DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Information Disclosure Statement
The Information Disclosure Statement filed on 10 October 2023 has been considered by the examiner.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-3, 5-13, and 15-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Archer et al. (Pub. No. US 2012/0185867) in view of Allen (U.S. Patent No. 9,998,392).
Claim 1:
Archer et al. disclose a method, comprising:
applying a selective harvesting (SH) algorithm to the infrastructure graph to identify the nodes that are able to meet requirements of a workload, and the nodes that are identified collectively form a subset of all the nodes of the infrastructure graph [fig. 6; pars. 0065-0069 – “The example of FIG. 6 also includes selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry. In the example of FIG. 6, selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry may be carried out, for example, by comparing the attributes (606) of a particular set of nodes (602a-602e) to the resource requirements and required geometry for a workload (612a) to determine a best match. Determining a best match may include prioritizing specific resource requirements of the workload (612a), determining a score for a candidate set of nodes (602a-602e), and so on.”]; and
applying a workload placement optimization algorithm to the nodes of the subgraph [fig. 6; pars. 0041, 0065-0069 – “In the example of FIG. 1, the deployment module (103) also optimizes the deployment of a workload by selecting a workload for deployment on a subset of the compute nodes (102) of the parallel computer (100). In the example of FIG. 1, the workload represents a series of computer program instructions that are to be executed. Workloads may be characterized, for example, by the amount of processor cycles that are required to execute the workload, the amount of memory that is required to execute the workload, the amount of a particular type of operations are required to execute the workload, and so on. In the example of FIG. 1, a workload may be selected for deployment on a subset of the compute nodes (102) of the parallel computer (100) based on, for example, a shortest-time-to-completion scheduling algorithm, a first-in-first-out scheduling algorithm, the availability of a particular type of system resource, a priority associated with the workload, and so on.” … “The example of FIG. 6 also includes deploying (620) the workload (612a) on the selected nodes. In the example of FIG. 6, deploying (620) the workload (612a) on the selected nodes may be carried out, for example, by sending the workload (612a), or a portion thereof, to an execution queue on the selected nodes, assigning the workload (612a) for execution on processors of the selected nodes, and so on.”].
However, Archer et al. do not specifically disclose,
building an infrastructure graph comprising nodes and edges, and each node represents a respective infrastructure, and each edge encodes information about aspects of a network that includes the nodes;
based on the applying, generating a subgraph of the infrastructure graph, and the subgraph comprises the subset [More specifically, Archer et al. disclose the selection of candidate nodes from a pool of nodes, but do not specifically disclose using a graph-based method.];
In the same field of endeavor, Allen discloses,
building an infrastructure graph comprising nodes and edges, and each node represents a respective infrastructure, and each edge encodes information about aspects of a network that includes the nodes [column 3, lines 6-30 – “In an embodiment, a placer (e.g., computer system implementing a placer process), constructs a network graph for a plurality of machines (computing devices) such that each edge between two nodes in the network graph is weighted according to connectivity between a corresponding pair of machines. Connectivity may be measured in various ways, such as bandwidth achievable between the machines. The network graph may be constructed by, for instance, encoding information about the network in an appropriate data structure. In some examples, the network graph is represented by a matrix modeling the network graph, such as the Laplacian of the network graph. The placer may receive a component graph (also referred to as a user graph) for components in a distributed system such that each edge between two nodes in the component graph is weighted according to connectivity requirements between a corresponding pair of components. The placer may similarly represent the component graph as a data structure encoding a matrix that represents the component graph.”];
based on the applying, generating a subgraph of the infrastructure graph, and the subgraph comprises the subset [column 4, line 43 – column 5, line 24 – “In an embodiment, a placer (e.g., computer system implementing a placer process), constructs a network graph for a plurality of machines (computing devices) such that each edge between two nodes in the network graph is weighted according to connectivity between a corresponding pair of machines. Connectivity may be measured in various ways, such as bandwidth achievable between the machines. The network graph may be constructed by, for instance, encoding information about the network in an appropriate data structure. In some examples, the network graph is represented by a matrix modeling the network graph, such as the Laplacian of the network graph. The placer may receive a component graph (also referred to as a user graph) for components in a distributed system such that each edge between two nodes in the component graph is weighted according to connectivity requirements between a corresponding pair of components. The placer may similarly represent the component graph as a data structure encoding a matrix that represents the component graph.”];
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Archer et al. to include a graph-based method, as taught by Allen, in order to improve performance by providing a simple and easy way to communicate relationships between nodes in the network.
