architecture according to yet another embodiment of the present disclosure.
Fig. 5 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to an embodiment of the present disclosure.
Fig. 6 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to another embodiment of the present disclosure.
Fig. 7 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to yet another embodiment of the present disclosure.
Fig. 8 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to yet another embodiment of the present disclosure.
[ symbolic description ]
100-hybrid quantum computer architecture;
110-classical computer clusters;
111-classical computer a; 112-a first interface of classical computer a;
113-classical computer b; 114-a first interface of classical computer b;
115-classical computer c; 116-a first interface of classical computer c;
117-common interface of a, b and c of classical computer;
120-quantum computer clusters;
121-quantum computer a; 122-a second interface of quantum computer a;
123-quantum computer B; 124-a second interface of quantum computer B;
130-a communication link;
131-physical communication lines; 132-line exchanger.
Detailed Description
The embodiment of the disclosure provides a hybrid quantum computer architecture and a method for executing a computing task thereof, wherein the hybrid quantum computer architecture realizes the interconnection between classical computer clusters and quantum computer clusters and the integration of computing resources, and the method improves the computing power and the computing efficiency by judging whether the resource allocation in available quantum computing units meets the condition of computing acceleration in advance, and cooperatively adopting the classical computer and the quantum computer to complete the computing task under the condition that the quantum computer clusters can realize computing acceleration.
For the purposes of promoting an understanding of the principles and advantages of the disclosure, reference will now be made to the embodiments illustrated in the drawings and specific language will be used to describe the same.
A first exemplary embodiment of the present disclosure provides a hybrid quantum computer architecture.
Fig. 1 is a schematic structural diagram of a hybrid quantum computer architecture according to an embodiment of the present disclosure. Fig. 2 is a schematic structural diagram of a hybrid quantum computer architecture according to another embodiment of the present disclosure. Fig. 3 is a schematic structural diagram of a hybrid quantum computer architecture according to yet another embodiment of the present disclosure. Fig. 4 is a schematic structural diagram of a hybrid quantum computer architecture according to yet another embodiment of the present disclosure.
Referring to fig. 1 to 4, a hybrid quantum computer architecture 100 provided in an embodiment of the present disclosure includes: classical computer cluster 110, quantum computer cluster 120, and communication link 130. The classical computer cluster 110 comprises at least one classical computer, each of which is provided with a first interface for connection with a quantum computer. The quantum computer cluster 120 includes at least one quantum computer, each of the at least one quantum computer having a second interface for connecting with the classical computer. The classical computer cluster 110 is configured to call the first interface according to a computing requirement, so as to send the distributed computing task to the quantum computer cluster 120 through the first interface; the second interface is used for receiving the calculation tasks distributed by the classical computer and feeding back calculation results to the first interface. The communication link 130 is disposed between the classical computer and the quantum computer for transmitting data between the classical computer cluster 110 and the quantum computer cluster 120.
In fig. 1 to 4, taking the classical computer cluster 110 as an example, three classical computers are described as a classical computer a 111, a classical computer b 113 and a classical computer c 115, and first interfaces provided on the classical computer a 111, the classical computer b 113 and the classical computer c 115 are denoted by reference numerals 112, 114 and 116, respectively. Taking the example of quantum computer cluster 120 comprising one quantum computer a in fig. 1 and 2, and taking the example of quantum computer cluster 120 comprising two quantum computers, namely quantum computer a 121 and quantum computer B123 in fig. 3 and 4, the second interfaces provided on quantum computer a 121 and quantum computer B123 are respectively denoted by reference numerals 122 and 124.
According to an embodiment of the present disclosure, the above-described quantum computer includes: the quantum computing unit is used for realizing quantum computing; and a quantum computer servo electrically connected with the quantum computer unit and used for receiving the calculation tasks distributed by the classical computer cluster through the second interface, converting the calculation tasks into input and control signals of the quantum computer unit and feeding back the calculation results of the quantum computer unit to the second interface.
