Method and device for a chiplet system

Abstract

The invention relates to a method for a chiplet system comprising a substrate, at least one first component disposed on the substrate, and a communication interface for transmitting a first signal between the first component and, for example, at least one second component of the chiplet system, wherein the method comprises: providing a second signal by means of a spread spectrum technique, and transmitting the second signal via at least one signal line of the communication interface.

Description

[0001] Description

[0002] title

[0003] Method and device for a chiplet system

[0004] State of the art

[0005] The disclosure relates to a method for a chiplet system.

[0006] The disclosure further relates to a device for a chiplet system.

[0007] Disclosure of the invention

[0008] Some examples relate to a method, for example a computer-implemented method, for a chiplet system having a carrier, at least one first component arranged on the carrier and a communication interface for transmitting a first signal between the first component and, for example, at least one second component of the chiplet system, the method comprising: providing a second signal by means of a spread spectrum method, transmitting the second signal via at least one signal line of the communication interface.

[0009] In some examples, the first component and / or the second component comprises at least one of the following elements: a) chiplet, or b) interposer.

[0010] In some examples, it is provided that the transmission comprises at least one of the following elements: a) transmitting the second signal at least temporally overlapping, for example simultaneously, with the first signal, or b) transmitting the second signal in a frequency range that at least overlaps, for example, contains, a frequency range associated with the first signal. In some examples, it is provided that the spread spectrum method is one of the following methods or a combination thereof: a) Direct Sequence Spread Spectrum (DSSS), b) Chirp Spread Spectrum.

[0011] In some examples, it is provided that this comprises: providing a plurality of second signals by means of a respective spread spectrum method, transmitting the plurality of second signals via the at least one signal line of the communication interface.

[0012] In some examples, the method comprises: providing a plurality of second signals by means of a respective spread spectrum method in respective different frequency ranges, transmitting the plurality of second signals via the at least one signal line of the communication interface.

[0013] In some examples, the method comprises: providing the second signal for transmission via at least two different signal lines of the communication interface, transmitting the second signal via the at least two different signal lines.

[0014] In some examples, the method comprises: receiving a signal generated by means of a spread spectrum method and transmitted via the at least one signal line of the communication interface, performing a despreading, for example despreading, of the received signal.

[0015] Some examples relate to a method for a chiplet system having a carrier, at least one first component arranged on the carrier and a communication interface for transmitting a first signal between the first component and, for example, at least one second component of the chiplet system, the method comprising: receiving a signal generated by means of a spread spectrum method and transmitted via the at least one signal line of the communication interface, carrying out a despreading, for example despreading, of the received signal.

[0016] In some examples, the method comprises at least one method according to the disclosure, for example, according to any one of claims 1 to 8. Some examples relate to an apparatus for carrying out the method according to the disclosure.

[0017] Some examples relate to a system, for example a chiplet system, comprising a carrier, at least one first component arranged on the carrier and a communication interface for transmitting a first signal between the first component and, for example, at least one second component of the chiplet system, comprising at least one device according to the disclosure.

[0018] Some examples relate to a component for a system, for example a chiplet system, comprising at least one device according to the disclosure, wherein the component is, for example, a chiplet or an interposer.

[0019] Some examples relate to a computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method according to the disclosure.

[0020] Some examples relate to a computer program comprising instructions that, when executed by a computer, cause the computer to carry out the method according to the disclosure.

[0021] Some examples relate to a data carrier signal that characterizes and / or transmits the computer program according to the disclosure.

[0022] Some examples relate to a use of the method according to the disclosure and / or the device according to the disclosure and / or the system according to the disclosure and / or the component according to the disclosure and / or the computer-readable storage medium according to the disclosure and / or the computer program according to the disclosure and / or the data carrier signal according to the disclosure for at least one of the following elements: a) Transmitting at least one spread spectrum signal via the communication interface, for example at least temporarily overlapping, e.g.simultaneously, to a transmission of the first signal, for example using a second signal line, b) multiple use of the at least one signal line, c) adding, for example integrating, at least one additional signal into the first signal, d) distributing a signal energy associated with the second signal over a comparatively large frequency range, for example compared to a frequency range associated with the first signal, e) providing a robust data transmission, f) hiding the second signal, for example in noise, g) bypassing a communication stack, for example stacks, of the communication interface.

