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 .
Drawings
Examiner is requiring suitable descriptive legends for numeric reference characters in figure 1-106, fig 2A 200A, 206, 208, fig 2B 216, 218, fig 5 516, Fig 8A all numeric reference designators, fig 8B all numeric reference designators except 826, fig 8C all numeric reference designators, fig 9A all numeric reference designators, fig 10 all numeric reference designators, as being necessary for understanding of the drawing. See 37 CFR 1.84(o). No new matter should be entered.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 10-19 are objected to because of the following informalities.
Claim 10 line 13 recites “generating a third matrix”. For grammatical consistency with the rest of the claim, this should recite “generate a third matrix”. Claims 11-19 inherit the same deficiency as claim 10 based on dependence.
Claim 12 line 5 recites “encoding each entry of the second matrix”. For grammatical consistency with the rest of the claim, this should recite “encode each entry of the second matrix”.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
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 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 1-3, 4, and 6-9 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by E. Luan et al., Towards a high-density photonic tensor core enabled by intensity-modulated microrings and photonic wire binding, nature portfolio, Scientific Reports, Open, 13:1260, 23 January 2023 (hereinafter “Luan”).
Regarding claim 1, Luan teaches the following:
encoding a second matrix into a plurality of optical signals based on a plurality of free spectral ranges (FSRs) of an array of resonator structures, the resonator structures having resonances tuned based on a first matrix (p. 4 paragraph above fig 2, information encoding, fig 3, p. 5 second line, encoding an input value w, p. 9 dot product section middle of second paragraph input MRR for input encoding, abstract and second paragraph, proposed device for convolutional neural network and matrix multiplication, input for second matrix, figure 1A input to modulation band for second matrix; p. 2-3 Intensity-modulated microring modulators MRR for the encoding of the second matrix into a plurality of optical signals based on a plurality of FSR (see eqn 1, eqn 2, and fig 1a), tuned based on weight bank, weight bank for first matrix; see also fig 10 showing input matrix, weight matrix kernels in weight banks, fig 11) ;
inputting the plurality of optical signals into input waveguides optically coupled to the array of resonator structures (fig 1a fig 10a); and
generating a third matrix based on optical power output from the array of resonator structures (fig 10 8-channel output).
Regarding claim 2, in addition to the teachings addressed in the claim 1 analysis, Luan teaches the following:
tuning resonances of the array of resonator structures according to entries of the first matrix (p. 4-5 Intensity-modulated microring modulators section, tuning the filters resonant peak to the wavelength of interest, fig 2, fig 3, p. 5 first two full sentences).
Regarding claim 3, in addition to the teachings addressed in the claim 2 analysis, Luan teaches the following:
tuning resonances of the array of resonator structures according to entries of the first matrix further comprises:
adjusting a plurality of biases applied to a plurality of tuning mechanisms of array of resonator structures according to the first matrix, wherein the plurality of adjusted biases tunes a transmission intensity of optical signals output from the plurality of resonator structures onto a plurality of drop waveguides coupled to the resonator structures of the array of resonator structures (fig 1-3, p. 3-6 section Characterization and control).
Regarding claim 4, in addition to the teachings addressed in the claim 1 analysis, Luan teaches the following:
filtering output optical signals onto a plurality of output waveguides from a plurality of drop waveguides coupled to the array of resonator structures, wherein optical signals associated with each FSR of the plurality of FSRs are filtered onto individual output waveguides of the plurality of output waveguides (fig 1 weight bank, fig 2 showing optical signals associated with each FSR); and
detecting optical power output from each output waveguide of the plurality of output waveguides (figure 1 detectors at the output waveguides of the weight bank, p. 2 last paragraph before Intensity-modulated microring modulators describing the photodetectors, p. 3 paragraph before Characterization and control),
wherein each entry for the third matrix is generated from the detected optical power from each output waveguide of the plurality of output waveguides (p. 12, first full paragraph, each single convolved pixel is obtained by adding all electrical signals together through voltage adders, fig 10a, fig 11).
