`571-272-7822
`
`
`
`
`
`
`
`
`
`
` Paper 10
`
`
`
` Entered: February 13, 2024
`
`UNITED STATES PATENT AND TRADEMARK OFFICE
`____________
`
`BEFORE THE PATENT TRIAL AND APPEAL BOARD
`____________
`
`MERCEDES-BENZ USA, LLC,
`Petitioner,
`v.
`DAEDALUS PRIME LLC,
`Patent Owner.
`____________
`
`IPR2023-01333
`Patent 10,049,080 B2
`____________
`
`
`
`
`
`
`Before WILLIAM V. SAINDON, THOMAS L. GIANNETTI, and
`GREGG I. ANDERSON, Administrative Patent Judges.
`
`
`GIANNETTI, Administrative Patent Judge.
`
`
`
`DECISION
`Granting Institution of Inter Partes Review
`35 U.S.C. § 314
`Dismissing Contingent Motion for Joinder
`35 U.S.C. § 315(c); 37 C.F.R. § 42.122
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`I.
`
`INTRODUCTION
`
`A. Background
`Mercedes-Benz USA, LLC (“Mercedes-Benz”) filed a Petition
`requesting inter partes review of claims 1–24 (the “challenged claims”) of
`U.S. Patent No. 10,049,080 B2 (Ex. 1001, the “’080 patent”). Paper 1
`(“Pet.”). The Petition was accompanied by a “Contingent Motion for
`Joinder” seeking joinder with IPR2023-00567 (the “’567 IPR”), a
`proceeding originally filed by Samsung and Qualcomm, involving a
`challenge to the same claims of the ’080 patent as this proceeding. Paper 2.
`That proceeding has now been terminated. ’567 IPR, Paper 22 (Termination
`Decision).
`Daedalus Prime (“Patent Owner”) has waived filing of a preliminary
`response. Paper 9. For the reasons stated below, we determine that
`Petitioner has established a reasonable likelihood that it would prevail with
`respect to at least one claim. See 35 U.S.C. § 314(a) (inter partes review
`may not be instituted unless “there is a reasonable likelihood that the
`petitioner would prevail with respect to at least 1 of the claims challenged in
`the petition.”) We therefore institute inter partes review as to all of the
`challenged claims of the ’080 patent and all of the asserted grounds of
`unpatentability. See SAS Inst. Inc. v Iancu, 138 S.Ct. 1348, 1356 (2018); 37
`C.F.R. § 42.108 (a) (“When instituting inter partes review, the Board will
`authorize the review to proceed on all of the challenged claims and on all
`grounds of unpatentability asserted for each claim.”).
`
`2
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`B. Related Proceedings
`The parties identify the following district court and ITC proceedings
`involving the ’080 patent: (1) Daedalus Prime LLC v. Arrow Electronics,
`Inc., 1:22-cv-01107 (D. Del.); (2) Daedalus Prime LLC v. Mazda Motor
`Corporation, 1:22-cv-01109 (D. Del.); (3) Daedalus Prime LLC v. Mazda
`Motor Corporation, 1:22-cv-01108 (D. Del.); (4) Daedalus Prime LLC v.
`Samsung Electronics Co., Ltd., 2:22-cv-00352 (E.D. Tex.); (5) Certain
`Integrated Circuits, Mobile Devices Containing the Same, and Components
`Thereof, Inv. No. 337-TA-1335 (USITC); and (6) Certain Semiconductors
`and Devices and Products Containing the Same, Including Printed Circuit
`Boards, Automotive Parts, and Automobiles, Inv. No. 337-TA-1332
`(USITC). Pet. 1–2; Paper 5, 2.
`As noted supra, the ’080 patent was also the subject of the ’567 IPR,
`now terminated.
`
`C. Real Parties-in-Interest
`Petitioner identifies the following real parties-in-interest: Mercedes-
`Benz USA, LLC; Mercedes-Benz Intellectual Property GmbH & Co. KG;
`Mercedes-Benz Group AG; and Mercedes-Benz AG. Pet. 1. Patent Owner
`identifies Daedalus Prime LLC as the real party-in-interest. Paper 5, 2
`At this stage, neither party challenges those identifications.
