Doshi, Kshitij A. et al.

Patent Trials and Appeals Board

Jan 31, 2020

14697832 - (D) (P.T.A.B. Jan. 31, 2020)

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.
14/697,832 04/28/2015 Kshitij A. Doshi ITL.3347US (P82178) 2354
47795 7590 01/31/2020
TROP, PRUNER & HU, P.C.
PO Box 41790
HOUSTON, TX 77241
EXAMINER
RIGOL, YAIMA
ART UNIT PAPER NUMBER
2135
NOTIFICATION DATE DELIVERY MODE
01/31/2020 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):
Inteldocs_docketing@cpaglobal.com
tphpto@tphm.com
PTOL-90A (Rev. 04/07)

UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte KSHITIJ A. DOSHI and CHRISTOPHER J. HUGHES
Appeal 2019-001389
Application 14/697,832
Technology Center 2100
Before ST. JOHN A. COURTENAY III, LARRY J. HUME, and
PHILLIP A. BENNETT, Administrative Patent Judges.
HUME, Administrative Patent Judge.
DECISION ON APPEAL
Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the
Examiner’s decision rejecting claims 1–4, 6–17 and 20–25, which are all the
claims pending in the application. Appellant has canceled claims 5, 18 and
19. We have jurisdiction under 35 U.S.C. § 6(b).
We REVERSE.

1 We use the word “Appellant” to refer to “Applicant(s)” as defined in 37
C.F.R. § 1.42(a). Appellants identify the real party in interest as Intel Corp.
App. Br. 2.
Appeal 2019-001389
Application 14/697,832

2
STATEMENT OF THE CASE2
The Invention
The claims are directed to “controlling displacement in a co-operative
and adaptive multiple level memory system.” See Title. In particular,
Appellant’s disclosed embodiments and claimed invention relate to “the
field of processing logic, microprocessors, and associated instruction set
architecture that, when executed by the processor or other processing logic,
perform logical, mathematical, or other functional operations.” Spec. ¶ 1.
Exemplary Claim
Claim 1, reproduced below, is representative of the subject matter on
appeal (emphasis added to contested prior-art limitations):
1. A processor comprising:
a control logic to determine whether to enable an
incoming data block associated with a first priority to displace,
in a cache memory coupled to the processor, a candidate victim
data block associated with a second priority and stored in the
cache memory, based at least in part on the first and second
priorities, a first access history associated with the incoming
data block and
a second access history associated with the candidate
victim data block, wherein the control logic is to perform a data
block displacement decision with respect to the incoming data
block and the candidate victim data block comprising a
statistical probability determination according to a first bias
value to randomly statistically bias displacement of the

2 Our decision relies upon Appellant’s Appeal Brief (“App. Br.,” filed May
30, 2018 ); Reply Brief (“Reply Br.,” filed Dec. 5, 2018 ); Examiner’s
Answer (“Ans.,” mailed Oct. 5, 2018 ); Final Office Action (“Final Act.,”
mailed Jan. 3, 2018 ); and the original Specification (“Spec.,” filed April 28,
2015 ).
Appeal 2019-001389
Application 14/697,832

3
candidate victim data block, wherein the control logic is to
select one of a first bias matrix storage and a second bias matrix
storage from which to obtain the first bias value based at least
in part on the first priority and the second priority.
Prior Art
The Examiner relies upon the following prior art as evidence in
rejecting the claims on appeal:
Hosoya et al. (“Hosoya”) US 2002/0007440 A1 Jan. 17, 2002
Cargnoni et al. (“Cargnoni”) US 2004/0215890 A1 Oct. 28, 2004
Fair et al. (“Fair”) US 7,752,395 B1 July 6, 2010
Lilly et al. (“Lilly”) US 2015/0026404 A1 Jan. 22, 2015
Evans US 9,047,225 B1 June 2, 2015
Schwetman, Jr. et al. (“Schwetman”) US 2016/0062894 A1 Mar. 3, 2016
Rejections on Appeal
R1. Claims 1, 6, 7, and 12 stand rejected under 35 U.S.C. § 103 as
being unpatentable over the combination of Lilly and Evans. Final Act. 5.
R2. Claims 2 and 8 stand rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, and Cargnoni. Final
Act. 9.
R3. Claims 3 and 4 stand rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, Cargnoni, and Fair.
Final Act. 10.
R4. Claim 9 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, and Hosoya. Final
Act. 12.
Appeal 2019-001389
Application 14/697,832

