Amazon Technologies, Inc.Download PDFPatent Trials and Appeals BoardJul 29, 20212020003088 (P.T.A.B. Jul. 29, 2021) Copy Citation 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. 14/622,661 02/13/2015 David James Borland AMZ2P034/PM9617-US 8123 136609 7590 07/29/2021 Weaver Austin Villeneuve & Sampson LLP - AMZ P.O. BOX 70250 OAKLAND, CA 94612-0250 EXAMINER LEE, CHUN KUAN ART UNIT PAPER NUMBER 2181 NOTIFICATION DATE DELIVERY MODE 07/29/2021 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@wavsip.com eofficeaction@appcoll.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte DAVID JAMES BORLAND and MARK BRADLEY DAVIS Appeal 2020-003088 Application 14/622,661 Technology Center 2100 Before JASON V. MORGAN, HUNG H. BUI, and MICHAEL J. ENGLE, Administrative Patent Judges. ENGLE, Administrative Patent Judge. DECISION ON APPEAL STATEMENT OF THE CASE Appellant1 appeals under 35 U.S.C. § 134(a) from the Examiner’s rejection of claims 1, 3–8, 11–15, and 17–24, which are all of the claims pending in the application. We have jurisdiction under 35 U.S.C. § 6(b). We reverse. 1 We use the word “Appellant” to refer to “applicant” as defined in 37 C.F.R. § 1.42(a). Appellant identifies Amazon Technologies, Inc. as the real party in interest. Appeal Br. 3. Appeal 2020-003088 Application 14/622,661 2 TECHNOLOGY The application relates to a system on a chip (SoC) with a plurality of modes to provide networking services only, compute services only, or both concurrently. Spec. Abstract. ILLUSTRATIVE CLAIM Claim 1 is illustrative and reproduced below with certain disputed limitations emphasized: 1. A system on a chip (SoC) comprising: a management compute subsystem comprising a processor, memory and a network interface, wherein the network interface is configured to connect to a remote entity over a network and wherein the management compute subsystem is configured to execute instructions from the memory on the processor to operate the SoC in one of a plurality of modes; a network compute subsystem comprising a first set of processing cores, caches, and memory controllers and configured to execute instructions for managing network traffic for a host system external to the SoC, the managing of the network traffic for the host system including monitoring and shaping of network traffic between the host system and a client computer, and the first set of processing cores, caches, and memory controllers forming a first set of resources that are pre-allocated to the network compute subsystem; and a server compute subsystem comprising a second set of processing cores, caches, and memory controllers and configured to execute instructions for providing compute services to the client computer, the second set of processing cores, caches, and memory controllers forming a second set of resources that are separate from the first set of resources and pre-allocated to the server compute subsystem, Appeal 2020-003088 Application 14/622,661 3 wherein in a first mode, the SoC is configured by the management compute subsystem to operate the network compute subsystem, in a second mode, the SoC is configured by the management compute subsystem to operate the server compute subsystem, in a third mode, the SoC is configured by the management compute subsystem to operate the network compute subsystem and the server compute subsystem concurrently, with the network compute subsystem being configured to manage network traffic for the host system and manage network traffic for the server compute subsystem, in the first mode, the management compute subsystem prevents the server compute subsystem from providing the compute services by deactivating or repurposing the second set of processing cores, caches, and memory controllers, and in the second mode, the management compute subsystem prevents the network compute subsystem from managing the network traffic for the host system by deactivating or repurposing the first set of processing cores, caches, and memory controllers. REFERENCES The Examiner relies on the following references as prior art: Name Number Date Davis US 2016/0154760 A9 June 2, 2016 Georgiou US 7,412,588 B2 Aug. 12, 2008 Wang US 2011/0295967 A1 Dec. 1, 2011 Yun US 2013/0268706 A1 Oct. 10, 2013 Appeal 2020-003088 Application 14/622,661 4 REJECTION The Examiner rejects claims 1, 3–8, 11–15, and 17–24 under 35 U.S.C. § 103 as obvious over Davis, Georgiou, Yun, and Wang. Final Act. 3–17. ANALYSIS Claim 1 recites a “network compute subsystem” and a “server compute subsystem,” each of which comprises a separate “set of processing cores, caches, and memory controllers” that are “pre-allocated” to that particular subsystem. Appellant argues that “there is no specific or identifiable subsystem in Davis responsible for providing the functions associated with the network compute subsystem or the functions associated with the server compute subsystem.” Appeal Br. 11. Instead, the components merely execute whichever instructions they are given, regardless of whether those are network compute or server compute instructions. Id. The Examiner finds that “resources are pre-allocated when instructions are executed to carry out the network compute subsystem and server compute subsystem, as these resources can later be re-configured for other function[s] base[d] on execution of other instruction[s].” Ans. 20. According to the Examiner, one of ordinary skilled in the art can also consider resources used for carrying out the network compute subsystem operation and server compute subsystem operation are “pre-allocated” because prior to the execution of the instructions for carrying out the network compute subsystem operation and server compute subsystem operation, the resources are intended to and capable of carrying out the network compute subsystem operation and server compute subsystem operation. Appeal 2020-003088 Application 14/622,661 5 Ans. 20. However, we agree with Appellant that the Examiner fails to address “the distinction between allocating resources . . . and pre-allocating resources.” Reply Br. 3. Although the Specification does not appear to use the term “pre-allocated,” it does disclose that in some embodiments, “each compute subsystem can have fixed allocation of resources.” Spec. ¶ 32; see also id. ¶¶ 30 (“once a SoC is fabricated with a certain configuration, the number and types of processing and memory resources may be fixed for each compute subsystem”), 51–52 (“In some embodiments, allocation of the processing and memory resources for the [network / server] compute subsystem [104 / 106] may be fixed,” such as “after power on reset”). A fixed allocation is one example of pre-allocating resources in advance of their usage. In contrast, merely running a task on any available processor core at the time of execution may be allocating resources, but it is not pre- allocating such resources. The Examiner further determines that “a user could have program[ed] the SOC with instructions so that the set of resources for the network compute subsystem operation is separate from the set of resources for the server compute subsystem operation.” Ans. 21 (emphasis added). However, the courts have explained that “obviousness concerns whether a skilled artisan not only could have made but would have been motivated to make the combinations or modifications of prior art to arrive at the claimed invention.” Belden Inc. v. Berk-Tek LLC, 805 F.3d 1064, 1073 (Fed. Cir. 2015). Here, the Examiner has given no reason or explanation why a person of ordinary skill would have been motivated to program separate resources for the network compute subsystem and server compute subsystem. Appeal 2020-003088 Application 14/622,661 6 Accordingly, we do not sustain the Examiner’s rejection of claims 1, 3–8, 11–15, and 17–24. OUTCOME The following table summarizes the outcome of the rejection: Claim(s) Rejected 35 U.S.C. § Reference(s)/Basis Affirmed Reversed 1, 3–8, 11–15, 17–24 103 Davis, Georgiou, Yun, Wang 1, 3–8, 11–15, 17–24 REVERSED Copy with citationCopy as parenthetical citation