Ex Parte Rhine

Patent Trial and Appeal Board

Jan 22, 2015

11855121 (P.T.A.B. Jan. 22, 2015)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
____________

Ex parte SCOTT RHINE
____________

Appeal 2012-0094711
Application 11/855,1212
Technology Center 2100
____________

Before CAROLYN D. THOMAS, MICHAEL J. STRAUSS, and
JOSEPH P. LENTIVECH, Administrative Patent Judges.

LENTIVECH, Administrative Patent Judge.

DECISION ON APPEAL

Appellant seeks our review under 35 U.S.C. § 134(a) of the
Examiner’s Final Rejection of claims 1–5, 7–17, and 19–25. App. Br. 5.
Claims 6 and 18 have been canceled. Id. We have jurisdiction over the
pending claims under 35 U.S.C. § 6(b).
We affirm.

1 Our decision refers to Appellant’s Appeal Brief filed February 7, 2012
(“App. Br.”); Appellant’s Reply Brief filed June 12, 2012 (“Reply Br.);
Examiner’s Answer mailed April 13, 2012 (“Ans.”); and original
Specification filed September 13, 2007 (“Spec.”).
2 According to Appellant, the real party in interest is Hewlett-Packard
Development Company, LP. App. Br. 3.

Appeal 2012-009471
Application 11/855,121

2

STATEMENT OF THE CASE
Appellant’s Invention
A multi-processor computing system may include multiple processors,
memory, and input/output grouped into cells. Spec. ¶ 1. The memory of
each cell includes interleaved memory and cell local memory. Id. For
interleaved memory, random accesses from each processor average the same
amount of time so that latency appears uniform. Id. For cell local memory,
accesses by processors from the same cell as the cell local memory have less
latency relative to accesses by processors from other cells in a process
known as non-uniform memory access. Id. Appellant’s invention generally
relates to a virtual machine scheduler for dynamically controlling non-
uniform memory access of a cellular server in interleaved and cell local
configurations. Id. ¶ 9. An understanding of the invention can be derived
from a reading of exemplary claims 1 and 12, which are reproduced below
with emphasis and paragraphing added to highlight the disputed limitations:

1. A computer system comprising:
a virtual machine scheduler that dynamically and with
computed automation controls non-uniform memory access of a
cellular server in interleaved and cell local configurations
comprising
mapping logical central processing units (CPUs) to
physical CPUs according to preference and
solving conflicts in preference based on a
predetermined entitlement weight and iterative switching
of individual threads,
Appeal 2012-009471
Application 11/855,121

3
wherein the virtual machine scheduler operates as
a secondary scheduler that supports a primary scheduler
which schedules substantially equal virtual machine
work for each of the physical CPUs.

12. The computer system according to Claim 9 further
comprising:
the virtual machine scheduler distributes the logical
CPUs into classes and performs locality domain (LDOM)
optimization comprising
selecting a best estimate mapping from
schedulable hardware entities to LDOMs,
swapping places between logical CPUs to remove
conflicts between jobs executing on schedulable
hardware entities.

References
The Examiner relies on the following prior art references:
Rhine US 2006/0195845 A1 Aug. 31, 2006
Chiaramonte et al. US 2007/0079308 A1 Apr. 5, 2007
Anand et al. US 2008/0163203 A1 July 3, 2008
Armstrong et al. US 7,493,515 B2 Feb. 17, 2009

Govil et al., Cellular Disco: Resource Management Using Virtual Clusters
on Shared-Memory Multiprocessors, ACM Transactions on Computer
Systems, Vol. 18, No. 3 (2000)

Rejections
Claims 2–5, 7–12, 14–17, and 19–24 are rejected under 35 U.S.C.
§ 112, second paragraph, as being indefinite for failing to particularly point
out and distinctly claim the subject matter which applicant regards as the
invention. Ans. 5.
Appeal 2012-009471
Application 11/855,121

4
Claims 1–5, 9–17, 21, 22, and 25 are rejected under 35 U.S.C. §
103(a) as being unpatentable over Govil and Armstrong. Id. at 5–6.
Claims 7 and 19 are rejected under 35 U.S.C. § 103(a) as unpatentable
over Govil, Armstrong, and Chiaramonte. Id. at 8–9.
Claims 8 and 23 are rejected under 35 U.S.C. § 103(a) as unpatentable
over Govil, Armstrong, and Anand. Id. at 9.
Claim 20 is rejected under 35 U.S.C. § 103(a) as unpatentable over
Govil, Armstrong, Anand, and Rhine. Id. 10.
Claim 24 is rejected under 35 U.S.C. § 103(a) as unpatentable over
Govil, Armstrong, and Rhine. Id. 11.