Regarding claim 6, in addition to the teachings addressed in the claim 1 analysis, Luan teaches the following:
wherein the plurality of resonator structures comprises a plurality of microring resonators (p. 2-3, fig 1, fig 2 Intensity-modulated microring modulators design section).
Regarding claim 7, in addition to the teachings addressed in the claim 1 analysis, Luan teaches the following:
wherein the first matrix comprises a plurality of columns and a plurality of rows, and the second matrix comprises a plurality of columns and a plurality of rows (fig 10a input matrix, kernel matrix).
Regarding claim 8, in addition to the teachings addressed in the claim 7 analysis, Luan teaches the following:
wherein encoding the second matrix into the plurality of optical signals based on the plurality of FSRs of the array of resonator structures further comprises:
encoding each column of the second matrix using a different FSR of the plurality of FSRs (fig 10a color coded columns of modulation banks showing different FSR for each column); and
encoding each entry of the second matrix using wavelength-division multiplexing (fig 10a WDM multiplexer).
Regarding claim 9, in addition to the teachings addressed in the claim 8 analysis, Luan teaches the following:
wherein channel spacing between each FSR of the plurality of FSRs is equal to or greater than the number of rows or columns of the first matrix (whichever is larger) times the channel spaces between each wavelength-division multiplexing channel (p. 4 scalability section first two paragraphs).
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.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of WO 2022256904 A1 Luan et al., (hereinafter “Huawei”).
Regarding claim 5, Luan teaches the claim 4 limitations. Luan discloses demultiplexing (p. 4 Scalability section first paragraph). Luan does not, however, explicitly disclose each drop waveguide is coupled to a demultiplexer configured to filter the output optical signals onto the plurality of output waveguides. However, in the same field of endeavor, Huawei, which includes inventors in common with authors of Luan, discloses an apparatus similar to that of Luan comprising a photonic device for matrix multiplication (abstract, fig 1a, 1b, 2). Huawei further discloses wherein each drop waveguide is coupled to a demultiplexer configured to filter the output optical signals into the plurality of output waveguides (fig 11 1120, [00113]). It would have been obvious to one of ordinary skill in the art before the effective filing date to add the demultiplexer of Huawei at the output waveguides of Luan. It would have been obvious to achieve the benefit of separating the output optical signal into multiple component signals each corresponding to a sub-band of the predetermined band wavelengths ([00113]).
Claims 10-14 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of US 20210246241 A1 Karanth et al., (hereinafter “Karanth”).
Regarding claim 10, Luan teaches the following:
a resonator cavity loaded crossbar array comprising a plurality of input waveguides, a plurality of drop waveguides, and a plurality of resonator structures coupled to the plurality of input waveguides and the plurality of drop waveguides (fig 1a weight bank for resonator cavity loaded crossbar array comprising a plurality of input waveguides, a plurality of drop waveguides and a plurality of drop waveguides, fig 10a, fig 11); and
one or more processors coupled to a memory (abstract photonic processing unit for one or more processors, coupled to memory as in figure 11), the one or more processors configured to:
encode a second matrix into a plurality of optical signals based on a plurality of free spectral ranges (FSRs) of the plurality of resonator structures (p. 4 paragraph above fig 2, information encoding, fig 3, p. 5 second line, encoding an input value w, p. 9 dot product section middle of second paragraph input MRR for input encoding, abstract and second paragraph, proposed device for convolutional neural network and matrix multiplication, input for second matrix, figure 1A input to modulation band for second matrix; p. 2-3 Intensity-modulated microring modulators MRR for the encoding of the second matrix into a plurality of optical signals based on a plurality of FSR (see eqn 1, eqn 2, and fig 1a), tuned based on weight bank, weight bank for first matrix; see also fig 10 showing input matrix, weight matrix kernels in weight banks, fig 11);
tune resonances of the plurality of resonator structures according to entries of a first matrix (p. 4-5 Intensity-modulated microring modulators section, tuning the filters resonant peak to the wavelength of interest, fig 2, fig 3, p. 5 first two full sentences);
input the plurality of optical signals into the input waveguides optically coupled to the plurality of resonator structures (fig 1a fig 10a); and
generating a third matrix based on optical power output from the plurality of resonator structures onto the plurality of drop waveguides (fig 10 8-channel output).
Luan discloses one or more processors coupled to memory, but does not explicitly disclose the one or more processors storing instructions, the one or more processors configured to execute the instructions. However, in the same field of endeavor, Karanth discloses an apparatus similar to Luan comprising an optical multiply and accumulate unit including an optical microring resonator that selective couples an optical signal indicative of a value of an input neuron (abstract, fig 1, fig 5-7). Karanth further discloses wherein the optical multiply and accumulate routines are implemented as part of a sequence of instructions stored in memory ([0112]). It would have been obvious to one of ordinary skill in the art before the effective filing date for Luan to store instruction in memory as in Karanth to implement the functions of Luan. It is obvious to use a known technique to improve similar devices in the same way. See MPEP 2141.III.(C).
Regarding claim 11, in addition to the teachings addressed in the claim 10 analysis, Luan teaches the following:
wherein the first matrix comprises a plurality of columns and a plurality of rows, and the second matrix comprises a plurality of columns and a plurality of rows (fig 10a input matrix, kernel matrix).
Regarding claim 12, in addition to the teachings addressed in the claim 11 analysis, Luan teaches the following:
wherein each of the one or more processors are configured to:
encode each column of the second matrix using a different FSR of the plurality of FSRs (fig 10a color coded columns of modulation banks showing different FSR for each column); and
encoding each entry of the second matrix using wavelength-division multiplexing (fig 10a WDM multiplexer).
Regarding claim 13, in addition to the teachings addressed in the claim 10 analysis, Luan teaches the following:
wherein the plurality of resonator structures comprises a plurality of microring resonators (p. 2-3, fig 1, fig 2 Intensity-modulated microring modulators design section).
Regarding claim 14, in addition to the teachings addressed in the claim 10 analysis, Luan teaches the following:
a plurality of tuning mechanisms coupled to the plurality of resonator structures (fig 1-3, tunable coupler in figure 1b, p. 2-3 intensity-modulated microring modulators design),
wherein the one or more processors are further configured to adjust a voltage bias applied to each tuning mechanism of the plurality of tuning mechanism according to entries of the first matrix. (fig 1-3, p. 3-6 section Characterization and control, fig 1b v control).
Regarding claim 20, Luan teaches the following:
tuning resonances of an array of microring resonators (MRRs) of a crossbar array according to entries of a first matrix, the first matrix having a plurality of columns and a plurality of rows and the crossbar array having a plurality of columns of MRRs and a plurality of rows of MRRs (p. 4-5 Intensity-modulated microring modulators section, tuning the filters resonant peak to the wavelength of interest, fig 2, fig 3, p. 5 first two full sentences, fig 10 showing kernel matrix as first matrix, tuned as weights in crossbar matrix above with rows and columns, figure 1 showing the tuned resonances as MRR as described p. 2-3 section Intensity-modulated microring modulators design);
encoding a second matrix into a first plurality of optical signals, the second matrix comprising a plurality of columns and a plurality of rows, wherein each column of the plurality of columns of the second matrix is encoded based on free spectral ranges (FSR) of the array of MRRs (p. 4 paragraph above fig 2, information encoding, fig 3, p. 5 second line, encoding an input value w, p. 9 dot product section middle of second paragraph input MRR for input encoding, abstract and second paragraph, proposed device for convolutional neural network and matrix multiplication, input for second matrix, figure 1A input to modulation band for second matrix; p. 2-3 Intensity-modulated microring modulators MRR for the encoding of the second matrix into a plurality of optical signals based on a plurality of FSR (see eqn 1, eqn 2, and fig 1a), tuned based on weight bank, weight bank for first matrix; see also fig 10 showing input matrix, weight matrix kernels in weight banks, fig 11);
inputting the first plurality of optical signals into a plurality input waveguides, each input waveguide of the plurality of input waveguides optically coupled to a row of MRRs of the plurality of rows of MRRs, wherein each column of the plurality of columns of MRRs is optically coupled to a drop waveguide of a plurality of drop waveguides (fig 1a fig 10a);
filtering a second plurality of optical signals output from the plurality of drop waveguides into a plurality of output waveguides, wherein each of the second plurality of optical signals comprises the FSRs of the array of MRRs and each FSR is filtered onto an output waveguide of the plurality of output waveguides (fig 1a 1b describes the MRR as filters in waveguide);
detecting optical power output from each output waveguide of the plurality of output waveguides (fig 1a BPD also shown in figure 10); and
generating entries of a third matrix based on detected optical power output from each of the plurality of output waveguides (fig 10 8-channel output).