In this disclosure, a classical computer may be a large computer center, such as a supercomputer, or a personal user's computer. Classical computers refer to existing computers that contain both hardware and software.
In the present disclosure, a quantum computer may include a pure quantum system (quantum computing unit) for realizing quantum computing, and a hardware and software system (quantum computer servo) for controlling and coordinating the operation of the pure quantum system. In the following description, the scalar subsystem is described as a quantum computing unit, and the software and hardware system is described as a quantum computer servo.
Among other physical implementations of quantum computing units include, but are not limited to: superconducting, semiconductor quantum dots, optical, etc., and the quantum computing units may be programmable or non-programmable. Under specified operating conditions, the quantum computing unit preferentially handles a series of homogeneous problems, but does not exclude any type of handling, in which case additional state switching time may be required. The quantum computing unit in the present disclosure may be a quantum computer using physical bits, or may be a computing unit in a quantum computer having logical bits. In addition, the physical places where the quantum computer clusters and the classical computer clusters are located are not limited, and can be adjacent or far apart, and the space positions among all quantum computers in the quantum computer clusters are not limited, and can be adjacent or far apart; the spatial locations between the individual classical computers within a cluster of classical computers are also not limiting and may be contiguous or widely spaced.
The quantum computer servo is a software and hardware aggregate of an instruction input device and a control device of a quantum computing unit, and can be a classical computer used for control locally of the quantum computer or a local special device. The quantum computer servo is used for receiving task data of classical computation (the task data can be received by the second interface from the first interface or can be directly input by a local user), converting the task data into input and control signals of special quantum computation, and feeding back the result given by the quantum computation unit to the second interface or the local classical computer.
According to an embodiment of the disclosure, the quantum computing unit and the quantum computer server are connected in a one-to-one, one-to-many or many-to-one manner.
According to an embodiment of the present disclosure, the setting form of the first interface in the classical computer includes one or more of the following forms: dynamic/static link libraries, or device files.
According to an embodiment of the present disclosure, the setting form of the above-mentioned second interface in the quantum computer includes one or more of the following forms: dynamic/static link libraries, device files, or dedicated hardware control logic.
According to an embodiment of the present disclosure, the communication link 130 includes a physical communication line 131, as shown with reference to fig. 1 and 2; or the communication link 130 includes a physical communication line 131 and a line switch 132. The circuit-switch may also be described as a switching center. The circuit switch 132 is used for communication interconnection of the physical communication circuit 131. The physical communication line 131 includes: ethernet, cable, optical fiber, wireless WIFI, USB direct-connection bus, RS232 direct-connection bus, RS485 direct-connection bus or GPIB direct-connection bus. The circuit-switching device includes: network switches or routers. The connection of the communication link between a classical computer and a quantum computer is also illustrated in fig. 3 in different lines.
Classical computers may employ classical modes when used or programmed, while tasks/programs (e.g., function functions) that may be accelerated by a quantum computer are invoked through an interface and then executed.
Each communication link may have a separate interface at the classical computer end, or a total interface may handle all communication links from the quantum computer cluster. That is, between a first interface in a classical computer cluster and a second interface in a quantum computer cluster: may be in many-to-one form as shown in fig. 1 (where a quantum computer cluster may include multiple quantum computers, not limited to the one illustrated in fig. 1); may be in a many-to-many form as shown in fig. 3; or in a one-to-many fashion, as shown in fig. 4, all of the classical computers in the classical computer cluster 110 employ a common one of the first interfaces, illustrated in fig. 4 as a common interface 117.
Each communication link is at the quantum computer end, and if the communication link adopts a bus form similar to network communication, the communication link is generally in a one-to-many connection form, namely one quantum computer can respond to the connection requests of a plurality of classical computers.
