Systems and methods for an asynchronous successive approximation register analog-to-digital converter (SAR ADC) with word completion algorithm may include a SAR ADC comprising a plurality of switched capacitors, a comparator, a metastability detector including a timer having a tunable time interval, and a successive approximation register. The SAR ADC may sample input signals at inputs of the switched capacitors; compare signals at outputs of the switched capacitors, each for a respective bit; sense whether a metastability condition exists for the comparator using the timer and setting a metastability flag upon each metastability detection for each bit; increase a value of the tunable time interval if more than one metastability flag is set during conversion of a sampled input signal; decrease a value of the tunable time interval if no metastability flags are set; and use the flags for a word completion in the cases when not all the bits have been evaluated.

Single-stage and multiple-stage current-mode Analog-to-Digital converters (iADC)s utilizing apparatuses, circuits, and methods are described in this disclosure. The disclosed iADCs can operate asynchronously and be free from the digital clock noise, which also lowers dynamic power consumption, and reduces circuitry overhead associated with free running clocks. For their pseudo-flash operations, the disclosed iADCs do not require their input current signals to be replicated which saves area, lowers power consumption, and improves accuracy. Moreover, the disclosed methods of multi-staging of iADCs increase their resolutions while keeping current consumption and die size (cost) low. The iADC's asynchronous topology facilitates decoupling analog-computations from digital-computations, which helps reduce glitch, and facilitates gradual degradation (instead of an abrupt drop) of iADC's accuracy with increased input current signal frequency. The iADCs can be arranged with minimal digital circuitry (i.e., be digital-light), thereby saving on die size and dynamic power consumption.

Analog multipliers circuits can provide signal processing asynchronously and clock free and with low power consumptions, which can be advantageous, including in emerging mobile, portable, and at edge or near sensor artificial intelligence (AI) and machine learning (ML) applications. As such, analog multipliers can process signals memory-free in AI and ML applications, which avoids the power consumption and latency delays attributed to memory read-write cycles in conventional AI and ML digital processors. Based on standard digital Complementary-Metal-Oxide-Semiconductor (CMOS) manufacturing process, the present invention discloses embodiments of multi-quadrant current-mode analog multiplier (iMULT) circuits that can be utilized in current-mode multiply-accumulate (iMAC) circuits and artificial neural network (ANN) end-applications that require high-volumes, low costs, medium precision, low power consumptions, and clock free asynchronous signal processing.

Multipliers and Multiply-Accumulate (MAC) circuits are fundamental building blocks in signal processing, including in emerging applications such as machine learning (ML) and artificial intelligence (AI) that predominantly utilize digital-mode multipliers and MACs. Generally, digital multipliers and MACs can operate at high speed with high resolution, and synchronously. As the resolution and speed of digital multipliers and MACs increase, generally the dynamic power consumption and chip size of digital implementations increases substantially that makes them impractical for some ML and AI segments, including in portable, mobile, near edge, or near sensor applications. The multipliers and MACs utilizing the disclosed current mode data-converters are manufacturable in main-stream digital CMOS process, and they can have medium to high resolutions, capable of low power consumptions, having low sensitivity to power supply and temperature variations, as well as operating asynchronously, which makes them suitable for high-volume, low cost, and low power ML and AI applications.

A family of current mode analog to digital converters, or TiADC, utilizing methods, circuits, and apparatuses, are disclosed with the following benefits: (1) There are normal and random non-systematic mismatch between devices in silicon manufacturing, that introduce non-linearity in current mode analog to digital converter's, or iADC, reference network. The iADC's linearity is improved by utilizing a thermometer current mode signal conditioning method, SCM. Successive applications of the SCM effectuates a segmented current reference network to function like a thermometer network, which operates based on the function of summation. Having a TiADC with a thermometer reference network, where current segments are summed or accumulated incrementally, would inherently reduce the impact of statistical distribution of component's random mismatch on the iADC's non-linearity. Accordingly, linearity of TiADC can be improved by the square root of the sum of the square of mismatch errors of the number of segmented current references in the thermometer network. (2) speed is improved by operating the TiADC in current mode, which is inherently faster. (3) voltage swings in current mode are small, which enables he iADC to operate at lower power supply voltages. (4) The TiADC can operate in subthreshold and at very low currents, which lower powers consumption. (5) the TiADC is asynchronous. Being clock free, TiADC has lower dynamic power consumption with reduces digital system noise. (6) the signal conditioning method or SCM utilized in TiADC provides concurrent functions of analog differencing and digital comparison. This trait enhances the dynamic response of iADC, wherein the digital output throughput accuracy degrades gradually and not abruptly as a function of increasing frequency of iADC's input signal. (7) No passive devices, such as capacitors or resistors, are required for the TiADC. (8) TiADC can be fabricated on low cost mainstream standard digital CMOS processes.

