` CALLAHAN. TII'fiOTHY J. AND WAWRZYNEK. JOHN. "Adapting Software Pipelining for Reconfigurable Computing".
`
`
`University olr California at Berkeley. November 1149. 2000. pp. 8.
`
` RATHA. NALINI K.. JAIN. ANIL K. AND ROVER. DIANE T.. “An FPGA-hased Point Pattern Matching Processor with
`
`
`Application to Fingerprint Matching“. titlehlgan sate University. Department of Computer Science pp. B.
`
`
`DEHON. ANDRE. "Comparing Computing Machines” .Unlversity of California at Berkeley. Proceedings of SPIE I\i’ol. 3525,
`November}3. 1930. pp. 11.
` VEMURl. RANGA R. AND HARR. RANDOLPH E. "Configurable Computing: Technology and Applications". University or
`
`Cincinnati and Svnopsvs Inc.. IEEE. April 2000. pp. 39-40.
`
`
`DEHDN. ANDRE. "The Density Advantage oi Cenligurafile Computing". California Institute oi Technology. IEEE. April 2000.
`
`pp. 1-3.
`
`HAYNES. small 0.. STONE. JOHN. CHEUNG. PETER ‘I’.K. AND LUK. WAYNE. “Video Image Processing with the Sonic
`
`
`Architecture". Sony Broadcast 0. Professional Europe. Imperial College. University at London. IEEE. April 2000. pp. 50-51
`
`
`
`PLATIHER . HARCO. “Reconfigurable Accelerators for Combinatorial Problems". Swiss Federal institute of 'I’ecl‘lrlelomlI
`
`{ETH} Zurich. IEEE, April 1000. pp. 50-60.
`
`
`
`CALLAHAN. TIMD'IHY J..I HAUSER. JOHN R. AND WAWRZYHEK. JOHN. "The Garp Architecture and C Compiler“.
`
`University of California, Berkeley. IEEE. April 2000. pp. 5249.
` GOLOSTEIN. SETH COPE“. SCHMIT. HERMAN. BUDIU . MIHAI. CADAMBI. SRIHARI. MOE. MATT AND TAYLOR. R. REED,
`I.-
`
`"PlpeRench: A Reconfigurable Architecture and Compilel’. Carnegie Mellon University. IEEE. April 2000. pp. TD-TG.
`.-n MUCflNICK. STEVEN 3.. “Advanced Compiler Design and Implementation”. Morgan Kaufmann Publishers. pp. 21?.
`
`
`HAMMES. JEFFREY P.. Dissertation "Compiling SA-c To Reconfigurable Computing Systems". Colorado State University.
`
`
`Department of Computer Science. Summer 2000. pp. 11's.
`
`
`
`I. AutomaticTargetRecognition. ColoradoState University 0.USAF, mtg:rm.m.§o[ostateeduicameroniagpiicalions.html.
`
`
`CE(
`CHODOWIEC. PAWEL. KHUDN. PO. GAJ. KRIS. Fast implementations ofSecrel--Key Block Ciphers Using Mixed lunch and
`Outer-Round Pipelining. George Mason University. February 11- 13. 2001. pp.ll
`J
`
`my
`
`
`
`EXAMINER: Initial If citation considered, whether or not citation Is in conformance with MPIEP 80!: Draw line through citation If not in
`conlonnlnce end not considered. include i:o|:lj|I of this term with next communication to applicant
`
`
`
`
`RECEIVED
`
`AUG 1 82003
`Technology Center 2100
`
`“165- mil-5256591
`
`\
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 104
`
`Petitioner Microsoft Corporation - EX. 1002, p. 104
`
`
`
`Index of Claims
`
`Applicatiom'Control Nu.
`
`313
`10985
`Examiner
`
`ApplicantlslfPatent under
`Reexamination
`
`HUPPENTHAL ET AL.
`Art Unit
`
`Eric Coleman
`
`2183
`
`{Through numeral}
`Cancelled
`
`H Non-Elected
`
`_ a
`
`Objacted
`
`245%
`
`ellInterference
`
`mIIIIIIIIIIIIIIIIIIII
`IIIIIIIIIIIIIII
`eIIIIIIIIIIIIIIIIIIIIIIIIIII
`
`III
`
`
`
`nIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII
`
`Restricted
`
`IIIIIIIIIIIIIII
`
`III-Illnm
`
`IIIIIIIIII
`
`IImm
`
`II
`
`II
`
`III
`
`IIIIIIIIIIII
`
`IIIIIIIIIII
`
`IIIIIIIIIIIII
`
`IIIIIIIIIIIII
`
`III
`
`«Eflflflflflflfllmi
`
`IIIIIIIIIIIIIIIIIIIIII
`
`III-I.-
`III-I..-
`
`1....IIa9
`
`[EH-III..-
`-- --IIIIIII
`
`nnnmmmnmmmmm
`
`
`
`
`
`
`
`
`11.11.1-1.1.111.1.1.111.111
`
`US. Patent and Trademark Office
`
`Part of Paper No. 100305
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 105
`
`Petitioner Microsoft Corporation - EX. 1002, p. 105
`
`
`
`
`
`Eric Coleman
`
`2183
`
`
`
`H
`
`|l|||||i|| ||||l||l||l|| fl l||i|||
`
`
` E:U
`
` ApplicationIContml No.
`Applicanttsm’atent under
`
` Search Notes
`Reexamination
`
`
`101235.318
`HUF'PENTHAL ET AL.
`Examiner
`Art Unit
`
`
`
`
`
`
`
`SEARCH NOTES
`{INCLUDING SEARCH STRATEGY}
`_-
`Smith IEArus m:
`mil?RicFfoffiie.
`1‘ ”“565
`
`
`
`
`
`
`
`US. Patent and Trademark Office
`
`Part of Paper No. 100305
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 106
`
`Petitioner Microsoft Corporation - EX. 1002, p. 106
`
`
`
`Dec-154005 09:29
`
`From-HOGANiHARTSON
`
`RECEIVED
`
`T470
`
`POM/015 F-m
`
`DEC 1 6 2005
`pm we mWi‘iSflfiié’Em‘mfi' 33%“MM‘SEEE
`r. -'r...-.n -fi..--I'I'll:lilnrlmlcs=itu1iil-
`IBIISJifl. OMB mm WIII'DIL
`
`mar-2.5mm;
`
`Certificate of Transmission under 37’ CFR 1.8
`
`Serial No. 10i285.318
`
`Appiication of: Jon M. Huppenthai and David E‘ Caliga
`
`Filed: October 31. 2002
`
`Art Unit: 2183
`
`Examiner: Coleman, Eric
`
`Attorney Docket No. SRCO15
`
`
`
`For. MULTi—ADAPTIVE PROCESSING SYSTEMS AND TECHNIQUES FOR
`ENHANCING PARALLELISM AND PERFORMANCE OF COMPUTATIONAL
`FUNCTIONS
`
`[953‘
`
`Confirmation No.: 1420
`
`Customer No.: 25235
`
`i hereby certify that this correspondence is being facsimile transmitted to the United
`States Patent and Trademark Office
`
`1. Amendment in response to the Office Action dated October 7. 2005.
`on
`i (a bungalow 1525'
`16
`Date
`No. of Pages
`(incl. Coversheet)
`
`to centralized fax number: 571-273-8300
`
`Juiie Lan e
`
`Typed or printed name of person signing Cedificate
`
`Note: Each paper must have its own certificate of transmission or its certificate must
`identify each submitted paper.
`
`Client Reference No. 804040018
`
`Fax No. 719-448-5922
`
`Wits-MIME - "Sit”!
`
`PRGE ”15‘ HOW iii 11002005 11:29:54 AM [Eastern Standard Time] ‘ SVR:USPTO-EiXflF-fii25 ‘ 0051273330? CSIBH‘ DURiiTIDN (mm-ss):93-34
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 107
`
`Petitioner Microsoft Corporation - EX. 1002, p. 107
`
`
`
`Dac-IE-ZUHS {15:29
`
`Frum-HUGANIHARTSDH
`
`+
`
`7-579
`
`PIER/DIE
`
`F449
`
`RECEIVED
`W W CENTER
`DEC 1 6 2005
`
`Client Matter Novgugggstifiilg
`
`IN THE UNITED STATES PATENT AND iRADEMARK OFFICE
`
`Serial NO. 101285.318
`
`Application of: Jon M. Huppenthal and David E. Caliga
`Filed: October 31, 2002
`Art Unit: 2183
`
`Confirmation NO; 1420
`
`Customer No.: 25235
`
`AND PERFORMANCE OF COMPUTATIONAL. FUNCTIONS
`
`Examiner: Coleman, Eric
`
`Attorney Docket No. 830015
`For: MULTl—ADAPTIVE PROCESSING SYSTEMS
`AND TECHNIQUES FOR ENHANCING PARALLELISM
`
`AMENDMENT
`
`MAIL STOP AMENDMENT
`Commissioner for Patents
`PO. Box 1450
`Alexandria. VA 22313-1450
`
`Sir:
`
`In reSponse to the office communication mailed October 7, 2005, please
`
`amend the above-identified application as follows:
`
`Amendments to the Claims are reflected in the listing of claims which
`
`begins on page 2 of this paper.
`
`RemarkslArguments begin on page 9 of this paper.
`
`\I'C'S - WMJDOTB - ”510 v2
`
`:-
`
`PEGE Ziifi ‘ RCVD H 13102005 11:29:54 i'lM [Eastlm Standard Time] ' SVR:USPTO-EFKRF£J25 ‘ DHIS:2?3830|J" CSIDH‘ DURATiDH[mm-ss):03-31
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 108
`
`Petitioner Microsoft Corporation - EX. 1002, p. 108
`
`
`
`Duo-Ifi-ZDEJB 03:30
`
`From-HUGANiHARTSUN
`
`+
`
`T-ETB
`
`PMS/016
`
`F-fldfi
`
`Serial No. 10(285,318
`Reply to Office Action of October 7. 2005
`
`Amendments to the Claims:
`
`This listing of claims will replace all prior versions and listings of claims in the
`
`application:
`
`Listing of Claims:
`
`1.
`
`(currently amended) A method for data processing in a reconfigurable
`
`computing system comprising a plurality of functional units, said method
`
`comprising:
`
`defining a calculation for said reconfigurable computing system;
`
`instantiating at least two of said functional units to perform said calculation
`
`wherein how many functional units and functional type of each functional unit is
`
`based on the galculation;
`
`utilizing a first of said functional units to operate upon a subsequent data
`
`dimension of said calculation; and
`
`substantially concurrentiy utilizing a second of said functional units to
`
`operate upon a previous data dimension of said calculation.
`
`2.
`
`(original) The method of ciaim 1 wherein said subsequent and previous data
`
`dimensions of said calculation comprise multiple Vectors in said calculation.
`
`3.
`
`(original) The method of ciaim 1 wherein said subsequent and previous data
`
`dimensions of said calculation comprise multiple planes in said calculation.
`
`4.
`
`(original) The method of claim 1 wherein said subsequent and previous data
`
`dimensions of said wlculation comprise multiple time steps in said calculation.
`
`5.
`
`(original) The method of claim 1 wherein said subsequent an previous data
`
`dimensions of said calculation comprise muitiple grid points in said calculation.
`
`lMCS . Bflanflflhn - fistD fl
`
`2
`
`FREE 306 ’ HC’i'D ET 12i1fii2085 11:29:54 AM [Eastern Siai'lllaid Title] " SURIUSPTO-EFXRHHB “ DNIS:2?333W ‘ OSIDH' ' DURlllTlOli [mm-55mm
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 109
`
`Petitioner Microsoft Corporation - EX. 1002, p. 109
`
`
`
`Dac-lfi-ZUBE {18:30
`
`Fron-HOGAHiHhRTSGN
`
`1?
`
`T-Ii’B
`
`ROM/015
`
`F-MB
`
`Serial No. 101285.318
`Reply to Office Action of October 7, 2005
`
`6.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`seismic imaging calculation.
`
`7.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`Synthetic aperture radar imaging calculation.
`
`8.
`
`(original) The method of claim 1 wherein said calculation comprises a JPEG
`
`image compression calculation.
`
`9.
`
`(original) The method of claim 1 wherein said calculation comprises an
`
`MPEG image compression calculation.
`
`to.
`
`(original) The method of claim 1 wherein said calculation comprises a fluid
`
`flow calculation for a reservoir simulation.
`
`11.
`
`(original) The method of claim 1 wherein said calculation comprises a fluid
`
`flow calculation for weather prediction.
`
`12.
`
`(original) The method of claim 1 wherein said calculation comprises a fluid
`
`flow calculation for automotive applications.
`
`13.
`
`(original) The method of claim 1 wherein said calculation comprises a fluid
`
`flow calculation for aerospace applications.
`
`14-
`
`(original) The method of claim 1 wherein said calculation comprises a fluid
`
`flow calculation for an injection molding application.
`
`15.
`
`(currently amended) The method of claim 1 wherein said-calculation
`
`common-beam instantlatlng includes
`
`establishing a stream communication connection between functional units.
`
`NCSvWMlUO'IB-YTETUVI
`
`3
`
`P1651116I RCVD AT 121116121105 11:29:51 11111 [Eastern Slandald Tillie] ‘ Sl'RillSPTU-EFXRF-fillfi‘ DRIS:2?333OB " CSIDH" DURliTIOPi (mm-sslzll-tl
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 110
`
`Petitioner Microsoft Corporation - EX. 1002, p. 110
`
`
`
`Dac-lfi-ZME 00:30
`
`From-HDGAflil-IARTSDH
`
`+
`
`T-ETB
`
`PRES/015
`
`F449
`
`Serial No. 10i285.31B
`Reply to Office Action at October 7, 2005
`
`16.
`
`(original) The method of claim 1 wherein said calculation is comprises a
`
`structures calculation for structural analysis.
`
`17.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`search algorithm for an image search.
`
`18.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`search algorithm for data mining.
`
`19.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`financial modeling application.
`
`20.
`
`(original) The method of claim 1 wherein said calculation comprises an
`
`encryption algorithm.
`
`21.
`
`(currently amended) The method of claim 1 wherein said saleelatlen
`
`eemprises—an—decefptlen-elgerithmmgnfigurablg computing system communicates
`
`between functional ugits independent of external communication grotocols.
`
`22.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`genetic pattern matching function.
`
`23.
`
`(original) The method of claim 1 wherein said calculation comprises a
`
`protein folding function.
`
`24.
`
`(original) The method of claim 1 wherein said calculation comprises an
`
`organic structure interaction function.
`
`25.
`
`(original) The method of claim 1 wherein said calculation comprises a signal
`
`filtering application.
`
`mos-WWIB-rrstcfl
`
`4
`
`FREE Elli ’ RCVD fl? 121159095 11:29:54 Alli [Eastern Standard Timer SHRIUSFTO-EFXRF-fiiifi’ DHIS:2?38390' CSIDH" DURATION [mm-55mm
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 111
`
`Petitioner Microsoft Corporation - EX. 1002, p. 111
`
`
`
`Dac-iE-ZUEIS DE:3U
`
`FrontiiGEANIHARTSGN
`
`+
`
`T-BTE
`
`RUDE/NE
`
`F-fidfl
`
`Serial No. 1D!285.318
`Reply to Office Action of October 7. 2006
`
`26.
`
`(original) A method for data processing in a reconfigurable computing
`
`system comprising a plurality of functional units, said method comprising:
`
`defining a first systolic wall comprising rows of cells forming a subset of said
`
`plurality of functional units:
`
`computing a value at each of said cells in at least a first row of said first
`
`systolic wail;
`
`communicating said values between cells in said first row of said cells to
`
`produce updated values;
`
`communicating said updated values to a second row of said first systolic
`
`wall; and
`
`substantially concurrently providing said updated values to a first row of a
`
`second systolic wail of.rows of cells in said subset of said plurality of functional
`units.
`
`27.
`
`(original) The method of claim 26 wherein said values correspond to vectors
`
`in a computation.
`
`28.
`
`(original) The method of claim 26 wherein said values correspond to planes
`
`in a computation.
`
`29.
`
`(original) The method of claim 26 wherein said values concepond to time;
`
`steps in a computation.
`
`30.
`
`(original) The method of claim 26 wherein said values correspond to grid
`
`points in a computation.
`
`31.
`
`(original) The method of claim 26 wherein said step of communicating said
`
`updated values to a second row of said first systolic wall is carried out without
`
`storing said updated values in an extrinsic memory.
`
`mos . corrosion“ . 7mm v2
`
`5
`
`PAGE Ellfi ‘ RC’JD flT 12i1fii2005 11:29:54 hill [Eastern Standard Time]* SWUSPTO-EFXRHRE * DHISRMEJM" CSID:+‘ DHRATION (mm-ssriil-Iil
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 112
`
`Petitioner Microsoft Corporation - EX. 1002, p. 112
`
`
`
`Dac-lB-Zflfli
`
`05:30
`
`From-HOGAN I. HARTSUH
`
`+
`
`T-Iifi
`
`POW/THE
`
`F-flllfl
`
`Serial No. 101235.31 8
`Reply to Office Action of October 7. 2005
`
`32.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`seismic imaging calculation.
`
`33.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`synthetic aperture radar imaging calculation.
`
`34.
`
`(original) The method of claim 26 wherein said values correspond to a JPEG
`
`image compression calculation.
`
`35.
`
`(original) The method of claim 26 wherein said values correspond to an
`
`MPEG image compression calculation.
`
`(original) The method of claim 26 wherein said values correspond to a fluid
`36.
`flow calculation for a reservoir simulation.
`
`3?.
`
`(original) The method of claim 26 wherein said values correspond to a fluid
`
`flow calculation for weather prediction.
`
`38.
`
`(original) The method of claim 26 wherein said values correspond to a fluid
`
`flow calculation for automotive applications.
`
`39.
`
`(original) The method of claim 26 wherein said values correspond to a fluid
`
`flow calculation for aerOSpace applications.
`
`40.
`
`(original) The method of claim 26 wherein sald values correspond to a fluid
`
`flow calculation for an injection molding application.
`
`41.
`
`(Currently amended) The method of claim 26 wherein-said—valees
`
`WWuas-ealemafien—ier—eraslmaiysiedefining include§
`establishing a steam communication cennection between functional units and
`
`mos-soawoma-rrsroa
`
`5
`
`FREE ”16 ‘ RCllD RT 12l1l5i2005 11 :29154 Nil Easlem Standard Tune] * SVRMSPTO-EFXRf-HZE' OHISWSSEGD " CSIDIi" DURfiTIDll (mm-sslm-al
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 113
`
`Petitioner Microsoft Corporation - EX. 1002, p. 113
`
`
`
`Dac-IE-ZDDS
`
`“9:30
`
`Fran-HERA" I HARTSflPl
`
`+
`
`T-WS
`
`P HOE/DIE
`
`F-M!
`
`Serial No. 101285.318
`Reply to Other: Action of October 7. 2005
`
`wherein how many functional units and functional type of eagh fungtjonal uni; is
`
`based on a comguting algorithm within the reconfigurable comggtigg sxstem.
`
`42.
`
`(original) The method of claim 26 wherein said values correspond to 3
`
`structures calculation for structural analysis.
`
`43.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`search algorithm for an image search.
`
`44.
`
`(original) The method of claim 28 wherein said values correspond to a
`
`search algorithm for data mining.
`
`45.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`financial modeling application-
`
`46.
`
`(original) The method of claim 26 wherein said values correspond to an
`
`encryption algorithm.
`
`4?.
`
`(currently amended) The method of claim 26 wherein said-vetoes
`
`correspond-te-aneeeryptien-elgendernreconfiggragle computing sgetem
`
`communicates between functional units inde endent o
`
`xtem l omrnunication
`
`grotocois.
`
`48.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`genetic pattern matching function.
`
`49.
`
`(original) The method of claim 26 wherein said values correspond to a
`
`protein folding functiOn.
`
`50.
`
`(original) The method of claim 26 wherein said values correspond to an
`
`organic structure interaction function.
`
`ms-BMMMWJHIDVI
`
`7
`
`P116! Eiifi ' REV!) ET 12l15i2055 11:29:51 kill [Eastern Stantard Time] ’ SURIUSPTO-EFXRHIEE ‘ DNiS:2?38300 ‘ CSIDH' ‘ DURATION [mm-SSIIOB-Si
`
`_
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 114
`
`Petitioner Microsoft Corporation - EX. 1002, p. 114
`
`
`
`Dac-lB-ZEJIIS
`
`09:31
`
`Frum-I-lOGANIHARTSOH
`
`+
`
`T4?!
`
`RUDE/DIE
`
`F-fi-IB
`
`Serial No. 101285.316
`Reply to Office Action of October 7, 2005
`
`51.
`
`(original) The method of claim 26 wherein said values correspond to a signal
`
`filtering application.
`
`52.
`
`(original) The method of claim 26 wherein said reconfigurable computing
`
`system comprises at least one adaptive processor.
`
`53.
`
`(original) The method of claim 52 wherein said reconfigurable computing
`
`system further comprises at least one microprocessor.
`
`54.
`
`(currently amended) A method for data processing in a reconfigurable
`
`computing system comprising a plurality of functional units. said method
`
`comprising:
`
`performing a calculation by a subset of said plurality of functional units to
`
`produce computed data;
`
`passing said computed data from a first column of said calculation to a next
`
`column in said calculation;
`
`evaluating a rate of change in at least one variable for each of said columns
`
`in said calculation;
`
`continuing said calculation [13mm said variable does not change for a
`
`particular column of said calculation; and
`
`restarting said calculation at said column of said calculation where said
`
`variable does change.
`
`55.
`
`(Canceled)
`
`56.
`
`(New) The method of claim 54 wherein how many functional units comprise
`
`the subset and functional type of each functional unit in said subset is based on the
`
`calculation and wherein the passing step is external communication protocol
`
`independent.
`
`\“CS- mmmme- Tl’fiiovz
`
`8
`
`Fifi iflfi' Rt’iti liT ithliiifllifi 11:19:51 Nil [Eastern Standard Time] ' SHRIUSPTOwEFXRF'filEE ‘ 9115;233:300 ‘ CSIDEP DURATION [mm-SSIZOG-St
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 115
`
`Petitioner Microsoft Corporation - EX. 1002, p. 115
`
`
`
`Dec-lE-ZWE 09:31
`
`Frum-HOBthHARTSDH
`
`+
`
`T—BT!
`
`REID/BIB
`
`F-Qd!
`
`Serial No. 1D!285.318
`Reply to Office Action of October 7, 2005
`
`REMARKSMRGUMEETfi
`
`Ctaims 1-55 were presented for examination and are pending in this
`
`application.
`
`In an Official Office Action dated October 7, 2005, claims 1-55 were
`
`rejected. The Applicants thank the Examiner for his consideration and address the
`
`Examiner's comments concerning the claims pending in this application below.
`
`Applicants herein amend claims 1, 15, 21. 41, 47 and 54 and respectfully
`
`traverse the Examiners rejections. Claim 55 is presently canceled without prejudice
`
`and new claim 56 is presently added. Claims 1-54 and 58 are now pending in this
`
`application. These changes are believed not to introduce new matter, and their
`
`entry is respectfully requested. Support of the amendments can be generally found
`
`on page 11 and page 16 of the specificatiOn. The claims have been amended to
`
`expedite the prosecution and issuance of the application.
`
`in making this
`
`amendment. Applicants have not and are not narrowing the scope of the protection
`
`to which the Applicants consider the claimed invention to be entitled and do not
`
`concede, directly or by implication, that the subject matter of such claims was in
`
`fact disclosed or taught by the cited prior art. Rather, Applicants reserve the right to
`
`pursue such protection at a later point in time and mereiy seek to pursue protection
`
`for the subject matter presented in this submission.
`
`35 U.S.C. §103(a) Obviousness Rejection of Claims
`
`Claims 1-5. 26-31, 52 and 53 were rejected under 35 U.S.C. §1D3(a) as
`
`being unpatentable over U.S. Patent No. 6,385,757 ("Gupta”) in View of US. Patent
`
`No. 5,274,832 (“Khan"). Applicants respectfutly traverse these rejections in light of
`
`the aforementioned remarks and respectfully requests reconsideration.
`
`MPEP §2143 provides:
`
`To establish a prima facie case of obviousness. three basic criteria
`
`must be met. First, there must be some suggestion or motivation,
`
`hes-ammoie-nsmuz
`
`9
`
`PAGE lflllfi ‘ROVD Al marinas 11:29:55 Mil [Eastd'lt Standard Time] ‘ SVRIUSPTD-EFXRF-fiflfi‘ DlllS:2?33iflfl *CSlliit ' lJURA'lIOll (medium
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 116
`
`Petitioner Microsoft Corporation - EX. 1002, p. 116
`
`
`
`Dac-IE-ZGUS
`
`89:31
`
`Frum-HDGAHIHARTSGN
`
`+
`
`T-BTB Mill/DIE
`
`F-Bdfi
`
`Serial No. 10i285,318
`Reply to Office Action of October 7. 2005
`
`either in the references themselves or in the knowledge generally
`
`available to one of ordinary skill in the art. to modity the reference or
`
`to combine reference teaching. Second. there must be a reasonable
`
`expectation of success. Finally. the prior art reference (or references
`
`when combined) must teach or suggest all the claim limitations.
`
`The cited references fail to teach or suggest all of the limitations recited in
`
`the claims as currently amended. For example, independent claim 1 recites,
`
`”...wherein how many functional units and functional type of each functional unit is
`
`based on the calculation ..." and “.. substantially concurrently utilizing a second of
`
`said functional units to operate upon a previous data dimension of said calculation.“
`
`Neither Gupta nor Khan teach or suggest a substantially concurrent use of
`
`functional units of a reconfigurable computing system to concorrently operate upon
`
`data dimensions of a calculation.
`
`in contrast both Gupta and Khan follow the
`
`traditional parallel processing format of sequential processing data since the result
`
`of one processor, functional unit. or cell may be required by an adjacent processor.
`
`functional unit, or cell.
`
`Typically. in a multiprocessor, microprocessonbased system, each
`
`processor is allocated but a relatively small pertion of the total problem called a cell.
`
`However, to solve the total problem, results of one processor are often required by
`
`many adjacent cells because their cells interact at the baundary. Consequently.
`
`intermediate results must be passed around the system in order to complete the
`
`computation of the total problem. This. by necessity, involves numerous other
`
`chips and bosses that run at much slower speeds than the microprocessor thus
`
`resulting in system performance often many orders of magnitude lower than the raw
`
`computation time.
`
`in the use of an adaptive or reconfigurable processor-based system as is
`
`claimed in the Applicants invention. ten to One thousand times more computations
`
`lucs_aomuums.nslo v3
`
`10
`
`PAGE 11l1lfi ‘ RC‘iD AT liiififlflflfi 11:29:54 Alli [Eastern Standard Timer SVEUSPTD-EFXRF-filtfi " DHIS:2i383flD‘ CSIOH“ Blflifllflfl (lilili-ssiiflm
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 117
`
`Petitioner Microsoft Corporation - EX. 1002, p. 117
`
`
`
`Darla-2005 09:31
`
`Fran-MEANSHARTSUN
`
`+
`
`T-BTQ
`
`RUIZ/015
`
`F-Mi
`
`Serial No. 105185.318
`Reply to Office Action of October 7. 2005
`
`can be performed within a single chip and any boundary data that is shared
`
`between these functional units need never leave a single integrated circuit chip
`
`eiiminating the need for external communication protocols and simplifying internal
`
`communications. For example a complier associated with the reconfigurable
`
`computing system can establish stream connections between functional units that
`
`rely on general communication protocols. Therefore. data moving around the
`
`system, and its impact on reducing overall System performance, can also be
`
`reduced by two or three orders of magnitude. This will allow both significant
`
`improvements in performance in certain applications as well as enabling certain
`
`applications to be performed in a practical timeframe that could not previously be
`
`accomplished. Such an adaptive processor-based system is distinct from that
`
`taught by Khan.
`
`in addition. the Applicants‘ invention build functional units of the
`
`reconfigurable processor-based system based on the algorithms being used in the
`
`calculations. The type of each functional unit and the total number of functional
`
`units created is unique for each assigned task. This is distinct from Gupta. Gupta
`
`teaches a system using a Very Long Instruction Word (“VLlW”) processor. VLiW
`
`processors do have the ability to use multiple arithmetic functional units one at a
`
`time but the set of functional units are limited and fixed within the VLlW processor.
`
`The flexible nature of the Applimnts' invention allows for computational flow in one
`
`or more dimensions of the problem. The system disclosed by Gupta and Kahn
`
`does not offer such an approach.
`
`Gupta also appears to teach a system to generate an instruction format that
`
`is used to control a processor control path in what is called parallel instruction
`
`camputing. This instruction-level parallelism issues several operations per
`
`instruction to multipie functional units to control a processors data path. As the
`
`Examiner admits, Gupta fails to teach a substantially concurrent use of data
`
`dimensions during a calculation. The Applicants disagree with the Examiner's
`
`MS - SOIMKIUIB - ”510 v2
`
`11
`
`PIIGE 12llfl ‘ RCVD llT tlefiitllfiS 11:29:5t All [Eastern Standard Time]' SVR:USPTO£FXHf-El26' DMSQISESUD‘ CSIDH‘ DURATION (mm-ss):tt«34
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 118
`
`Petitioner Microsoft Corporation - EX. 1002, p. 118
`
`
`
`Dec-154005 09:3l
`
`Fron—HDEANIHARTSON
`
`+
`
`T-BTE
`
`PUB/DIE
`
`F44!
`
`Serial No. 102285.318
`Reply to Office Action of October 7. 2005
`
`conclusion that Khan teaches this noted insufficiency of Gupta. Khan appears to
`
`teach a serialized or sequential approach to multi-processor parallelism using
`
`systolic arrays- As stated in Khan. “.. .the corresponding matrix and vector signals
`
`are inputted into their respective processing elements sequentially, multiplied and
`
`accumulated therein.” See Khan Col. 12, lines 35-37. Thus, Khan teaches a
`
`systolic sequential parallel approach to processing that maves in one direction in a
`
`one by one fashion.
`
`Systolic sequential parallelism utilizes an array of processing elements
`
`(typically multiplier-accumulator chips) in a pipeline structure. The "systolic," coined
`
`by H. T. Kung of Carnegie-Mellon, refers to the rhythmic transfer of data through
`
`the pipeline, like blood flowing through the vascular system. Such an approach
`
`inherently accomplishes calculations by using a serialized approach. As recited in
`
`Gupta, "...the algorithm selects a set of FUs [Functional Units] to be instantiated in
`
`the data path, one by one. by looking at the requirement of the operation group
`
`cliques provided.” Gupta. Col. 21, lines 23-24. (emphasis added)
`
`In contrast to the sequential processing operation of Khan and Gupta, the
`
`Applicants' invention uttllzas available resources to have an application evaiuato a
`
`problem in a concurrent data flow sense. That is, itwill "pass" a subsequent
`
`. dimension of a given problem through a first loco of logic concurrently with the
`
`previous dimension of data being processed through a second loop. This type of
`
`concurrent operation is not taught or suggested by Gupta or Kahn.
`
`in practice. a
`
`“dimension” of data can be: multiple vectors of a problem, multiple planes of a
`
`problem, multiple time steps in a problem and so forth.
`
`In addition, and as recited in claim 26, the Applicants' method “substantially
`
`concurrently provides updated values to a E row of a second systolic wail of rows
`
`of cells. .. ." (emphasis added) The combination of defining a calculation for a
`
`reconfigurable computing system and concurrently operating on data and
`
`communicating values between cells is distinct from Gupta in view of Khan. This
`
`lWES—WWIB-??5mv2
`
`12
`
`PRGE 13M ' RCl'li AT 121153005 11 :29154 Alli |Easlem Standard Time] ’ SRUSPTD-EFXRF-fiiifl * DMS:2i383DD' CSIDH' " DURATION (mm-55mm
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 119
`
`Petitioner Microsoft Corporation - EX. 1002, p. 119
`
`
`
`Dec-IB-ZUDE
`
`fl!:32
`
`Fron-HDEANlilARTSGN
`
`+
`
`T-iil’S
`
`POM/MB
`
`F449
`
`Serial No. 101935.313
`Reply to Office Action of October 7. 2005
`
`and other features of claim 26 were recognized as having novelty. an inventive
`
`step, and industrial applicability by the international Preliminary Examining Authority
`of the Patent Cooperation Treaty. A recently received International Preliminary
`
`Examination Report received November 16, 2005 found that the combination of
`
`limitations found in claim 26 and 54 (designated as claims 1 and 7 of the PCT
`
`application) in full consideration of Gupta and Khan, possessed novelty. inventive
`
`step, and industrial applicability.
`
`The Applicants also assert that Gupta in view of Khan are improperly
`
`combined. To establish a prima facie case of obviousness there must be some
`
`suggestion or motivation, either in the references themselves or in the knowledge
`
`generally available to one of ordinary skill in the art. to modify the reference or to
`
`combine reference teaching. Assuming for arguments sake that the elements of
`
`the Applicants' invention are found in a combination of Gupta and Khan. (an
`
`assumption to which the Applicants do not agree) there is nothing in either Gupta or
`
`Khan to suggest or motivate such a combination or modification. The tong felt need
`
`of the Applicants' invention given problems associated with parallel processing as
`
`well as the commercial success of products derived from the Applicants invention
`
`are evidence that one of ordinary skill in the art would not and have not been
`
`motivated to combine these references. The Applicants thus traverse the
`
`Examiner’s rejections of independent claims 1 and 26 for the aforementioned
`reasons.
`
`Claims 2~5. 27-31. 52 and 53 depend from claims 1 and 26 respectively and
`
`are for at least the same aforementioned reasons. patentabte over Gupta in view
`
`of Khan. The Appiicants respectfully request the rejections be withdrawn and the
`claims reconsidered.
`
`Claims 19 and 45 were rejected under 35 U.S.C § 103(a) as being
`
`unpatentabte over Gupta in view of Khan and in further view of U.S. Patent No.
`
`4,372,133 (“Leeland”). Leeland fails to rectify the aforementioned deficiencies of
`
`runs. amma . yrs-in»:
`
`1.3
`
`PAGE 14l15 ‘ ilC'iD iii WISHES 11:29:54 Mil [Eastern Standard Time] ' SVkUSPTD-EFXRF-tflfi ' DNISQTSESW‘ CSIDit‘ BUMTIDN (lllllt-ss):fl3~34
`
`Petitioner Microsoft Corporation - Ex. 1002, p. 120
`
`Petitioner Microsoft Corporation - EX. 1002, p. 120
`
`
`
`UBC‘IE‘ZDBS
`
`35:32
`
`Frun-ilGEAHIHARTSDH
`
`+
`
`1"!”
`
`RUN/ME
`
`F449
`
`Serial NO. 10m85.318
`Reply to Office Action of October 7. 2005
`
`Gupta and Khan with respect to independent claims 1 and 26 and therefore. as
`claims 19 and 45 depend from claims 1 and 26 respectively. the Applicants submit
`
`claims 19 and 45 are patentable over Gupta in view of Khan in further view of
`Leeland.
`
`The Examiner also rejects dependent claims 10-15. 36-42 and independent
`
`claim 54 under 35 U.S.C. § 103(a) as being unpatentable over Gupta in view of
`
`Khan in further view of US. Patent No. 5.072.371 (“Banner”). The Applicants
`
`traverse these rejections. For at least the aforementioned reasons. the Applicants
`
`submit that Brenner fails to resolve the deficiencies noted in Gupta and Kahn.
`
`Claims 10-16 and 16—42. which depend from claims 1 and 21 respectively. are
`
`therefore patentabie over Gupta in view of Khan in further view of Benner.
`
`With regard to independent claim 54. the Examiner asserts that Benner
`
`discloses continuing calculations of variables that do not change in a column and
`
`restarting calculations of variables once a change occurs. The Applicants disagree.
`
`The text cited by the Examiner (Benner Col. 22, lines 35—52) does not teach or
`
`suggest systolic calculations as recited in claim 54 and the Examiner‘s conclusion
`
`that the words "wave mechanics. fluid dynamics. and beam strain analysis" imply
`
`the data processing in a reconfigurable computing system claimed by the
`
`Applicants is unjustified. The Applicants respectfully request either the rejection be
`
`withdrawn or specific reference to portions of Gupta. Kahn, and Benner that teach
`
`and suggest each and every limitation of claim 54 be identified.
`
`Claims 6-9. 17-18. 20-25. 32435, 43—44 and 46-51 are rejec