According to an embodiment of the disclosure, the classical computer is in a blocking state when the first interface is invoked, and when the classical computer is in the blocking state, the result returned from the quantum computer cluster through the communication link must be waited for, and the program executed by the classical computer can be executed continuously. Alternatively, the classical computer may be in a non-blocking state when the first interface is called, the classical computer calls the first interface based on a parallel running process or thread, the quantum computer executes the assigned calculation task, the main program of the classical computer continues to execute the predetermined task without being affected by the parallel running process or thread, and when receiving the calculation result returned from the quantum computer cluster through the communication link, the parallel running process or thread notifies the main program to use the calculation result.
According to the hybrid quantum computer architecture provided by the embodiment, interfaces are respectively arranged on a classical computer and a quantum computer, and a communication link is arranged between the classical computer and the quantum computer, the interfaces package remote equipment into local equipment, after a first interface on the classical computer is called, a first calculation task/program assigned by the classical computer is subjected to data conversion according to the requirements of the remote quantum computer, and is regulated and transmitted according to the type of the communication link, and the return data is waited to be received so as to be reported to the classical computer; the second interface on the quantum computer converts the data transmitted by the remote classical computer through the communication link into the standard input which can be understood by the local quantum computer servo, packages the return value, and transmits the return value to the remote classical computer through the communication link, thus realizing the effective communication between the classical computer and the quantum computer, forming a mixed computer architecture with stronger performance under the condition that the classical computer and the quantum computer are only rarely changed, and being beneficial to improving the operation force and the operation efficiency.
In an embodiment, the procedure of calling the first interface by the classical computer is as follows: when a classical computer executes a computing task or converts the computing task into a computing program to execute, when the program executes a first computing task/program (such as a function) which can be accelerated by a quantum computer, the first interface is called, and judges whether the quantum computer in a quantum computer cluster can provide services (such as whether a usable quantum computing unit exists or not, whether a classical user side has calling authority or whether the total time for computing by the quantum computer has advantages or not) or not, if the quantum computer can not provide services, a result of failure in calling is returned, or the classical computer is switched to continue to execute the task, or the result of refusing to execute the first computing task/program is given because the first computing task/program is too long to be executed by the classical computer or the current resource cannot be realized. If the quantum computer is available for service, the first interface of the classical computer prepares the data for the requirements of the quantum computer, and sends the data to the second interface of the quantum computer via a communication link. Meanwhile, after receiving data, the second interface of the quantum computer prepares the data, and provides the data for the quantum computer for servo, and the quantum computer servo controls the quantum computing unit to perform computation. After the calculation result is given, the quantum computer unit is handed to the second interface through the quantum computer servo, the second interface performs data preparation and then sends the data to the first interface of the classical computer through the communication link, and the first interface of the classical computer returns the data to the program which calls the interface at the time.
When the classical computer calls the first interface, the classical computer may be in a blocking type, for example, the classical program must wait for a link return structure before continuing to execute; or the non-blocking type classical program throws out the process or thread type to call the interface, the main program continues to execute the following content, and when the interface feeds back the result, the previous process/thread is responsible for informing the main program to use the subsequent data result.
The interface is called and data conversion is carried out by the communication link, and links such as data return through the communication link are time overhead, so that the real acceleration advantage is achieved only when the actual calculation time of the quantum computer is smaller than the calculation total time of a classical computer, and the interface in the disclosure needs to judge whether to call the quantum computer to serve or not, and the judging condition is that the quantum computer can be accelerated by a quantum computer cluster.
A second exemplary embodiment of the present disclosure provides a method of performing a computational task by the above hybrid quantum computer.
Fig. 5 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to an embodiment of the present disclosure.
Referring to fig. 5, a method for performing a computational task by a hybrid quantum computer provided by an embodiment of the present disclosure includes the operations of: s201, S202, S203, S204, S205, and S206.
In operation S201, the classical computer cluster receives a complete task/program of the target calculation.
In operation S202, the classical computer cluster determines whether there is a first computing task/program that can be accelerated by the quantum computer cluster during execution of the complete task/program of the target computation.
In operation S203, in the case where it is determined that the first computing task/program exists, a first interface in the classical computer cluster is called to send the first computing task/program to the quantum computer cluster via a communication link to perform an availability query.