[0023] Further features, possible applications, and advantages of the invention will become apparent from the following description of examples of the invention, which are illustrated in the figures of the drawing. All described or illustrated features, individually or in any combination, constitute the subject matter of the invention, regardless of their summary in the claims or their references, as well as regardless of their wording or representation in the description or drawing.

[0024] The drawing shows:

[0025] Fig. 1 schematically shows a simplified block diagram,

[0026] Fig. 2 schematically shows a simplified flow diagram,

[0027] Fig. 3 schematically shows a simplified flow diagram,

[0028] Fig. 4 schematically shows a simplified flow diagram,

[0029] Fig. 5 schematically shows a simplified flow diagram,

[0030] Fig. 6 schematically shows a simplified flow diagram,

[0031] Fig. 7 schematically shows a simplified flow diagram,

[0032] Fig. 8 shows a simplified block diagram,

[0033] Fig. 9 schematically shows a simplified block diagram,

[0034] Fig. 10 schematically shows examples of uses. Some examples, see Fig. 1, 2, relate to a method, for example a computer-implemented method, for a chiplet system 10 which has a carrier, e.g. substrate, 12, at least one first component 14-1 arranged on the carrier 12 and a communication interface KS for transmitting a first signal SIG-1 between the first component 14-1 and, for example, at least one second component 14-2 of the chiplet system 10. By way of example, the second component 14-2 is also arranged on the carrier 12. The method, Fig. 2, comprises: providing 100 a second signal SIG-2 by means of a spread spectrum method, transmitting 102 the second signal SIG-2 via at least one signal line SL (Fig. 1) of the communication interface KS.

[0035] For example, the communication interface KS is of the UCIe type or compatible therewith and has, for example, a plurality of signal lines by means of which one or more communication channels, for example of the UCIe Main Band or UCIe Side Band type, can be implemented, wherein, for example, the above-mentioned at least one signal line SL belongs to the plurality of signal lines.

[0036] For example, the first signal SIG-1 is a signal that is transmitted according to the UCIe standard via the communication interface KS, for example via the UCIe main band channel or the UCIe side band channel, whereby the first signal SIG-1 is transmitted, for example, in a frequency range corresponding to the UCIe standard.

[0037] In some examples, Fig. 1 , it is provided that the first component 14-1 and / or the second component 14-2 comprises at least one of the following elements: a) chiplet, or b) interposer.

[0038] In some examples, Fig. 2, it is provided that the transmitting 102 comprises at least one of the following elements: a) transmitting 102a the second signal SIG-2 at least temporally overlapping, for example simultaneously, with the first signal SIG-1, or b) transmitting 102b the second signal SIG-2 in a frequency range that at least overlaps, for example contains, a frequency range associated with the first signal (e.g. the frequency range corresponding to the UCIe standard).

[0039] For example, in addition to the first signal SIG-1, a

[0040] The useful signal SIG-N (Fig. 1) to be transmitted via the communication interface KS with an associated useful signal spectrum is transformed into the second signal SIG-2 by means of the spread spectrum method in such a way that the second signal SIG-2 has a significantly, for example many times, greater bandwidth than the useful signal spectrum. In this way, signal energy components of the useful signal SIG-N are distributed over the comparatively large bandwidth of the spread spectrum second signal SIG-2, which in some examples enables the second signal SIG-2 to be transmitted via the communication interface KS, e.g. without interfering with the transmission of the first signal SIG-1, e.g. because individual spectral components of the spread spectrum second signal SIG-2 are lost in a noise floor associated with the first signal SIG-1, e.g. background noise, or are not detectable therein, e.g. without appropriate despreading.are detectable, or at least do not significantly impair relevant signal components of the first signal SIG-1.