Luan discloses one or more processors coupled to memory, but does not explicitly disclose a non-transitory computer-readable storage medium having stored thereon executable computer program instructions that, wherein executed by one or more processors cause the one or more processors to perform the above operations. However, in the same field of endeavor, Karanth discloses an apparatus similar to Luan comprising an optical multiply and accumulate unit including an optical microring resonator that selective couples an optical signal indicative of a value of an input neuron (abstract, fig 1, fig 5-7). Karanth further discloses wherein the optical multiply and accumulate routines are implemented as part of a sequence of instructions stored in memory ([0112]). It would have been obvious to one of ordinary skill in the art before the effective filing date for Luan to store instruction in memory as in Karanth to implement the functions of Luan. It is obvious to use a known technique to improve similar devices in the same way. See MPEP 2141.III.(C).
Claim 15 rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of Karanth in view of US 20240036365 A1 Peng et al., (hereinafter “Peng”).
Regarding claim 15, Luan discloses voltage control as a tuning mechanism (see claim 14), but does not explicitly disclose wherein the plurality of tuning mechanism comprise a plurality of metal oxide semiconductor capacitors. However, in the same field of endeavor, Peng discloses an apparatus for modulating an optical waveguide by shifting the phase using a metal-oxide semiconductor capacitor (MOSCAP) used in wavelength division multiplexing applications ([0002], [0022-0023]). It would have been obvious to one of ordinary skill in the art before the effective filing date to use the MOSCAP of Peng as the plurality of tuning mechanisms of Luan in view of Karanth. Peng discloses the MOSCAP as a known implementation of an optical waveguide modulator ([0022]). It is obvious to use a known technique to improve similar devices in the same way. See MPEP 2141.III.(C).
Claims 16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of Karanth in view of Huawei.
Regarding claim 16, in addition to the teachings addressed in the claim 10 analysis, Luan teaches weighted signals from the plurality of drop waveguides, the weighted signals comprise the plurality of FSRs (p. 2 introduction last paragraph, fig 1). Luan in view of Karanth does not, however, explicitly disclose wherein a plurality of demultiplexers coupled to the plurality of drop waveguides and configured to receive the weighted signals; and a plurality of output waveguides coupled to outputs of the plurality of demultiplexers, wherein each demultiplexer is configured to filter each FSR of the plurality of FSRs onto an output waveguide of the plurality of waveguides. However in the same field of endeavor, Huawei, which includes inventors in common with authors of Luan, discloses an apparatus similar to that of Luan comprising a photonic device for matrix multiplication (abstract, fig 1a, 1b, 2). Huawei further discloses wherein a plurality of demultiplexers coupled to the plurality of drop waveguides and configured to receive the weighted signals (fig 11 1120, [00113]); and a plurality of output waveguides coupled to outputs of the plurality of demultiplexers, wherein each demultiplexer is configured to filter each FSR of the plurality of FSRs onto an output waveguide of the plurality of waveguides (fig 11 1120, [00113]). It would have been obvious to achieve the benefit of separating the output optical signal into multiple component signals each corresponding to a sub-band of the predetermined band wavelengths ([00113]).