In operation S204, the above-described quantum computer cluster or the above-described classical computer cluster determines whether there are available quantum computing units.
In operation S205, the above-described quantum computer cluster or the above-described classical computer cluster determines whether the resource allocation in the available quantum computing units satisfies a condition for computation acceleration.
In an embodiment, the information may be fed back to the classical computer cluster periodically by the quantum computer cluster according to the available state and resource allocation situation of the quantum computer, in which case, whether a usable quantum computing unit exists and whether the resource allocation in the usable quantum computing unit satisfies the condition of computing acceleration may be determined by the classical computer cluster according to the information fed back by the quantum computer cluster.
In another embodiment, it may be that after operation S203, it is determined by the quantum computer cluster whether there are available quantum computing units inside and whether resource allocation in the available quantum computing units satisfies a condition for computational acceleration.
In operation S206, in case it is determined that there are available quantum computing units and that the resource allocation in the available quantum computing units satisfies the condition of the computation acceleration, the available quantum computing units execute the first computation task/program and feed back the computation result to the classical computer cluster through the second interface.
Referring to fig. 5, the method of performing a computing task by a hybrid quantum computer provided by an embodiment of the present disclosure includes the following operations S209 in addition to the operations S201, S202, S203, S204, S205, and S206 described above: in case it is determined that there is no first computing task/program that can be accelerated by the quantum computer cluster, that there is no available quantum computing unit, or that the resource allocation in all available quantum computing units does not meet the condition of the computational acceleration, the above-mentioned classical computer cluster performs the above-mentioned first computing task/program with the computing resources of the classical computer, or gives a feedback result refusing to perform the above-mentioned first computing task/program, so that an instruction for a re-operation or intervention is issued by the task issuer.
In one embodiment, the classical computer is in a blocking state when the first interface is invoked, and the method further comprises operations S207a and S208a as shown in fig. 5. The above-described operation S208a must be performed after operation S206.
In operation S207a, in case of invoking the first interface in the classical computer cluster, the classical computer cluster is in a blocking state waiting for a result returned from the quantum computer cluster via the communication link.
In operation S208a, in case a result returned by the quantum computer cluster is received, the classical computer cluster continues to perform the given task.
Fig. 6 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to another embodiment of the present disclosure.
In another embodiment, the classical computer is in a non-blocking state when the first interface is invoked, the above method further comprising operations S207b and S208b as shown in fig. 6.
In this embodiment, in operation S203, the classical computer is in a non-blocking state when calling the first interface, and the classical computer calls the first interface based on a form of parallel running processes or threads.
In operation S207b, the cluster of classical computers is in a non-blocking state, and the main program of the classical computer continues to perform the given task without being affected by the parallel running processes or threads.
In operation S208b, when a result returned from the quantum computer cluster is received, the parallel running process or thread notifies the main program to use the calculation result.
Fig. 7 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to yet another embodiment of the present disclosure. Fig. 8 is a flow chart of a method of performing computational tasks by a hybrid quantum computer according to yet another embodiment of the present disclosure.
According to an embodiment of the present disclosure, as shown with reference to fig. 7 and 8, the above-described method includes operations in addition to the above-described operations S201 to S206, S207a, S208a, and S209, or in addition to the above-described operations S201 to S206, S207b, S208b, and S209: s301 and S302.
In operation S301, in case it is determined that the first computing task/program exists, it is further determined whether the first computing task/program has a call authority to the first interface.
In operation S302, it is determined whether the first computing task/program has a right of use for the quantum computers in the quantum computer cluster.
Operation S203 is performed in the case where the results of operations S301 and S302 are both yes.
That is, in operation S203 of the present embodiment, when the first computing task/program has a call authority to the first interface and a use authority to the quantum computers in the quantum computer cluster, the first interface in the classical computer cluster is called, and the first computing task/program is transmitted to the quantum computer cluster via a communication link to perform availability query.
