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 .
DETAILED ACTION
1. This action is in response to the amendment filed 8/27/2026.
2. Claims 1-20 have been examined and are pending in the application.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
3. Claims 1-7 and 9-17 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Longo U.S Patent No. 11,627,097.
As to claim 1, Longo teaches a method comprising:
receiving an input via an application programming interface from an application (…The API 137 may provide an interface through which the cluster 135 is configured and/or queried by external actors (e.g., the performance manager 138, the computer system 110, and a cloud-based, centralized normalizing agent (e.g., normalizing agent 230 shown in Fig. 2). Depending upon the particular implementation, the API 137 may represent a Representational State Transfer (REST)ful API that uses Hypertext Transfer Protocol (HTTP) methods (e.g., GET, POST, PATCH, DELETE, and OPTIONS) to indicate its actions. Depending upon the particular embodiment, the API 137 may provide access to various telemetry data (e.g., performance, configuration and other system data) relating to the cluster 135 or components thereof…, lines 25-37 column 5), the input specifying a quality-of-service (QoS) parameter for processing a workload associated with the application (…receiving, in a normalizing agent, one or more compute load parameters from one or more background compute processes executing on the one or more computer systems and one or more Quality of Service (QoS) parameters for one or more client compute processes executing on the one or more computer systems…, lines 44-50 column 1);
determining a partition configuration comprising a subset of circuitry of a hardware compute unit dedicated to processing the workload, the determining based at least in part on the QoS parameter; generating a partition in the hardware compute unit having the determined partition configuration; and processing the workload from the application using the generated partition by the hardware compute unit (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
As to claim 2, Longo further teaches the QoS parameter defines latency or throughput (…compute load parameters for a distributed computing system include latency, utilization, a number of input output operations per second (IOPS), a slice service (SS) load, Quality of Service (QoS) settings, or any other performance related information.…, lines 1-5 column 4).
As to claim 3, Longo further teaches the determining the partition configuration includes determining a size of the hardware compute unit to meet the QoS parameter (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
As to claim 4, Longo further teaches the determining the size includes determining a number of columns in a compute array of the hardware compute unit to be used to process the workload (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
As to claim 5, Longo further teaches receiving workload statistics describing the workload and wherein the determining of the partition configuration is based at least in part on the QoS parameter and the workload statistics (…Performance manager 138 can be configured to periodically poll and/or monitor for compute load parameters of the cluster 135 via the API 137. In some examples the polling may be performed on static periodic intervals. In other examples the polling interval may vary based upon one or more parameters (e.g., load, capacity, etc.). Depending upon the particular implementation, the polling may be performed at a predetermined or configurable interval (e.g., X milliseconds or Y seconds). The performance manager 138 may locally process and/or aggregate the collected compute load parameters (e.g., latency, utilization, IOPS, SS load, Quality of Service (QoS) settings, etc.) over a period of time by data point values and/or by ranges of data point values and provide frequency information regarding the aggregated compute load parameters retrieved from the cluster 135 to the normalizing agent 230. …, line 56 column 5 to line 4 column 6).
As to claim 6, Longo further teaches the workload statistics include a number of operations or data movement (…Performance manager 138 can be configured to periodically poll and/or monitor for compute load parameters of the cluster 135 via the API 137. In some examples the polling may be performed on static periodic intervals. In other examples the polling interval may vary based upon one or more parameters (e.g., load, capacity, etc.). Depending upon the particular implementation, the polling may be performed at a predetermined or configurable interval (e.g., X milliseconds or Y seconds). The performance manager 138 may locally process and/or aggregate the collected compute load parameters (e.g., latency, utilization, IOPS, SS load, Quality of Service (QoS) settings, etc.) over a period of time by data point values and/or by ranges of data point values and provide frequency information regarding the aggregated compute load parameters retrieved from the cluster 135 to the normalizing agent 230. …, line 56 column 5 to line 4 column 6).
