IN THE UNITED STATES DISTRICT COURT
`FOR THE EASTERN DISTRICT OF TEXAS
`MARSHALL DIVISION
`
`ALACRITECH, INC.,
`
`Plaintiff,
`
`Case No. 2:16-cv-693-JRG
`
`v.
`
`CENTURYLINK COMMUNICATIONS
`LLC, et al.
`
`Defendants.
`
`LEAD CASE
`
`JURY TRIAL DEMANDED
`
`

`

`TABLE OF CONTENTS
`
`I.
`
`II.
`
`III.
`
`INTRODUCTION ...............................................................................................................1
`
`LEVEL OF SKILL IN THE ART .......................................................................................2
`
`DISPUTED CLAIM TERMS..............................................................................................3
`
`A.
`
`B.
`
`C.
`
`D.
`
`E.
`
`F.
`
`G.
`
`H.
`
`I.
`
`J.
`
`K.
`
`L.
`
`M.
`
`“context [for communication]”................................................................................3
`
`“status information”...............................................................................................15
`
`“significant network layer or significant transport layer processing” ...................20
`
`“substantially no network layer or transport layer processing”.............................23
`
`“without an interrupt dividing”..............................................................................24
`
`“second apparatus(es)”...........................................................................................31
`
`“RE-ASSEMBLY” CLAIM TERMS....................................................................34
`
`“FLOW” CLAIM TERMS ....................................................................................55
`
`Other Terms ...........................................................................................................80
`
`“means for receiving, by the network interface device from the computer,
`a command to transmit data from the computer to the network;” .........................90
`
`“means for sending, by the network interface device to the network, data
`corresponding to the command, including means for prepending a
`transport layer header to at least some of the data” ...............................................96
`
`“means for sending, by the network interface device to the computer, an
`indication that the data has been sent from the network interface device to
`the network, prior to receiving, by the network interface device from the
`network, an acknowledgement (ACK) that the data has been received”.............102
`
`“means, coupled to the host computer, for receiving from outside the
`apparatus a response to an ISCSI read request command and for fast-path
`processing a portion of the response to the ISCSI read request command,
`the portion including data, the portion being fast-path processed such that
`the data is placed into the destination memory on the host computer
`without the protocol stack of the host computer doing significant network
`layer or significant transport layer processing, the means also being for
`receiving a subsequent portion of the response to the ISCSI read request
`command and for slowpath processing the subsequent portion such that
`the protocol stack of the host computer does network layer and transport
`layer processing on the subsequent portion.” ......................................................108
`
`i
`
`

`

`N.
`
`“first mechanism” / “second mechanism” ...........................................................116
`
`IV.
`
`OTHER COMMENTS.....................................................................................................131
`
`ii
`
`

`

`REBUTTAL DECLARATION OF PAUL S. MIN IN SUPPORT OF PLAINTIFF’S
`CLAIM CONSTRUCTION BRIEF
`
`I.
`
`INTRODUCTION
`
`1.
`
`I have been retained by counsel for Plaintiff Alacritech, Inc. (“Alacritech”) as an
`
`expert in this litigation to provide opinions regarding certain claim terms in U.S. Patent Nos.
`
`7,124,205 (“the ’205 Patent”), 7,237,036 (“the ’036 Patent”), U.S. Patent No. 7,337,241 (“the
`
`’241 Patent”), 7,673,072 (“the ’072 Patent”), U.S. Patent No. 7,945,699 (“the ’699 Patent”),
`
`8,131,880 (“the ’880 Patent”), U.S. Patent No. 8,805,948 (“the ’948 Patent”), and U.S. Patent
`
`No. 9,055,104 (“the ’104 Patent”) (collectively, the “Asserted Patents”). The scope and nature
`
`of my retention is set forth in my February 22, 2017 Declaration (“Opening Declaration”), which
`
`I incorporate into this document in its entirety.
`
`2.
`
`3.
`
`My qualifications and experience are listed in my Opening Declaration.
`
`I am not a lawyer. I have been instructed on the relevant legal standards
`
`regarding claim construction, which I set forth in my Opening Declaration.
`
`4.
`
`The purpose of this Declaration is to address opinions rendered by Mr. Mark
`
`Lanning in his February 22 Declaration of Mr. Mark Lanning Regarding Claim Construction.
`
`(“Lanning Decl.”).
`
`5.
`
`In rendering my opinions, I considered the items listed in Exhibit A attached to
`
`this Declaration, the items discussed or listed herein, and my own experiences in the field. I also
`
`considered and consulted my Opening Declaration as well as the exhibits thereto. I understand
`
`that discovery in this litigation is still ongoing, and I reserve the right to amend or supplement
`
`my opinions in light of further documents, depositions, or discovery disclosures. I further
`
`reserve the right to rely upon any additional information or materials that may be provided to me
`
`or that are relied upon by any of Defendants’ experts or witnesses, if called to testify or to give
`
`1
`
`