In summary, the embodiments of the present disclosure provide a hybrid quantum computer architecture and a method for executing a computing task thereof, where interfaces are respectively provided on a classical computer and a quantum computer, and a communication link is provided between the classical computer and the quantum computer, where the interfaces package remote devices into a local device, after a first interface on the classical computer is called, a first computing task/program assigned by the classical computer performs data conversion according to a requirement of the remote quantum computer, and adjusts and transmits according to a type of the communication link, and waits for receiving return data to report the return data to the classical computer; the second interface on the quantum computer converts the data transmitted by the remote classical computer through the communication link into the standard input which can be understood by the local quantum computer servo, packages the return value, and transmits the return value to the remote classical computer through the communication link, thus realizing the effective communication between the classical computer and the quantum computer, forming a mixed computer architecture with stronger performance under the condition that the classical computer and the quantum computer are only rarely changed, and being beneficial to improving the operation force and the operation efficiency. The hybrid quantum computer architecture described above enables the integration of computing resources and interconnections between classical and quantum computer clusters. According to the method, whether the resource allocation in the available quantum computing units meets the condition of computing acceleration is judged in advance, and under the condition that the computing acceleration can be achieved by adopting the quantum computer cluster, the classical computer and the quantum computer are cooperatively adopted to jointly complete the computing task, so that the computing power and the computing efficiency are improved.
The disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. Various component embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a related device according to embodiments of the present disclosure may be implemented in practice using a microprocessor or Digital Signal Processor (DSP) or programmable gate array (FPGA). The present disclosure may also be embodied as a device or apparatus program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present disclosure may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
The various embodiments of the disclosure described above may be freely combined to form additional embodiments, unless otherwise technical hurdles or contradictions exist, which are all within the scope of the disclosure.
While the foregoing embodiments have been described in some detail for purposes of clarity of understanding, it will be understood that the foregoing embodiments are merely illustrative of the invention and are not intended to limit the invention, and that any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (9)
1. A hybrid quantum computer architecture, comprising:
a classical computer cluster comprising at least one classical computer, each of the at least one classical computer being provided with a first interface for connection with a quantum computer; a quantum computer cluster comprising at least one quantum computer, each of the at least one quantum computer being provided with a second interface for connection with the classical computer; the classical computer cluster is used for calling the first interface according to the calculation requirement so as to send the distributed calculation tasks to the quantum computer cluster through the first interface; the second interface is used for receiving the calculation tasks distributed by the classical computer and feeding back calculation results to the first interface;
the quantum computer comprises a quantum computing unit and a quantum computer servo; the quantum computer servo is used for receiving a calculation task distributed by a classical computer cluster through the second interface, converting the calculation task into an input and control signal of the quantum computing unit, and feeding back a calculation result of the quantum computing unit to the second interface; and
the communication link is arranged between the classical computer and the quantum computer and is used for transmitting data between the classical computer cluster and the quantum computer cluster;
wherein the classical computer determines whether there is a first computational task/program that can be accelerated by the quantum computer; calling the first interface to judge whether a quantum computer capable of providing service exists in the quantum computer cluster or not under the condition that the first computing task/program exists;
wherein, the quantum computer capable of providing service characterizes that available quantum computers exist in the quantum computer and the resource allocation in the available quantum computer units meets the condition of calculation acceleration;
wherein, in the event that it is determined that the serviceable quantum computer is present in the quantum computer cluster, the serviceable quantum computer performs the first computing task/program;
the classical computer is in a blocking state when the first interface is called, and when the classical computer is in the blocking state, the classical computer must wait for a result returned from the quantum computer cluster through the communication link before the program executed by the classical computer can be executed continuously; or,
the classical computer is in a non-blocking state when the classical computer calls the first interface, the classical computer calls the first interface based on the form of parallel running processes or threads, the quantum computer executes distributed computing tasks, a main program of the classical computer continues to execute established tasks without being influenced by the parallel running processes or threads, and when a computing result returned from the quantum computer cluster through the communication link is received, the parallel running processes or threads inform the main program of utilizing the computing result.
