DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant's arguments filed 2 September 2025 have been fully considered but they are not persuasive. Applicant’s arguments with respect to the prior art have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 (i.e., changing from AIA to pre-AIA ) 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, 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, 2, 4, 5, 10, 11, 13, 14, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Benthin (U.S. Publication 2023/0298254) in view of Plotnikov (U.S. Publication 2020/0195965) and further in view of Lee (U.S. Publication 2019/0342372).
As to claim 1, Benthin discloses a method of building a bounding volume hierarchy, the method comprising:
performing a nearest neighbor search for a set of clusters to generate a set of nearest neighbors (p. 80, section 1067-p. 81, section 1078; a set of bounding boxes including primitives, reading on clusters, are evaluated to determine nearest neighbors);
performing a merge operation for the set of clusters, based on the set of nearest neighbors to generate merge results for the set of clusters (p. 80, section 1067-p. 81, section 1078);
and without performing a global barrier operation, outputting clusters for a level of the bounding volume hierarchy, based on the merge results (p. 81, section 1079; the “while(anyMerged and localN > T) pass the localN and contents of I to the caller” is an output step for the clusters/boxes and occurs after any barriers rather than including them).
Benthin does not disclose, but Plotnikov discloses wherein the set of clusters includes a first subset assigned to a first wavefront and a second subset assigned to a second wavefront (p. 5-6, sections 0046-0057; blocks/clusters of pixels are assigned to a number of wavefronts, including block/cluster 304 assigned to wavefront 1, which can read on a second cluster assigned to second wavefront and blocks/clusters 305, 306, which can read on a first cluster assigned to first wavefront), and in response to the second wavefront being prior to the first wavefront in a wavefront order, performing a merge operation for the set of clusters (p. 2, section 0028; p. 5, section 0046; in the case where second wavefront containing block 303 is before first wavefront containing blocks 305 and 306, blocks 305 and 306 are processed in parallel after block 303, and operations, such as a coding mode selection operation, which can be a merge mode operation, can go forward). The motivation for this is to prevent non-optimal mode decisions that would otherwise occur along wavefront boundaries. It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin to have the set of clusters include a first subset assigned to a first wavefront and a second subset assigned to a second wavefront, and in response to the second wavefront being prior to the first wavefront in a wavefront order, performing a merge operation for the set of clusters in order to prevent non-optimal mode decisions that would otherwise occur along wavefront boundaries as taught by Plotnikov.
Benthin discloses using workgroup and thread level barriers (p. 73, sections 0991-0996), at least one of which would appear to be part of the merge operation, but would not appear to be global in nature. However, Benthin does not explicitly state that each of the barriers is not global. Thus, Benthin does not explicitly disclose that the merge operation based on searched neighbors is performed without performing a global barrier operation. Lee, however, does disclose that such a search that can be used for a merge would be done without performing a global barrier operation (p. 3, section 0046; p. 5, sections 0082-0086; graph processing tasks such as searches are executed without a global barrier operation between steps). The motivation for this is to lower latency and increase efficiency. It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin and Plotnikov to perform search without performing a global barrier operation in order to lower latency and increase efficiency as taught by Lee.
As to claim 2, Benthin discloses wherein performing the nearest neighbor search includes, for a first cluster of the set of clusters, identifying a second cluster as a nearest neighbor of the first cluster (p. 80, sections 1070-1075; the nearest neighbor cluster/box which is the minimum distance from the first cluster/box is identified as the nearest neighbor).
As to claim 4, Benthin discloses wherein performing the merge operation comprises determining that a first cluster of the set of clusters is part of a nearest neighbor pair that includes a second cluster (p. 80, sections 1070-1075; the nearest neighbor cluster/box which is the minimum distance from the first cluster/box is identified as the nearest neighbor for a box/cluster pair)
As to claim 5, Benthin discloses wherein performing the merge operation further comprises: generating a merged cluster for the first cluster and the second cluster (p. 81, section 1079; the two cluster/boxes are merged into a new cluster/box).
As to claim 10, see the rejection to claim 1. Further, Benthin discloses a system, comprising: a memory storing instructions; and a processor configured to execute the instructions (p. 82, sections 1109-1110).
As to claim 11, see the rejection to claim 2.
As to claim 13, see the rejection to claim 4.
As to claim 14, see the rejection to claim 5.
As to claim 19, see the rejections to claims 1 and 10.
As to claim 20, see the rejection to claim 2.