`

`additional opinions regarding this matter. I reserve the right to address, including through
`
`reference to new evidence and/or opinions, any further arguments and opinions raised by
`
`Defendants, Mr. Lanning, or any other of Defendants’ experts once they are disclosed.
`
`II.
`
`LEVEL OF SKILL IN THE ART
`
`6.
`
`In my Opening Declaration, I set forth my opinion that “a person of ordinary skill
`
`in the art with respect to the Asserted Patents would have: (i.) at least four years of relevant work
`
`or research experience in the field of network engineering and/or design; (ii.) a Bachelor’s of
`
`Science degree in electrical engineering, computer science, or a related field plus at least two to
`
`three years of relevant work or research experience in the field of network engineering and/or
`
`design, or (iii) an advanced degree (e.g., Masters or PhD) and one to two years of relevant work
`
`or research experience in the field of network engineering and/or design.” (Opening Decl. at
`
`¶55.)
`
`7.
`
`In his opening declaration, Mr. Lanning states that “I have been asked to assume
`
`that a person of ordinary skill in the art at the time of the invention of the Patents-in-Suit would
`
`be a person with at least the equivalent of a B.S. degree in computer science, computer
`
`engineering or electrical engineering with at least five years of industry experience including
`
`experience in computer architecture, network design, network protocols, software development,
`
`and hardware development. In addition, someone with less technical education and more work or
`
`research experience (or vice versa) could also qualify as a person of ordinary skill in the art.”
`
`(Lanning Decl. at ¶ 7.)
`
`8.
`
`Initially, it is unclear whether Mr. Lanning is reciting his own opinion as to the
`
`relevant level of skill in the art, or whether he is merely repeating an opinion that someone
`
`else—presumably Defendants—instructed him to adopt. In either case, I disagree with Mr.
`
`2
`
`

`

`Lanning and/or Defendants that the patent requires “at least five years of industry experience” in
`
`addition to a B.S. degree in a computer-related field. As I recite above, I believe “at least two to
`
`three years of relevant work or research experience” are required in addition to a B.S. degree in a
`
`computer-related field. However, I have reviewed the relevant claim language, my opinions, and
`
`the bases therefor in both my Opening Declaration and this Declaration, and confirmed that they
`
`remain unchanged under Mr. Lanning’s and/or Defendants’ standard.
`
`III.
`
`DISPUTED CLAIM TERMS
`
`A.
`
`9.
`
`“context [for communication]”
`
`I understand the parties have proposed the following constructions for this term:
`
`Alacritech
`“data regarding an active connection”
`
`Indefinite
`
`Defendants
`
`10.
`
`I set forth my opinions and the bases for those opinions as to Alacritech’s
`
`construction in Paragraphs 71-79 of my Opening Declaration.
`
`11.
`
`In his declaration, Mr. Lanning asserts that a person of skill in the art would not
`
`have understood “context” to have a particular meaning “because Alacritech has used the term
`
`inconsistently.” (Lanning Decl. at ¶ 15.) Mr. Lanning then lists portions of different
`
`specifications and transcripts wherein the context is described as containing data regarding an
`
`active connection. (Lanning Decl. at ¶ 31.) Rather than supporting Defendants’ proposal, these
`
`excerpts only show that Alacritech’s construction is appropriate, and that “context” should be
`
`construed as “data regarding an active connection.”
`
`12. Mr. Lanning’s complaint seems to be that because the “context” is described as
`
`containing different data regarding the active connection, a person of skill in the art would be
`
`uncertain as to its scope, and thus it should be deemed indefinite. This is akin to arguing that a
`
`person would not know the scope of a “basket of fruit” should the basket be alternately described
`
`3
`
`

`

`as containing apples, oranges, or bananas. Mr. Lanning’s opinion is without merit. Rather, a
`
`person of skill would understand that by choosing to employ a broader term like “context” or
`
`“context for communication” rather than a narrower term like “context for IP fragments” or
`
`“context for TCP’s sliding window protocol,” the applicants intended the corresponding claims
`
`to cover all such data regarding an active connection, rather than any singular embodiment. In
`
`other words, the examples Mr. Lanning identifies in his declaration would be understood by a
`
`person of skill in the art to be different, non-mutually exclusive embodiments of “context,” the
`
`inclusion of which are exemplary, not self-contradictory.
`
`13.
`
`Paragraph 16 of Mr. Lanning’s declaration excerpts a paragraph from the 1997
`
`Provisional Application, which is also recited at 37:63 to 38:10 of the ’036 patent.1 As I noted in
`
`my prior declaration, this paragraph shows that “‘a context is required to keep track of
`
`information that spans many, possibly discontiguous, pieces of information’ such as IP
`
`reassembly, checksum information being calculated across an IP datagram, and information
`
`regarding segments sent, received, and/or acknowledged.” (Opening Decl. at ¶ 75.) “These
`
`examples of ‘context’ in the specification are all consistent with Alacritech’s proposed
`
`construction as well as the manner in which a person of ordinary skill in the art would have
`
`understood the tern ‘context’ as used in the asserted claims.” (Id.)
`
`14.
`
`In Paragraph 17, Mr. Lanning refers to the portion of the 1997 Provisional
`
`Application that is replicated in 37:63 to 38:50 of the ’036 patent, then asserts “one of ordinary
`
`skill in the art reading the 1997 Provisional Application would have concluded that for TCP data,
`
`the ‘context’ must include the information required to handle the sliding window protocol of
`
`1 Since the ’036 and ’072 patents share a specification, the same section naturally appears in the
`’072 patent at 37:31-45. For the sake of brevity, I have refrained from providing redundant
`citations during the remainder of this declaration.
`
`4
`
`

`

`TCP (the second context).” I disagree. Rather, a person of skill in the art would have concluded
`
`that the context may include “the information required to handle the sliding window protocol of
`
`TCP,” but that it is not required to do so. That the same paragraph explicitly describes a second
`
`type of context used to reassemble IP fragments shows that “context” is broader than a “TCP
`
`sliding window” embodiment.
`
`15.
`
`In Paragraphs 18-19, Mr. Lanning refers to a portion of the 1997 Provisional
`
`Application, which is also recited at 39:34-40 of the ’036 patent. As I noted in my prior
`
`declaration, this paragraph shows that a “‘context associated with [a] connection’ may include
`
`‘the source and destination IP addresses and source and destination TCP ports that define the
`
`connection’ as well as ‘information about the connection itself such as the current send and
`
`receive sequence numbers, and the first-hop MAC addresses etc.’” (Opening Decl. at ¶ 75.)
`
`Again, “[t]hese examples of ‘context’ in the specification are all consistent with Alacritech’s
`
`proposed construction as well as the manner in which a person of ordinary skill in the art would
`
`have understood the tern ‘context’ as used in the asserted claims.” (Id.)
`
`16. Mr. Lanning, however, asserts that because that patent states that a “TCB is a
`
`structure that contains the entire context associated with a connection,” a person of skill “would
`
`further conclude that for TCP data, the scope of the term ‘context’ is the information contained
`
`in the TCB.” First, Mr. Lanning’s interpretation of the cited portion of the specification (’072
`
`Patent at 39:2-3) as limiting the scope of the claim term “context,” is misplaced. The
`
`specification explicitly states that the “connection” referred to in this embodiment is a “TCP
`
`connection.” See ’072 Patent at 38:64-68. Thus, in the embodiment Mr. Lanning refers to, it
`
`makes sense that a TCB would be used to store context. However, the specification also
`
`expressly contemplates contexts for non-TCP connections, e.g. SPX and TTCP. (See ’072 Patent
`
`5
`
`

`

`at 8:53:9:5, 9:10:27, 11:18-36, 15:1-19, 15:33-43, 17:2-18, 18:25-35.) This disclosure makes
`
`clear to a person of ordinary skill in the art that a context need not contain any TCP-specific
`
`information at all. For example, the SPX protocol is based on the IPX protocol at the network
`
`layer, which is different from the IP protocol, on which the TCP protocol is based. SPX relies on
`
`buffer allocation at the receiver and does not use the sliding window flow control used in TCP.
`
`(Encyclopedia of Networking, Electronic Edition (1998) at 739-740.) Further, Mr. Lanning’s
`
`conclusion is logically flawed: even when a TCB is used, a person of ordinary skill in the art
`
`would not understand a TCB to be limited to context information; and nothing in the
`
`specification precludes the TCB from storing other, non-context information nor is context
`
`always stored in a TCB. Instead, as the specification makes clear, in that particular embodiment,
`
`the context associated with a connection is contained in a TCB (along with other information).
`
`Moreover, that the patent describes the TCB as “contain[ing] the entire context associated with a
`
`connection” would indicate to a person of skill that a “context” as recited in the claims—without
`
`the “entire”—is intended to correspond to part or all of the stored data regarding the active
`
`connection. In any event, a person of skill would understand that the specification’s description
`
`of one embodiment of how context may be stored does not require that all contexts in all
`
`embodiments be stored in the same manner, for the same reason that a specification describing a
`
`“basket of bananas”—among other embodiments—would not require that a claim reciting a
`
`“basket of fruit” to be limited to bananas.
`
`17.
`
`In Paragraphs 20-23, Mr. Lanning cites to a number of extrinsic sources that he
`
`believes support his opinion that the term “context” as used in the claims of the ’036 and ’072
`
`Patents is indefinite. As an initial matter, Mr. Lanning does not demonstrate that a person of
`
`skill in the art would have had access to, much less considered such sources relevant, in
`
`6
`
`

`

`ascertaining the meaning of “context” as it is used in the patents. I do not believe that any of the
`
`sources Mr. Lanning relies on inform or reflect the way a person of ordinary skill in the art
`
`would understand “context” in these particular patent claims.
`
`18.
`
`In Paragraph 20, Mr. Lanning points to two sentences in the 1981 Transmission
`
`Control Protocol (TCP) specification (RFC 793) that introduce the notion of a “TCB.” A person
`
`of ordinary skill in the art would not consider the cited sections of RFC 793 as relevant to the
`
`meaning of “context” within the scope of the ’036 and ’072 Patent claims. Indeed, I do not see
`
`the word “context” used at all in the cited sections, and a word search finds it is only mentioned
`
`once in an unrelated section (88801DOC000923). I reserve the right to provide testimony as to
`
`RFC 793, should Mr. Lanning ever opine on its relevance, but based on his declaration, it does
`
`not appear relevant to the definition of “context” as used herein.
`
`19.
`
`In Paragraph 21, Mr. Lanning quotes from an April 13, 1999 document that he
`
`contends was produced in prior litigation between Alacritech and Microsoft. (ALA07371912.)
`
`Mr. Lanning’s declaration does not establish any basis for his opinion that this document would
`
`be relevant to show or inform the manner in which a person of ordinary skill in the art would
`
`interpret the term “context” as it is used in the ’072 and ’036 Patent claims. For example, I do
`
`not see any indication that this document was publicly-available at or around the time of the
`
`invention and Mr. Lanning does not articulate any basis for assuming that an internal,
`
`unpublished document would inform the understanding of a person of ordinary skill in the art.2
`
`20.
`
`To the extent Mr. Lanning is suggesting that this piece of extrinsic evidence
`
`would be considered by a person of ordinary skill in the art to limit the meaning of “context” as
`
`2 Indeed, the document appears to have been created approximately two years after the date of
`the invention and does not appear to have been produced in the Microsoft litigation until seven
`years after the date of the invention.
`
`7
`
`

`

`it is used in the ’072 and ’036 Patents to something narrower than its plain and ordinary
`
`meaning, I disagree. The first page of the cited document (Lanning Decl. Ex. 14) states that the
`
`attached documents provides “a rough idea of the amount of changes that would be required to
`
`port our fast path tcp task offload to your TCP/IP protocol stack.” (ALA07371911.) Moreover,
`
`a facial review of the cited portions of the document suggests that, at most, the author is talking
`
`about an example of a specific type of context – i.e., the “TCP context” that was used in the
`
`particular the embodiment reflected in the document. In any event, that a “TCP context”
`
`embodiment contains “the set of variables used to represent the state of a given TCP connection”
`
`does not mandate that the broader “context” term be so limited. Again by way of analogy, that a
`
`particular fruit basket (e.g., a tropical fruit basket) contains pineapples does not mean that every
`
`type of fruit basket must contain pineapples.
`
`21.
`
`In Paragraph 22, Mr. Lanning cites to a transcript of an audio recording submitted
`
`to the United States Patent Office in interference proceedings relating to the ’140 Patent, which I
`
`understand is not asserted in this case. Again, Mr. Lanning does not provide any basis for any
`
`suggestion that this transcript would have been considered relevant to a person of ordinary skill
`
`in the art in interpreting the claims of the ’036 and ’072 Patent. To the contrary, it appears that
`
`the recording only became a matter of public record in 2011, which is years after the invention
`
`date. I further note that based on the date of the transcript, the discussion occurred in February,
`
`2011 (ALA07396518), long after the effective filing dates for either the ’036 or ’072 patents
`
`(Opening Decl. at ¶¶ 24-26) and after both patents had issued. Moreover, the corresponding
`
`Interference—matter 105,775—involved U.S. Application No. 09/692,561 (ALA07370248),
`
`which matured into U.S. Patent No. 8,631,140. I have been informed that the ’140 Patent is not
`
`asserted in this case, does not share a specification with either the ’036 or ’072 Patents, and its
`
`8
`
`

`

`claims do not even recite a “context.” It is thus unclear how the cited excerpt relates to the
`
`construction of “context” in the ’036 and ’072 Patents.
`
`22.
`
`Additionally, the transcript attached to Mr. Lanning’s declaration as Exhibit 15
`
`does not identify the speakers and there are many portions marked “inaudible,” therefore it is not
`
`clear to me that the recording/transcript actually is “a discussion among the inventors of the ’072
`
`and ’036 Patents relating to who invented what and when.” (Lanning Decl. at ¶ 22.) To the
`
`contrary, the cited portion of the transcript appears to be a discussion of the speakers’
`
`recollections of their contributions to a particular embodiment of their inventions wherein some
`
`context information is passed between the host and the network interface device. Thus, at most,
`
`the cited portion of the transcript reflects one inventor’s post hoc recollection, at the time of the
`
`recording, more than a decade after most of the salient work had been done, regarding his
`
`contribution to the claimed invention(s) recited in the un-asserted ’140 Patent.
`
`23.
`
`In Paragraph 23, Mr. Lanning quotes two documents from the same interference
`
`proceeding that occurred after the ’036 and ’072 Patent issued, involving a patent application
`
`with a different specification and with claims that do not recite a “context.” The first document
`
`confirms my understanding of the prior conversation: that the “context” being described in the
`
`recording reflected one inventor’s post hoc recollection of his contribution to the unasserted ’140
`
`patent. (ALA07370264 at 67:21 to 68:2.) At most, it indicates that one of the embodiments of a
`
`context in the unasserted ’140 patent is “defined by the TCB.” The second document similarly
`
`indicates that one of the embodiments of a context in the unasserted ’140 patent may be
`
`information in the TCB. (ALA07370542 at 122:11 to 123:12.) These disclosures are not
`
`inconsistent with Alacritech’s proposed construction of “context” nor do they contain any
`
`9
`
`

`

`indication that the statements are intended to limit the term in a particular manner that is
`
`inconsistent with its plain and ordinary meaning.
`
`24.
`
`In Paragraph 24, Mr. Lanning quotes from the shared specification of the ’036
`
`and ’072 patents, but omits relevant portions of the document, which I have included below:
`
`If, on the other hand, the attention bit is a zero, then processor 470 determines that
`the packet is a “fast-path candidate”. If processor 470 determines that the packet
`is a “fast-path candidate”, then processor 470 uses the buffer descriptor from the
`summary to DMA transfer the first approximately 96 bytes of information from
`buffer 2114 from DRAM 460 into a portion of SRAM 440 so processor 470 can
`examine it. This first approximately 96 bytes contains status 2223 as well as the
`IP source address of the IP header, the IP destination address of the IP header, the
`TCP source address of the TCP header, and the TCP destination address of the
`TCP header. The IP source address of the IP header, the IP destination
`address of the IP header, the TCP source address of the TCP header, and the
`TCP destination address of the TCP header together uniquely define a single
`connection context (TCB) with which the packet is associated.
`Processor 470 examines these addresses of the TCP and IP headers and
`determines the connection context of the packet. Processor 470 then checks a list
`of connection contexts that are under the control of INIC card 200 and determines
`whether the packet is associated with a connection context (TCB) under the
`control of INIC card 200.
`
`(’036 patent at 30:63 to 31:17.) As the full quote makes clear, the applicants used “TCB” to
`
`refer to a specific kind of “connection context”: one that includes TCP and IP source and
`
`destination addresses. This embodiment of “context” was explicitly claimed in, e.g., ’072 claim
`
`15, which requires “a context that includes status information and Internet Protocol (IP)
`
`addresses and TCP ports for the connection.” That claim 15 further requires that the “context”
`
`contain TCP ports and IP addresses would indicate to a person of skill in the art that “context”
`
`standing alone is not so limited.
`
`25.
`
`In Paragraph 25, Mr. Lanning asserts that “a person of ordinary skill in the art
`
`would understand ‘context’ as used in the ’072 and ’036 Claims to mean the TCB, or
`
`equivalently, ‘the set of variables used to represent the state of a given TCP connection.’” I
`
`disagree. As I discuss above, the descriptions recited by Mr. Lanning only describe one
`
`10
`
`

`

`embodiment of the context as relating to the state of the TCP connection. Nothing in the
`
`documents Mr. Lanning cites indicates that the applicants intended to restrict or disclaim other
`
`meanings of “context.” Moreover, the invention explicitly supports transport protocols other
`
`than TCP, including SPX, NCP, and TTCP:
`
`FIG. 3 diagrams the general flow of messages received according to the current
`invention. A large TCP/IP message such as a file transfer may be received by the
`host from the network in a number of separate, approximately 64 KB transfers,
`each of which may be split into many, approximately 1.5 KB frames or packets
`for transmission over a network. Novell NetWare protocol suites running
`Sequenced Packet Exchange Protocol (SPX) or NetWare Core Protocol
`(NCP) over Internetwork Packet Exchange (IPX) work in a similar fashion.
`Another form of data communication which can be handled by the fast-path is
`Transaction TCP (hereinafter T/TCP or TTCP), a version of TCP which
`initiates a connection with an initial transaction request after which a reply
`containing data may be sent according to the connection, rather than initiating a
`connection via a several-message initialization dialogue and then transferring data
`with later messages. In any of the transfers typified by these protocols, each
`packet conventionally includes a portion of the data being transferred, as well as
`headers for each of the protocol layers and markers for positioning the packet
`relative to the rest of the packets of this message.
`
`(‘036 Patent at 8:50 to 9:4.) Given the patents’ explicit recitation of non-TCP protocols, a person
`
`of skill in the art would not have understood “context” to require information about a TCP
`
`connection.
`
`26.
`
`In Paragraph 26, Mr. Lanning asserts that the ’036 and ’072 Patents “equate[]
`
`‘context’ with a communication control block (CCB).” That is incorrect, as the patents treat
`
`“contexts” and “CCBs” as different concepts, even in Mr. Lanning’s quote: “FIGS. 19A-C show
`
`a least-recently-used register 900 that is employed for choosing which contexts or CCBs to
`
`maintain in INIC cache memory.” (‘036 Patent at 24:38-40.) As the shared specification
`
`explains earlier, “[t]he context may be passed between an interface for the session layer 42 and
`
`the CPD 30, as shown by arrows 52 and 54, and stored as a communication control block
`
`(CCB) at either CPD 30 or storage 35.” (’036 Patent at 7:66 to 8:2 (emphasis added).) Thus the
`
`11
`
`