`
`D. The ’080 Patent
`The ’080 patent is titled “Asymmetric Performance Multicore
`Architecture with Same Instruction Set Architecture.” Ex. 1001, (54). The
`’080 patent relates to multi-core processors in computing systems and
`
`3
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`methods of managing power in multi-core processors. Id. at 1:16–1:20; 2:1–
`2:42; 3:50–4:19.
`According to the ’080 patent, typically, power management schemes
`scale up processing performance as the system’s workload increases and
`scale down processing performance as the system’s workload decreases. Id.
`at 2:22–26. Scaling process performance with workload is usually
`accomplished by enabling or disabling entire cores and raising or lowering
`core supply voltages and operating frequencies in response to workload. Id.
`at 2:30–33. For example, all cores are enabled under a maximum
`performance/power consumption state, and only one core is enabled under a
`minimum performance/power consumption state. Id. at 2:33–41; see also id.
`Fig. 2.
`The ’080 patent explains that some prior art multi-core processor
`power management schemes have been implemented on processors whose
`constituent cores are identical, while others have been implemented on
`processors in which the cores are radically different from each other (i.e.,
`asymmetric). Ex. 1001, 3:34–39. For example, a processor with cores that
`are different from each other may have a low power core that lacks sizeable
`“chunks” of logic circuitry responsible for executing the program code
`instructions compared to the other cores in the processor and supports a
`reduced instruction set. Id. at 3:39–46. However, processors with cores that
`are different from each other can suffer from drawbacks because it is
`difficult for system software to adjust switch operation between processor
`cores having different instruction sets. Id. at 3:46–49.
`The ’080 patent purports to address this issue by disclosing multi-core
`processors in which at least one of the cores is designed to be lower
`4
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`performance and therefore consumes less power than other cores in the
`processor. Id. at 3:50–4:9. According to the ’080 patent, the lower power
`cores have the same logic design as the higher power cores and support the
`same instruction set, but consume less power by having narrower drive
`transistor widths than the higher power cores or other power consumption-
`related design features. Id. at 3:50–62.
`The ’080 patent explains that the lower power core allows the multi-
`processor “to entertain a power management strategy that is the same/similar
`to already existing power management strategies, yet, still achieve an even
`lower power consumption in the lower/lowest performance/power states.”
`Id. at 4:20–46; see also id. Fig. 5. The process begins with a multi-core
`processor in which multiple high power cores and at least one low power
`core are operating. Id. Fig. 6 (610), 4:54–59. When the demand on the
`processor drops below a threshold, a high power core is disabled. Id. at
`4:54–59. This process is repeated with the enabled high power cores each
`time demand reaches a lower threshold. Id. at 4:54–5:6. When all of the
`high power cores are disabled and the demand on the processor continues to
`drop, the low power cores are disabled one by one in the same manner until
`only one low power core is enabled and the lower power state is reached. Id.
`at 5:25–35.
`
`5
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`E. Illustrative Claim
`The Petition challenges claims 1–24, of which claims 1, 9, and 17 are
`independent. Claim 1 is illustrative of the claimed subject matter and
`reproduced below: 1
`1. [preamble] A multi-core processor comprising:
`[a][i] a first plurality of cores and a second plurality of cores
`that support a same instruction set,
`[a][ii] wherein the second plurality of cores consume less
`power, for a same applied operating frequency and supply
`voltage, than the first plurality of cores; and
`[b][i] power management hardware to, from a state where the
`first plurality of cores and the second plurality of cores are
`enabled, disable all of the first plurality of cores for a drop in
`demand below a threshold without disabling any of the
`second plurality of cores,
`[b][ii] wherein an operating system to execute on the multi-core
`processor is to monitor a demand for the multi-core processor
`and control the power management hardware based on the
`demand.
`Ex. 1001, 7:56–8:3.
`Independent claim 9 is directed to a method of operating a multi-core
`processor. Id. at 8:38–53. Independent claim 17 is directed to “[a] non-
`transitory machine readable medium containing program code” that causes
`the method of claim 9 to be performed. Id. at 9:24–41.