[0041] In some examples, Fig. 2, the method, for example the providing 100, comprises: transforming 100a one or the useful signal SIG-N into the second signal SIG-2.

[0042] In some examples, the spread spectrum method is one of the following methods or a combination thereof: a) Direct Sequence Spread Spectrum (DSSS), b) Chirp Spread Spectrum. In some examples, other spread spectrum methods than those mentioned above may also be used.

[0043] In some examples, Fig. 3, it is provided that the method comprises: providing 110 a plurality of second signals SIG-2a, SIG-2b (for example based on one or more useful signals) by means of a respective spread spectrum method, transmitting 112 the plurality of second signals Sig-2a, Sig-2b via the at least one signal line SL (Fig. 1) of the communication interface KS.

[0044] In some examples, Fig. 4, it is provided that the method comprises: providing 120 a plurality of second signals SIG-2a, SIG-2b (for example based on one or more useful signals) by means of a respective spread spectrum method in respectively different frequency ranges FB-a, FB-b, transmitting 122 the plurality of second signals SIG-2a, SIG-2b via the at least one signal line SL of the communication interface KS. In some examples, Fig. 5, it is provided that the method comprises: providing 130 the second signal SIG-2 for transmission via at least two different signal lines SL-a, SL-b of the communication interface KS (for example two differential transmission lines), transmitting 132 the second signal SIG-2 via the at least two different signal lines SL-a, SL-b.

[0045] In some examples, the two different signal lines can also be different non-differential signal lines.

[0046] In some examples, Fig. 6, it is provided that the method comprises: receiving 140 a signal SIG-SS generated by means of a spread spectrum method (e.g. according to the disclosure, see e.g. Fig. 2, block 100) and transmitted via the at least one signal line SL of the communication interface KS, carrying out 142 a despreading, for example despreading, of the received signal, whereby, for example, a despread useful signal SIG-DS can be obtained.

[0047] Some examples, Fig. 7, relate to a method for a chiplet system (see e.g. Fig. 1) which has a carrier, at least one first component arranged on the carrier and a communication interface for transmitting a first signal between the first component and, for example, at least one second component of the chiplet system, the method comprising: receiving 200 a signal SIG-SS generated by means of a spread spectrum method and transmitted via the at least one signal line SL of the communication interface KS, carrying out 202 a despreading, for example despreading, of the received signal SIG-SS.

[0048] In some examples, Fig. 7, it is provided that the method comprises at least one method according to the disclosure, for example according to one of claims 1 to 8. In other words, in some examples, e.g., in addition to receiving 202 and despreading 202, the method may also comprise, e.g., providing 100 and transmitting 102, e.g., according to Fig. 1, etc.

[0049] Some examples, Fig. 8, relate to an apparatus 300 for carrying out the method according to the disclosure. In some examples, the apparatus 300 is configured, for example, to carry out at least some aspects, e.g., according to at least one of Figures 2, 3, 4, 5, 6.

[0050] In some examples, the device 300 is configured, for example, to carry out at least some aspects, for example, according to at least Figure 7.

[0051] In some examples, the device 300 is configured, for example, to carry out at least some aspects according to at least one of Figures 2, 3, 4, 5, 6 and to carry out at least some aspects of at least Figure 7.

[0052] In some examples, Fig. 8, it is provided that the device 300 comprises: a computing device ("computer") 302 having at least one computing core, a memory device 304 assigned to the computing device 302 for at least temporarily storing at least one of the following elements: a) data DAT (e.g. data associated with the useful signal SIG-N or the second signal SIG-2 or at least one of the signals SIG-SS, SIG-DS), b) computer program PRG, for example for carrying out the method according to the disclosure.

[0053] In further examples, the storage device 304 comprises a volatile memory (e.g., random access memory (RAM)) 304a, and / or a non-volatile (NVM) memory (e.g., flash EEPROM) 304b, or a combination thereof or with other memory types not explicitly mentioned.

[0054] In further examples, the device 300 is implemented as a hardware circuit, for example a pure hardware circuit (not shown).