2. The hybrid quantum computer architecture of claim 1, wherein the quantum computer comprises:
the quantum computing unit is used for realizing quantum computing; and
and the quantum computer servo is electrically connected with the quantum computer unit.
3. The hybrid quantum computer architecture of claim 2, wherein the quantum computing unit and the quantum computer servo are in a one-to-one, one-to-many, or many-to-one connection.
4. The hybrid quantum computer architecture of claim 1, wherein the first interface is provided in a classical computer in a form comprising one or more of the following forms: dynamic/static link libraries, or device files.
5. The hybrid quantum computer architecture of claim 1, wherein the form of placement of the second interface in the quantum computer comprises one or more of the following forms: dynamic/static link libraries, device files, or dedicated hardware control logic.
6. The hybrid quantum computer architecture of claim 1, wherein the communication link comprises a physical communication line or comprises a physical communication line and a circuit switch for communication interconnection of the physical communication line;
the physical communication line includes: ethernet, cable, optical fiber, wireless WIFI, USB direct-connection bus, RS232 direct-connection bus, RS485 direct-connection bus or GPIB direct-connection bus;
the circuit-switched device comprises: network switches or routers.
7. A method of performing computational tasks by the hybrid quantum computer architecture of claim 2, comprising:
the classical computer cluster receives the complete task/program of the target calculation;
the classical computer cluster determines whether a first computing task/program which can be accelerated by the quantum computer cluster exists in the execution process of the complete task/program of the target computing;
in the case that the first computing task/program exists, calling a first interface in the classical computer cluster to send the first computing task/program to the quantum computer cluster through a communication link for availability inquiry;
the quantum computer cluster or the classical computer cluster determines whether there are available quantum computing units and whether resource allocation in the available quantum computing units satisfies a condition for computational acceleration;
in case it is determined that there are available quantum computing units and that the resource allocation in the available quantum computing units fulfils the condition of computational acceleration, the available quantum computing units execute a first computational task/program and feed back the computational result to the classical computer cluster via a second interface.
8. The method as recited in claim 7, further comprising:
in case it is determined that there is no first computational task/program that can be accelerated by the quantum computer cluster, that there is no available quantum computing unit, or that the resource allocation in all available quantum computing units does not meet the condition of computational acceleration, the classical computer cluster executes the first computational task/program with the computing resources of the classical computer, or gives a feedback result refusing to execute the first computational task/program, in order to issue an instruction for a re-operation or intervention by the task issuer.
9. The method as recited in claim 7, further comprising:
further determining, in the event that the first computing task/program is determined to be present, whether the first computing task/program has call rights to the first interface and use rights to quantum computers in the quantum computer cluster; and
and under the condition that the first computing task/program has calling authority to the first interface and has using authority to the quantum computers in the quantum computer cluster, calling the first interface in the classical computer cluster, and sending the first computing task/program to the quantum computer cluster through a communication link to perform availability inquiry.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110359265.0A CN112862104B (en) | 2021-04-01 | 2021-04-01 | Hybrid quantum computer architecture and method for executing computing tasks thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110359265.0A CN112862104B (en) | 2021-04-01 | 2021-04-01 | Hybrid quantum computer architecture and method for executing computing tasks thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862104A CN112862104A (en) | 2021-05-28 |
| CN112862104B true CN112862104B (en) | 2024-02-27 |
Family