`
`F. References and Other Evidence
`The Petition relies on the following references:
`
`
`1 Paragraph labeling in brackets is based on those provided by Petitioner.
`
`6
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`Publication Date Exhibit(s)
`Nov. 20, 2008
`Ex. 1007
`Apr. 12, 2007
`Ex. 1008
`Dec. 17, 2009
`Ex. 1006
`Jun. 16, 2011
`Ex. 1009
`Sep. 1, 2011
`Ex. 1005
`
`Reference
`Name
`Sutardja ’7482 US 2008/0288748 A1
`Sutardja ’785 US 2007/0083785 A1
`Carmack
`US 2009/0309243 A1
`Rychlik
`US 2011/0145615 A1
`Mathieson3
`US 2011/0213950 A1
`
`In addition, Petitioner submits the Declaration of Dr. Robert Horst.
`Ex. 1034 (“Horst Decl.”). In his declaration, Dr. Horst adopts the positions
`of Dr. Trevor Mudge, who served as petitioners’ expert in the ’567 IPR.
`Horst Decl. ¶ 3.
`
`G. Asserted Grounds of Unpatentability
`Petitioner asserts the challenged claims are unpatentable on the
`following grounds:
`
`
`2 Sutardja ’748 incorporates by reference the disclosure of Sutardja ’785
`(Ex. 1008) in its entirety. See Ex. 1007, 1:8–12.
`
`3 Petitioner represents that Mathieson incorporates by reference the
`disclosure of Carmack in its entirety. Pet. 5 n.5; see also id. at 18.
`
`7
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`Claims Challenged
`
`35 U.S.C. §4
`
`References
`
`1–4, 7–12, 15–20, 23, 24
`
`5, 6, 13, 14, 21, 22
`
`7, 15, 23
`
`1–4, 7–12, 15–20, 23, 24
`
`5, 6, 13, 14, 21, 22
`
`See Pet. 5–6.
`
`103
`
`103
`
`103
`
`103
`
`103
`
`Sutardja5
`
`Sutardja, Rychlik
`
`Sutardja, Carmack
`
`Mathieson,6 Sutardja
`
`Mathieson, Sutardja, Rychlik
`
`H. Overview of the Prior Art
`1. Sutardja ’748 (Ex. 1007)
`Sutardja ’748 is titled “Dynamic Core Switching.” Ex. 1007, (54).
`Sutardja ’748 relates to dynamically switching cores of multi-core
`processing systems of mobile computing devices. Id. ¶ 2. Sutardja ’748
`explains that processor systems in such computing devices may be
`asymmetric, with the processors or cores having different instruction set
`
`4 Because the earliest application from which the ’080 patent claims priority
`was filed before March 16, 2013, the pre-AIA (“America Invents Act”)
`version of § 103 applies. Leahy-Smith America Invents Act (“AIA”), Pub.
`L. No. 112-29, 125 Stat. 284, 285–88 (2011).
`5 Petitioner states that it relies on Sutardja ’748 and Sutardja ’785,
`combined, “as a single reference obviousness ground.” Pet. 4 n.2. Petitioner
`therefore refers to the combined references as “combined Sutardja” or just
`“Sutardja.” See id.; Horst Decl. ¶ 36 n.2.
`6 References to Mathieson in this ground refer to Mathieson and Carmack
`(incorporated by reference into Mathieson). Pet. 14 n.3.
`8
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`architectures, or symmetric, with the processors or cores having identical
`instruction set architectures. Id. ¶¶ 7–8, Figs. 1A, 1B.
`Sutardja ’748 discloses obtaining increased power savings by using a
`multi-core processing system with a low-speed, low-power (LP) core and a
`high-speed, high-power (HP) core. Id. ¶ 212. The instruction set
`architecture (ISA) of the LP core may differ from the ISA of the HP core, or
`alternatively, both may use the same ISAs. Id. ¶ 213.
