Dell Products L.P.

Patent Trials and Appeals Board

Jan 26, 2022

2020006593 (P.T.A.B. Jan. 26, 2022)

UNITED STATES PATENT AND TRADEMARK OFFICE UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www.uspto.gov APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 15/499,050 04/27/2017 Farzad Khosrowpour DC-107934.01 7626 160816 7590 01/26/2022 Terrile, Cannatti & Chambers, LLP - Dell P.O. Box 203518 Austin, TX 78720 EXAMINER LO, SUZANNE ART UNIT PAPER NUMBER OPA NOTIFICATION DATE DELIVERY MODE 01/26/2022 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address(es): USPTO@dockettrak.com tmunoz@tcciplaw.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE ____________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________ Ex parte FARZAD KHOSROWPOUR and NIKHIL VICHARE ________________ Appeal 2020-006593 Application 15/499,050 Technology Center 2100 ____________ Before ERIC S. FRAHM, BETH Z. SHAW, and MATTHEW J. McNEILL, Administrative Patent Judges. McNEILL, Administrative Patent Judge. DECISION ON APPEAL Appellant appeals under 35 U.S.C. § 134(a) from the Examiner’s rejection of claims 1, 4, 6, 7, 10, 12, 13, 16, and 18.1 Claims 2, 3, 5, 8, 9, 11, 14, 15, and 17 are canceled. Appeal Br. 7-11 (Claims App.). We have jurisdiction under 35 U.S.C. § 6(b). We affirm. 1 We use the word “Appellant” to refer to “applicant” as defined in 37 C.F.R. § 1.42. Appellant identifies Dell Products L.P. as the real party in interest. Appeal Br. 1. Appeal 2020-006593 Application 15/499,050 2 STATEMENT OF THE CASE Introduction Appellant’s application relates to measuring performance of systems handling stochastic workloads. Spec. ¶ 1. Claim 1 is illustrative of the appealed subject matter and reads as follows: 1. A computer-implementable method for optimizing performance of an information handling system comprising: identifying a simulated application load that represents a target application workload to use when executing a performance optimization operation based upon a particular workload; testing the information handling system being optimized by executing the simulated application load that represents the target application workload on the information handling system; profiling a workload of the information handling system based upon executing the simulated application load that represents the target application workload; applying performance optimization changes to a software configuration of the information handling system based upon analysis of the profiling, the performance optimization changes being applied automatically; analyzing performance of the information handling system after the performance analysis changes are applied; and, presenting information regarding performance improvement to allow a user to appreciate an effect of the performance optimization changes to the information handling system; and wherein the testing comprises generating a plurality of performance measurements based upon performance of the information handling system when executing a plurality of pre- configured simulated workloads; and, the plurality of performance measurements include response time performance measurements, time to completion Appeal 2020-006593 Application 15/499,050 3 performance measurements and latency performance measurements. The Examiner’s Rejections Claims 1, 6, 7, 12, 13, and 18 stand rejected under 35 U.S.C. § 103 as unpatentable over Garrett (US 9,043,788 B2; May 26, 2015) and Lizy Kurian John, More on finding a Single Number to indicate Overall Performance of a Benchmark Suite, 32 ACM SIGARCH Computer Architecture News (Mar. 2004) (“John”) . Final Act. 5-7. Claims 4, 10, and 16 stand rejected under 35 U.S.C. § 103 as unpatentable over Garrett, John, and AJ KleinOsowski & David J. Lilja, MinneSPEC: A New SPEC Benchmark Workload for Simulation-Based Computer Architecture Research, 1 IEEE Computer Architecture Letters (2002) (“KleinOsowski”). Final Act. 7-8. ANALYSIS We adopt as our own (1) the findings and reasons set forth by the Examiner in the Action from which this appeal is taken (Final Act. 5-8), and (2) the reasons set forth by the Examiner in the Examiner’s Answer (Ans. 3- 7) in response to Appellant’s Appeal Brief. We disagree with Appellant’s arguments (see Appeal Br. 5-6). We concur with the findings and conclusions reached by the Examiner. We provide the following for emphasis. Claim 1 Appellant argues the Examiner errs in rejecting claim 1 because Garrett and John do not teach or suggest “the testing comprises generating a plurality of performance measurements based upon performance of the information handling system when executing a plurality of pre-configured simulated workloads.” Appeal Br. 5. In particular, Appellant argues Garrett Appeal 2020-006593 Application 15/499,050 4 does not teach simulated workloads, much less