Claims 3 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Benthin in view of Plotnikov and Lee and further in view of Bortnikov (U.S. Publication 2017/0140012)
As to claim 3, Benthin discloses wherein the first cluster is with a radius of a stage subsequent to a current stage (p. 80, section 1070; the clusters/boxes scanned are within a radius i-R to i+R; a stage in this application is defined as a group of consecutive data/clusters, and thus the clusters/boxes scanned from i to i+R would be in the radius of the stage or group subsequent to the current stage i); and performing the nearest neighbor search further includes writing the nearest neighbor to a memory (p. 80, section 1070; the found nearest neighbor is written to memory). Benthin discloses that the memory written to is local memory rather than global memory. Bortnikov, however, discloses writing the set of nearest neighbors to global memory (p. 6, section 0070). The motivation for this is that data within the global memory is visible to all threads in an application (p. 3, section 0031). It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin, Plotnikov, and Lee to write the set of nearest neighbors to global memory in order to make the set visible to all threads in an application as taught by Bortnikov.
As to claim 12, see the rejection to claim 3.
Claims 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Benthin in view of Plotnikov and Lee and further in view of McCormack (U.S. Publication 2002/0097241).
As to claim 6, Benthin does not disclose, but McCormack does disclose wherein performing the merge operation further comprises generating an invalid cluster to replace the first cluster (p. 13, section 0186-p. 14, section 0189; a first fragment, which is a cluster of the geometry, is replaced with an invalid fragment/cluster after it is merged). The motivation for this is that after a merge, the fragment/cluster has been superceded by a merged fragment. It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin, Plotnikov, and Lee to generate an invalid cluster to replace the first cluster in order to compensate for the fact that after a merge, the fragment/cluster has been superceded by a merged fragment as taught by McCormack.
As to claim 15, see the rejection to claim 6.
Claims 7, 8, 16, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Benthin in view of Plotnikov and Lee and further in view of Knittel (U.S. Patent 6,532,017).
As to claim 7, Benthin discloses merge operations for elements including clusters as discussed in the rejection to claim 1. Benthin does not disclose, but Knittel does disclose wherein performing the merge operation comprises: in response to a first element having a nearest neighbor within a subsequent wavefront, refraining from performing merge operations for the first element (col. 10, lines 18-38; if a volume element has a nearest neighbor that enters the pipeline in a subsequent stage/wavefront after the element, merging is refrained from being performed immediately and a delay is performed before the merge; this is similar to what is described in applicant’s specification where merging is refrained from being done and then shifted to another wavefront). The motivation for refraining from merging is to delay one element, synchronizing the elements so that they can be merged later. It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin, Plotnikov, and Lee to, in response to a first element having a nearest neighbor within a subsequent wavefront, refraining from performing merge operations for the first element in order to synchronize the elements so that they can be merged later as taught by Knittel.
As to claim 8, Benthin discloses merge operations for elements including clusters as discussed in the rejection to claim 1. Benthin does not disclose, but Knittel does disclose wherein performing the merge operation comprises merging elements in a shifted frame (col. 10, lines 18-38; if a volume element has a nearest neighbor that enters the pipeline in a subsequent stage/wavefront after the element, a delay is performed before the merge, shifting the frame of one of the elements). Motivation for the combination is given in the rejection to claim 7.
As to claim 16, see the rejection to claim 7.
As to claim 17, see the rejection to claim 8.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Benthin in view of Plotnikov, Lee, and Knittel and further in view of Huang (U.S. Publication 2016/0364468).
As to claim 9, Benthin discloses clusters in a bounding volume hierarchy, as discussed in the rejection to claim 1. Benthin does not disclose, but Huang does disclose repeating the operations of performing the nearest neighbor search, performing the merge operation, and outputting the clusters for each cluster of each level of the hierarchy (p. 7, section 0091; the nearest cluster search, merge, and output is repeated for each level). The motivation for merging on a level-by-level basis is that it then enables the movement of clusters to different levels based on cardinality. It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to modify Benthin, Plotnikov, Lee and Knittel to repeat the operations of performing the nearest neighbor search, performing the merge operation, and outputting the clusters for each cluster of each level of the hierarchy in order to enable the movement of clusters to different levels based on cardinality as taught by Huang.
As to claim 18, see the rejection to claim 9.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AARON M RICHER whose telephone number is (571)272-7790. The examiner can normally be reached 9AM-5PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, King Poon can be reached at (571)272-7440. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AARON M RICHER/Primary Examiner, Art Unit 2617