`Sutardja ’748 discloses using “core morphing” to optimize power
`consumption and improve performance. Id. ¶ 216. In core morphing, cores
`are dynamically enabled (i.e., activated) or disabled (i.e., deactivated) based
`on the system load. Id. ¶ 218. When one core is active, other cores may be
`disabled (i.e., deactivated) to save power. Id. For example, the other cores
`may be put in a standby mode wherein the clock frequency and/or the supply
`voltage of the other cores may be decreased to values that are lower than
`when the cores are active. Id. Alternatively, the other cores may be
`completely shut down by disconnecting the power supply to the cores. Id.
`Sutardja ’748 discloses that “[c]ore morphing may be used in multi-
`core systems comprising one LP core and one HP core. When applications
`demand still higher performance than that provided by one HP core, multiple
`HP cores may be used.” Id. ¶ 219. In the HP mode, the HP core is in the
`active state and processes threads. Id. ¶ 223. The LP core may also operate
`during the HP mode. In other words, the LP core may be in the active state
`during all or part of the HP mode. Id. Sutardja ’748 discloses that core
`morphing is useful for optimizing battery life and performance of mobile
`devices. Id. ¶¶ 217, 222.
`
`9
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`2. Sutardja ’785 (Ex. 1008)
`Sutardja ’785 is titled “System with High Power and Low Power
`Processors and Thread Transfer.” Ex. 1008, (54). Sutardja ’785 and
`Sutardja ’748 are related, in that the application for Sutardja ’785, U.S.
`Patent Application No. 11/523,996 (the “’996 application”), is the
`grandparent (through a continuation and continuation in part) of the
`application for Sutardja ’748. Id. (21).7 As previously noted, the entirety of
`the Sutardja ’785 disclosure is incorporated by reference in Sutardja ’748.
`See supra, Section I.F.
`Sutardja ’785 relates to low power data storage systems. Ex. 1008
`¶ 3. Sutardja ’785 discloses a computing device with a system on chip
`(“SOC”) that includes first and second processors. Id. ¶ 9. The first
`processor implemented by the SOC has active and inactive states and
`processes first and second sets of threads during the active state. Id. The
`second processor implemented by the SOC also has active and inactive
`states. Id. Sutardja ’785 explains that the second processor consumes less
`power in its active state than the first processor when it is in its active state.
`Id.
`
`A control module implemented by the SOC communicates with the
`first and second processors and selectively transfers the second set of threads
`from the first processor to the second processor and selects the inactive state
`of the first processor. Id.
`
`
`7 Sutardja ’748 is a publication of U.S. Patent Application No. 12/215,760,
`which is a continuation of U.S. Patent Application No. 12/145,660, which is
`a continuation-in-part of the ’996 application. Ex. 1007, (21), (63).
`
`10
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`3. Rychlik (Ex. 1009)
`Rychlik is titled “System and Method for Controlling Central
`Processing Unit Power Based on Inferred Workload Parallelism.” Ex. 1009,
`(54). Rychlik discloses portable computing devices with multiple cores and
`methods of controlling power in such devices. Id. ¶¶ 3–4, 26–30. Rychlik
`discloses that a computing device includes an operating system with a
`scheduler that schedules tasks, threads, or a combination of the two for
`execution within the cores, a parallelism monitor that tracks the workload on
`the cores, and a controller that controls the power to the cores (i.e., powers
`them on or off). Id. ¶¶ 35–38. When the workload on the cores meets or
`exceeds a threshold value, the controller may wake up another core, and
`when the workload on the cores falls below a threshold value, the controller
`may power off or put a core into standby mode. Id. ¶¶ 39–40, 88, 95–96.
`According to Rychlik, this process may reduce power consumption. Id.
`¶¶ 4, 95, 97.
`
`4. Carmack (Ex. 1006)
`Carmack is titled “Multi-core Integrated Circuits Having Asymmetric
`Performance Between Cores.” Ex. 1006, (54). Carmack discloses a multi-
`core integrated circuit with asymmetric cores that are each capable of
`implementing substantially all the functionality of the integrated circuit. Id.