[0055] Further examples, Fig. 8, relate to a computer-readable storage medium SM comprising instructions PRG' which, when executed by a computer 302, cause the computer 302 to carry out the method according to the disclosure.

[0056] Further examples relate to a computer program PRG, PRG', comprising instructions that, when the program PRG, PRG' is executed by a computer 302, cause the computer 302 to carry out the method according to the disclosure. Further examples relate to a data carrier signal DCS that characterizes and / or transmits the computer program PRG according to the disclosure. The data carrier signal DCS can be received, for example, via an optional data interface 306 of the device 300.

[0057] Some examples, Fig. 1 , relate to a system, for example a chiplet system, 10 comprising a carrier 12, at least a first component 14-1 arranged on the carrier 12 and a communication interface KS for transmitting a first signal SIG-1 between the first component 14-1 and, for example, at least one second component 14-2 of the chiplet system 10, comprising at least one device 300 according to the disclosure.

[0058] Some examples, Fig. 1 , relate to a component 14-1, 14-2 for a system, for example, a chiplet system 10, comprising at least one device 300 according to the disclosure. For example, the device 300 can be integrated into at least one of the components 14-1, 14-2, or arranged, for example, on the carrier 12.

[0059] Further aspects and examples are described below, which - in the case of further examples - can each be combined individually or in any combination with at least one of the aspects and / or examples described above.

[0060] In some examples, for example, a Direct Sequence Spread Spectrum (DSSS) method is used to provide the second signal SIG-2.

[0061] In some examples, the useful signal SIG-N (Fig. 1) to be subjected to band spreading may be characterized, for example, by a bit sequence.

[0062] In some examples, DSSS band spreading can be achieved by bitwise ORing (e.g., "xoring") the bit sequence with a predefined, e.g., secret (e.g., known only to a sender or an intended receiver) code word of a predefined length. For example, in this way, an original bit (e.g., one bit of the bit sequence of the useful signal SIG-N) is converted into a sequence of several bits with different values ​​(e.g., HIGH / LOW or "1" / "0" or similar). Since in some examples, more signal changes (e.g., per time period) are present in the signal transformed in the described manner, i.e., band-spread, a comparatively low-frequency (lower-bandwidth) signal (e.g., corresponding to the useful signal bit sequence) is converted into a comparatively "high-frequency" (higher-bandwidth) signal. In some examples, this enables the use of an entire signal spectrum (e.g., the communication interface), e.g.from high to low frequencies, e.g. also for a comparatively low-frequency or low-bit-rate useful signal SIG-N.

[0063] Since in some examples the signal energy associated with the wanted signal SIG-N remains constant, the signal energy of the second signal SIG-2 is distributed, for example, across the entire available / used frequency spectrum. In this way, in some examples, many, for example, all, spectral components of the second signal SIG-2 are each transmitted with an energy level that is, for example, close to or even below a noise level, for example, of the first signal SIG-1. With despreading appropriate for the codeword used, reconstruction of the wanted signal is nevertheless possible in some examples.

[0064] In some examples, the second signal SIG-2 may be combined with the first signal SIG-1, for example, added to the first signal SIG-1, for example, without affecting the first signal SIG-1.

[0065] As mentioned above, the first signal SIG-1 is, for example, a signal according to the UCIe standard, and in some examples, the second signal SIG-2 can be combined with the UCIe signal and, for example, use the same signal line(s) as the UCIe signal, without the UCIe signal being affected.

[0066] When reconstructing the transmitted second signal SIG-2, e.g., at a receiver end, the same (e.g., potentially secret) codeword can be used for despreading. For example, despreading can be performed by ORing the received second signal SIG-2 with the codeword again, resulting in, e.g., the original useful signal SIG-N.

[0067] Below is an example of a DSSS-based spread spectrum algorithm. This example assumes a binary payload signal that can assume the values ​​"1" or "0," for example, where a codeword for the spread spectrum is "11000111." After ORing, this results in the bit sequence "11000111" for a payload signal with the value "0," and the bit sequence "00111000" for a payload signal with the value "1." A further ORing with the code word, as can be carried out at a receiver for despreading, leads to the bit sequence "00000000 for the useful signal with the value "0" or its bit sequence "11000111", which can therefore be interpreted as "0" at the receiver, and to the bit sequence "11111111" for the useful signal with the value "1" or its bit sequence "00111000", which can therefore be interpreted as "1" at the receiver.

[0068] Another variant of band spreading according to some examples is chirp spread spectrum band spreading. Here, the signal bits associated with the useful signal SIG-N are encoded, for example, as (parts of) frequency sweeps that form physical symbols, thereby converting a low-frequency signal into a higher-bandwidth range (frequency spread). In some examples, by selecting at least one parameter of the chirp spread spectrum band spreading, it can be specified how the low-frequency signal components of the useful signal SIG-N are distributed to higher frequencies during band spreading.

[0069] In further examples, the principle of chirp spread spectrum can be implemented multiple times, for example, for different target frequency ranges, each of which lies within an available overall frequency range (e.g., "bandwidth") of the communication interface KS, thereby achieving redundancy, for example, in communication via a single physical line SL (Fig. 1) or differential signal line pairs, e.g., UCIe pairs SL-a, SL-b (Fig. 5). In some examples, individual, e.g., "virtual," channels can be represented by dividing the bandwidth available on a given signal line into multiple bands.

[0070] In further examples, one or more spread-spectrum signals, e.g., second signals SIG-2a, SIG-2b, ..., can be transmitted over multiple (e.g., differential or non-differential) signal lines of the communication interface KS. In some examples, it is conceivable to transmit two spread-spectrum signals, e.g., each over one signal line of a differential signal line.

[0071] The principle according to the disclosure makes it possible in some examples to transmit information, e.g. control information or supplementary information (e.g. relating to a primary data communication using the first signal SIG-1), e.g. as a secondary signal SIG-2, e.g. between different chiplets or chiplet tiles and / or other components such as an interposer, for example, without affecting an existing transmission of the first signal SIG-1, e.g. according to a standard such as UCIe.

[0072] The principle according to the disclosure makes it possible in some examples to bypass a, for example, deep, software stack and / or UCIe ISO / OSI stack, since the second signal SIG-2 can be added, for example, directly to a PHY layer signal of an existing UCIe transceiver, for example, using an analog and / or digital adder circuit.

[0073] The principle according to the disclosure enables efficient implementation of information exchange via the second signal SIG-2, e.g., for security measures, e.g., in automotive applications, e.g., without modifying existing, possibly conventional, UCIe components in a chiplet system. For example, conventional UCIe-compatible chiplets can be supplemented with the functionality of the disclosure, e.g., by providing at least one device 300 in a common target system.

[0074] The principle according to the disclosure enables, in some examples, transmission of the second signal SIG-2 in a manner that is transparent to conventional chiplets or interposers that use the communication interface KS. This means that, in some examples, conventional chiplets or interposers that use the same communication interface KS that is also used, for example, for transmitting the second signal SIG-2 cannot obtain any information about the presence of the second signal SIG-2 or its information because, due to the band spreading, this information is hidden, for example, in a noise floor and can only be reconstructed, for example, with knowledge of the correct despreading method and associated code.

[0075] The principle according to the disclosure enables, in some examples, the provision of additional services with respect to chiplet systems that, for example, use the communication interface KS for transmitting the first signal SIG-1, e.g., without dependence on existing communication stacks ("stacks") of conventional UCIe communication partners. The principle according to the disclosure enables, in some examples, the use, e.g., multiple use, of existing signal lines SL and components thereof (such as bumps for contacting chiplets with interposers) also for the second signal SIG-2.

[0076] The principle according to the disclosure enables, in some examples, a safeguard, e.g. by keeping an alternative communication channel available by using the second signal SIG-2, e.g. in addition to the first signal SIG-1, which e.g. increases security against a, e.g. systematic, failure of a conventional UCIe communication.

[0077] Fig. 9 schematically shows a simplified block diagram according to some examples. Element E1 symbolizes a carrier, e.g., in the form of a first interposer. Element E2 symbolizes a second interposer, e.g., a chiplet tile wrapper, comprising a UCIe-compatible or UCIe-compliant chiplet E3, whose UCIe-PHY device is designated by reference symbol E3a in Fig. 9. Element E10 symbolizes another UCIe-compatible or UCIe-compliant chiplet.

[0078] Element a1 symbolizes a connection of the chiplet E3 or its UCIe PHY device E3a to a UCIe interface a3, via which the two chiplets E2, E10 can communicate with each other, for example UCIe-compliant, see also the first signal SIG-1 according to Fig. 1.

[0079] Element E4 symbolizes a device associated with providing, for example transmitting, and / or receiving spread-spectrum signals via the UCIe interface a3, e.g., the second signal SIG-2 according to Fig. 1. Element E5 symbolizes spread spectrum according to the disclosure, and element E6 symbolizes a corresponding despreading. A second signal a2 generated by means of spread spectrum E5, see also reference symbol SIG-2 from Fig. 1, can in some examples, see Fig. 9, be combined by means of the combining device E7, e.g., with signals a1 of a physical layer, e.g., PHY layer, of the UCIe interface. In other words, in some examples, element E7 combines conventional UCIe signals transmitted by the chiplet E3 with the second signal SIG-2, a2, as provided by element E5. In some examples, the combining is done by adding the signals a1, a2, where the combined signal, containing e.g.the first signal SIG-1 (e.g. in a UCIe-compliant subband or frequency range) and the second signal SIG-2 (e.g. within a (e.g. entire) bandwidth of the UCIe interface a3) are transmitted via at least one signal line of the UCIe interface a3, e.g. to the further chiplet E10.

[0080] Spread-spectrum signals that chiplet E2 receives via UCIe interface a3, e.g., from the further chiplet E10, are symbolized in Fig. 9 by arrow a4 and are fed, e.g., to despreader E6. For example, element E4 can operate at least temporarily as a source or sink of useful signals SIG-N (see also Fig. 1), which, according to the principle of the disclosure, are transmitted at least temporarily using spread-spectrum signals SIG-2, SIG-SS via UCIe interface a3.

[0081] Element E11 of FIG. 9 symbolizes a UCIe PHY of chiplet E10, e.g., similar to element E3a of chiplet E3, and arrow a5 symbolizes corresponding UCIe-compliant signals (e.g., the first signal SIG-1), which can be combined via combiner E13 with a second or further spread-spectrum signal a6, which can be provided in chiplet E10 by element E12. In some examples, the combined signals a5, a6 can be transmitted from chiplet E10 to interposer E2 or its chiplets E3, E4 via UCIe interface a3.

[0082] Spread-spectrum signals received by the chiplet E10 (see, for example, signal a2 according to Fig. 9) can be fed, for example as signal a7, to a despreader E14 and are then present in the chiplet E10 as a reconstructed received useful signal a8.

[0083] In the examples described above according to Fig. 9, both components E2, E10 can both transmit (see arrows a2, a6) and receive (see arrows a4, a7) spread-spectrum signals. In further examples, it is also possible for a component, e.g., interposer E2 or chiplet E3, to provide and transmit spread-spectrum signals, e.g., only transmit (arrow a2), but for the interposer E2, for example, not to provide despreading (E6) or reception of spread-spectrum signals.

[0084] Some examples, Fig. 10, relate to a use 400 of the method according to the disclosure and / or the device 300 according to the disclosure and / or the system 10 according to the disclosure and / or the component 14-1, 14-2 according to the disclosure and / or the computer-readable storage medium SM according to the disclosure and / or the computer program PRG, PRG' according to the disclosure and / or the data carrier signal DCS according to the disclosure for at least one of the following elements: a) Transmitting 401 at least one spread spectrum signal via the communication interface KS, for example at least temporarily overlapping, e.g.simultaneously, to a transmission of the first signal SIG-1, for example using a second signal line SL, b) multiple use 402 of the at least one signal line SL, c) adding, for example integrating, 403 at least one additional signal into the first signal, d) distributing 404 a signal energy associated with the second signal SIG-2 over a comparatively large frequency range, for example compared to a frequency range associated with the first signal, e) providing 405 a robust data transmission, f) hiding 406 the second signal SIG-2, for example in noise, g) bypassing 407 a communication stack, for example stacks, (e.g. associated with one or more layers according to the ISO / OSI layer model) of the communication interface KS.

[0085] In some examples, the principle according to the disclosure can be used to provide chiplet systems or other distributed embedded systems, in which, for example, an overall computer system is composed of multiple chiplets. The chiplets can, for example, have different sizes, manufacturing technologies, and intended uses.

[0086] In some examples, the principle according to the disclosure can be used to implement time monitoring, e.g., deadline monitoring, across different chiplets, for example, using the second signal SIG-2. This allows, in some examples, measures to be implemented that monitor the actual execution times of individual chiplets, e.g., with respect to safety-critical time limits (deadlines), and, e.g., intervene in the event of deviations, e.g., at a computational task level. In some examples, the principle according to the disclosure can be used to transmit watchdog information and / or "heartbeats," e.g., using the second signal SIG-2, between chiplets and / or interposers and / or other components, e.g., of a chiplet system.

[0087] In some examples, the principle according to the disclosure may be used to transmit information for reconfiguration and / or rescheduling, e.g., regarding computation tasks executed by different chiplets, e.g., by means of the second signal SIG-2.

[0088] In some examples, the principle according to the disclosure can be used to exchange information regarding a role consensus, e.g. in the case of redundancy for availability (e.g. multiple redundant chiplets for the same computation task) between different chiplets, e.g. by means of the second signal SIG-2.

[0089] In some examples, the principle according to the disclosure can be used to exchange information for comparing, e.g., redundant, calculation results of different chiplets, e.g., by means of the second signal SIG-2.

[0090] In some examples, the principle according to the disclosure can be used to at least temporarily or at least partially achieve at least some of the following advantages: a) shared use of signal lines, e.g. the physical lanes according to the UCIe standard, for both signals SIG-1, SIG-2, b) no disruption of, e.g., standardized UCIe communication (signal SIG-1) by the transmission of the second signal SIG-2, c) bypassing a UCIe software stack, d) enabling secure, e.g., redundant, communication, e.g., also physical redundancy, e.g., when using multiple signal lines, e.g., differential UCIe signal pairs, e) provision of chiplet system-related services, e.g., using the second signal SIG-2, e.g., in addition to the standard UCIe communication by means of the first signal SIG-1, e.g., without disclosing the information associated with the second signal SIG-2.

Claims

Claims 1 . Method, for example a computer-implemented method, for a chiplet system (10) which has a carrier (12), at least one first component (14-1) arranged on the carrier (12) and a communication interface (KS) for transmitting a first signal (SIG-1) between the first component (14-1) and, for example, at least one second component (14-2) of the chiplet system (10), the method comprising: providing (100) a second signal (SIG-2) by means of a spread spectrum method, transmitting (102) the second signal (SIG-2) via at least one signal line (SL) of the communication interface (KS).

2. The method according to claim 1, wherein the first component (14-1) and / or the second component (14-2) comprises at least one of the following elements: a) chiplet, or b) interposer.

3. Method according to at least one of the preceding claims, wherein the transmitting (102) comprises at least one of the following elements: a) transmitting (102a) the second signal (SIG-1) at least temporally overlapping, for example simultaneously, with the first signal (SIG-1), or b) transmitting (102b) the second signal (SIG-1) in a frequency range that at least overlaps, for example contains, a frequency range associated with the first signal (SIG-1).

4. Method according to at least one of the preceding claims, wherein the spread spectrum method is one of the following methods or a combination thereof: a) Direct Sequence Spread Spectrum, DSSS, b) Chirp Spread Spectrum.

