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 .
Claim Objections
Claim 20 is objected to because of the following informalities: “for a BVH build operations”. For further prosecution, it will be assumed that claim 20 reads “for a BVH build operation” as in claim 2. Appropriate correction is required.
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, 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, 5-6, 10, 14-15 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles (US 20260187924) in view of Isherwood (US 20100257322).
Regarding claim 1, Knowles teaches a method comprising:
Sorting a set of bounding volume hierarchy ("BVH") build operations into bins based on a sorting criterion (Paragraph 32, a clustering algorithm that builds on top-down bounding volume hierarchy (BVH) construction. This can include, for example, the recursive splitting of a space based on one or more splitting criteria);
While Knowles fails to disclose the following, Isherwood teaches:
For each bin, inserting work and one or more barriers into a work queue corresponding to the bin (Paragraph 27, The last is to use the comparison information to add an `order enforcement sideband` to each request (or insert separate `barrier requests`) so the memory arbiter 33 can enforce an order for issuing requests to the memory bus as intended by the incoherency detection module 35; Paragraph 40, requests queued for that thread in FIFO 580); Note: Knowles teaches sorting the work into bins.
Executing the work inserted into the work queues (Paragraph 48, A back-end barrier insert check stage 560 is provided at the exit of each request FIFO 580). Note: A request exiting the queue means that the work is being executed.
Isherwood and Knowles are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Knowles by using Isherwood and inserting work and barriers into queues and executing the work. Doing so would allow for completing the work efficiently with respect to dependencies.
System claim 10 and CRM claim 19 correspond to method claim 1. Therefore, claims 10 and 19 are rejected for the same reasons as above. Note Isherwood teaches the differences between claim 1 and 10 including a memory configured to store bounding volume hierarchy (“BVH”) data (Paragraph 27, build a bounding volume hierarchy (BVH) or other acceleration structure that the hardware can trace. This information is obtained or generated, then stored into local memory to allow tracing to be performed by a GPU) and generate the BVH data (Paragraph 27, BVH is generated).
Regarding claim 5, the combination of Knowles and Isherwood teaches the method of claim 1, wherein the set of BVH build operations is received from an application (Knowles, Paragraph 27, Existing raytracing application programming interfaces (APIs) are often based around an application providing all the geometry up front, or providing a mesh that can be used to build a bounding volume hierarchy (BVH) or other acceleration structure that the hardware can trace).
System claim 14 corresponds to method claim 5. Therefore, claim 14 is rejected for the same reasons as used above.
Regarding claim 6, the combination of Knowles and Isherwood teaches the method of claim 1, wherein the sorting criterion includes one or more of a size of the BVH build operations, an algorithm of the BVH build operations, or a type of the BVH build operations. (Knowles, Paragraph 23, Clusters can be set to be the same target size (or within a given range of sizes), where that size/range is determined in part by the number of triangles that can be stored concurrently in memory on a processing unit, such as a graphics processing unit (GPU)).
System claim 15 corresponds to method claim 6. Therefore, claim 15 is rejected for the same reasons as used above.
Claims 2, 4, 11, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles in view of Isherwood as applied to claims 1, 5-6, 10, 14-15 and 19 above and further in view of Newbern (US 20170177414).
Regarding claim 2, the combination of Knowles and Isherwood teaches the method of claim 1. While the combination fails to disclose the following, Newbern teaches:
Wherein the work includes, for a BVH build operation, a set of phases separated by the one or more barriers (Abstract, A partition, associated with a unique holding queue, is assigned to each work unit stored in a given holding queue, according to a partitioning rule). Note: Knowles teaches a BVH build operation and Isherwood teaches barriers.
Newbern and the combination of Knowles and Isherwood are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles and Isherwood by using Newbern dividing the work into phases. Doing so would allow for facilitating preservation of relative ordering among certain work units when necessary (Newbern, Paragraph 39).
System claim 11 and CRM claim 20 correspond to method claim 2. Therefore, claims 10 and 20 are rejected for the same reasons as used above.
Regarding claim 4, the combination of Knowles, Isherwood, and Newbern teaches the method of claim 2. While the combination as presented previously fails to disclose the following, Isherwood further teaches:
Wherein a barrier of a first work queue has no effect on work of a second queue (Abstract, there is a separate request queue for each thread for read and write requests sent from the cache memory to the memory arbiter…if the address of the subsequent read request matches an indication, inserts a barrier corresponding to the read request into the request queue of the thread to which the matching indication belongs, and wherein the memory arbiter prevents the read request from accessing the memory bus until the corresponding barrier has been received by the memory arbiter).