`Abstract, ¶ 3. Carmack specifies that the cores may have the same hardware
`design, but different component device designs such that the first core may
`be implemented using a high threshold voltage transistor with a lower
`leakage current, and the second core may be implemented using a low
`
`11
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`threshold voltage transistor with a lower switching delay and lower supply
`voltage. Id. ¶ 15.
`Carmack also describes methods of controlling cores based on
`performance parameters such as workload, operating frequency, power
`consumption, quality of service, or operating temperature. Id. Abstract,
`¶¶ 13, 21. Carmack explains that a core control circuit determines which
`one or more of the cores to use based on the performance parameters and
`then utilizes a first core and idles a second core if a performance parameter
`is within a first range, and utilizes a second core and idles a first core if a
`performance parameter is within a second range. Id. Abstract, ¶¶ 3–5, 23–
`25. A particular core may be idled by turning off its power rail, internally
`gating its power rail, back biasing its substrate, or gating its clock. Id. ¶ 16.
`
`5. Mathieson (Ex. 1005)
`Mathieson is titled “System and Method for Power Optimization.”
`Ex. 1005, (54). Mathieson is a continuation-in-part of U.S. Patent
`Application No. 12/137,053 (“the ’053 application”) and incorporates its
`disclosures. Id. (63), ¶ 1. Carmack issued from the ’053 application.
`Ex. 1006, (21).
`Mathieson discloses a system and method for power optimization.
`Ex. 1005 ¶ 3. Mathieson discloses a method for optimizing power in a
`multi-core processing complex that includes a first set of cores comprising
`one or more fast cores, a second set of cores comprising one or more slow
`cores, and a controller that determines which mode of operation is more
`power efficient and causes processing operations to be executed by the first
`
`12
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`set of cores or the second set of cores to achieve the lowest total power
`consumption. Ex. 1005, Abstract, ¶¶ 20, 28, 38.
`Mathieson explains that a controller within the CPU switches between
`a first mode of operation and a second mode of operation based on workload
`characteristics, performance characteristics of the cores, power
`characteristics of the cores, and operating conditions of the processing
`complex. Id. Abstract, ¶¶ 8–10, 25, 30, Fig. 2. Mathieson discloses that
`“[i]n the first mode of operation, the first set of cores is enabled and operable
`and the second set of cores is disabled” and “[i]n the second mode of
`operation, the second set of cores is enabled and operable and the first set of
`cores is disabled.” Id. ¶ 30 (reference numbers omitted).
`
`The method begins when a processor’s controller directs one or more
`operations to be executed by a first set of cores. Id. ¶ 55, Fig. 4A. Next, the
`controller evaluates a processing parameter associated with processing the
`operations, such as a processing frequency or instruction throughput, and
`determines whether the parameter is above a threshold value. Id. ¶¶ 55–56.
`If the parameter exceeds the threshold, the processor continues processing
`operations using the first set of cores. Id. If the parameter is not above the
`threshold value, the controller directs one or more operations to be executed
`by a second set of cores. Id.
`
`II. DISCRETIONARY DENIAL OF INSTITUTION
`The Petition addresses the issue of discretionary denial under 35
`
`U.S.C. §§ 314(a) and 325(d). Pet. 9–14. Petitioner asserts that the Board
`should not exercise its discretion to deny institution under 35 U.S.C.
`§ 314(b) because the current district court proceedings are stayed and the
`
`13
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`proceeding in the ITC is “not a basis to discretionally deny IPR institution.”
`Id. at 9 (citing the USPTO Director’s June 21, 2022 Guidance Memo
`“Interim Procedure For Discretionary Denials in AIA Post- Grant
`Proceedings with Parallel District Court Litigation”). Petitioner asserts that
`the Board should not exercise its discretion to deny institution under 35
`U.S.C. § 325(d)8 because the analysis under the framework of the Board’s
`precedential decision Advanced Bionics, LLC v. Med-El Elektromedizinische
`Geräte GMBH, IPR2019-01469, Paper 6 at 8 (PTAB Feb. 13, 2020),
`“weigh[s] against denial.” Id. at 9–14.
`
`In this proceeding, Patent Owner has not requested that we exercise
`our discretion to deny institution under either § 314(a) or § 325(d).
`Therefore, we do not reach those issues here. In the ’567 IPR, Patent Owner
`argued that the petition there should be denied under § 325(d). ’567 IPR,
`Paper 12 at 10–22. In our Institution Decision in the ’567 IPR, we addressed
`that issue and, after analyzing Patent Owner’s arguments, we were not
`persuaded to exercise our discretion to deny institution under § 325(d). Id.,
`Paper 13 at 13–19.
`
`III. ANALYSIS OF THE CHALLENGED CLAIMS
`A. Level of Ordinary Skill in the Art
`Petitioner contends a person of ordinary skill in the art of the ’080
`patent would have possessed “a bachelor’s degree in electrical engineering,
`
`
`8 “[T]he Director may take into account whether, and reject the petition or
`request because, the same or substantially the same prior art or arguments
`previously were presented to the Office.” 35 U.S.C. § 325(d).
`14
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`computer science, computer engineering, material science, physics, applied
`physics, or a related field” and would have had “at least two years of
`experience in the research, design, development, or testing of electronic
`circuits or components or software for controlling electronic circuits or
`components, or the equivalent, with additional education substituting for
`experience and vice versa.” Pet. 14–15 (citing Horst Decl. ¶ 31).
`As noted, Patent Owner has expressly waived filing a preliminary
`response. Paper 9. At this stage, therefore, Patent Owner does not dispute
`Petitioner’s description of a person of ordinary skill in the art or provide its
`own description.
`We regard Petitioner’s description as consistent with the prior art
`before us. See Okajima v. Bourdeau, 261 F.3d 1350, 1355 (Fed. Cir. 2001)
`(prior art itself may reflect an appropriate level of skill). Thus, for the
`purpose of our decision, we adopt Petitioner’s proposal.
`
`B. Claim Construction
`We construe claim terms only as relevant to the parties’ contentions
`and only to the extent necessary to resolve the issues in dispute. See Vivid
`Techs., Inc. v. Am. Sci. & Eng’g, Inc., 200 F.3d 795, 803 (Fed. Cir. 1999);
`Nidec Motor Corp. v. Zhongshan Broad Ocean Motor Co., 868 F.3d 1013,
`1017 (Fed. Cir. 2017).
`Neither party proposes claim constructions for our consideration.
`Petitioner reports that it “does not believe that any term requires explicit
`construction.” Pet. 15 (citing Horst Decl. ¶¶ 84–85). Patent Owner does not
`dispute Petitioner’s position or address claim construction. Therefore, we
`determine there are no claim terms that need to be construed at this stage.
`
`15
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`C. Obviousness
`A claim is unpatentable as obvious under 35 U.S.C. § 103(a) if the
`differences between the claimed subject matter and the prior art are such that
`the subject matter, as a whole, would have been obvious at the time the
`invention was made to a person having ordinary skill in the art to which said
`subject matter pertains. KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 406
`(2007). The question of obviousness is resolved on the basis of underlying
`factual determinations, including: (1) the scope and content of the prior art;
`(2) any differences between the claimed subject matter and the prior art; (3)
`the level of skill in the art; and (4) where in evidence, so-called “secondary
`considerations,” including commercial success, long-felt but unsolved needs,
`failure of others, and unexpected results. Graham v. John Deere Co., 383
`U.S. 1, 17–18 (1966). At this stage, neither party has presented any
`evidence on the fourth Graham factor.
`
`D. Obviousness of Claims 1–4, 7–12, 15–20, 23, and 24 Based on
`Sutardja
`Petitioner asserts that Sutardja teaches or suggests each limitation of
`claims 1–4, 7–12, 15–20, 23, and 24 and provides an element-by-element
`analysis. Pet. 21–45; Horst Decl. ¶¶ 86–160. Patent Owner has not filed a
`preliminary response and does not dispute these assertions at this stage.
`
`1. Independent Claim 1
`a. Preamble: A multi-core processor comprising
`Petitioner contends Sutardja ’748 teaches a multi-core processor. Pet.