4
R5. Claim 10 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, Hosoya, and Fair. Final
Act. 13.
R6. Claim 11 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, and Schwetman. Final
Act. 14.
R7. Claim 13 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, and Cargnoni. Final
Act. 15.
R8. Claims 14–16 stand rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, Cargnoni, and Fair.
Final Act. 18.
R9. Claim 17 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Lilly, Evans, Cargnoni, and
Schwetman. Final Act. 19.
R10. Claim 20 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Evans and Schwetman. Final Act. 20.
R11. Claims 21, 23, 24, and 25 stand rejected under 35 U.S.C. § 103
as being unpatentable over the combination of Evans, Schwetman, and
Hosoya. Final Act. 23.
R12. Claim 22 stands rejected under 35 U.S.C. § 103 as being
unpatentable over the combination of Evans, Schwetman, Hosoya, and Fair.
Final Act. 26.
Appeal 2019-001389
Application 14/697,832

5
ISSUES AND ANALYSIS
Based upon our review of the record, we find a preponderance of the
evidence supports particular arguments advanced by Appellant with respect
to claims 1–4, 6–17 and 20–25 for the specific reasons discussed below. We
highlight and address specific findings and arguments for emphasis as
follows.
1. § 103 Rejection R1 of Claims 1, 6, 7, and 12
Issue 1
Appellant argues (App. Br. 9–10; Reply Br. 2–3) the Examiner’s
rejection of claim 1 under 35 U.S.C. § 103(a) as being obvious over the
combination of Lilly and Evans is in error. These contentions present us
with the following issue:
Did the Examiner err in finding the cited prior art combination teaches
or suggests a processor that includes, inter alia, “control logic” wherein,
inter alia,
the control logic is to perform a data block displacement
decision with respect to the incoming data block and the
candidate victim data block comprising a statistical probability
determination according to a first bias value to randomly
statistically bias displacement of the candidate victim data
block, wherein the control logic is to select one of a first bias
matrix storage and a second bias matrix storage from which to
obtain the first bias value based at least in part on the first
priority and the second priority,
as recited in claim 1?
Appeal 2019-001389
Application 14/697,832

6
ANALYSIS
Appellant submits “Evans does not teach or suggest . . . that this
statistical probability determination is according to a first bias value.”
Appeal Br. 10. Appellant further argues:
[N]owhere in Evans is there any teaching or suggestion of a
control logic to select a bias value from one of multiple bias
matrix storages. Evans further fails to teach or suggest that this
selection of bias matrix storage from which to obtain a bias
value be based on priorities of both incoming data block and
victim candidate data block.
Id. Additionally,
[t]he Examiner never mentions, and cannot identify anything in
the art for selection of a bias value that is selected from one of
multiple storages based on priorities of both incoming data
block and candidate victim data block. Instead, Evans’ teaching
of bias is only for weighting which of its multiple replacement
protocols to use. And this biasing is taught to be based on cache
hit rate. Evans, col. 3, lns. 37–50. But nothing teaches or
suggests a bias value based on data block priorities.
Reply Br. 3.
The Examiner finds Lilly does not explicitly teach or suggest the
limitations “a statistical probability determination according to a first bias
value to randomly statistically bias displacement of the candidate victim data
block” and “wherein the control logic is to select one of a first bias matrix
storage and a second bias matrix storage from which to obtain the first bias
value based at least in part on the first priority and the second priority.”
Final Act. 6.
Appeal 2019-001389
Application 14/697,832

7
Instead, the Examiner finds:
Evans Col: 1 line 42 to Col: 2 line: 21, Col: 3 lines: 28–42 and
Col: 4 lines 16–41 teaches pre-fetching data from the disk and
loading it into the cache. Once the cache fills, it becomes
necessary to evict some of the data stored in the cache to make
room for newly arriving data. For the eviction process, a
probability with different weight factors with respect to data
replacement protocols for evicting data is performed. The
weights affects how data is evicted (LRU, FIFO, random, etc.)
based on what would have a better reward than punishment for
evicting.
Ans. 4. The Examiner additionally finds:
Evans Fig. 3 teaches a cache manager 130 which comprises
protocol selector 132, as well as a record 310 of data
replacement protocols, a current protocol 330, a hit rate detector
340 and a protocol adjuster 350. Col: 4 lines 17–33 teaches the
record 310 of data replacement protocols includes entries of
replacement protocols selection (whether candidate data will be
evicted based on LRU, FIFO, random replacement, etc.). Each
protocol having a weight. Weights for all protocols may
initially be set to be the same values or to random values. Col: 4
lines: 34–41 and Col: 8 lines: 32–57 teaches that the probability
of the protocol selector 132 selecting any given protocol is
equal to the weight associated with that protocol divided by the
sum of all the weights for all of the protocols, [t]his sum would
be equivalent to the bias value.
Ans. 5.
Appellant responsively contends, “[w]hile Evans teaches that a
random selection process can be used to select the replacement protocol,
there is absolutely nothing in the reference that in any way teaches or
suggests that any replacement decision for a given data block be by a
statistical probability determination.” Reply Br. 2.
Appeal 2019-001389
Application 14/697,832