Single-stage and multiple-stage current-mode Analog-to-Digital converters (iADC)s utilizing apparatuses, circuits, and methods are described in this disclosure. The disclosed iADCs can operate asynchronously and be free from the digital clock noise, which also lowers dynamic power consumption, and reduces circuitry overhead associated with free running clocks. For their pseudo-flash operations, the disclosed iADCs do not require their input current signals to be replicated which saves area, lowers power consumption, and improves accuracy. Moreover, the disclosed methods of multi-staging of iADCs increase their resolutions while keeping current consumption and die size (cost) low. The iADC's asynchronous topology facilitates decoupling analog-computations from digital-computations, which helps reduce glitch, and facilitates gradual degradation (instead of an abrupt drop) of iADC's accuracy with increased input current signal frequency. The iADCs can be arranged with minimal digital circuitry (i.e., be digital-light), thereby saving on die size and dynamic power consumption.

Apparatus and associated methods relate to a clock generation circuit which generates asynchronous clock signals for a successive approximation ADC architecture based on time-interleaved comparators. In an illustrative example, a circuit may include (a) a first comparator configured to receive an input signal and generate a first ready signal to indicate a comparison decision being complete, (b) a second comparator configured to receive the input signal and generate a second ready signal to indicate a comparison decision being complete, and (c) a clock generation circuit coupled to receive the first and the second ready signals and generate a first clock for the first comparator and a second clock for the second comparator. The first and the second clock signals may be in anti-phase. Thus, each comparator may have enough time to reach a valid comparison in each successive approximation cycle, and kickback noises at comparator' inputs may be advantageously reduced.

Systems and methods for an asynchronous successive approximation register analog-to-digital converter (SAR ADC) with word completion algorithm may include a SAR ADC comprising a plurality of switched capacitors, a comparator, a metastability detector including a timer having a tunable time interval, and a successive approximation register. The SAR ADC may sample input signals at inputs of the switched capacitors; compare signals at outputs of the switched capacitors, each for a respective bit; sense whether a metastability condition exists for the comparator using the timer and setting a metastability flag upon each metastability detection for each bit; increase a value of the tunable time interval if more than one metastability flag is set during conversion of a sampled input signal; decrease a value of the tunable time interval if no metastability flags are set; and use the flags for a word completion in the cases when not all the bits have been evaluated.

There is disclosed in one example a communication apparatus, including: an analog data source; a digital communication interface; and an analog-to-digital converter (ADC) circuit assembly, including: an analog sample input; an input clock to provide frequency f.sub.in; a time-interleaved front end to interleave n samples of the analog sample input; and an ADC array including n successive-approximation register (SAR) ADCs, the SAR ADCs including self-clocked comparators and configured to operate at a frequency no less than $\frac{f_{\mathrm{in}}}{n}.$

Methods and systems for an asynchronous successive approximation register analog-to-digital converter with word completion may include a successive approximation register (SAR) analog-to-digital converter (ADC) including a switched capacitor digital-to-analog converter (DAC), a word completion block, a comparator, and a metastability detector. The SAR ADC may sample a received analog electrical signal using the DAC, and convert the electrical signal to an n-bit digital signal by evaluating bits from a most significant bit to a least significant bit using the comparator. If the metastability detector determines that a time to evaluate one of the bits is longer than a threshold time, the metastability detector generates a metastability flag for each such bit. The converting may be initiated using a conversion enable clock pulse generated in the first SAR ADC. The metastability flag may be generated when a conversion enable pulse overlaps with a sampling clock pulse.