Prosecution Insights
Last updated: April 19, 2026
Application No. 17/854,322

CONFIDENTIAL COMPUTING EXTENSIONS FOR HIGHLY SCALABLE ACCELERATORS

Final Rejection §103
Filed
Jun 30, 2022
Examiner
NAM, HYUN
Art Unit
2183
Tech Center
2100 — Computer Architecture & Software
Assignee
Intel Corporation
OA Round
2 (Final)
86%
Grant Probability
Favorable
3-4
OA Rounds
2y 7m
To Grant
86%
With Interview

Examiner Intelligence

Grants 86% — above average
86%
Career Allow Rate
750 granted / 867 resolved
+31.5% vs TC avg
Minimal -1% lift
Without
With
+-0.7%
Interview Lift
resolved cases with interview
Typical timeline
2y 7m
Avg Prosecution
20 currently pending
Career history
887
Total Applications
across all art units

Statute-Specific Performance

§101
10.4%
-29.6% vs TC avg
§103
38.5%
-1.5% vs TC avg
§102
16.1%
-23.9% vs TC avg
§112
19.2%
-20.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 867 resolved cases

Office Action

§103
DETAILED ACTION The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Claim Rejections - 35 USC § 103 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-6 and 8-25 are rejected under 35 U.S.C. 103 as being unpatentable over Lakshman et al. (U.S. Publication 2020/0320017), hereinafter Lakshman in view of Wash (U.S. 2019/0037406), hereinafter Wash further in view of Atamli et al. (U.S. Publication 2023/0297666), hereinafter Atamli. Referring to claim 1, Lakshman teaches, as claimed, an apparatus comprising: a processor (see Fig. 1, Processor 125(1)) to execute one or more software clients (see Fig. 1, APP 120(1)); and a hardware (see Fig. 1, Network Interface Card 118) accelerator (network interface card 118 could be... a specialized interface which performs and accelerates a specific protocol, see Paragraph 21) coupled to the processor, the hardware accelerator comprising an assignable interface (initializing the network interface at the PCI-E level… with assignable interfaces, see Paragraph 17) to receive a work (Work Queues, see Paragraph 13) request with a tag (PASIDs, see Paragraphs 13 and 17; and A PASID is a unique identifier … are tagged with a PASID, see Paragraph 27) from the one or more software clients; wherein the hardware accelerator is to, in response to receiving the work request, process the work request based at least in part on a configuration (configured to run, see Paragraph 21) of the assignable interface and a value of the tag (tagged with a PASID value, see Paragraph 27). Lakshman does not expressly disclose a single bit tag (PSSID is 20-bit identifier, see Paragraph 27) from the one or more software, wherein the tag is to indicate whether the work request originated from a trusted software logic or an untrusted software logic. Wash does disclose a single bit tag (see Fig. 1, Is it Safe?; Note, yes or no is a binary determination, hence ‘a single bit’) from the one or more software, wherein the tag is to indicate whether the work request originated from a trusted software logic (see Fig. 1, Yes – Display Web Content) or an untrusted software logic (see Fig. 1, No – HTTP redirect to warning page). At the time of the invention it would have been obvious to a person of ordinary skill in the art to incorporate a single bit tag into Lakshman PASID identification (see Wash Fig. 1, Is it Labeled?; Note, Wash demonstrates flagging safety along with identifying (i.e. labeling) is common practice). The suggestion/motivation for doing so would have been to provide very concise (i.e. just using one bit to answer yes or no question) safe environment for data processing. Lakshman/Wash does not expressly disclose a trusted software entity or an untrusted software entity. Atamli does disclose a Trusted Execution Environment (TEE) mode (see Fig. 1, Trusted Execution Environment 132A) that determines a trusted software entity (trusted memory area, see Paragraph 78) or an untrusted software entity (untrusted area, see Paragraph 78). At the time of the invention it would have been obvious to a person of ordinary skill in the art to incorporate Atamli into Lakshman/Wash. The suggestion/motivation for doing so would have been to provide data security priority where data sharing and resource partitioning would implicitly trigger resource sharing conflict. Referring to claim 2, Lakshman teaches, as claimed, the apparatus of claim 1, wherein the configuration of the assignable interface is to include an environment. Lakshman does not disclose expressly to include a Trusted Execution Environment (TEE) mode. Atamli does disclose to include a Trusted Execution Environment (TEE) mode (see Fig. 1, Trusted Execution Environment 132A). At the time of the invention it would have been obvious to a person of ordinary skill in the art to incorporate Atamli into Lakshman. The suggestion/motivation for doing so would have been to provide data security priority where data sharing and resource partitioning would implicitly trigger resource sharing conflict. As to claim 3, the modification teaches the apparatus of claim 2, wherein the tag value (tagged with a PASID value, see Lakshman Paragraph 27) of the work request is to indicate whether the work request originated from a trusted software entity (see Atamli Fig. 1, Trusted Execution Environment 132A), wherein the trusted software entity corresponds to one of: a TEE application (see Atamli Fig. 1, App), a TEE driver, a TEE operating system, a TEE container, a TEE virtual machine (see Atamli Fig. 1, VM), or a TEE security manager (see Atamli Fig. 1, Security App 135Z). As to claim 4, the modification teaches the apparatus of claim 3, wherein the hardware accelerator is to reject the work request (see Wash, Fig. 1, HTTP Redirect to Warning Page; Note, identified content has been labelled and flagged unsafe therefore it is rejected) based at least in part on a determination that the TEE mode is disabled (see Wash, Fig. 1, Is it Safe? No) for the assignable interface. As to claim 5, the modification teaches the apparatus of claim 1, wherein the hardware accelerator is to support a state machine (see Lakshman Fig. 3; Note, a computer is a state machine and Fig. 3 show various states going from one to another) for management of the assignable interface. As to claim 6, the modification teaches the apparatus of claim 5, wherein the state machine is to transition between one or more states selected from a group comprising: interface disabled, interface configured (see Lakshman Fig. 3, Configure PASID for a given queue), interface enabled, and interface halted. As to claim 8, the modification teaches the apparatus of claim 6, wherein the hardware accelerator is to reject the work request in response to a determination that a state of the assignable interface is different from the interface enabled state (see Wash, Fig. 1, Is it Safe? No; Note, No is different from Yes). As to claim 9, the modification teaches the apparatus of claim 6, wherein the state machine is to transition to interface halted (blocked, see Wash Paragraph 27) state based on an event from a group comprising: configuration change, interface reset, and interface error (warning, see Wash, Paragraph 27) . As to claim 10, the modification teaches the apparatus of claim 5, wherein the state machine is to transition between one or more states based on a command from a group comprising: lock interface, enable interface (see Wash, Fig. 1, Is it Safe? Yes), disable interface (see Wash, Fig. 1, Is it Safe? No), and reset interface. As to claim 11, Lakshman teaches the apparatus of claim 1, wherein a configuration interface of the accelerator is to receive a command (see Lakshman Fig. 3, Request PASID) from the one or more software entities with the tag. As to claim 12, the modification teaches the apparatus of claim 11 wherein the trusted software entity comprises one of: a TEE application, a TEE driver, a TEE operating system, a TEE container, a TEE virtual machine, and a TEE security manager, and wherein the untrusted software entity comprises one of: an application, a driver, an operating system, a container, a virtual machine, or a virtual machine monitor. As to claim 13, the modification teaches the apparatus of claim 11, wherein the hardware accelerator is to reject the command in response to a determination that a TEE mode is enabled and the software entity is an untrusted software entity. As to claim 14, the modification teaches the apparatus of claim 1, wherein the one or more software entities comprise one of: an application, a driver, an operating system (see Atamli Fig. 1, Operating System 126A to Z), a container, a virtual machine, a virtual machine monitor, a TEE application (see Atamli Fig. 1, App 133A), a TEE driver, a TEE operating system, a TEE container (see Atamli Fig. 1, Container 133A), a TEE virtual machine (see Atamli Fig. 1, VM 133A), and a TEE security manager (see Atamli Fig. 1, Security App 135Z). As to claim 15, the modification teaches the apparatus of claim 1, wherein the assignable interface comprises one of: a dedicated work queue (see Lakshman Fig. 2, Work Queue), a shared work queue, a transmission/reception (Tx/Rx) queue, or a command queue. As to claim 16, the modification teaches the apparatus of claim 1, wherein the assignable interface comprises one of: a Peripheral Component Interconnect express (PCIe) (PCI-E, see Lakshman Paragraph 21) or a Compute Express Link (CXL) physical function, a PCIe/CXL Single Root Input/Output Virtualization (SR-IOV) virtual function, and a Scalable Input/Output (I/O) Virtualization Assignable Device Interface (Scalable IOV ADI). As to claim 17, the modification teaches the apparatus of claim 1, wherein the hardware accelerator is to tag a Direct Memory Access (DMA) (see Lakshman Fig. 1, DMA Remapping Hardware 130) request based at least in part on the tag value of the work request. As to claim 18, the modification teaches the apparatus of claim 1, wherein the tag comprises a single bit (PASID is 20-bit identifier, see Lakshman Paragraph 27; Note, 20-bit comprises at least a single bit). As to claim 19, the modification teaches the apparatus of claim 1, wherein the hardware accelerator is to support one or more: data movement (to move the data back and forth, see Lakshman Paragraph 14) or data transformation operations. As to claim 20, the modification teaches the apparatus of claim 19, wherein the one or more data movement or data transformation operations comprise one or more of: a memory move operation (DMA transaction, see Lakshman Paragraph 27), a Cyclic Redundancy Code (CRC) operation, a Data Integrity Field (DIF) operation, a dual-cast operation, a memory fill operation, a memory compare operation, a delta record create or merge operation, a pattern detect operation, a cache flush operation, a scatter-gather operation, a data reduction operation, a memory compression or decompression operation, a scan operation, a filter operation, a select operation, a data compression or decompression operation, one or more cryptographic operations, and one or more public-key exchange operations. Referring to claim 21, Lakshman teaches, as claimed, an apparatus comprising: circuitry to provide an interface (initializing the network interface at the PCI-E level… with assignable interfaces, see Paragraph 17) to a host entity (see Fig. 1, Processor 125(1)) to cause assignment of a resource (see Fig. 1, Network Interface Card 118) to an entity (see Fig. 1, APP 120(1)) based at least in part on a value (PASIDs, see Paragraphs 13 and 17; and A PASID is a unique identifier … are tagged with a PASID, see Paragraph 27) of a tag (tagged with a PASID value, see Paragraph 27); and work queue (Work Queues, see Paragraph 13) configuration circuitry (configured to run, see Paragraph 21) to configure one or more work queues of a hardware accelerator (network interface card 118 could be .. a specialized interface which performs and accelerates a specific protocol, see Paragraph 21). Lakshman does not expressly disclose a single bit tag (PSSID is 20-bit identifier, see Paragraph 27) from the one or more software, wherein the tag is to indicate whether the work request originated from a trusted software logic or an untrusted software logic. Wash does disclose a single bit tag (see Fig. 1, Is it Safe?; Note, yes or no is a binary determination, hence ‘a single bit’) from the one or more software, wherein the tag is to indicate whether the work request originated from a trusted software logic (see Fig. 1, Yes – Display Web Content) or an untrusted software logic (see Fig. 1, No – HTTP redirect to warning page). At the time of the invention it would have been obvious to a person of ordinary skill in the art to incorporate a single bit tag into Lakshman PASID identification (see Wash Fig. 1, Is it Labeled?; Note, Wash demonstrates flagging safety along with identifying (i.e. labeling) is common practice). The suggestion/motivation for doing so would have been to provide very concise (i.e. just using one bit to answer yes or no question) safe environment for data processing. Lakshman/Wash does not disclose expressly a security manager and an assignment of resource to a trusted entity. Atamli does disclose a security manager (see Fig. 1, Security App 135Z) and an assignment of resource to a trusted entity (see Fig. 1, Trusted Execution Environment 132A). At the time of the invention it would have been obvious to a person of ordinary skill in the art to incorporate Atamli into Lakshman/Wash. The suggestion/motivation for doing so would have been to provide data security priority where data sharing and resource partitioning would implicitly trigger resource sharing conflict. As to claim 22, the modification teaches the apparatus of claim 21, wherein the work queue (Work Queues, see Lakshman Paragraph 10) configuration (see Lakshman Fig. 3, Configure PASID for a given queue) logic circuitry is to support a state machine (see Fig. 3; Note, a computer is a state machine and Fig. 3 show various states going from one to another) for management of the one or more work queues. As to claim 23, the modification teaches the apparatus of claim 22, wherein the state machine is to transition between one or more states selected from a group comprising: work queue disabled, work queue configured (see Lakshman Fig. 3, Configure PASID for a given queue), work queue enabled, and work queue halted. As to claim 24, the modification teaches the apparatus of claim 21, wherein the host entity is untrusted (see Atamli, Fig. 1; Note, any area outside of the dotted box are untrusted entity). As to claim 25, the modification teaches the apparatus of claim 21, wherein the trusted entity comprises a Trusted Execution Environment (TEE) Virtual Machine (TVM) (see Atamli Fig. 1, VM 133A). Allowable Subject Matter Claim 7 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Response to Arguments Applicant's arguments filed 11/08/2025 have been fully considered but they are moot in view of new grounds of rejections. Conclusion Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action. Contact Information Any inquiry concerning this communication or earlier communications from the examiner should be directed to Hyun Nam whose telephone number is (571) 270-1725 and fax number is (571) 270-2725. The examiner can normally be reached on Monday through Friday 8:30 AM to 5:00 PM EST. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jyoti Mehta can be reached on (571) 270-3995. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /HYUN NAM/Primary Examiner, Art Unit 2183
Read full office action

Prosecution Timeline

Jun 30, 2022
Application Filed
Aug 19, 2022
Response after Non-Final Action
Apr 05, 2025
Non-Final Rejection — §103
Oct 08, 2025
Response Filed
Jan 06, 2026
Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12591431
ARTIFICIAL INTELLIGENCE PROCESSING APPARATUS, AND DATA PREFETCHING DEVICE AND METHOD FOR ARTIFICIAL INTELLIGENCE PROCESSOR
2y 5m to grant Granted Mar 31, 2026
Patent 12591527
INTEGRATED CIRCUIT GENERATION WITH IMPROVED INTERCONNECT
2y 5m to grant Granted Mar 31, 2026
Patent 12579083
EFFICIENT QUEUE ACCESS FOR USER-SPACE PACKET PROCESSING
2y 5m to grant Granted Mar 17, 2026
Patent 12566718
CONFIGURING PCI EXPRESS MODULE USING HARDWARE IN A MEMORY SUB-SYSTEM
2y 5m to grant Granted Mar 03, 2026
Patent 12554660
HIGH CAPACITY MEMORY SYSTEM WITH IMPROVED COMMAND-ADDRESS AND CHIP-SELECT SIGNALING MODE
2y 5m to grant Granted Feb 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
86%
Grant Probability
86%
With Interview (-0.7%)
2y 7m
Median Time to Grant
Moderate
PTA Risk
Based on 867 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month