5. Method according to at least one of the preceding claims, comprising: providing (110) a plurality of second signals (SIG-2a, SIG-2b, ...) by means of a respective spread spectrum method, transmitting (112) the plurality of second signals (SIG-2a, SIG-2b, ...) via the at least one signal line (SL) of the communication interface (KS).

6. Method according to at least one of the preceding claims, comprising: providing (120) a plurality of second signals (SIG-2a, SIG-2b, ...) by means of a respective spread spectrum method in respective different frequency ranges (FB-a, FB-b), transmitting (122) the plurality of second signals (SIG-2a, SIG-2b, ...) via the at least one signal line (SL) of the communication interface (KS).

7. Method according to at least one of the preceding claims, comprising: providing (130) the second signal (SIG-2) for transmission via at least two different signal lines (SL-a, SL-b) of the communication interface (KS), transmitting (132) the second signal (SIG-2) via the at least two different signal lines (SL-a, SL-b).

8. Method according to at least one of the preceding claims, comprising: receiving (140) a signal (SIG-SS) generated by means of a spread spectrum method and transmitted via the at least one signal line (SL) of the communication interface (KS), carrying out (142) a despreading, for example despreading, of the received signal (SIG-SS).

9. Method, for example a computer-implemented method, for a chiplet system (10) which has a carrier (12), at least one first component (14-1) arranged on the carrier (12) and a communication interface (KS) for transmitting a first signal (SIG-1) between the first component (14-1) and, for example, at least one second component (14-2) of the chiplet system (10), the method comprising: receiving (200) a signal (SIG-SS) generated by means of a spread spectrum method and transmitted via the at least one signal line (SL) of the communication interface (KS), carrying out (202) a despreading, for example despreading, of the received signal (SIG-SS).

10. The method according to claim 9, comprising at least one method according to one of claims 1 to 8.

11. Device (300) for carrying out the method according to at least one of claims 1 to 10.

12. System, for example chiplet system, (10), comprising a carrier (12), at least one first component (14-1) arranged on the carrier (12) and a communication interface (KS) for transmitting a first signal (SIG-1) between the first component (14-1) and, for example, at least one second component (14-2) of the chiplet system (10), comprising at least one device (300) according to claim 11.

13. Component (14-1, 14-2) for a system, for example a chiplet system (10), comprising at least one device (300) according to claim 11, wherein, for example, the component (14-1, 14-2) is a chiplet or an interposer.

14. Computer-readable storage medium (SM) comprising instructions (PRG) which, when executed by a computer (302), cause the computer to carry out the method according to at least one of claims 1 to 10.

15. Computer program (PRG) comprising instructions which, when the computer program (PRG) is executed by a computer (302), cause the computer to carry out the method according to at least one of claims 1 to 10.

16. Data carrier signal (DCS) that characterizes and / or transmits the computer program (PRG) according to claim 15.

17. Use (400) of the method according to at least one of claims 1 to 10 and / or the device (300) according to claim 11 and / or the system (10) according to claim 12 and / or the component (14-1, 14-2) according to claim 13 and / or the computer-readable storage medium (SM) according to claim 14 and / or the computer program (PRG) according to claim 15 and / or the data carrier signal (DCS) according to claim 16 for at least one of the following elements: a) transmitting (401) at least one spread-band signal via the communication interface (KS), for example at least temporarily overlapping, e.g.simultaneously, to a transmission of the first signal (SIG-1), for example using the same signal line, b) multiple use (402) of the at least one signal line, c) adding, for example integrating, (403) at least one additional signal (SIG-2) into the first signal (SIG-1), d) distributing (404) a signal energy associated with the second signal (SIG-2) over a comparatively large frequency range, for example compared to a frequency range associated with the first signal (SIG-1), e) providing (405) a robust data transmission, f) hiding (406) the. second signal (SIG-2), for example in a noise, g) bypassing (407) a communication stack, for example stacks, of the communication interface (KS).

Images