`
`22 (citing Ex. 1007 ¶ 221; Fig. 3B); Horst Decl. ¶ 87. Dr. Horst testifies,
`“Sutardja [’748] teaches a multi-core processor in the form of ‘a multi-core
`16
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`processing system having a LP core and a HP core.’” Horst Decl. ¶ 87
`(citing Ex. 1007 ¶ 221).
`
`At this stage, Patent Owner does not dispute this contention. We
`determine that on this record Petitioner demonstrates sufficiently that the
`preamble of claim 1 is taught or suggested by Sutardja.9
`
`b. Element 1[a][i]: a first plurality of cores and a second plurality of
`cores that support a same instruction set,
`Petitioner contends that Sutardja discloses this element. Pet. 22.
`
`Petitioner contends that Sutardja ’748 discloses a high-speed, high-power
`(HP) core and a low-speed, low-power (LP) core, both of which support the
`same instruction set. Id. (citing Ex. 1007 ¶ 225). Further, Petitioner
`contends that “Sutardja [’748] also teaches a plurality of HP cores and a
`plurality of LP cores.” Id. (citing Horst Decl. ¶¶ 90–101; Ex. 1007 ¶¶ 219,
`248).
`
`At this stage, Patent Owner does not dispute these contentions. We
`find that Petitioner has made a sufficient showing at this stage that this claim
`element is met by Sutardja ’748. Dr. Horst testifies that “[a person of
`ordinary skill] would have been motivated to include multiple LP cores” in
`Sutardja’s multi-core processor. Horst Decl. ¶ 91. He reasons that “it was
`well-known to include multiple low-power cores together with multiple
`high-power cores in a multi-core processor.” Id. Dr. Horst backs up his
`opinion with citations to technical literature. Id. He testifies further that
`“Sutardja [’748] also provides explicit motivation for including multiple LP
`
`
`9 We do not express an opinion on whether the preamble is limiting.
`
`17
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`cores.” Id. ¶ 92. He continues, “[a]s Sutardja [’748] explains, various types
`of applications may be executed on Sutardja’s multi-core processor.” Id.
`(citing Ex. 1007 ¶ 226). This includes first applications “that require
`relatively low processing speed during operation” and second and third
`applications, “each with their own processing requirements.” Id. ¶¶ 92–93
`(citing Ex. 1007 ¶¶ 226–227). He testifies that a person of ordinary skill
`“seeking to implement Sutardja’s teachings in a system in which a large
`number of applications that require relatively low processing speed during
`operation are expected to operate would therefore have been motivated to
`include multiple LP cores capable of handling the execution of such
`applications without needing to transfer the execution of any of the
`applications to the HP cores.” Id. ¶ 98 (internal quotation marks omitted).
`
`Alternatively, Petitioner relies on the teachings of Sutardja ’785 for
`this claim element. Pet. 25–26.
`
`We determine that on this record Petitioner demonstrates sufficiently
`that this imitation of claim 1 is taught or suggested by Sutardja.
`
`
`
`c. Element 1[a][ii]: wherein the second plurality of cores consume less
`power, for a same applied operating frequency and supply voltage,
`than the first plurality of cores
`Petitioner relies on Sutardja ’748 to meet this claim element. Pet. 26–
`
`27. Petitioner explains that “[t]he second cores (Sutardja’s LP cores)
`consume less power, for a same applied operating frequency and supply
`voltage, than the first cores (Sutardja’s HP cores).” Id. at 27; Horst Decl.
`¶ 103.
`Dr. Horst testifies that “the power consumption of a core with narrow
`transistors will be less than a core with wider transistors.” Horst Decl.
`18
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`¶ 103. He concludes that “[a person of ordinary skill] would recognize that
`Sutardja [’748]’s LP core will consume less power than its HP cores for the
`same reason.” Id. (citing Ex. 1007 ¶ 230). His testimony is supported by
`Sutardja ’748, which discloses that “[t]he transistors 106 of the HP core 24
`tend to consume more power during operation in the active state than the
`transistors 110 of the LP core 28 . . . . Gates of the transistors 106 may be
`larger than gates of the transistors 110.” Ex. 1007 ¶ 230 (quoted in Horst
`Decl. ¶ 103).