ANALYSIS
Rejection under 35 U.S.C. § 112, second paragraph

Appellant does not appeal the rejection of claims 2–5, 7–12, 14–17,
and 19–24 under 35 U.S.C. § 112, second paragraph. App. Br. 12. As such,
we summarily sustain the rejection. See MPEP § 1205.02, 8th ed., Rev. 9,
Aug. 2012 (“If a ground of rejection stated by the examiner is not addressed
in the appellant’s brief, that ground of rejection will be summarily sustained
by the Board.”).

Rejections under 35 U.S.C. § 103(a)
Claims 1–5, 7–11, 13–17, and 19–25:
Appellant argues independent claims 1, 13, and 25 as a group. App.
Br. 12–13. We select claim 1 as the representative claim. Accordingly,
Appeal 2012-009471
Application 11/855,121

5
claims 2–5, 7–11, 13–17, and 19–25 stand or fall with claim 1. 37 C.F.R.
§ 41.37(c)(1)(iv) (2012).
Issue: Under 35 U.S.C. § 103(a), did the Examiner err in finding
Govil discloses a virtual machine scheduler operating as a secondary
scheduler that supports a primary scheduler?
Appellant contends Govil’s load balancing and gang scheduler do not
teach or suggest a secondary scheduler that supports a primary scheduler
because Govil does not disclose the gang scheduler being secondary to the
load balancing. App. Br. 13. Appellant argues Govil teaches the load
balancing schemes would be ineffective without a scalable gang scheduler
and, therefore, teaches the gang scheduler as being equal to or primary over
the load balancer. Id.
With regard to independent claims 1 and 25, we find the contested
“wherein” clause limitation is not positively recited as requiring steps to be
performed. See In re Johnston, 435 F.3d. 1381, 1384 (Fed. Cir. 2006)
(“[O]ptional elements do not narrow the claim because they can always be
omitted.”). Our reviewing Court has held that a statement of intended use in
an apparatus claim cannot distinguish over a prior art apparatus that
discloses all the recited limitations and is capable of performing the recited
function. See In re Schreiber, 128 F.3d 1473, 1477 (Fed. Cir. 1997). We
also note that “[a]n intended use or purpose usually will not limit the scope
of the claim because such statements usually do no more than define a
context in which the invention operates.” Boehringer Ingelheim Vetmedica,
Inc. v. Schering-Plough Corp., 320 F.3d 1339, 1345 (Fed. Cir.
2003). Although “[s]uch statements often . . . appear in the claim’s
preamble,” In re Stencel, 828 F.2d 751, 754 (Fed. Cir. 1987), a statement of
Appeal 2012-009471
Application 11/855,121

6
intended use or purpose can appear elsewhere in a claim. Id. Here, the
disputed limitation does no more than define a context in which the virtual
machine scheduler operates. As explained infra with reference to claim 13,
we find that Govil teaches or suggests a secondary scheduler. Accordingly,
we find that Govil’s gang scheduler is capable of performing the recited
function.
Accordingly, we are not persuaded the Examiner erred in rejecting
independent claims 1 and 25 and dependent claims 2–5 and 7–11, not argued
separately.
With regard to independent claim 13, we find the disputed limitations
to be positively recited and, therefore, not a statement of intended use.
Nevertheless, we are not persuaded that the Examiner erred.
The Examiner finds the term “secondary” describes a relative order in
time or position or that which depends on or is derived from something
primary, original, or first. Ans. 12. Based on this construction of the term
“secondary,” the Examiner finds because the scheduling decisions of Govil’s
gang scheduler are made subsequent to, and are dependent upon, the
scheduling decisions of the load balancer, Govil discloses the gang scheduler
as being a secondary scheduler relative to a primary scheduler, i.e., the load
balancer. Id. at 12–13.
“During examination, ‘claims . . . are to be given their broadest
reasonable interpretation consistent with the [S]pecification, and . . . claim
language should be read in light of the [S]pecification as it would be
interpreted by one of ordinary skill in the art.”’ In re Am. Acad. of Sci. Tech
Ctr., 367 F.3d 1359, 1364 (Fed. Cir. 2004) (citations omitted). In
determining whether a reference discloses a claimed limitation, we “must
Appeal 2012-009471
Application 11/855,121

