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 .
RESPONSE TO ARGUMENTS
Applicant's arguments filed 8/18/2025 have been fully considered but they are not persuasive.
In response to applicant’s arguments with regard to the independent claims 1 and 11 rejected under 35 U.S.C. 103(a) that the combination of the references does not teach/suggest the claimed feature “… inter-cluster switch … configured to … while receiving the data transmission, providing a portion of the data transmission to the available output data path …” because KIM does not disclose inter-cluster switch and Long does not discloses switches are configured so that while receiving a data transmission, they can “provide a portion of the data transmission to the available output path”; applicant's arguments have fully been considered, but are not found to be persuasive.
The examiner respectfully disagrees, and to further clarify, by combining Long’s switch(es), interconnecting computing components including TPUs, that are configured to receive and forward data over communication fabric (Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; and [0067]-[0071]) with KIM’s data/request being transmitted from source TPU of one TPU group to destination TPU of another TPU group, wherein the request (e.g. data transmission) is sliced into plurality of requests by the source TPU and forwarded accordingly via corresponding inter-cluster interface interconnecting the one TPU group and the another TPU group, such that while the request/data transmission is received, a slice/portion of the request/data transmission is provided accordingly (Fig. 7-8; and [0134]-[0185]), the resulting combination of the references would further teach/suggest the above claimed features.
I. REJECTIONS BASED ON PRIOR ART
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over KIM et al. (US Pub.: 2022/0156002) in view of Long (US Pub.: 2022/0283974).
As per claim 1, KIM teaches/suggests a system for distributed data processing comprising: a plurality of tensor processing unit (TPU) clusters (e.g. associated with plurality of TPU groups in Fig. 7: [0135]), each TPU cluster having a plurality of interconnected tensor processing units (TPUs) (e.g. associated with each TPU group have plurality of TPU interconnected accordingly in Fig, 7: [0135]); inter-cluster interface, wherein the inter-cluster interface is configured to transmit data between two TPU clusters from the plurality of TPU clusters (e.g. associated with data/request being transmitted from one TPU group to another TPU group via corresponding interface: [0140]-[0142]); wherein a first interconnected TPU of a first TPU cluster is configured to direct a data transmission to a second TPU that is part of a second TPU cluster, and wherein an interface-cluster interface, from the interface-cluster interface (e.g. associated with S806 as WIO/RIO TPU of HOST TPU GROUP direct transmission to CHK TPU of CACHE TPU GROUP via corresponding bus interface in Fig. 8), and a bus interface is configured to: receive the data transmission; communicating TPU destination information for the data transmission; operating based on the TPU destination information; and while receiving the data transmission, provide a portion of the data transmission accordingly (e.g. associated with TPU data/request being transmitted from source TPU of one TPU group to destination TPU of another TPU group via corresponding bus interface: [0140]-[0148]) (Fig. 7-8; and [0134]-[0185]).
KIM does not teach the system for distributed data processing comprising:
a plurality of switches, wherein each switch is configured to transmit data;
wherein a first switch, from the plurality of switches, is configured to:
identify data;
select an available output data path, from a plurality of output data paths; and
provide to the available output data path.
Long teaches/suggests a system comprising: a plurality of switches, wherein each switch is configured to transmit data (e.g. associated with switching elements (211)-(212) transmitting data in Fig. 2: [0023]; [0025]-[0026]); wherein a first switch, from the plurality of switches (e.g. associated with one of the switching element (211)-(212) in Fig. 2), is configured to: identify data; select an available output data path, from a plurality of output data paths; and provide to the available output data path (e.g. associated with data being transferred/routed over the communication fabric via corresponding switching element(s): [0002]-[0003]; [0023]; [0049]) (Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; and [0067]-[0071]).
It would have been obvious for one of ordinary skill in this art, before the effective filing date of the claimed invention, to include Long’s switching fabric into KIM’s system for the benefit of dynamically composing groupings of computing on-the-fly (Long, [0018]) to obtain the invention as specified in claim 1.
As per claim 2, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein each of the plurality of output data paths is associated with an external TPU that is part of an external TPU cluster that is different than the first TPU cluster (e.g. associated with path being associated with another group of TPU: Fig. 7-8 of KIM) (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]).
As per claim 3, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein the first inter-cluster switch is further configured to place received data from the data transmission into an input buffer, and wherein the TPU destination information is identified from the received data prior to receiving all of the data transmission (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further include buffer of data as data is communicated across the switching fabric.
As per claim 4, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein the TPU destination information comprises a first set of bits identifying the second TPU cluster and a second set of bits identifying the second TPU (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 5, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein the first inter-cluster switch is further comprised to access a next-hop lookup that identifies a plurality of potential output paths by latency with respect to the TPU destination information (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features as TPU data is communicated across the switching fabric.