`
`At this stage we find Dr. Horst’s testimony to be credible in light of
`Sutardja ’748. Patent Owner does not challenge Petitioner’s contentions at
`this stage. We, therefore, find that, on this record Petitioner demonstrates
`sufficiently that Sutardja ’748 meets this limitation.
`
`d. Element 1[b][i]: power management hardware to, from a state where
`the first plurality of cores and the second plurality of cores are
`enabled, disable all of the first plurality of cores for a drop in demand
`below a threshold without disabling any of the second plurality of
`cores,
`Petitioner relies on Sutardja ’748 to meet this element. Pet. 27–34;
`Horst Decl. ¶¶ 104–118. Specifically, Petitioner identifies the “hypervisor”
`in Sutardja ’748 as disclosing this element. Pet. 32–34. Petitioner explains
`that “[a person of ordinary skill] would have understood that the hardware
`on which the disclosed hypervisor is installed corresponds to the claimed
`power management hardware.” Id. at 33–34 (citing Horst Decl. ¶ 118).
`We find also that Petitioner demonstrates sufficiently that Sutardja
`’748 discloses that the first and second plurality of cores are enabled and the
`first plurality of cores is disabled (but not the second plurality) when there is
`a drop in demand. Pet. 29–32. Referring to Figure 4 of Sutardja ’748,
`19
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`Petitioner explains that “[a person of ordinary skill] would have . . .
`understood that the transition from the HP mode (with both the HP and LP
`cores enabled) to the LP mode (with only the LP cores enabled) would occur
`without disabling any of the LP cores (the claimed second plurality of
`cores).” Pet. 31–32. Dr. Horst provides supporting testimony. Horst Decl.
`¶¶ 112–113. Patent Owner does not challenge this assertion at this stage.
`We find that Petitioner has sufficiently shown on this record that Sutardja
`’748 meets this element.
`
`e. Element 1[b][ii]: wherein an operating system to execute on the multi-
`core processor is to monitor a demand for the multi-core processor
`and control the power management hardware based on the demand.
`Petitioner asserts that Sutardja ’748 meets this element. Pet. 34–35;
`Horst Decl. ¶¶ 119–124. Referring to Figure 5 of Sutardja ’748, Petitioner
`identifies Kernel Module 220 and PMS Module 242 as the claimed operating
`system software. Pet. 34–35. Petitioner contends that “Sutardja ’[748]
`further discloses that the operating system (kernel module and PMS module)
`controls the power management hardware (core switching module) based on
`the demand.” Id. at 35 (citing Ex. 1007 ¶ 253).
`Patent Owner does not challenge this assertion at this stage. On this
`record we find that Petitioner has sufficiently shown that Sutardja ’748
`meets this element.
`
`f. Summary
`We find, on this record, that Petitioner demonstrates a reasonable
`
`likelihood of prevailing on this challenge to claim 1.
`
`20
`
`
`
`
`IPR2023-01333
`Patent 10,049,080 B2
`
`
`2. Independent Claims 9 and 17
`Petitioner’s analysis of these claims incorporates its analysis of claim
`
`1. Pet. 43–44. At this stage, Patent Owner does not address these claims.
`For the reasons given for claim 1, we find that on this record Petitioner
`demonstrates a reasonable likelihood of prevailing on these challenges.
`
`3. Dependent Claims 2–4, 7, 8, 10–12, 15, 16, 18–20, 23, and 24
`Petitioner provides an analysis for each of these dependent claims in
`
`relation to Sutardja. Pet. 35–42 (claims 2–4, 7, 8), 44–45 (claims 10–12, 15,
`16, 18–20, 23, 24). Patent Owner does not address these claims.
`
`For the reasons given above and in the Petition, we find that on this
`record Petitioner demonstrates a reasonable likelihood of prevailing on these
`challenges.
`
`E. Obviousness of Claims 5, 6, 13, 14, 21, and 22 Based on