`

`’036 and ’072 Patents indicate that a context may be stored within a CCB, not that the two are
`
`equivalent.
`
`27.
`
`In paragraph 27, Mr. Lanning simplistically asserts that “the CCB is different
`
`from the TCB.” That is imprecise: rather, the specification suggests that a TCB is a type of
`
`CCB—neither of which is a “context” but which may be used to store a context. As the patents
`
`explain, a context “summariz[es] various features of the connection” and may be stored as a
`
`CCB. (’036 Patent at 7:62-8:2.) Since the patents support multiple transport layers such as TCP,
`
`SPX, and TTCP, the patents describe creating CCBs to handle contexts for each of the
`
`corresponding connections. (Id. at 11:20-28.) The patents then note that “[i]n any case, the CCB
`
`provides protocol and status information regarding each of the protocol layers.” (Id. at 11:30-
`
`31.) “Thus a CCB can include source and destination media access control (MAC) addresses,
`
`source and destination IP or IPX addresses, source and destination TCP or SPX ports, TCP
`
`variables such as timers, receive and transmit windows for sliding window protocols, and
`
`information indicating the session layer protocol.” (Id. at 15:22-27 (emphasis added).) This is
`
`similar to the information that defines a TCB: “the source and destination IP addresses and
`
`source and destination TCP ports that define the connection” as well as “information about the
`
`connection itself such as the current send and receive sequence numbers, and the first-hop MAC
`
`address, etc.” (Id. at 39:33-40.) Unlike the CCB, however, the TCB is described as storing
`
`TCP-related information, rather than information relating to other transport protocols such as
`
`SPX and TTCP. Given their similar names—“communication control block” and “transmit
`
`control block”—and that they may both used to store the context of a connection, a person of
`
`skill in the art would conclude that a TCB is a CCB that contains information related to a TCP
`
`connection.
`
`12
`
`

`

`28.
`
`In Paragraph 28, Mr. Lanning quotes from the patent specification while omitting
`
`relevant information. The full paragraph and corresponding figure are below:
`
`FIG. 4B, depicts the case in which the receive logic 32 of the CPD determines
`that a message packet is a candidate for fast-path processing, for example by
`deriving from the packet's headers that the packet belongs to a TCP/IP, TTCP/IP
`or SPX/IPX message. A processor 55 in the CPD 30 then checks to see whether
`the word that summarizes the fast-path candidate matches a CCB held in a
`cache 62. Upon finding no match for this packet, the CPD sends the validated
`packet from memory 60 to the host protocol stack 44 for processing. Host
`stack 44 may use this packet to create a connection context for the message,
`including finding and reserving a destination for data from the message associated
`with the packet, the context taking the form of a CCB. The present embodiment
`employs a single specialized host stack 44 for processing both fast-path and non-
`fast-path candidates, while in an embodiment described below fast-path
`candidates are processed by a different host stack than non-fast-path candidates.
`Some data (D1) 66 from that initial packet may optionally be sent to the
`destination in storage 35, as shown by arrow 68. The CCB is then sent to the
`CPD 30 to be saved in cache 62, as shown by arrow 64. For a traditional
`connection-based message such as typified by TCP/IP, the initial packet may be
`part of a connection initialization dialogue that transpires between hosts before
`the CCB is created and passed to the CPD 30.
`
`(’036 Patent at 10:10-34.) This section describes how an embodiment of the invention handles a
`
`new connection: by passing an incoming packet to the host stack, which allocates memory for
`
`the data of the packet as well as data from additional expected packets, then passing a CCB
`
`containing the context back to the CPD. The CPD then uses that cached CCB to store
`
`subsequent packets in the allocated memory, bypassing the host stack. (Id. at 10:35-51; Fid. 4C.)
`
`Thus in this embodiment, the context—the data regarding the active connection—also includes
`
`the memory address in which to store information received from that connection. As a person of
`
`13
`
`

`

`skill in the art would understand, the corresponding memory must be allocated before
`
`information can be stored in it.
`
`29.
`
`In Paragraphs 29 and 30, Mr. Lanning complains that the ’072 claims are
`
`“inconsistent with the meaning of ‘context’ in the 1997 Provisional.” That is incorrect. Mr.
`
`Lanning’s primary complaint seems to be that the disclosure is inconsistent with his narrowly
`
`circumscribed view of what “context” should mean when limited to a particular example raised
`
`in the Provisional Application. As I discuss above and in my Opening Declaration, the 1997
`
`Provisional describes a context as “keep[ing] track of information that spans many, possibly
`
`discontiguous, pieces of information” relating to a connection. A context may include any such
`
`information. Some of the ’072 claims then further limit the invention by explicitly reciting
`
`information that the “context” must contain within those claims, e.g. “protocol header
`
`information for the connection” or “status information.” They are thus consistent with how a
`
`person of skill in the art would interpret “context” in light of the specification. Mr. Lanning’s
`
`conclu