As per claim 6, KIM and Long teach/suggest all the claimed features of claim 5 above, where KIM and Long further teach/suggest the system comprising wherein the first inter-cluster switch is further comprised to select the available output data path based on identification of a potential output path from the next-hop lookup that is not currently busy (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 7, KIM and Long teach/suggest all the claimed features of claim 6 above, where KIM and Long further teach/suggest the system comprising wherein the first inter-cluster switch is further configured to access a data-path usage table to determine whether one or more of the plurality of potential output paths are busy, and wherein selecting the available output data path is based on the first inter-cluster switch determining that the available output data has the lowest latency of the potential output data paths that are not identified as busy within the data-path usage table (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features as data is communicated across the switching fabric.
As per claim 8, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein the first inter-cluster switch is further configured to have a non-blocking internal connectivity for the plurality of output data paths with respect to a plurality of input data paths (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 9, KIM and Long teach/suggest all the claimed features of claim 1 above, where KIM and Long further teach/suggest the system comprising wherein the output path corresponds to an intermediate TPU within an intermediate TPU cluster, and wherein the data transmission is provided by the intermediate TPU cluster to a second inter-cluster switch (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 10, KIM and Long teach/suggest all the claimed features of claim 9 above, where KIM and Long further teach/suggest the system comprising wherein the second inter-cluster switch is configured to: receive the data transmission; identify the TPU destination information for the data transmission; select a second output data path, from a plurality of output data paths within the second inter-cluster switch, based on the TPU destination information; and while receiving the data transmission, provide a portion of the data transmission to the second output data path (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 11, claim 11 is rejected in accordance to the same rational and reasoning as the above rejection of claim 1.
As per claim 12, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method comprising wherein the available output data path is one of a plurality of output data paths, and wherein each output data path is associated with an external TPU that is part of an external TPU cluster that is different than the first TPU cluster (e.g. associated with path being associated with another group of TPU: Fig. 7-8 of KIM) (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]).
As per claim 13, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method further comprising placing, by the inter-cluster switch, received data from the data transmission into an input buffer, and wherein the TPU destination information is identified from the received data prior to receiving all of the data transmission (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further include buffer of data as data is communicated across the switching fabric.
As per claim 14, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method comprising wherein the TPU destination information comprises a first set of bits identifying the second TPU cluster and a second set of bits identifying the second TPU within the second TPU cluster (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 15, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method comprising wherein identifying the available output data path further comprises accessing a next-hop lookup that identifies a plurality of potential output paths by latency with respect to the TPU destination information (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features as TPU data is communicated across the switching fabric.
As per claim 16, KIM and Long teach/suggest all the claimed features of claim 15 above, where KIM and Long further teach/suggest the method further comprising selecting the available output data path based on identification of a potential output path from the next-hop lookup that is not currently busy (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 17, KIM and Long teach/suggest all the claimed features of claim 16 above, where KIM and Long further teach/suggest the method further comprising accessing, by the inter-cluster switch, a data-path usage table to determine whether one or more of the plurality of potential output paths are busy, and wherein selecting the available output data path is based on the available output data having the lowest latency of the potential output data paths that are not identified as busy within the data-path usage table (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features as data is communicated across the switching fabric.
As per claim 18, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method further comprising providing, by the inter-cluster switch, the data transmission to the available data path over a plurality of non-blocking sub-switches (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 19, KIM and Long teach/suggest all the claimed features of claim 11 above, where KIM and Long further teach/suggest the method comprising wherein the output path corresponds to an intermediate TPU within an intermediate TPU cluster and the inter-cluster switch is a first inter-cluster switch, further comprising providing the data transmission, by the intermediate TPU cluster, to a second inter-cluster switch (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
As per claim 20, KIM and Long teach/suggest all the claimed features of claim 19 above, where KIM and Long further teach/suggest the method further comprising: receiving the data transmission at the second inter-cluster switch; identifying, by the second inter-cluster switch, the TPU destination information for the data transmission; selecting, by the second inter-cluster switch, a second output data path, from a plurality of output data paths within the second inter-cluster switch, based on the TPU destination information; and while receiving the data transmission, providing, by the second inter-cluster switch, a portion of the data transmission to the second output data path (KIM, Fig. 7-8; [0134]-[0185]; and Long, Fig. 1-2; [0002]-[0003]; [0016]-[0040]; [0049]; [0067]-[0071]), wherein it would have been obvious to one of ordinary skilled in the art to further implement the above claimed features.
II. PERTINENT RELATED PRIOR ART
AWAN et al. (US Pub.: 2024/0354271): discloses a switch where multiple communications can happen simultaneously between different transmit and receive interfaces.
III. CLOSING COMMENTS
CONCLUSION
STATUS OF CLAIMS IN THE APPLICATION
The following is a summary of the treatment and status of all claims in the application as recommended by M.P.E.P. 707.07(i):
CLAIMS REJECTED IN THE APPLICATION
THIS ACTION IS MADE FINAL. 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.
DIRECTION OF FUTURE CORRESPONDENCES
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHUN KUAN LEE whose telephone number is (571)272-0671. The examiner can normally be reached Monday-Friday.
IMPORTANT NOTE
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Idriss Alrobaye can be reached on (571) 270-1023. 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.
/CHUN KUAN LEE/Primary Examiner
Art Unit 2181 April 09, 2026