generating a plurality of performance measurements based upon performance of the information handling system when executing a plurality of pre-configured simulated workloads. Id. Appellant has not persuaded us of Examiner error. The Examiner finds, and we agree, Garrett teaches executing applications in a virtual machine environment. Ans. 4 (citing Garrett 1:15-26, 2:35-59). The Examiner finds that virtual machines are execution environments for simulating target applications and, therefore, input loads to virtual machines are simulated workloads. Id. The Examiner finds Garrett teaches obtaining performance metrics such as speed and quality of service for various input loads to the virtual machine. Id. (citing Garrett 5:24-32, 5:56-63, 6:7-19). The Examiner determines that under the broadest reasonable interpretation of “simulated workload,” these disclosures teach this disputed limitation. Appellant argues these findings are in error (see Appeal Br. 5), but Appellant’s argument is conclusory and has not persuasively identified any error in these findings. Appellant also argues Garrett and John do not teach or suggest “presenting information regarding performance improvement to allow a user to appreciate an effect of the performance optimization changes to the information handling system.” Appeal Br. 5. In particular, Appellant argues John teaches calculating a single metric that summarizes overall performance of a system, but does not teach presenting an effect of performance optimization changes. Id. Appellant has not persuaded us of Examiner error. The Examiner finds John teaches a benchmark representing an overall speedup for a suite Appeal 2020-006593 Application 15/499,050 5 of applications. Ans. 5. The overall speedup benchmark is calculated based on a series of weighted individual benchmarks. Id. The Examiner finds this overall speedup represents an improvement in performance of an optimized system. Id. Appellant argues this does not teach or suggest “information regarding performance improvement” that allows “a user to appreciate an effect of the performance optimization changes to the information handling system,” but Appellant has not persuasively explained the alleged insufficiency of these teachings. Instead, Appellant offers a conclusory assertion that John’s teachings are patentably distinct from the disputed claim limitation. We are not persuaded of Examiner error by Appellant’s conclusory assertions. For these reasons, we sustain the obviousness rejection of claim 1. We also sustain the obviousness rejection of independent claims 7 and 13, which Appellant argues are patentable for the same reasons. See Appeal Br. 5. We also sustain the rejections of dependent claims 6, 12, and 18, which Appellant argues are patentable for the same reasons. See id. Claim 4 Claim 4 recites “[t]he method of claim 1, further comprising: identifying longer benchmark tests; and, performing an application specific configuration operation, the application specific system configuration operation correlating longer benchmark tests to smaller simulated loads to generate an application specific system configuration performance score.” Appellant argues the Examiner errs in rejecting claim 4 because KleinOsowski teaches a simulator for determining instruction counts which provides an indication in terms of instruction count of each benchmark, but does not teach the limitations of claim 4. Appeal Br. 6. Appeal 2020-006593 Application 15/499,050 6 Appellant has not persuaded us of Examiner error. The Examiner finds, and we agree, Garrett teaches application specific system configurations to be simulated by a virtual machine. Ans. 5 (citing Garrett 9:34-46, 10:10-19, Fig. 8). The Examiner finds KleinOsowski teaches running a simulated application load for a specific application configuration. Id. (citing KleinOsowski 2). The Examiner finds KleinOsowski teaches simulated loads of different sizes, with some short, some medium, and some long instructions. Id. The Examiner finds the combination of these references teaches the disputed limitation. Appellant’s arguments to the contrary are conclusory and do not persuasively identify error in the Examiner’s findings. For these reasons, we sustain the obviousness rejection of claim 4. We also sustain the obviousness rejection of dependent claims 10 and 16, which Appellant argues are patentable for the same reasons. See Appeal Br. 6. CONCLUSION In summary: Claim(s) Rejected 35 U.S.C. § Reference(s)/Basis Affirmed Reversed 1, 6, 7, 12, 13, 18 103 Garrett, John 1, 6, 7, 12, 13, 18 4, 10, 16 103 Garrett, John, KleinOsowski 4, 10, 16 Overall Outcome 1, 4, 6, 7, 10, 12, 13, 16, 18 Appeal 2020-006593 Application 15/499,050 7 No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a)(1)(iv). See 37 C.F.R. § 41.50(f) (2019). AFFIRMED