Ex Parte O et al

Patent Trial and Appeal Board

Feb 28, 2017

14219136 (P.T.A.B. Feb. 28, 2017)

United States Patent and Trademark Office
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O.Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
14/219,136 03/19/2014 Kathryn M. O'Brien YOR920130913US1 3545
48915 7590 03/02/2017
TANTOR TOT RTTRN T T P-TRM YORKTOWN
EXAMINER
20 Church Street WARREN, TRACY A
22nd Floor
Hartford, CT 06103 ART UNIT PAPER NUMBER
2131
NOTIFICATION DATE DELIVERY MODE
03/02/2017 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
usptopatentmail@cantorcolbum.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte KATHRYN M. O’BRIEN, JOHN K. O’BRIEN,
and
ZEHRA N. SURA
Appeal 2016-008677
Application 14/219,136
Technology Center 2100
Before CARLA M. KRIVAK, HUNG H. BUI, and
JEFFREY A. STEPHENS, Administrative Patent Judges.
KRIVAK, Administrative Patent Judge.
DECISION ON APPEAL
Appellants appeal under 35 U.S.C. § 134(a) from a Final Rejection of
claims 1—20, which are all the claims pending in the application. We have
jurisdiction under 35 U.S.C. § 6(b).
We affirm.
Appeal 2016-008677
Application 14/219,136
STATEMENT OF THE CASE
Appellants’ invention is directed to a system and method for “creating
compiler-generated memory mapping hints in a computer system” using “a
compiler of the computer system, to identify data access patterns in the
code” (Abstract; Spec. 2, 5).
Independent claim 1, reproduced below, is exemplary of the subject
matter on appeal.
1. A method for creating compiler-generated memory
mapping hints in a computer system, the method comprising:
analyzing code, by a compiler of the computer system, to
identify data access patterns in the code;
accessing system configuration information defining data
processing system characteristics of a target system for the code,
the data processing system characteristics comprising a plurality
of processing resources and memory domain characteristics of a
plurality of memory domains accessible by the processing
resources;
selecting, by the compiler, two or more of the processing
resources to execute the code as a parallel application;
determining a preferred allocation of data in the memory
domains of the target system based on mapping the code to the
two or more selected processing resources to execute as the
parallel application and mapping the data to one or more of the
memory domains based on the memory domain characteristics of
the memory domains accessible by the two or more selected
processing resources; and
storing the preferred allocation as compiler-generated
memory mapping hints in a format accessible by a physical
memory mapping resource of the target system.
REFERENCES and REJECTION
The Examiner rejected claims 1—20 under 35 U.S.C. § 103(a) based
upon the teachings of Lopez-Lagunas (Abelardo Lopez-Lagunas and Sek M.
2
Appeal 2016-008677
Application 14/219,136
Chai, “Compiler Manipulation of Stream Descriptors for Data Access
Optimization,” International Conference on Parallel Processing
Workshops, 2006) and Stevens (US 6,289,424 Bl; issued Sept. 11, 2001)
(Final Act. 3—27).
ANALYSIS
With respect to claim 1, Appellants contend the Examiner erred in
finding Lopez-Lagunas discloses “analyzing code, by a compiler of the
computer system, to identify data access patterns in the code”; rather, Lopez-
Lagunas’ compiler “looks only at stream descriptors (which are not a
programming code) to optimize data movement (which is not identifying
data access patterns in programming code)” (App. Br. 6 (citing Lopez-
Lagunas § 2,11; Spec. 1 50); see also Reply Br. 2). Appellants assert
Lopez-Lagunas relies on “a programmer [to] separately defineH data access
and computation in an explicit manner” in contrast to Appellants’ method—
which identifies data access patterns “by the compiler itself’ and “does not
rely on a programmer to explicitly identify data accesses in the form of
stream descriptors” (App. Br. 7 (citing Lopez-Lagunas § 2,11)). Appellants
also contend Lopez-Lagunas is silent as to “selecting, by the compiler . . .