ID=75992166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110359265.0A Active CN112862104B (en) | 2021-04-01 | 2021-04-01 | Hybrid quantum computer architecture and method for executing computing tasks thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862104B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114048857B (en) * | 2021-10-22 | 2024-04-09 | 天工量信(苏州)科技发展有限公司 | Calculation force distribution method and device and calculation force server |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1870015A (en) * | 2006-06-28 | 2006-11-29 | 中山大学 | Cooperative quantum computer architecture structural conceptual |
| US7875876B1 (en) * | 2006-06-15 | 2011-01-25 | Hrl Laboratories, Llc | Scalable quantum computer |
| WO2020018752A1 (en) * | 2018-07-18 | 2020-01-23 | IonQ, Inc. | Quantum hybrid computation |
| WO2020047426A1 (en) * | 2018-08-30 | 2020-03-05 | Rigetti & Co, Inc. | Low-latency, high-performance hybrid computing |
| CN112368722A (en) * | 2018-05-16 | 2021-02-12 | 河道研究有限公司 | Estimating energy levels of a physical system |
| CN112465146A (en) * | 2020-11-19 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Quantum and classical hybrid cloud platform and task execution method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080313430A1 (en) * | 2007-06-12 | 2008-12-18 | Bunyk Paul I | Method and system for increasing quantum computer processing speed using digital co-processor |
-
2021
- 2021-04-01 CN CN202110359265.0A patent/CN112862104B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7875876B1 (en) * | 2006-06-15 | 2011-01-25 | Hrl Laboratories, Llc | Scalable quantum computer |
| CN1870015A (en) * | 2006-06-28 | 2006-11-29 | 中山大学 | Cooperative quantum computer architecture structural conceptual |
| CN112368722A (en) * | 2018-05-16 | 2021-02-12 | 河道研究有限公司 | Estimating energy levels of a physical system |
| WO2020018752A1 (en) * | 2018-07-18 | 2020-01-23 | IonQ, Inc. | Quantum hybrid computation |
| WO2020047426A1 (en) * | 2018-08-30 | 2020-03-05 | Rigetti & Co, Inc. | Low-latency, high-performance hybrid computing |
| CN112465146A (en) * | 2020-11-19 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Quantum and classical hybrid cloud platform and task execution method |
Non-Patent Citations (1)
| Title |
|---|
| 量子计算机与经典计算机;王勇等;《创新科技》;20021231(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862104A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10305823B2 (en) | Network interface card configuration method and resource management center | |
| US10592298B2 (en) | Method for distributing load in a multi-core system | |
| US5517662A (en) | Multiprocessor system with distributed memory | |
| EP1518368B1 (en) | Load balancing device and method therefor | |
| WO1990002378A1 (en) | Multilevel distributed computer system | |
| CN112862104B (en) | Hybrid quantum computer architecture and method for executing computing tasks thereof | |
| US8775637B2 (en) | Recording medium storing communication program, information processing apparatus, and communication procedure | |
| EP0871308A2 (en) | Method and program product for flexible control of interrupts in multiprocessor systems | |
| CN110365786B (en) | Job processing system, asynchronous job scheduling method, and computer device | |
| US20230328134A1 (en) | Methods, apparatus and systems for cloud native application multi-factor load balancing | |
| US6810457B2 (en) | Parallel processing system in which use efficiency of CPU is improved and parallel processing method for the same | |
| US11513858B2 (en) | System for operating and method for arranging nodes thereof | |
| CN116233022A (en) | Job scheduling method, server and server cluster | |
| CN1430144A (en) | Method of multiplexing peripheral PCI equipment by multiprocessor | |
| US6035366A (en) | Computer architecture using packet switches for internal data transfer | |
| US10877800B2 (en) | Method, apparatus and computer-readable medium for application scheduling | |
| US11789777B2 (en) | Resource utilization method, electronic device, and computer program product | |
| JP4877317B2 (en) | Information processing apparatus and interrupt control method | |
| KR0175534B1 (en) | Data distribution and communication methods on a shared distributed memory system | |
| KR101483603B1 (en) | Method and apparatus for controling resource with enhanced efficiency in communication system | |
| KR100442599B1 (en) | Message handling apparatus and method in exchange system using distributed objects of workstation | |
| WO2021111586A1 (en) | Distributed processing system | |
| JPS619742A (en) | Phenomenon control system | |
| KR920008263B1 (en) | Method for dynamic rearrangement of processor network | |
| JP2000242609A (en) | Distributed object dynamic arrangement control method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |