DETAILED ACTION
Claims 1-8 have been examined.
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 .
Priority
Applicant’s claim for the benefit of a prior-filed application (PCT/JP2024/005102) under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged.
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy of JP 2023-034879 was electronically retrieved by the USPTO on September 16, 2025.
Specification
The title of the invention is not sufficiently descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
The abstract of the disclosure is objected to because of the following informalities:
The first sentence is grammatically incorrect and must be reworded.
In lines 4-5, there is a lack of antecedent basis for “the processor adjacent in the X direction or the Y direction”. It is the examiner’s understanding that there could be multiple adjacent processors in each of the X and Y directions (e.g. in FIG.1, PE101 has two adjacent PEs in the X direction (PE100 and PE102) and two adjacent PEs in the Y direction (PE001 and PE201). It is not clear which one adjacent processor in the X direction or Y direction applicant is referring to.
In the last two lines, there is a lack of antecedent basis for “the processor adjacent in the different dimension” for similar reasoning. That is, for PE101 in FIG.1, there are potentially two different PEs in the different dimension (PE501 and PE105) and it isn’t clear which one applicant is referring to.
In the last two lines, there is a lack of antecedent basis for “the different dimension”. From line 3, there are two or more different dimensions; thus, it is unclear which dimension applicant is referring to.
A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
The lengthy specification has not been checked to the extent necessary to determine the presence of all possible minor errors. Applicant’s cooperation is requested in correcting any errors of which applicant may become aware in the specification.
The disclosure is objected to because of the following informalities:
There are locations in the specification (e.g. at least paragraphs 4, 11, and 13-19) that include unclear language similarly found in the abstract. Please locate and correct.
In paragraph 8, line 2, is “PE 12” correct, or should it be --PEs 12--?
In paragraph 9, line 3, is “PE 12” correct, or should it be --PEs 12--?
In paragraph 22, line 4, the examiner questions whether applicant means
--processed-- instead of “calculated”. If the target data is an output/result of the calculation, then “calculated” is fine; however, if the target data is the input data that is processed to generate an output/result, then “calculated” is grammatically incorrect.
In paragraph 33, please confirm the first sentence is accurate, and, if so, please clarify what is meant.
In paragraph 36, please confirm the first sentence is accurate, and, if so, please clarify what is meant. How can each PE be considered 4+ PEs?
Please clarify paragraph 49. How can the wirings be shortest but along longer?
In paragraph 60, what is meant by the multiple instances of “ego PE”?
Appropriate correction is required.
Drawings
All FIGs are objected to for failing to comply with 37 CFR 1.84(a)(1) and 37 CFR 1.84(L), which requires that all drawings be made by a process which will give them satisfactory reproduction characteristics. Every line, number, and letter must be durable, clean, solid black (except for color drawings), sufficiently dense and dark, and uniformly thick and well-defined. The weight of all lines and letters must be heavy enough to permit adequate reproduction. This requirement applies to all lines however fine, to shading, and to lines representing cut surfaces in sectional views. The examiner asserts that the FIGs include fuzzy, blurry, and noisy features and non-uniform lines, among other quality issues.
All FIGs are objected to for failing to comply with 37 CFR 1.84(a)(1) and 37 CFR 1.84(l), which requires the drawings be in black, and that all drawings be made by a process which will give them satisfactory reproduction characteristics. Every line, number, and letter must be durable, clean, solid black (except for color drawings), sufficiently dense and dark, and uniformly thick and well-defined. The weight of all lines and letters must be heavy enough to permit adequate reproduction. This requirement applies to all lines however fine, to shading, and to lines representing cut surfaces in sectional views. The drawings are pixelated, at least in part because applicant did not use black (RGB = 000), despite the drawings appearing black to the naked eye. In such a case, the dithering used to convert applicant's grayscale image to black and white will add white pixels to try to estimate applicant's "gray" color, and the final drawings may not print properly or may print with reduced quality. Therefore, applicant must be sure to use only black and white. Applicant may be able to correct some of the pixelation via the following process (where there is blur/noise in the source PDF, this may not work):
1. Open the drawings PDF file with Adobe Acrobat (a similar Adobe product may work, but the examiner has only tested this in Adobe Acrobat);
2. Click “File” and then click “Print”;
3. Select “Adobe PDF” as the printer. If not available, “Microsoft Print to PDF” may also work, though this has not been tested. If neither option is available, this process may not be applicable, and applicant should try to find an alternate way to print in only black and white.
4. Uncheck “Print in grayscale (black and white)”;
5. Uncheck “Save ink/toner”;
6. Click “Advanced”;
7. Under “Color Management”, for the “Color Profile” field, select “Black & White” near the bottom of the list. The examiner also had “Treat grays as K-only grays” checked, and “Preserve Black” checked.
8. Click “OK” and then click “Print”. The resulting PDF should comprise only black and white drawings. Please review the final drawings for potential unintended consequences of this process.
FIGs.3 and 5 are objected to for failing to comply with 37 CFR 1.84(L), which requires that every line, number, and letter be in black (except for color drawings). Applicant uses white letters with black shading. Please use black text on a white background (and optionally surrounding hatching).
FIGs.7-8 fail to comply with 37 CFR 1.84(p)(3), which states that numbers, letters, and reference characters should not be placed upon hatched or shaded surfaces. Applicant may leave a blank space in the hatching or shading where the text occurs so that it appears distinct.
The drawings are objected to because of the following minor informalities:
In FIGs.3 and 5, when v = w = y = 0, why does the row have values 0 through 15? Does applicant mean to precede each of these values with --00-- or --0-- such that they are 3-digit values? Clarification is requested.
In FIG.7, when y = 0, why does the row have values 0 through 11? Does applicant mean to precede these with one of more zeros to make them 3-digit values?
In FIG.8, again, when w = 0 and y = 0, and when w = 1 and y = -4, should the values in the rows be preceded with one or more zeros?
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.” 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
The claims are objected to because of the following informalities:
In claim 1, line 1, insert a colon after “wherein”.
In claim 2, line 1, insert a colon after “wherein”.
In claim 2, line 5, delete “same”
In claim 3, line 1, insert a colon after “wherein”.
In claim 4, line 1, insert a colon after “comprising”.
In claim 4, the examiner questions whether “data to be calculated” should be
--data to be processed-- (see similar specification objection).
In claim 4, line 4, insert a colon after “wherein”.
In claim 5, line 1, insert a colon after “wherein”.
In claim 6, line 1, insert a colon after “wherein”.
In claim 6, the examiner questions whether both instances of “is to be calculated” should be --is to be processed-- (see similar specification objection).
In claim 7, line 1, insert a colon after “wherein”.
In claim 8, the examiner questions whether “calculating…input data” should be
--processing…input data-- (see similar specification objection).
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-8 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The claims recite the following limitations for which there is a lack of antecedent basis:
In claim 1, line 6, “the processor adjacent in the X direction or the Y direction”, for reasoning similar to that in an abstract objection above.
In claim 1, last line, “the processor adjacent in the different dimension”, for reasoning similar to that in an abstract objection above.
In claim 1, last line, “the different dimension” since there are two or more different dimensions in claim 1, lines 3-4.
In claim 2, “the different dimension” for similar reasoning.
In claim 3, “the different direction” because there are multiple different directions in claim 1.
In claim 4, last line, “the same coordinate”. Which coordinate is applicant referring to? There would appear to be at least X and Y coordinates.
In claim 6, both instances of “the processor adjacent…” for similar reasoning given above.
In claim 6, “the different dimension” for similar reasoning given above.
In claim 8, both instances of “the processor adjacent…” for similar reasoning given above.
In claim 8, “the different dimension” for similar reasoning given above.
Claim 1 is indefinite because it is not clear what applicant means by “each of which has the different dimension with one another”. This seems to state that each processor can communicate with all others of the group in this dimension, which from paragraph 48 is a diagonal dimension. However, in FIG.1, the group with PEs 101, 105, 501, and 505 do not include a diagonal connection between 101 and 501. Also, there are multiple diagonal dimensions in this group, so they don’t all seem to share the same dimension. Thus, the disclosure appears to conflict with the claim. This inconsistency renders the claim unclear because the examiner does not know if applicant intends for all processors in a group to be connected in a single dimension or if applicant is intending to claim the group in FIG.1. See MPEP 2173.03.
Claim 5 is indefinite because it is unclear what applicant means by total length and minimum. Paragraph 49 states that “the total length of the wiring becomes longer”, which suggests it’s not at a minimum length. Further, it is not clear if applicant means wiring for a single movement of data between two adjacent elements, at which point a direct connection could constitute minimal length, or if applicant means the wiring between any two elements, including non-adjacent elements, in which case, it appears the length is not minimal. For instance, in FIG.1, to move data from PE101 to PE505, wiring would only be minimal if the two PEs were directly coupled together; however, they are not shown as connected. Thus, this illustrated movement would involve an intermediate PE501 or PE105 and non-minimal wiring. As such, the intended scope of the claim is generally unclear as there are some contradicting teachings in the specification/drawings. The claim will be interpreted such that moving data between adjacent PEs requires only a minimum length of data.
All dependent claims are rejected due to their dependence on an indefinite claim.
Any interpretations of the claims due to clarity issues will be evident from the prior art rejections below.
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 and 3-8 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Cismas et al. (US 7,958,341).
Referring to claim 1, Cismas has taught a calculation device (FIG.1) comprising a plurality of processors (FIG.1, Px,y), wherein
the plurality of processors are represented by a coordinate system, which includes two dimensions indicating X direction and Y direction and two or more different dimensions indicating different directions (from FIG.1, note the notation Px,y, where x is a row/horizontal direction, and y is a column/vertical direction, e.g. P1,0 is in row 1, column 0. Values x and y also indicate two other dimensions relative to another element. For instance, given a processor Pm,n, processor Px,y is in a first diagonal direction with respect to Pm,n if m = x+1 and n = y+1 (e.g. P2,4 is on a first diagonal with respect to P1,3) and in a second diagonal direction with respect to Pm,n if m = x+1 and n = y-1 (e.g. P2,2 is on a second diagonal with respect to P1,3). When m = x-1 and y = ±1, these may be considered different diagonals or the same as those previously mentioned).
each of the plurality of processors is configured to perform data input or data output with the processor adjacent in the X direction or the Y direction (see FIGs.1 and 2B. Each processor is connected to its eight nearest neighbors in all directions, to allow for communication to the next adjacent element in the X direction (east or west) or in the Y direction (north or south)), and
each of the plurality of processors is configured to perform data input or data output with the processor adjacent in the different dimension (from FIGs.1 and 2B, the processors can input from or output to an adjacent processor in a diagonal direction (NW, NE, SW, SE). FIG.4B, for instance, shows data output from P4,8 to P3,9).
Referring to claim 3, Cismas has taught the calculation device according to claim 1, wherein each of the plurality of processors is configured to perform data input or data output with one of the plurality of processors arranged in a diagonal direction with respect to at least one of the X direction, the Y direction, or the different direction (see FIGs.1, 2B, 4A, and 6A, for instance, which show diagonal communication with respect to X or Y, or even with respect to an opposite diagonal (e.g. the diagonals are perpendicular to one another)).
Referring to claim 4, Cismas has taught the calculation device according to claim 3, further comprising a plurality of external memories (FIG.2A: each processor has various memories external to the local pipeline, including a register file, cache, local memory, direct memory, etc.) storing data to be calculated by the plurality of processors and transferring the data to the plurality of processors (e.g. a register file holds data to be transferred to an ALU of the pipeline (column 6, lines 43-44)), wherein the plurality of external memories store the data using a coordinate system, which includes two dimensions indicating X direction and Y direction and two or more different dimensions indicating different directions (each memory is associated with a respective Px,y and, thus, includes the same coordinate system), and each of the plurality of external memories is configured to perform data input or data output with one of the plurality of processors having the same coordinate (each memory Mx,y will perform data input/output with Px,y).
Referring to claim 5, Cismas has taught the calculation device according to claim 1, wherein the plurality of processors are arranged such that a total length of wiring for performing data input or data output among the plurality of processors has a minimum length (each processor is directly coupled to its eight nearest neighbors. Thus, any data movement between nearest neighbors requires a minimum amount of wiring).
Referring to claim 6, Cismas has taught the calculation device according to claim 1, wherein each of the plurality of processors receives, from an external memory, processing data, which is to be calculated in a current calculation, together with overlapping data, which is adjacent to the processing data and is to be calculated in a next calculation (again, data is received in the pipeline, which includes an ALU, from at least the register file, which is a memory external to the pipeline. A pipeline, as is known, comprises multiple stages to overlap processing of different instructions. Thus, the ALU would perform adjacent calculations (current and next calculations) on processing (current) data and subsequent (overlapping) data), each of the plurality of processors is configured to perform input or output of the processing data and the overlapping data with the processor adjacent in the X direction or the Y direction (again, each processor is configured to perform I/O of all data, including that exiting the pipeline after processing (FIG.2A, the pipeline outputs data to the switch 52, which connects to neighboring elements in the X and Y directions)). Note that the claim sets forth a mere configuration (which Cismas includes per the connections). The claim does not required that the processors actually perform the input/output), and each of the plurality of processors is configured to perform input or output of the processing data and the overlapping data with the processor adjacent in the different dimension (for similar reasoning, data from the pipeline may be sent to diagonal elements as the configuration includes connections to diagonal elements).
Referring to claim 7, Cismas has taught the calculation device according to claim 1, wherein (this struck-through language is not addressed at this time due to the alternative nature of the claim), or the plurality of processors are capable of performing a process at different timings (in FIG.4A, the processors may perform the data movement at a first time. In FIG.5A, the processors may perform a broadcast operation at a different time. Many other individual processes are capable of being performed over time).
Referring to claim 8, Cismas has taught a method for moving data among a plurality of processors (FIG.1 and 4A, at least some of processors Px,y form a plurality) included in a calculation device (FIG.1), the method comprising:
representing the plurality of processors using a coordinate system, which includes two dimensions indicating X direction and Y direction and two or more different dimensions indicating different directions (from FIG.1, note the notation Px,y, where x is a row/horizontal direction, and y is a column/vertical direction, e.g. P1,0 is in row 1, column 0. Values x and y also indicate two other dimensions relative to another element. For instance, given a processor Pm,n, processor Px,y is in a first diagonal direction with respect to Pm,n if m = x+1 and n = y+1 (e.g. P2,4 is on a first diagonal with respect to P1,3) and in a second diagonal direction with respect to Pm,n if m = x+1 and n = y-1 (e.g. P2,2 is on a second diagonal with respect to P1,3). When m = x-1 and y = ±1, these may be considered different diagonals or the same as those previously mentioned);
performing, by each of the plurality of processors, data input or data output with the processor adjacent in the X direction or the Y direction (FIG.5A shows a broadcast operation in which multiple processors send data in the X or Y direction); performing, by each of the plurality of processors, data input or data output with the processor adjacent in the different dimension (some of the processors that send data in the X or Y direction also send data in the diagonal direction. The processors that send in both X or Y and diagonal directions are the plurality of processors); and calculating, by each of the plurality of processors, input data and outputting a calculation result (each processor is shown in FIG.2A and includes a pipeline (with ALU) to input data (e.g. from register file) and output a result).
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 2 is rejected under 35 U.S.C. 103 as being unpatentable over Cismas in view of Kao et al. (US 2023/0066045).
Referring to claim 2, Cismas has taught the calculation device according to claim 1, wherein four or more of the plurality of processors, each of which has the different dimension with one another, are virtually grouped as a group (FIG.4A sets forth a virtual group of processors that takes part in moving data from source processor to destination processor. Since communication can occur on any diagonal (per the fourth quadrant code of FIG.4B), any diagonal is a communicative diagonal group (virtual group). For example, processors P3,0, P2,1, P1,2, and P0,3 form a virtual group along which data can be communicated among these processors. Since these processors are all on the same diagonal, they all have the same different dimension with one another), and each processor included in the group is configured to perform data input or data output with (ii) two of the plurality of processors, which are included in a different group and arranged adjacent in the X direction and Y direction (each processor in this diagonal, by way of connections in FIG.2B, can perform data input/output with at least two other processors in a different group (e.g. processor P3,0 can communicate with P2,0, P4,0, and P3,1; processor P2,1 can communicate with P1,1, P3,1, P2,0, and P2,2, etc.).