two or more processing resources” to execute the code as a parallel
application, and “determining a preferred allocation of data,” as claimed
(App. Br. 7). Instead, Lopez-Lagunas executes “computation kernel
requirements . . . [which] cannot reasonably be read as the claimed code
since requirements cannot be executed as a parallel application” (App. Br. 7
(citing Lopez-Lagunas § 2,11)). We do not agree.
3
Appeal 2016-008677
Application 14/219,136
We agree with and adopt the Examiner’s findings as our own.
Particularly, we agree with the Examiner that Lopez-Lagunas’ stream
descriptors are code analyzed by a compiler, as claimed (Ans. 27 (citing
Lopez-Lagunas § 2,11, § 3.1; Chai Fig. 1, p. 4)).1 Lopez-Lagunas’ stream
descriptors—which program stream units and data structures’ movement in
memory (see Lopez-Lagunas §3.1,11; Chai p. 4)—are commensurate with
the term “code” as claimed and with the broad description of “code” in
Appellants’ Specification.2 Appellants’ arguments regarding “programming
language code” (App. Br. 6; Reply Br. 2) are also not commensurate with
the scope of the claim. The claim recites “code,” not “programming
language code” (Ans. 27).3
Moreover, contrary to Appellants’ argument that Appellants’ method
does not rely on a programmer (App. Br. 7), claim 1 does not preclude a
programmer from defining data access patterns in code before the compiler
analyzes the code for access patterns (Ans. 29). We agree with the
Examiner that Lopez-Lagunas identifies data access patterns in the code as
claimed because Lopez-Lagunas’ compiler identifies data and memory
access patterns specified in stream descriptors’ code (Ans. 28; Final Act. 3
(citing Lopez-Lagunas § 2,11)).
1 The Chai publication (Sek M. Chai et al., “Streaming Processors for Next
Generation Mobile Imaging Applications,” 2005) is incorporated in Lopez-
Lagunas’ disclosure (see Lopez-Lagunas § 2, reference [11]).
2 Appellants’ Specification provides “code 130 may be a source program,
object code, script, or any other entity comprising a set of instructions to be
performed” (Spec. 120 (emphasis added)).
3 Appellants’ Amendment dated March 3, 2016, seeking to amend “code” to
“programming language code,” was not entered (Advisory Action dated
March 24, 2016).
4
Appeal 2016-008677
Application 14/219,136
We are also not persuaded by Appellants’ argument that Lopez-
Lagunas is silent as to “selecting, by the compiler, two or more of the
processing resources to execute the code as a parallel application” and
“determining a preferred allocation of data” as claimed (App. Br. 6—7).
Appellants merely assert there is no description in Lopez-Lagunas of these
limitations without persuasive evidence or reasoning rebutting the
Examiner’s specific findings. We agree with the Examiner that Lopez-
Lagunas’ stream descriptors describe data structures “that can be processed
in parallel” (see Lopez-Lagunas § 3,11; see also final Act. 4).
Additionally, as recognized by the Examiner, Lopez-Lagunas’ compiler
matches stream descriptors’ data structures to multiple hardware functional
units (processing resources), thereby teaching the claimed “selecting, by the
compiler, two or more of the processing resources to execute the code as a
parallel application” as recited in claim 1 (Ans. 28 (citing Lopez-Lagunas
§§ 2, 3.1); see also Lopez-Lagunas § 6 (describing processing
resources/hardware accelerators selected to process red and green pixels in
parallel)).
In light of the broad terms recited in claim 1 and the arguments
presented, Appellants have failed to clearly distinguish the claimed
invention over the prior art relied on by the Examiner. Thus, we sustain the
Examiner’s rejection of independent claim 1, and independent claims 8 and
14 argued for substantially the same reasons (App. Br. 5, 6, 8). We also
sustain the Examiner’s rejection of dependent claims 2—7, 9-13, and 15—20
for which no substantive arguments are provided.
5
Appeal 2016-008677
Application 14/219,136
DECISION
The Examiner’s decision rejecting claims 1—20 is affirmed.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(l)(iv).
AFFIRMED
6