Claim 2 (as applied to claim 1 above):
Archer et al. disclose,
wherein each of the nodes is associated with respective computing resources [par. 0050 – “Also stored in RAM (156) is a compute node operating system (162), a module of computer program instructions and routines for an application program's access to other resources of the compute node. It is typical for an application program (159) and parallel communications library (161) in a compute node (102) of a parallel computer to run a single thread of execution with no user login and no security issues because the thread is entitled to complete access to all resources of the compute node (102).”].
Claim 3 (as applied to claim 1 above):
Allen discloses,
wherein each edge is directed to those nodes that have a direct connection to a communication network [column 3, lines 6-30 – “In an embodiment, a placer (e.g., computer system implementing a placer process), constructs a network graph for a plurality of machines (computing devices) such that each edge between two nodes in the network graph is weighted according to connectivity between a corresponding pair of machines. Connectivity may be measured in various ways, such as bandwidth achievable between the machines. The network graph may be constructed by, for instance, encoding information about the network in an appropriate data structure. In some examples, the network graph is represented by a matrix modeling the network graph, such as the Laplacian of the network graph. The placer may receive a component graph (also referred to as a user graph) for components in a distributed system such that each edge between two nodes in the component graph is weighted according to connectivity requirements between a corresponding pair of components. The placer may similarly represent the component graph as a data structure encoding a matrix that represents the component graph.”].
Claim 5 (as applied to claim 1 above):
Archer et al. disclose,
wherein a query budget constraint determines a minimum number of nodes to which the SH algorithm is applied [fig. 6; pars. 0065-0069 – Nodes are selected from the entire set of nodes. (“The example of FIG. 6 also includes selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry. In the example of FIG. 6, selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry may be carried out, for example, by comparing the attributes (606) of a particular set of nodes (602a-602e) to the resource requirements and required geometry for a workload (612a) to determine a best match. Determining a best match may include prioritizing specific resource requirements of the workload (612a), determining a score for a candidate set of nodes (602a-602e), and so on.”)].
Claim 6 (as applied to claim 1 above):
Archer et al. disclose,
wherein all the nodes in the subgraph are able to support the workload [figs. 6-7; pars. 0065-0081 - The example of FIG. 6 also includes selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry. In the example of FIG. 6, selecting (618) a set of nodes having attributes that meet the specific resource requirements and arranged to meet the required geometry may be carried out, for example, by comparing the attributes (606) of a particular set of nodes (602a-602e) to the resource requirements and required geometry for a workload (612a) to determine a best match. Determining a best match may include prioritizing specific resource requirements of the workload (612a), determining a score for a candidate set of nodes (602a-602e), and so on.].
Claim 7 (as applied to claim 1 above):
Allen discloses,
wherein the selective harvesting (SH) algorithm is iteratively applied until enough nodes are identified to support the workload [column 5, lines 25-62 – “For example, the placer may randomly add and/or subtract values to one or more weights or may tighten and/or relax one or more constraints. Such alterations to the weights and/or constraints produce an altered set of conditions which may result in a different placement solution when the placement is run again. The different placement solution may result in a better or worse suitability score and thus, solutions that result in better suitability scores may be retained while those that do not may be discarded. Iteratively perturbing weights and/or constraints on placement of the components with random value changes, re-running the placement and selecting those perturbations that improve the placement solution may result in a solution that converges to an optimal and/or near optimal placement solution using a global optimization approach such as, for example, a metaheuristic such as simulated annealing, a heuristic such as a genetic algorithm and/or some other such approach.”].
Claim 8 (as applied to claim 1 above):
Archer et al. disclose,
wherein the workload placement optimization algorithm is applied based on the infrastructure subgraph, and based on the workload and associated tasks [par. 0041 – “In the example of FIG. 1, the deployment module (103) also optimizes the deployment of a workload by selecting a workload for deployment on a subset of the compute nodes (102) of the parallel computer (100). In the example of FIG. 1, the workload represents a series of computer program instructions that are to be executed. Workloads may be characterized, for example, by the amount of processor cycles that are required to execute the workload, the amount of memory that is required to execute the workload, the amount of a particular type of operations are required to execute the workload, and so on. In the example of FIG. 1, a workload may be selected for deployment on a subset of the compute nodes (102) of the parallel computer (100) based on, for example, a shortest-time-to-completion scheduling algorithm, a first-in-first-out scheduling algorithm, the availability of a particular type of system resource, a priority associated with the workload, and so on.”].