As to claim 7, Longo further teaches the workload statistics are determined based on prior knowledge of implementation of the workload (…Performance manager 138 can be configured to periodically poll and/or monitor for compute load parameters of the cluster 135 via the API 137. In some examples the polling may be performed on static periodic intervals. In other examples the polling interval may vary based upon one or more parameters (e.g., load, capacity, etc.). Depending upon the particular implementation, the polling may be performed at a predetermined or configurable interval (e.g., X milliseconds or Y seconds). The performance manager 138 may locally process and/or aggregate the collected compute load parameters (e.g., latency, utilization, IOPS, SS load, Quality of Service (QoS) settings, etc.) over a period of time by data point values and/or by ranges of data point values and provide frequency information regarding the aggregated compute load parameters retrieved from the cluster 135 to the normalizing agent 230. …, line 56 column 5 to line 4 column 6).
As to claim 9, Longo further teaches receiving operation data describing operation of the hardware compute unit and wherein the determining of the partition configuration is based at least in part on the QoS parameter and the operation data (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
As to claim 10, Longo further teaches the operation data describes operation of another partition by the hardware compute unit (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
As to claims 11-17, note the discussions of claims 1-6 and 9 above, respectively.
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.
4. Claims 8 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Longo in view of Porter U.S Patent No. 12,333,336.
As to claim 8, Longo does not teach the workload includes execution of a machine-learning model selected from a plurality of precompiled machine-learning models.
Porter teaches a system of managing workload for real-time QoS wherein the workload includes execution of a machine-learning model selected from a plurality of precompiled machine-learning models (…The applications 162 generate workloads that are executed on the GPU 104. Examples of workloads include graphics rendering workloads, transposing workloads, media playback workloads, machine learning workloads and the like..., lines 7-11 column 6).
It would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to have modified Longo reference to include the teachings of Porter reference because executing machine learning workloads from applications is part of managing QoS parameter, as disclosed by Porter.
As to claim 18, Longo further teaches configuring the partition to comply with the quality-of-service parameter (…if during operation 430 it is determined that the available system capacity is not adequate to satisfy the QoS parameters for client processes, then operation passes to operation 435 and a compute resource allocation to one or more background processes may be adjusted (e.g., throttled) to provide additional capacity required to satisfy the QoS parameters for client processes. In some embodiments, one or more background processes may be forced to yield at least a portion of the CPU time allocated to the process for a specified amount of time. This allows the CPU time to be reallocated to a client process. Thus, the operations defined in Fig. 4 define a process by which the normalizing agent 230 may monitor operating conditions and load parameters of a system 300 and periodically adjust compute resources allocated to background processes in an effort to satisfy compute resource requirements associated with client processes…, line 54 column 13 to line 3 column 14).
Longo does not teach configuring the partition to minimize power consumption in processing the workload.
Porter teaches a system of managing workload for real-time QoS wherein the system is configured to minimize power consumption in processing the workload (lines 21-53 column 2).
It would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to have modified Longo reference to include the teachings of Porter reference because by using minimizing power consumption, the system could improve the performance of the system, as disclosed by Porter.
As to claim 19, note the discussions of claims 11 and 18 above.
As to claim 20, note the discussions of claims 2 and 6 above.
Response to Arguments
5. Applicant’s arguments have been fully considered but are moot in view of the new ground(s) rejection.
Applicant’s arguments presented issues which required the Examiner to further view the previous rejection. The Examiner conducted a further search regarding the issues mentioned in Applicant’s response. Therefore, all arguments regarding the cited references of the previous rejection are moot in view of the new grounds of rejection.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andy Ho whose telephone number is (571) 272-3762. A voice mail service is also available for this number. The examiner can normally be reached on Monday – Friday, 8:30 am – 5:00 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Kevin Young can be reached on (571) 270-3180.
Any inquiry of a general nature or relating to the status of this application or proceeding should be directed to the receptionist whose telephone number is 571-272-2100.
Any response to this action should be mailed to:
Commissioner for Patents
P.O Box 1450
Alexandria, VA 22313-1450
Or fax to:
AFTER-FINAL faxes must be signed and sent to (571) 273 - 8300.
OFFICAL faxes must be signed and sent to (571) 273 - 8300.
NON OFFICAL faxes should not be signed, please send to (571) 273 – 3762
/Andy Ho/
Primary Examiner
Art Unit 2194
Prosecution Insights