Isherwood and the combination of Knowles and Newbern are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles and Newbern by using Isherwood and preventing a barrier in a first queue from affecting work in a second queue. Doing so would allow for efficiently prioritizing work in a queue without interfering with work in other queues.
System claim 13 corresponds to method claim 4. Therefore, claim 13 is rejected for the same reasons as used above.
Claims 3 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles in view of Isherwood and further in view of Newbern as applied to claims 2, 4, 11, 13 and 20 above and further in view of Zaltsman (US 20150331638).
Regarding claim 3, the combination of Knowles, Isherwood, and Newbern teaches the method of claim 2. While the combination fails to disclose the following, Zaltsman teaches:
Wherein within each work queue, a barrier causes work after the barrier to wait to begin until work before the barrier is complete (Paragraph 9, including reading a barrier command that is duplicated by the host across the multiple queues, halting each queue upon identifying the barrier command in the queue, and releasing the multiple queues upon reaching the barrier command in all the queues).
Zaltsman and the combination of Knowles, Isherwood, and Newbern are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles, Isherwood, and Newbern by using Zaltsman and preventing work after a barrier from running until work before the barrier is complete. Doing so would allow for efficiently prioritizing work in a queue.
System claim 12 corresponds to method claim 3. Therefore, claim 12 is rejected for the same reasons as used above.
Claims 7 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles in view of Isherwood as applied to claims 1, 5-6, 10, 14-15 and 19 above and further in view of Drabinski (US 20250308128).
Regarding claim 7, the combination of Knowles and Isherwood teaches the method of claim 1. While the combination fails to disclose the following, Drabinski teaches:
Wherein the work inserted into each bin comprises a kernel invocation that describes a shader program to execute (Paragraph 93, set of execution resources that may be used to perform graphics, media, and compute operations in response to requests by graphics pipeline, media pipeline, or shader programs; Paragraph 124, the run of kernel or shader program that executes).
Drabinski and the combination of Knowles and Isherwood are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles and Isherwood by using Drabinski and using a kernel invocation that describes a shader program to execute. Doing so would allow for using a known way of executing shader programs as work in a queue.
System claim 16 corresponds to method claim 7. Therefore, claim 16 is rejected for the same reasons as used above.
Claims 8 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles in view of Isherwood and further in view of Drabinski as applied to claims 7 and 16 above and further in view of Newbern.
Regarding claim 8, the combination of Knowles, Isherwood, and Drabinski teaches the method of claim 7. While the combination fails to disclose the following, Newbern teaches:
Wherein the kernel invocation causes execution of a kernel including one or more workgroups and one or more wavefronts (Paragraph 50, For example, links between different types of ports can lead to nested subsets of components in different “execution sets” that provide a hierarchical form of parallelism where each execution is fed by an upstream collection of work units that can be partitioned among multiple instances of the components in that execution set). Note: Drabinski teaches the kernel invocation. Newbern teaches execution sets as wavefronts and partitions as workgroups.
Newbern and the combination of Knowles, Isherwood, and Drabinski are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles, Isherwood, and Drabinski by using Newbern and executing workgroups and wavefronts. Doing so would allow for efficiently prioritizing work in a queue.
System claim 17 corresponds to method claim 8. Therefore, claim 17 is rejected for the same reasons as used above.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Knowles in view of Isherwood as applied to claims 1, 5-6, 10, 14-15 and 19 above and further in view of Smith-Lacey (US 20240303905).
Regarding claim 9, the combination of Knowles and Isherwood teaches the method of claim 1. While the combination fails to disclose the following, Smith-Lacey teaches:
Wherein the BVH build operations of the set of BVH build operations are each either a rebuild operation or a refit operation (Paragraph 7, Known methods for adapting the acceleration structure in response to a change in geometric LOD in a ray tracing regime are ‘refit’ and ‘rebuild’).
Smith-Lacey and the combination of Knowles and Isherwood are both considered to be analogous to the claimed invention because they are in the same field of organizing work. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Knowles and Isherwood by using Smith-Lacey and using rebuilt or refit operations. Doing so would allow for using a known way of creating a BVH.
System claim 18 corresponds to method claim 9. Therefore, claim 18 is rejected for the same reasons as used above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SNIGDHA SINHA whose telephone number is (571)272-6618. The examiner can normally be reached Mon-Fri. 12pm-8pm.
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, Jason Chan can be reached at 571-272-3022. 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.
/SNIGDHA SINHA/Examiner, Art Unit 2619
/JASON CHAN/Supervisory Patent Examiner, Art Unit 2619