Claim 9 (as applied to claim 1 above):
Archer et al. disclose,
wherein the workload placement optimization algorithm is able to identify nodes for placement of the workload more quickly in the nodes of the subgraph than if the workload placement optimization algorithm searched all the nodes of an entire infrastructure [fig. 6; pars. 0041, 0065-0069 – A subset of nodes may be identified more quickly than traversing the entire set of nodes. (“In the example of FIG. 1, the deployment module (103) also optimizes the deployment of a workload by selecting a workload for deployment on a subset of the compute nodes (102) of the parallel computer (100). In the example of FIG. 1, the workload represents a series of computer program instructions that are to be executed. Workloads may be characterized, for example, by the amount of processor cycles that are required to execute the workload, the amount of memory that is required to execute the workload, the amount of a particular type of operations are required to execute the workload, and so on. In the example of FIG. 1, a workload may be selected for deployment on a subset of the compute nodes (102) of the parallel computer (100) based on, for example, a shortest-time-to-completion scheduling algorithm, a first-in-first-out scheduling algorithm, the availability of a particular type of system resource, a priority associated with the workload, and so on.” … “The example of FIG. 6 also includes deploying (620) the workload (612a) on the selected nodes. In the example of FIG. 6, deploying (620) the workload (612a) on the selected nodes may be carried out, for example, by sending the workload (612a), or a portion thereof, to an execution queue on the selected nodes, assigning the workload (612a) for execution on processors of the selected nodes, and so on.”)].
Claim 10 (as applied to claim 1 above):
Archer et al. disclose,
wherein the applying of the selective harvesting (SH) algorithm is performed in response to a user request to execute the workload [fig. 7; par. 0077 – “In the example of FIG. 7, determining (614) specific resource requirements for the workload (612a) to be deployed can include receiving (702) specific resource requirements from a user. In the example of FIG. 7, receiving (702) specific resource requirements from the user can include, for example, receiving information from a user indicating the number of nodes (602a-602e) upon which a workload (612a) should run, the amount of memory needed for executing the workload (612a), and so on. In the example of FIG. 7, receiving (702) specific resource requirements from the user can may also include receiving information from a user indicating a prioritization of system processing capabilities. For example, a user may indicate that processing I/O operations should be prioritized over data communications operations, such that nodes (602a-602e) with high I/O performance will be favored for selection over nodes that perform data communications operations efficiently.”].
Claim 11:
Claim 11, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 1 above.
Claim 12 (as applied to claim 11 above):
Claim 12, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 2 above.
Claim 13 (as applied to claim 11 above):
Claim 13, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 3 above.
Claim 15 (as applied to claim 11 above):
Claim 15, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 5 above.
Claim 16 (as applied to claim 11 above):
Claim 16, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 6 above.
Claim 17 (as applied to claim 11 above):
Claim 17, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 7 above.
Claim 18 (as applied to claim 11 above):
Claim 18, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 8 above.
Claim 19 (as applied to claim 11 above):
Claim 19, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 9 above.
Claim 20 (as applied to claim 11 above):
Claim 20, directed to a non-transitory storage medium, is rejected for the same reasons set forth in the rejection of claim 10 above.
Allowable Subject Matter
Claims 4 and 14 objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Teixeira de Abreu Pinho et al. (Pub. No. US 2023/0121060) disclose, “In Step 312, the best encoded infrastructure candidate subgraph is selected based on the predicted execution results obtained in Step 310. In one or more embodiments, the best encoded infrastructure candidate subgraph is the one for which the best predicted execution result is obtained relative to the execution requirement set associated with the workload to be executed. As an example, the execution prediction set may include that the execution time should be 50 minutes or less. Therefore, the predicted execution result of the ML model is the predicted execution time if the workload is executed on a given infrastructure candidate. The best encoded infrastructure candidate subgraph selected, then, is the encoded infrastructure candidate subgraph corresponding to the lowest predicted execution time among all the candidates assessed, as that candidate is the most likely to have an execution time that satisfies the relevant execution requirement of the execution requirement set associated with the workload.” [par. 0060]
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LARRY T MACKALL whose telephone number is (571)270-1172. The examiner can normally be reached Monday - Friday, 9am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Reginald G Bragdon can be reached at (571) 272-4204. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
LARRY T. MACKALL
Primary Examiner
Art Unit 2131
1 February 2026
/LARRY T MACKALL/Primary Examiner, Art Unit 2139