Disclosed is a spike neural network circuit according to an embodiment of the present disclosure, which includes a self-correcting control circuit that generates an input signal and a first control code, a bias voltage generation circuit that generates a first bias voltage based on the first control code, a synaptic circuit including a first synaptic column that performs an operation of the input signal and a first weight signal and generates a first operation signal, a neuron circuit including a first neuron that generates a first output signal based on a comparison of the first operation signal and a threshold voltage, and a spike comparison circuit that generates a first comparison signal corresponding to a difference between the first output signal and a reference number, and the self-correcting control circuit further generates a second control code for correcting the first bias voltage.

An integrated circuit includes a multiplexer circuit configured to provide an output signal on a conductive line, a programmable gain amplifier having a non-inverting input connected to the conductive line to receive the output signal from the multiplexer, a slew rate adjust circuit connected at a first node on the conductive line between the multiplexer circuit and the programmable gain amplifier, a first switch including a first terminal connected to the first node and a second terminal connected to the input of the programmable gain amplifier, and a low pass filter connected between the first and second terminals of the first switch.

An apparatus includes a primary processor and a secondary processor configured to receive a first signal, a second signal and a plurality of input signals, and perform same operations as each other based on the first signal, the second signal and the plurality of input signals, a comparison circuit configured to receive output signals of the primary processor and the secondary processor, and detect a lockstep mismatch between the primary processor and the secondary processor based on the output signals, a fault capturing circuit configured to receive the first signal and the second signal, and capture a fault signal generated by the comparison circuit, and a first glitch absorption device configured to receive the first signal and the second signal, and absorb glitches fed into the first glitch absorption device.

This application relates to control of semiconductor devices, in particular MOS devices, so as to reduce RTS/flicker noise. A circuit (100) includes a first MOS device (103, 104) and a bias controller (107). The circuit is operable in at least a first circuit state (P.sub.RO) in which the first MOS device is active to contribute to a first signal (Sout) and a second circuit state (P.sub.RST) in which the first MOS device does not contribute to the first signal. The bias controller is operable to control voltages at one or more terminals of the first MOS device to apply a pre-bias (V.sub.PB1, V.sub.PB2) during an instance of the second circuit state. The pre-bias is applied to set an occupancy state of charge carriers traps within the first MOS device, to limit noise during subsequent operation in the first circuit state. In embodiments, the bias controller is configured so that at least one parameter of the pre-bias is selectively variable in use based on one or more operating conditions.

A new class of logic gates are presented that use non-linear polar material. The logic gates include multi-input majority gates. Input signals in the form of digital signals are driven to non-linear input capacitors on their respective first terminals. The second terminals of the non-linear input capacitors are coupled a summing node which provides a majority function of the inputs. The majority node is then coupled driver circuitry which can be any suitable logic gate such as a buffer, inverter, NAND gate, NOR gate, etc. In the multi-input majority or minority gates, the non-linear charge response from the non-linear input capacitors results in output voltages close to or at rail-to-rail voltage levels. Bringing the majority output close to rail-to-rail voltage eliminates the high leakage problem faced from majority gates formed using linear input capacitors.

A new class of logic gates are presented that use non-linear polar material. The logic gates include multi-input majority gates. Input signals in the form of digital signals are driven to non-linear input capacitors on their respective first terminals. The second terminals of the non-linear input capacitors are coupled a summing node which provides a majority function of the inputs. The majority node is then coupled driver circuitry which can be any suitable logic gate such as a buffer, inverter, NAND gate, NOR gate, etc. In the multi-input majority or minority gates, the non-linear charge response from the non-linear input capacitors results in output voltages close to or at rail-to-rail voltage levels. Bringing the majority output close to rail-to-rail voltage eliminates the high leakage problem faced from majority gates formed using linear input capacitors.

A new class of logic gates are presented that use non-linear polar material. The logic gates include multi-input majority gates. Input signals in the form of digital signals are driven to non-linear input capacitors on their respective first terminals. The second terminals of the non-linear input capacitors are coupled a summing node which provides a majority function of the inputs. The majority node is then coupled driver circuitry which can be any suitable logic gate such as a buffer, inverter, NAND gate, NOR gate, etc. In the multi-input majority or minority gates, the non-linear charge response from the non-linear input capacitors results in output voltages close to or at rail-to-rail voltage levels. Bringing the majority output close to rail-to-rail voltage eliminates the high leakage problem faced from majority gates formed using linear input capacitors.

This application relates to control of semiconductor devices, in particular MOS devices, so as to reduce RTS/flicker noise. A circuit (100) includes a first MOS device (103, 104) and a bias controller (107). The circuit is operable in at least a first circuit state (P.sub.RO) in which the first MOS device is active to contribute to a first signal (Sout) and a second circuit state (P.sub.RST) in which the first MOS device does not contribute to the first signal. The bias controller is operable to control voltages at one or more terminals of the first MOS device to apply a pre-bias (V.sub.RB1, V.sub.PB2) during an instance of the second circuit state. The pre-bias is applied to set an occupancy state of charge carriers traps within the first MOS device, to limit noise during subsequent operation in the first circuit state. In embodiments, the bias controller is configured so that at least one parameter of the pre-bias is selectively variable in use based on one or more operating conditions.

A method and system for reducing power supply noise comprising receiving a primary data stream at a data rate. The primary data stream comprises a stream of bits having logical values of either zero or one. Then, splitting the primary data stream to create a first group of lower rate data streams and a second group of lower rate data streams. Processing the second group of lower rate data streams to invert the logic values of the bits of the lower rate data streams to create processed lower rate data streams. The first group of lower rate data streams are combined with the processed lower rate data streams to create a complementary data stream. Then, processing the primary data stream and the complementary data stream concurrently with a data processing system, the concurrent processing reducing noise on the power supply.

During normal operation of a processor, voltage droop is likely to occur and there is, therefore, a need for techniques for rapidly addressing this droop so as to reduce the probability of circuit timing failures. This problem is addressed by provided an apparatus that is configured to detect the droop and react to mitigate the droop. The apparatus includes a frequency divider that is configured to receive an output of a clock signal generator (e.g. a phase locked loop) and produce an output signal in which a predefined fraction of the clock pulses in the output of the clock signal generator are removed from the output signal. By reducing the frequency of the clock signal in this way (as may be understood by examining equation 3) V.sub.DD is increased, hence mitigating the voltage droop. This technique provides a fast throttling mechanism that prevents excessive V.sub.DD droop across the processor.