Ex Parte Franceschini et al

Patent Trial and Appeal Board

Feb 16, 2017

13525757 (P.T.A.B. Feb. 16, 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.
13/525,757 06/18/2012 Michele Franceschini YOR920120328US1 7484
48237 7590 02/21/2017
HARRINGTON & SMITH
4 RESEARCH DRIVE, Suite 202
SHELTON, CT 06484-6212
EXAMINER
GU, SHAWN X
ART UNIT PAPER NUMBER
2138
NOTIFICATION DATE DELIVERY MODE
02/21/2017 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):
USPTO@HSPATENT.COM
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte MICHELE FRANCESCHINI,
ASHISH JAGMOHAN, MOINUDDIN K. QURESHI, and
LUIS A. LASTRAS
Appeal 2016-006352
Application 13/525,7571
Technology Center 2100
Before ALLEN R. MacDONALD, HUNG H. BUI, and
MICHAEL J. ENGLE, Administrative Patent Judges.
ENGLE, Administrative Patent Judge.
DECISION ON APPEAL
Appellants appeal under 35 U.S.C. § 134(a) from a final rejection of
claims 1—26. We have jurisdiction under 35 U.S.C. § 6(b).
We AFFIRM.
Technology
The application relates to “wear leveling” in non-volatile memory by
preventing portions of memory from wearing out prematurely. Spec. 1—2.
Illustrative Claim
Claim 1 is illustrative and reproduced below with the limitations at
issue emphasized:
1 According to Appellants, the real party in interest is International Business
Machines Corporation. App. Br. 4.
Appeal 2016-006352
Application 13/525,757
1. A method, comprising:
determining, for data to be written to a nonvolatile
memory, a location in the nonvolatile memory to which the data
should be written based at least on one or more wear metrics
corresponding to the location, where the one or more wear
metrics comprise one or more of the following:
an observed bit-error rate,
a number of stuck bits,
a write/read latency,
a number of defects,
read and write power,
storage capacity, or
measurements of physical characteristics of the
location, the measurements estimating physical wear of
the location
but where the one or more wear metrics do not comprise a count
of usage of the location, where the count of usage is a count of
writes or a count of erasures', and
writing the data to the determined location in the
nonvolatile memory.
Examiner’s Rejections & References
(1) Claims 1, 23, and 24 stand rejected under 35 U.S.C. § 102(e) as
anticipated by Son et al. (US 2012/0096217 Al; Apr. 19, 2012). Final
Act. 3.
(2) Claims 2—11, 22, 25, and 26 stand rejected under 35 U.S.C.
§ 103(a) as obvious over the combination of Son and Moore et al. (US
2009/0327602 Al; Dec. 31, 2009). Final Act. 4.
(3) Claims 12—21 stand rejected under 35 U.S.C. § 103(a) as
obvious over the combination of Son and Lee et al. (US 2007/0204128 Al;
Aug. 30, 2007). Final Act. 16.
2
Appeal 2016-006352
Application 13/525,757
ISSUE
Did the Examiner err in finding Son discloses “the one or more wear
metrics comprise . . . storage capacity . . . but where the one or more wear
metrics do not comprise a count of usage of the location, where the count of
usage is a count of writes or a count of erasures,” as recited in claim 1 and
commensurately recited in independent claims 23 and 24?
ANALYSIS
Anticipation: Claims 1, 23, and 24
The Examiner relies on Son for disclosing the claimed wear metrics
comprising storage capacity. Ans. 22—24. Specifically, the Examiner finds
Son’s “selection of superblock for storing source data is based on evaluation
of. . . the number of free, valid and/or invalid pages in each candidate
superblock.” Final Act. 3 (citing Son 147).
Appellants contend “the number of free, valid pages in Son is defined
as being free or valid based on a wear count.'1'’ App. Br. 18 (emphasis
added). A wear count is “a count of how many times a particular superblock
has been erased,” which fails to meet the claimed negative limitation that the
“wear metrics do not comprise ... a count of erasures.” Id. at 14.
We are not persuaded by Appellants’ contention that Son’s free or
valid pages are based on a wear count. Son separately tracks a wear count
from a valid or invalid count: “The superblock table associates each
superblock (column 335a) with a wear count (column 335b), a valid page
count (column 335c), [and] an invalid page count (column 335d).” Son
139. Appellants are correct that “[t]he wear count column indicates how
many times a particular superblock has been erased.” Id. However, the
“free” and “valid” counts are different:
3
Appeal 2016-006352
Application 13/525,757
A physical page is “free” if the page has not been programmed
with data since its superblock was last erased. The data in a
physical page is “valid” if it represents up-to-date data that is in
use by the file system or another system component, such as the
SSD module. A physical page is “invalid” if the data it contains
is stale, either because the file system or another component is
no longer using the data stored in the physical page (e.g., because
a file was deleted from the file system) or because an updated
version of the stored data was stored in a different physical page
(e.g., during a re-write operation).
Son 136. Thus, we agree with the Examiner that “Son’s ‘free page count’ is
not calculated, derived, or obtained based on ‘wear count.’” Ans. 23.
“While it might be true that a page’s status becomes ‘free’ due to an erase
operation, the count of free or valid pages is not a count of writes or a count
of erasures in a superblock, as a page that is not free may have been erased
once and later written to again.” Id. at 22.
We also agree with the Examiner that Son discloses choosing the
superblock based on the number of free or valid pages, separate from a wear
count: “When selecting the superblock, the SSD module may evaluate any
combination of several factors including ... the number of free, valid and/or
invalid pages in each candidate superblock,. . . [or] the wear count.” Son
1147, 80.
Appellants’ further contention that Son’s “wear leveling” only occurs
based on “wear count” is not persuasive. App. Br. 21—22. Son expressly
says it “may implement wear leveling upon the occurrence of other triggers
(e.g., at periodic intervals, scheduled times, etc.).” Son 179 (emphasis
added). Moreover, the claims are directed to selecting a memory and Son
discloses that regardless of what triggers wear leveling, the superblock can
4
Appeal 2016-006352
Application 13/525,757
be chosen based on “free page count”; “valid page count”; or “invalid page
count,” which are separate from “wear count.” Id. 1 80.
Although Appellants argue “Son never in fact uses the term ‘storage
capacity’” (App. Br. 18), we agree with the Examiner (Ans. 23) that a prior
art reference need not use identical language as the claim (i.e., an ipsissimis
verbis or in haec verbis test is not required). Whitserve, LLC v. Computer
Packages, Inc., 694 F.3d 10, 21 (Fed. Cir. 2012). As defined above, the
number of free or valid pages in a memory is a measure of storage capacity.
Accordingly, we sustain the rejection of claims 1, 23, and 24.
Obviousness: Claims 2—22, 25, and 26
Appellants contend dependent claims 2—22, 25, and 26 are allowable
for the same reasons as independent claims 1, 23, and 24 and because Moore
(claims 2—11, 22, 25, and 26) and Fee (claims 12—21) do not cure the
deficiencies set forth for those independent claims. See App. Br. 24—38
(Moore), 39-46 (Fee). For the same reasons discussed above, we also
sustain the obviousness rejection of claims 2—22, 25, and 26.
DECISION
We affirm the Examiner’s decision rejecting claims 1—26.
No time for taking subsequent action in connection with this appeal
maybe extended under 37 C.F.R. § 1.136(a). 37 C.F.R. § 41.50(f).
AFFIRMED
5