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 . 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.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 6, 8-12, 16, and 18-24 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by the IEEE paper RDMA-Based Deterministic Communication Architecture for Autonomous Driving by Abaza et al., hereinafter referred to as Abaza.
Referring to claim 1, Abaza discloses a computer-implemented method when executed on data processing hardware causes the data processing hardware to perform operations comprising: when a logical execution time (LET) of a first task ends (pg. 138, D. Nondeterministic behavior of Soft RoCE, “data produced by the same periodic/sporadic task”), copying data from a first memory buffer of a first device to a second memory buffer of the first device (pg. 139, fig. 4, step 4 depicts copying data from User Space buffer 1 to RDMA NIC buffer of Sender SoC), the data written to the first memory buffer during the first task (pg. 139, A. Communication using an RDMA connection, “the data from the memory region specified in the WQE”); receiving a periodic work request scheduled during a configuration phase of a vehicle (pg. 137, Abstract, “vehicles”; pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed”; pg. 143, D. Support for more QoS metrics, “task to wait for a timer signal activated periodically”; NOTE: the limitation “configuration phase” is not described in the specification or claims beyond the actions “the periodic work request is scheduled” in [0003], “scheduling a periodic work request” in [0009], “schedule periodic work requests” in [0038], “scheduling a periodic work request” in [0051], therefore the claimed “configuration phase” is being equated to the initiation phase of the RDMA taught by Abaza), the periodic work request automatically posted by a remote direct memory access (RDMA) communication controller of the first device to a send queue of an RDMA engine of the first device (pg. 139, fig. 4, step 2 depicts posting WQE to SQ of RDMA engine of the Sender SoC); reading the data from the second memory buffer (pg. 139, fig. 4, step 5 depicts reading data from RDMA NIC buffer of Sender SoC); transmitting the data to a second device in communication with the first device (pg. 139, fig. 4, step 5 depicts transmitting from Sender SoC to Receiver SoC); writing the transmitted data into a third memory buffer of the second device (pg. 139, fig. 4, data written to RDMA NIC buffer of Receiver SoC), the transmitted data needed to complete a second task (pg. 139, A. Communication using an RDMA connection, “at the receiving side, the application creates and places a WQE on the RQ in the HCA 6 . Now, when the receiver HCA receives a data packet and identifies the RDMA connection, it checks the corresponding RQ for a WQE 7 . If a WQE is available, the HCA puts the data in the memory region specified in the WQE using DMA”); and before a logical execution time (LET) of the second task begins (pg. 142, “threads are created to carry out different RDMA operations. These threads can be scheduled according to a policy…scheduler dispatches them using a FIFO policy.”), copying the transmitted data from the third memory buffer of the second device to a fourth memory buffer of the second device (pg. 139, fig. 4, step 8 depicts copying data from RDMA NIC buffer of User Space buffer of Receiver SoC), wherein the second task reads the copied data from the fourth memory buffer of the second device (pg. 142, C. Real-time extensions, “a set of tasks on the receiver side {τKr, τKr+1, .., τKrn} that consume the same data channel ϵks on the sender side”).
As to claim 2, Abaza discloses the periodic work request comprises one or more of a read request or a write request (pg. 138, fig. 2, “write results”, “Proposed data flow for AD/ADAS applications:…data is being read”).
As to claim 6, Abaza discloses copying the transmitted data from the first memory buffer of the first device to the second memory buffer of the first device comprises preempting any application tasks running on the first device (pg. 142, C. Real-time extensions, “d a preemption feature in RDMA communication. This preemption policy is particularly useful where multiple applications use the same RDMA port to send/receive data and have different priorities. In essence, our flow control layer supports fixed-point preemption [18], i.e., scheduling decisions can be taken at one or more fixed points while sending the whole data”).
As to claim 8, Abaza discloses the second device is in communication with the first device via an in-vehicle communication system of a vehicle (pg. 137, Abstract, “vehicles”; pg. 139, A. Communication using an RDMA connection).
As to claim 9, Abaza discloses copying the transmitted data from the first memory buffer of the first device to the second memory buffer of the first device is executed by an operating system of the first device (pg. 139, II REMOTE DIRECT MEMORY ACCESS (RDAM), “In Figure 3a, we see that multiple interventions of the operating system in the CPU are necessary to transfer data through different layers of the conventional communication stack. Also, in the process, data is copied in the buffers of different layers”).
As to claim 10, Abaza discloses the periodic work request is initiated by a remote direct memory access (RDMA) communication controller of the first device (pg. 138, “Proposed data flow for AD/ADAS applications:…RDMA is normally implemented at hardware level (e.g., integrated into a NIC”; pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed”).