7
apply the broadest reasonable meaning to the claim language, taking into
account any definitions presented in the [S]pecification.” Id. (citations
omitted).
Appellant’s Specification does not expressly define the term
“secondary” or “secondary scheduler.” Appellant’s Specification states “the
virtual machine scheduler 102 can operate as a secondary scheduler
supporting a primary scheduler” (Spec. ¶ 13) and “the virtual machine
scheduler 102 can be configur[ed] as a secondary scheduler that is
subservient to a main throughput scheduler” (Spec. ¶ 22). We note that
Appellant’s Specification uses the term “can” in describing the “virtual
machine scheduler.” Spec. ¶ 22. We find that such a description merely
denotes exemplary types of “virtual machine schedulers” as opposed to
giving a definitive description. Although giving claims their broadest
reasonable interpretation must take into account any definitions given in the
Specification (In re Morris, 127 F.3d 1048, 1054 (Fed. Cir. 1997)), it is
improper to read into the claims any limitations from examples given in the
Specification. In re Zletz, 893 F.2d 319, 321–22 (Fed. Cir. 1989). In other
words, we are not to read limitations from examples in the Specification into
the claims. See In re Am. Acad. of Sci. Tech. Ctr., 367 F.3d at 1369. As
such, there is no requirement that the “virtual machine scheduler” be
subservient to the primary scheduler, as this is a mere example.
Here, we find that it is best to look at the usual and ordinary meaning
of the term “secondary.” Specifically, the term “secondary” describes
something “of second rank, importance, or value” or something “not first in
order of occurrence or development.” See www.merriam-
webster.com/dictionary/secondary (last visited Jan. 8, 2015). As such, we
Appeal 2012-009471
Application 11/855,121

8
find that the broadest reasonable interpretation of the claimed “secondary
scheduler” refers to a scheduler that is of second rank, importance, or value
to another scheduler or performs a scheduling function after another
scheduler performs its scheduling function.
Govil teaches an idle balancer that, when a processor becomes idle,
searches run queues of other processors for a virtual CPU that, if moved to
the processor, would allow a virtual machine to run. Govil, pp. 245–246.
Govil further discloses after migration of the virtual CPU to the idle
processor, the virtual CPUs of the virtual machine are gang scheduled to run
concurrently on different physical processors. Id. at 246. As such, Govil
teaches or suggests the disputed limitation.
Accordingly, we are not persuaded that the Examiner erred in
rejecting claims 13–17 and 19–24.

Claim 12:
Issue: Under 35 U.S.C. § 103(a), did the Examiner err in finding that
Govil discloses swapping places between logical CPUs to remove conflicts
between jobs executing on schedulable hardware entities?
Appellant contends Govil does not teach or suggest “swapping places
between logical CPUs to remove conflicts,” as recited in claim 12. App. Br.
13–14; Reply Br. 1–2. Appellant argues that Govil’s migration of virtual
CPUs and subsequent de-scheduling/scheduling of virtual CPUs by a single
physical CPU does not teach or suggest swapping places between logical
CPUs. App. Br. 14.
We do not find Appellant’s contentions persuasive. We agree with
the Examiner’s findings and conclusion and adopt them as our own. We
Appeal 2012-009471
Application 11/855,121

9
note the following for emphasis. Appellant’s arguments are directed to
Govil’s migration of a virtual CPU from one physical CPU to another
physical CPU. See App. Br. 13–14; Reply Br. 1–2. We note that claim 12
does not require the logical CPUs to be swapped between physical CPUs.
Claim 12 only requires that logical CPUs be swapped to remove conflicts.
See App. Br., Claims Appendix. Govil teaches after selecting a virtual CPU,
the scheduler sends an RPC to all processors that have virtual CPUs
belonging to the same virtual machine as the selected virtual CPU. Govil, p.
248. Govil further teaches upon receiving an RPC, a processor de-schedules
the virtual CPU it is currently running and runs a virtual CPU, from the same
virtual machine as the selected virtual CPU, currently in its run queue. Id.
Govil, therefore, discloses the disputed limitation.
Accordingly, we are not persuaded that the Examiner erred in
rejecting claim 12.

CONCLUSION
On the record before us, we conclude the Examiner has not erred in
rejecting claims 2–5, 7–12, 14–17, and 19–24 under 35 U.S.C. § 112, second
paragraph, and claims 1–5, 7–17, and 19–25 under 35 U.S.C.
§ 103(a).

Appeal 2012-009471
Application 11/855,121

10
DECISION
As such, we AFFIRM the Examiner’s rejections of:
(1) claims 2–5, 7–12, 14–17, and 19–24 under 35 U.S.C. § 112,
second paragraph;
(2) claims 1–5, 9–17, 21, 22, and 25 under 35 U.S.C. § 103(a) based
on Govil and Armstrong;
(3) claims 7 and 19 under 35 U.S.C. § 103(a) based on Govil,
Armstrong, and Chiaramonte;
(4) claims 8 and 23 under 35 U.S.C. § 103(a) based on Govil,
Armstrong, and Anand;
(5) claim 20 under 35 U.S.C. § 103(a) based on Govil, Armstrong,
Anand, and Rhine; and
(6) claim 24 under 35 U.S.C. § 103(a) based on Govil, Armstrong,
and Rhine.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(1)(iv).

AFFIRMED

tj