8
We disagree with the Examiner because, for the reasons set forth by
Appellant, we do not find the cited portions of Evans teach or suggest the
disputed limitation, i.e.,
wherein the control logic is to perform a data block
displacement decision with respect to the incoming data block
and the candidate victim data block comprising a statistical
probability determination according to a first bias value to
randomly statistically bias displacement of the candidate victim
data block, wherein the control logic is to select one of a first
bias matrix storage and a second bias matrix storage from
which to obtain the first bias value based at least in part on the
first priority and the second priority.
as recited in claim 1.
We disagree with the Examiner because, as argued by Appellant,
“regardless of how a protocol is selected in Evans, once selected,
replacement decisions are made according to the selected protocol — none
of which relies on a statistical probability determination according to a bias
value.” Appeal Br. 10.
Therefore, for essentially the same reasons argued by Appellant, we
reverse the Examiner's rejection of independent claim 1, and grouped
claims 6, 7, 12 that depend therefrom and stand therewith.3 See Claim
Grouping, supra.

3 Because we agree with at least one of the dispositive arguments advanced
by Appellant, we need not reach the merits of Appellant’s other arguments.
See Beloit Corp. v. Valmet Oy, 742 F.2d 1421, 1423 (Fed. Cir. 1984)
(finding an administrative agency is at liberty to reach a decision based on “a
single dispositive issue”).
Appeal 2019-001389
Application 14/697,832

9
2. § 103 Rejections R2–R12 of Claims 2–4, 8–11, 13–17, and 20–25
Because we have reversed the Examiner's rejection of independent
claim 1 under Rejection R1, we also reverse Rejection R7 of independent
claim 13 and Rejection R10 of independent claim 20, which both recite the
disputed limitation in commensurate form, and which all rely upon the
disclosure of Evans to teach or suggest the disputed limitation.
Accordingly, in light of our reversal of Rejections R1, R7, and R10 of
independent claims 1, 13 and 20, supra, we also reverse obviousness
Rejections R2–R6, R8, R9, R11, and R12 under § 103 of dependent
claims 2–4, 8–11, 14–17, and 21–25, which variously and ultimately depend
from independent claims 1, 13, and 20. On this record, the Examiner has not
shown how the additionally cited references overcome the aforementioned
deficiencies with Evans, as discussed above regarding claim 1.
CONCLUSION
The Examiner erred with respect to obviousness Rejections R1–R12
of claims 1–4, 6–17, and 20–25 under 35 U.S.C. § 103(a) over the cited prior
art combinations of record, and we do not sustain the rejections.
DECISION
We reverse the Examiner’s decision rejecting claims 1–4, 6–17
and 20–25.

Appeal 2019-001389
Application 14/697,832

10
DECISION SUMMARY
Claims
Rejected
35 U.S.C.
§
Basis/
References
Affirmed Reversed
1, 6, 7, 12 103 Lilly, Evans 1, 6, 7, 12
2, 8 103 Lilly, Evans,
Cargnoni
2, 8
3, 4 103 Lilly, Evans,
Cargnoni,
Fair
3, 4
9 103 Lilly, Evans,
Hosoya
9
10 103 Lilly, Evans,
Hosoya, Fair
10
11 103 Lilly, Evans,
Schwetman
11
13 103 Lilly, Evans,
Cargnoni
13
14–16 103 Lilly, Evans,
Cargnoni,
Fair
14–16
17 103 Lilly, Evans,
Cargnoni,
Schwetman
17
20 103 Evans,
Schwetman
20
21, 23, 24, 25 103 Evans,
Schwetman,
Hosoya
21, 23, 24, 25
22 103 Evans,
Schwetman,
Hosoya, Fair
22
Overall
Result
1–4, 6–17,
20–25
REVERSED