Referring to claim 11, Abaza discloses a system comprising: data processing hardware; and memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations (pg. 137, Abstract, “Automotive platform”) comprising: when a logical execution time (LET) of a first task ends (pg. 138, D. Nondeterministic behavior of Soft RoCE, “data produced by the same periodic/sporadic task”), copying data from a first memory buffer of a first device to a second memory buffer of the first device (pg. 139, fig. 4, step 4 depicts copying data from User Space buffer 1 to RDMA NIC buffer of Sender SoC), the data written to the first memory buffer during the first task (pg. 139, A. Communication using an RDMA connection, “the data from the memory region specified in the WQE”); receiving a periodic work request scheduled during a configuration phase of a vehicle (pg. 137, Abstract, “vehicles”; pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed”; pg. 143, D. Support for more QoS metrics, “task to wait for a timer signal activated periodically”; NOTE: the limitation “configuration phase” is not described in the specification or claims beyond the actions “the periodic work request is scheduled” in [0003], “scheduling a periodic work request” in [0009], “schedule periodic work requests” in [0038], “scheduling a periodic work request” in [0051], therefore the claimed “configuration phase” is being equated to the initiation phase of the RDMA taught by Abaza), the periodic work request automatically posted by a remote direct memory access (RDMA) communication controller of the first device to a send queue of an RDMA engine of the first device (pg. 139, fig. 4, step 2 depicts posting WQE to SQ of RDMA engine of the Sender SoC); reading the data from the second memory buffer (pg. 139, fig. 4, step 5 depicts reading data from RDMA NIC buffer of Sender SoC); transmitting the data to a second device in communication with the first device (pg. 139, fig. 4, step 5 depicts transmitting from Sender SoC to Receiver SoC); writing the transmitted data into a third memory buffer of the second device (pg. 139, fig. 4, data written to RDMA NIC buffer of Receiver SoC), the transmitted data needed to complete a second task (pg. 139, A. Communication using an RDMA connection, “at the receiving side, the application creates and places a WQE on the RQ in the HCA 6 . Now, when the receiver HCA receives a data packet and identifies the RDMA connection, it checks the corresponding RQ for a WQE 7 . If a WQE is available, the HCA puts the data in the memory region specified in the WQE using DMA”); and before a logical execution time (LET) of the second task begins (pg. 142, “threads are created to carry out different RDMA operations. These threads can be scheduled according to a policy…scheduler dispatches them using a FIFO policy.”), copying the transmitted data from the third memory buffer of the second device to a fourth memory buffer of the second device (pg. 139, fig. 4, step 8 depicts copying data from RDMA NIC buffer of User Space buffer of Receiver SoC), wherein the second task reads the copied data from the fourth memory buffer of the second device (pg. 142, C. Real-time extensions, “a set of tasks on the receiver side {τKr, τKr+1, .., τKrn} that consume the same data channel ϵks on the sender side”).
As to claim 12, Abaza discloses the periodic work request comprises one or more of a read request or a write request (pg. 138, fig. 2, “write results”, “Proposed data flow for AD/ADAS applications:…data is being read”).
As to claim 16, Abaza discloses copying the transmitted data from the first memory buffer of the first device to the second memory buffer of the first device comprises preempting any application tasks running on the first device (pg. 140, Fixed-point preemption).
As to claim 18, Abaza discloses copying the transmitted data from the first memory buffer of the first device to the second memory buffer of the first device is executed by an operating system of the first device (pg. 139, II REMOTE DIRECT MEMORY ACCESS (RDAM), “In Figure 3a, we see that multiple interventions of the operating system in the CPU are necessary to transfer data through different layers of the conventional communication stack. Also, in the process, data is copied in the buffers of different layers”).
As to claim 19, Abaza discloses the periodic work request is initiated by a remote direct memory access (RDMA) communication controller of the first device (pg. 138, “Proposed data flow for AD/ADAS applications:…RDMA is normally implemented at hardware level (e.g., integrated into a NIC”; pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed”).
Referring to claim 20, Abaza discloses a computer-implemented method when executed on data processing hardware causes the data processing hardware to perform operations comprising: during a configuration phase of a vehicle (pg. 137, Abstract, “vehicles”; pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed”; NOTE: the limitation “configuration phase” is not described in the specification or claims beyond the actions “the periodic work request is scheduled” in [0003], “scheduling a periodic work request” in [0009], “schedule periodic work requests” in [0038], “scheduling a periodic work request” in [0051], therefore the claimed “configuration phase” is being equated to the initiation phase of the RDMA taught by Abaza): scheduling a periodic work request for a remote direct memory access (RDMA) communication controller of a first device of the vehicle (pg. 139, fig. 1 Sender SoC; pg. 140, D. Nondeterministic behavior of Soft-RoCE, “each RDMA connection can be used by an application to transfer specific data… periodic…task”; pg. 141, B. Flow control layer, “schedule work requests across different RDMA connections”), the periodic work request causing the RDMA communication controller to automatically create a work request to transmit data (pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed on the SQ”) between the first device and a second device (pg. 139, fig. 1, Receiver SoC) in communication with the first device, the work request based on parameters of the periodic work request, wherein the parameters of the periodic work request specify a start time, a repetition interval (pg. 143, D. Support for more QoS metrics, “task to wait for a timer signal activated periodically”; NOTE” “activated” is the start time parameter and periodically is the repetition interval parameter the work request is “based on”), and a reference to a memory buffer of the first device (pg. 139, A. Communication using an RDMA connection, “primary content of a WQE is a pointer to the target buffer. In SQ, a WQE contains a pointer to the data that needs to be sent”), and wherein the RDMA communication controller automatically posts the work request to a send queue of an RDMA engine of the first device at the start time and at each repetition interval thereafter (pg. 139, A. Communication using an RDMA connection, “When an application initiates an RDMA send operation, a WQE is created and placed on the SQ”; pg. 140, . Nondeterministic behavior of Soft-RoCE, “RDMA connection can be used by an application to transfer specific data (or a series of data produced by the same periodic/sporadic task”; pg. 143, D. Support for more QoS metrics, “task to wait for a timer signal activated periodically”).
