`
`Case Nos. IPR2015-00158
`IPR2015-00159
`IPR2015-00163
`
`
`In re Patent of: Morton et al.
`U.S. Patent No. 7,296,121
`Issue Date:
`Nov. 13, 2007
`Appl. Serial No.: 10/966,161
`Filing Date:
`Oct. 15, 2004
`Title: REDUCING PROBE TRAFFIC IN MULTIPROCESSOR SYSTEMS
`
`
`DECLARATION OF VOJIN OKLOBDZIJA, Ph.D.
`IN SUPPORT OF PATENT OWNER’S MOTIONS TO AMEND
`
`
`I, Vojin Oklobdzija, PhD, hereby declare as follows:
`
`1.
`
`My name is Dr. Vojin Oklobdzija. I submit this declaration in
`
`support of Patent Owner’s Motions to Amend in IPR2015-00158, -00159, and -
`
`00163. I have been asked to offer technical opinions relating to U.S. Patent No.
`
`7,296,121 and the proposed substitute claims presented by the motions.
`
`2.
`
`I received a Dipl. Ing. (equivalent to a Master’s in Electrical
`
`Engineering in the U.S.) degree in Telecommunications and Electronics in 1971
`
`from the University of Belgrade, Yugoslavia, followed by a Master’s in Computer
`
`Science from the University of California, Los Angeles in 1978. I received a Ph.D.
`
`in Computer Science with a minor in Electronics from the University of California,
`
`Los Angeles in 1982.
`
`3.
`
`Following my Ph.D. graduation, I spent 9 years at IBM’s T.J.
`
`Watson Research Center working on microprocessor architecture, development
`
`
`
`1
`
`
`
`and design. In my career at IBM, I worked on the early development of RISC
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`(Reduced Instruction Set Architecture Computer) architecture and development of
`
`a new processor generation for IBM. Most notably, I worked on the first
`
`commercial RISC computer, IBM ROMP, as well as the first super-scalar
`
`microprocessor, IBM RS/6000.
`
`4.
`
`After leaving IBM, I have held faculty (Full Professor) position at
`
`the University of California, Davis; and visiting positions at the University of
`
`California Berkeley, Sydney University in Australia; EPFL in Switzerland and
`
`others. I have over 20 years of teaching experience, teaching courses in:
`
`Computer Architecture, Computer Design, Digital Design, VLSI Circuits as well
`
`as advanced post-graduate courses in Computer Architecture and Design. During
`
`this time, I served as a consultant with members of the microprocessor industry
`
`extensively and was a principal architect in the Siemens/Infineon TriCore
`
`processor.
`
`5.
`
`After retiring from the academia, I returned back to industry. In
`
`2013, I became a Senior Director of Microprocessor Development at Skyera Inc., a
`
`startup company that was subsequently acquired by Hitachi Ltd. While working at
`
`Skyera, I lead a team developing an on-chip processor array consisting of a grid or
`
`256 processors, including development of its cache-coherency mechanism and its
`
`fast cache memory hierarchy.
`
`
`
`2
`
`
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`Currently I am President and CTO of my own startup company,
`
`6.
`
`Silicon Analytics Inc. and I also work as a consultant. I am a named inventor on
`
`15 issued U.S. Patents and a similar number of international patents. I have also
`
`authored several books on microprocessor design, including a book titled
`
`“Computer Engineering Handbook,” published by CRC Press in 2001, which won
`
`the CHOICE Outstanding Academic Title Award for 2002, as well as “High
`
`Performance Energy Efficient Microprocessor Design” published Springer in 2006.
`
`I have attached a true and correct copy of my curriculum vitae as Exhibit 2017,
`
`which further sets forth my qualifications.
`
`7.
`
`I have reviewed and am familiar with the content of U.S. Patent No.
`
`7,296,121 (“the ’121 Patent”). I have also reviewed each of the items of prior art
`
`cited on the face of the ’121 Patent. I have also reviewed the prior art submitted in
`
`connection with IPR2015-00158, -00159, -00161, -00163, and -00172. I have also
`
`reviewed the prior art disclosed by the Samsung defendants in their answer filed
`
`Memory Integrity LLC v. Samsung Electronics Company Ltd. et al, Dkt. No. 12 (D.
`
`Del. Feb. 24, 2014), Ex. 2038. I have also reviewed the invalidity contentions
`
`served by Intel Corporation for the ’121 Patent in Memory Integrity LLC v. Intel
`
`
`
`3
`
`
`
`Corporation, (D. Or. filed Nov. 1, 2013), Ex. 2039, and the associated prior art1. I
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`understand and am informed that, together, this comprises all prior art of record of
`
`the ’121 Patent as well as all prior art to the ’121 Patent known to the Patent
`
`Owner.
`
`8.
`
`I have reviewed the art of record and the prior art known to the
`
`Patent Owner and it is my opinion that substitute claims 26-34 are patentable over
`
`such prior art, even if the Board concludes that the corresponding original claims
`
`are unpatentable. No single reference which I have reviewed contains each
`
`
`1
`The only qualification to my review of these materials is that, in the
`
`invalidity contentions served by Intel Corporation, there are certain documents
`
`relating to the Intel 870 Chipset which have not been provided to me, and certain
`
`quotes from those documents which have been redacted. I understand that I am not
`
`permitted to see those documents because Intel has designated those documents
`
`“Confidential Attorneys’ Eyes Only” and “Subject to the Prosecution Bar,” and
`
`because the protective order in the litigation prohibits anyone who sees such
`
`materials from being involved in, among other things, participating in advising on
`
`new or amended claims. However, I believe I have been able to adequately review
`
`and understand the materiality of the Intel 870 Chipset based on other public
`
`documentation available regarding that chipset.
`
`
`
`4
`
`
`
`limitation of any of the proposed substitute claims, and no combination of such
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`references renders any of the proposed substitute claims obvious.
`
`9.
`
`As to the limitations of the original claim 16 of the ’121 Patent, it is
`
`my opinion that the Pong and Koster references are the closest and most material
`
`prior art to those claim limitations and the only references of which I have
`
`reviewed which arguably teach probe filtering in a system with processing nodes
`
`connected by point-to-point links.2 As to the Koster reference, I am informed that
`
`Koster is not prior art because the substitute claims are entitled to the November 4,
`
`2002 priority date of the ’347 Application.
`
`10.
`
`As to the Pong reference, Pong itself does not teach any particular
`
`cache coherence protocol states and thus does not practice the limitation of the
`
`proposed substitute claims that “wherein said states comprise cache coherency
`
`states of a cache coherence protocol, and wherein said cache coherence protocol
`
`includes at least a modified state, an exclusive state, a shared state, and an invalid
`
`
`2 I say arguably because, as set forth in my declaration in support of Patent
`
`Owner’s responses, I do not believe that Pong or Koster render any claims of the
`
`’121 Patent invalid. However, I understand that the Board may disagree with my
`
`analysis and that the purpose of these motions is to substitute claims if the Board
`
`concludes that the original claims are invalid.
`
`
`
`5
`
`
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`state.” Moreover, I do not believe that Pong can be readily adapted or modified, or
`
`combined with other references to practice this limitation. In particular, Fong
`
`Pong et al., Design and Performance of SMPs With Asynchronous Caches (Nov.
`
`1999) teaches, in describing the same system as the Pong patent application
`
`reference, that the specific way of connecting the asynchronous architecture
`
`employed by Pong prevented use of the conventional Exclusive state. Ex. 2024.
`
`In particular, Mr. Pong states that “[b]ecause we have no Shared, Dirty or Inhibit
`
`bus lines . . . we cannot implement the E (Exclusive) state of the MESI protocol.”
`
`Ex. 2024 at 7. The reason for this is straightforward—as the Pong patent
`
`publication discusses, the Pong architecture uses two separate sets of connections
`
`for connecting the processors—a “memory control path” and a “data path.” Ex.
`
`1003 ¶¶ 28-42. In Pong’s system “[t]he control path is implemented using an
`
`address bus or switch,” and the “data path” is “implemented with [its own] data
`
`bus or switch .” Ex. 1003 ¶¶ 28-42; see also id. Fig. 3 (depicting separate “address
`
`bus/switch” and “data bus/switch.”). The Pong article further explains that prior
`
`art systems using the full MESI protocol, including the Exclusive state, included
`
`Shared and Dirty Buses. Ex. 2024 at 3. However, the Pong article teaches that the
`
`limited point-to-point architecture of Pong does not have those buses or a point-to-
`
`point equivalent. Ex. 2024 at 7. Thus, it is my opinion that the Pong system is not
`
`readily adaptable to being modified to add an Exclusive state or being combined
`
`
`
`6
`
`
`
`with another reference using an Exclusive state to create a system which includes
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`an Exclusive state.
`
`11.
`
`As to the limitation, “wherein said probe filtering unit is coupled to a
`
`coherent protocol interface and a non-coherent protocol interface,” based on the
`
`prior art I have reviewed, I do not believe that such interfaces are taught in the art
`
`prior to November 4, 2002 (which I understand is the effective filing date of the
`
`proposed substitute claims). The closest prior art regarding these limitations I
`
`found in my review was several patents issued to Mr. David Glasco, one of the
`
`inventors of the ’121 Patent and assigned to Newisys, Inc. In particular, they are
`
`U.S. Patent Nos. 7,103,725 (filed Mar. 22, 2002, published Sep. 25, 2003 as
`
`US2003/0182514, issued Sep. 5, 2006); 7,107,408 (filed Mar. 22, 2006, published
`
`Sep. 25, 2003 as US2003/0182508, issued Sep. 12, 2006); 7,107,409 (filed Mar.
`
`22, 2002, published Sep. 25, 2003 as US2003/0182509, issued Sep. 12, 2006);
`
`7,395,379 (filed May 13, 2002, published Nov. 13, 2003 as US 2003/0212741,
`
`issued Jul. 1, 2008); 7,653,790 (filed May 13, 2002, published Nov. 13, 2003 as
`
`US2003/0210655, issued Jan. 26, 2010); 7,251,698 (filed May 28, 2002, published
`
`Dec. 4, 2003 as US2003/0225909, issued Jul. 31, 2007); 7,155,525 (filed May 28,
`
`2002, published Dec. 18, 2003 as US2003/0233388, issued Dec. 26, 2006);
`
`7,281,055 (filed May 28, 2002, published Dec. 4, 2003 as 2003/0225938, issued
`
`Oct. 9, 2007); 6,865,595 (filed May 28, 2002, published Dec. 4, 2003 as
`
`
`
`7
`
`
`
`US2003/0225978, issued Mar. 8, 2005); and 7,103,636 (filed May 28, 2002,
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`published Dec. 4, 2003 as US2003/0225979, issued Sep. 5, 2006). Each of these
`
`discuss a coherent protocol interface and a non-coherent protocol interface, and
`
`have a figure identical to Figure 3 of the ’121 Patent. E.g. Ex. 2031 (U.S. Patent
`
`No. 6,865,595) at Fig. 3, 8:36-43 (“The cache coherence controller 230 is an
`
`Application Specific Integrated Circuit (ASIC) supporting the local point-to-point
`
`coherence protocol. The cache coherence controller 230 can also be configured to
`
`handle a non-coherent protocol to allow communication with I/O devices”.).
`
`However, it is my opinion that none of these patents anticipates any of the
`
`proposed substitute claims because, for at least the reason that none of them teach
`
`or discuss “probe filtering information representative of states associated with
`
`selected ones of the cache memories.” I understand and am informed that these
`
`patents to Mr. Glasco cannot be prior art to the substitute claims under an
`
`obviousness combination due to their common ownership with the ’121 Patent.
`
`12.
`
`Another reference which I believe reflects the state of the art of
`
`coherent and non-coherent interfaces in November 4, 2002 is Hellwagner et al.,
`
`SCI: Scalable Coherent Interface (1999). This reference teaches:
`
`[C]ache coherence protocols are provided as options only. A
`compliant SCI implementation need not cover coherence; an SCI
`network even cannot participate in coherence actions when it is
`
`
`
`8
`
`
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`attached to the I/O bus . . .
`Ex. 2038 at 9. Thus, this reference appears to teach the use of a coherent interface
`
`or a non-coherent interface, but suggests that a system cannot have both at once.
`
`In particular the phrase that it “cannot participate in coherence actions when it is
`
`attached to the I/O bus” teaches that the system of Hellwagner may not be coupled
`
`to a coherent interface while also being coupled to a non-coherent interface.
`
`Moreover, the Hellwagner does not teach probe filtering.
`
`13.
`
`Thus, it is my opinion that the prior art of record to the ’121 Patent,
`
`as well as the prior art known to the Patent Owner, as of November 4, 2002, does
`
`not teach having a coherent protocol interface and a non-coherent protocol
`
`interface, and certainly does not teach coupling them to a probe filtering unit.
`
`
`
`
`
`
`
`
`
`9
`
`
`
`Case Nos. IPR2015-00158, -00159, -00163
`
`Patent No. 7,296,121
`
`I declare under penalty of perjury that the foregoing is true and correct.
`
`Executed on: August 11, 2015
`
`<
`
`‘._
`
`r’ éfi.
`
`Vojin Oklobdzija, PhD
`
`
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
`CERTIFICATE OF SERVICE
`
`The undersigned hereby certifies that a copy of the foregoing Declaration Of
`
`Vojin Oklobdzija, Ph.D. In Support Of Patent Owner’s Motions to Amend was
`
`served via email on August 11, 2015, on the attorneys for the Petitioners:
`
`W. Karl Renner, Reg. No. 41,265
`Roberto Devoto, Reg. No. 55,108
`3200 RBC Plaza
`60 South Sixth Street
`Minneapolis, MN 55402
`Phone: 202-783-5070
`Fax: 202-783-2331
`Email:
`IPR39521-0007IP1@fr.com
`
`
`IPR39521-0007IP2@fr.com
`
`
`IPR39521-0007IP3@fr.com
`
`
`IPR39521-0007IP4@fr.com
`
`
`renner@fr.com
`
`
`devoto@fr.com
`
`Lewis V. Popovski, Reg. No. 37,423
`Zaed M. Billah, Reg. No. 71,418
`Michael Sander, Reg. No. 71,667
`Kenyon & Kenyon LLP
`One Broadway
`New York, NY 10004
`Phone: 212-425-7200
`Fax: 212-425-5288
`Email:
`MemoryIntegrityv.Sony10760-225@kenyon.com
`lpopovski@kenyon.com
`zbillah@kenyon.com
`msander@kenyon.com
`
`
`
`
`
`
`
`11
`
`
`
`Date: August 11, 2015
`
`
`
`
`
`Patent No. 7,296,121
`Case Nos. IPR2015-00158, -00159, -00163
`
`
` /Michael D. Saunders/
`Michael D. Saunders, Admitted Pro
`Hac Vice
`
`12
`
`