Cismas has not taught that each processor included in the group is configured to perform data input or data output with (i) at least two processors included in the same group. That is, while processors P2,1 and P1,2 perform such input/output, P3,0 and P0,3 are shown to communicate with only one other processor in that group. However, Kao has taught a mesh with wraparound/circular connections, including on the diagonals, so that the last element in a line can directly communicate with the first element in the line (e.g. see FIGs.2 and 5). One of ordinary skill in the art would have recognized that adding such extra connections could speed up data transfer even further. For instance, if P3,0 is sending data to P0,3, Cismas requires three hops (to P2,1 to P1,2, and to P0,3). If the wraparound link is added to directly connect P3,0 to P0,3 (to fully connect the diagonal such that each processor in the diagonal can communicate with two other processors in that diagonal), then the algorithm of FIG.4B could be modified to make use of this new connection and achieve the same transfer in one hop (from P3,0 directly to P0,3). As a result, in order to increase flexibility and speed up some transfers, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cismas to include the circular/wrap links for each line in the network. This results in each processor included in the group to be configured to perform data input or data output with (i) at least two processors included in the same group.
---------------------------------------------------------------------------------------------------------------------
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 and 8 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Wang et al. (US 2013/0073814).
Referring to claim 1, Wang has taught a calculation device (FIG.7) comprising a plurality of processors (see FIG.7, where each group is shown in FIG.8. Note, from paragraph 43 that the number of node groups and CPUs is freely extendable), wherein
the plurality of processors are represented by a coordinate system, which includes two dimensions indicating X direction and Y direction and two or more different dimensions indicating different directions (each given processor could be assigned coordinates that not only indicate their x,y position in a group/node (FIG.8), but also to determine where in 3D space the group/node is located (in FIG.7). From FIG.8 note that the system allows for X and Y communication along with at least two different diagonal communications (different dimensions from X and Y)).
each of the plurality of processors is configured to perform data input or data output with the processor adjacent in the X direction or the Y direction (see FIG.8. A given CPU1 can communicate with CPU2 (X direction) and CPU3 (Y direction). All other processors can similarly communicate), and
each of the plurality of processors is configured to perform data input or data output with the processor adjacent in the different dimension (see FIG.8 and note the diagonal communications).
Referring to claim 2, Wang has taught the calculation device according to claim 1, wherein four or more of the plurality of processors, each of which has the different dimension with one another, are virtually grouped as a group (see FIG.8. Each set of four CPUs is a virtual group. Each are diagonally connected to another in the group), and each processor included in the group is configured to perform data input or data output with (i) at least two processors included in the same group (see FIG.8) (ii) two of the plurality of processors, which are included in a different group and arranged adjacent in the X direction and Y direction (see the connections in FIG.8).
Claim 8 is mostly rejected for similar reasoning as claim 1. Further, Wang has taught calculating, by each of the plurality of processors, input data and outputting a calculation result (this is the purpose of processors, i.e., to operate on data to generate a result).
Examiner Note
Because the examiner has already rejected the full set of claims based on Cismas, the examiner has not fully addressed all claims with respect to Wang at this time. However, this is not an indication that they are allowable over Wang. Should applicant amend to overcome Cismas (in a manner other than simply writing a dependent claim into independent form), the examiner will reject the dependent claims with respect to Wang at that time, where possible. Any dependent claim rejections based on Wang will be necessitated by applicant's amendment to overcome Cismas. The examiner is not required to make any rejections based on Wang at this point in time but has done so only to expedite prosecution.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Pechanek (US 6,167,502) has taught, in FIG.17, mapping a torus into a 4D hypercube, and a 4-bit coordinate. There is intragroup and intergroup communication including in directions other than X and Y.
Westfall (GB 2405298) has taught X, Y, and diagonal links (FIG.13A, 15, etc.).
Chen (US 2023/0038051) has taught groups of GPUs connected in X, Y, and diagonal directions.
Han (US 2022/0308890) has taught groups of PPUs connected in X, Y, and diagonal directions.
Liao (US 2018/0181536) has taught configuring an interconnect network between CPUs of a group and between multiple groups.
Towles (US 2022/0173973) has taught a twisted torus configuration (e.g. FIG.2B).
Galles (US 5,669,008) has taught connecting n-dimensional hypercubes at a second level utilizing an m-dimensional metacube.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to David J. Huisman whose telephone number is 571-272-4168. The examiner can normally be reached on Monday-Friday, 9:00 am-5:30 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jyoti Mehta, can be reached at 571-270-3995. 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.
/David J. Huisman/Primary Examiner, Art Unit 2183