As to clam 21, Abaza discloses the first device and the second device each comprise a remote direct memory access (RDMA) capable electronic control unit (ECU) of the vehicle (pg. 137, fig. 1(a) SoC-1 ECU for CAM and SoC-1 ECU for LIDAR).
As to claim 22, Abaza discloses the RDMA engine of the first device continuously processes work requests at a front of the send queue (pg. 142, “the scheduler dispatches them using a FIFO policy”) and removes the work requests from the send queue after the work requests are complete (pg. 143, D. Support for more QoS metrics, “once an RDMA communication is completed successfully, there is a WQE in the CQ”).
As to clam 23, Abaza discloses the first device and the second device each comprise a remote direct memory access (RDMA) capable electronic control unit (ECU) of the vehicle (pg. 137, fig. 1(a) SoC-1 ECU for CAM and SoC-1 ECU for LIDAR).
As to claim 24, Abaza discloses the RDMA engine of the first device continuously processes work requests at a front of the send queue (pg. 142, “the scheduler dispatches them using a FIFO policy”) and removes the work requests from the send queue after the work requests are complete (pg. 143, D. Support for more QoS metrics, “once an RDMA communication is completed successfully, there is a WQE in the CQ”).
Claim Rejections - 35 USC § 103
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 4, 7, 14, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Abaza in view of Mentovich et al. (US Pub. No. 2021/0174237), hereinafter referred to as Mentovich.
As to claims 4 and 14, while Abaza discusses time synchronization in the section on Related Work in pg. 145, Abaza appears silent regarding time synchronization applied to the sender and receiver SoCs, and therefore does not appear to explicitly disclose the first device and the second device are time synchronized.
However, Mentovich discloses the first device and the second device are time synchronized ([0038], [0045]).
Abaza and Mentovich are analogous art because they are from the same field of endeavor, work queue management.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of Abaza and Mentovich before him or her, to modify RDMA system of Abaza to include the time-synchronization of Mentovich because the time-synchronization would provide compatibility for time-constrained computations.
The suggestion/motivation for doing so would have been the recognition and suggestion of time-synchronization as related and pertinent to the RDMA system of Abaza and further the compatibility motivation indicated by Mentovich.
Therefore, it would have been obvious to combine Abaza and Mentovich to obtain the invention as specified in the instant claim.
As to claims 7 and 17, while Abaza anticipates transmitting the data to the second device in communication with the first device, and considers the transmission occurring for a time duration (pg. 141, “worst-case response time analysis”), Abaza does not appear to explicitly disclose a time bounded duration.
However, Mentovich discloses a time bounded duration (a cutoff time (e.g., t.sub.c) is set, [0046]).
The suggestion/motivation to combine remains as indicated above.
Response to Arguments
Applicant's arguments filed 5/6/2026 have been fully considered but moot in view of the new grounds of rejection necessitated by the amendments.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The US Pub. No. 2014/0181241 is pertinent to managing RDMA work requests in an on-chip architecture.
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
The examiner has cited particular column, line, and/or paragraph numbers in the references as applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in its entirety as potentially teaching of all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
The examiner requests, in response to this office action, support be shown for language added to any original claims on amendment and any new claims. That is, indicate support for newly added claim language by specifically pointing to page(s) and line number(s) in the specification and/or drawing figure(s). This will assist the examiner in prosecuting the application. When responding to this office action, applicant is advised to clearly point out the patentable novelty which he or she thinks the claims present, in view of the state of art disclosed by the references cited or the objections made. He or she must also show how the amendments avoid such references or objections. See 37 C.F.R. 1.111(c).
Applicants seeking an interview with the examiner, including WebEx Video Conferencing, are encouraged to fill out the online Automated Interview Request (AIR) form (http://www.uspto.gov/patent/uspto-automated-interview-request-air-form.html). See MPEP §502.03, §713.01(11) and Interview Practice for additional details.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC T OBERLY whose telephone number is (571)272-6991. The examiner can normally be reached on M-F 800am-430pm (MT).
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Dr. Henry Tsai can be reached on (571) 272-4176. 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 Center. For more information about the Patent Center, see https://patentcenter.uspto.gov/. Should you have questions on access to the Patent Center 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.
/ERIC T OBERLY/ Primary Examiner, Art Unit 2184
Prosecution Insights