Regarding claim 19, in addition to the teachings addressed in the claim 16 analysis, Luan teaches
a plurality of photodetectors coupled to the plurality of output waveguides, wherein the plurality of photodetectors are configured to detect optical power output from the plurality of output waveguides (fig 1a BPD also shown in figure 10),
wherein the entries for the third matrix are generated based on the detected optical power (fig 10 showing third matrix generated based on the detected optical power).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of Karanth in view of Huawei in view of Optoplex Corporation, Standard Optical Interleaver, 2016, (hereinafter “Optoplex”) found at optoplex.com/Optical_Interleaver.htm.
Regarding claim 17, Luan in view of Karanth in view of Huawei teach the claim 16 limitations. Huawei discloses an optical demultiplexer (fig 11 1120), but does not explicitly disclose the details of the structure of the optical demultiplexer. However, in the same field of endeavor, Optoplex discloses a demultiplexer structure as a de-interleaver (figure showing de-interleaver). It would have been obvious to one of ordinary skill in the art before the effective filing date to implement the demultiplexer of Huawei using the de-interleaver of Optoplex. It would have been obvious to achieve the benefit of wide and flat passband, low and customizable dispersion, low and uniform insertion loss, low PDL, high channel isolation and very low thermal drift (Optoplex second to last paragraph).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Luan in view of Karanth in view of Huawei in view of W. Shi et al., Ultra-compact, flat-top demultiplexer using anti-reflection contra-direction couplers for CWDM networks on silicon, Optical Society of America, 2013 (hereinafter “Shi”).
Regarding claim 18, Luan in view of Karanth in view of Huawei teach the claim 16 limitations. Huawei discloses an optical demultiplexer (fig 11 1120), but does not explicitly disclose the details of the structure of the optical demultiplexer. However, in the same field of endeavor, Shi discloses a demultiplexer structure as a contra-directional coupler (section 3. Fig 5). It would have been obvious to one of ordinary skill in the art before the effective filing date to implement the demultiplexer of Huawei using the contra-directional coupler of Shi. It would have been obvious to achieve the benefit of a more compact device with low channel crosstalk (Shi section 3).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
D Liang et al., An Energy-Efficient and Bandwidth-Scalable DWDM Heterogeneous Silicon Photonics Integration Platform, IEEE Journal of Selected Topics in Quantum Electronics, Vo. 28, No 6, Nov/Dec 2022 (hereinafter “Liang”) discloses aspects in dense wavelength division multiplexed transceivers (abstract, introduction). Liang further discloses using a MOSCAP drop filter, MOSCAP microring modulator, and a deinterleaver (fig 1).
J. Feldmann et al., Parallel convolutional processing using an integrated photonic tensor core, Article Nature, Vol 589, 2021 (hereinafter “Feldmann”) disclosing integrated photonics used in machine learning applications for matrix vector multiplication operations and using wavelength division multiplexing/demultiplexing, and a crossbar array (introduction, fig 1-2)
X. Xiao et al., Wavelength-Parallel Photonic Tensor Core Based on Multi-FSR Microring Resonator Crossbar Array, OFC 2023, Optica Publishing Group, 2023 (hereinafter “Xiao”) disclosure including authorship by some of the named inventors of aspects of the claimed invention (abstract, fig 1-3).
B. Tossoun et al., Large-Scale Integrated Photonic Device Platform for Energy-Efficient AI/ML Accelerators, IEEE Journal of Selected Topics in Quantum Electronics, Vo. 31, No 3, 2025 (hereinafter “Tossoun”) disclosure including authorship by some of the named inventors of aspects of the claimed invention (abstract, fig 33)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMILY E LAROCQUE whose telephone number is (469)295-9289. The examiner can normally be reached on 10:00am - 1200pm, 2:00pm - 8pm ET M-F.
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 Andrew Caldwell can be reached on 571-272-3701. 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.
/EMILY E LAROCQUE/Examiner, Art Unit 2182
Prosecution Insights