Abstract: A digital low dropout (LDO) voltage regulator enabling on-chip fine-grain power management in multi-core microprocessor and system-on-a-chip platforms to increase system level energy efficiency. Its design synthesizability with automatic placement and routing enables per-core dynamic voltage and frequency scaling with quick design turnaround. To enable per-core voltage regulation, the digital LDO is designed in a 65 nm complementary metal-oxide-semiconductor process. It exhibits core-level high load current driving capability of up to 125 mA and a large voltage regulation range of 0.15 V to 1.15 V.

Abstract: A digital low dropout (LDO) voltage regulator enabling on-chip fine-grain power management in multi-core micro-processor and system-on-a-chip platforms to increase system level energy efficiency. Its design synthesizability with automatic placement and routing enables per-core dynamic voltage and frequency scaling with quick design turnaround. To enable per-core voltage regulation, the digital LDO is designed in a 65 nm complementary metal-oxide-semiconductor process. It exhibits core-level high load current driving capability of up to 125 mA and a large voltage regulation range of 0.15 V to 1.15 V.

Abstract: Power supply rejection (PSR) peaking in Low Dropout (LDO) voltage regulators can lead to reduced bandwidth and efficiency. The present invention is directed to a new design method by combining power transmission lines (PTL) with LDOs for enhancing its bandwidth and efficiency. This approach is applicable for LDOs regulating high speed I/O drivers. The PTL combined with decoupling capacitors on the package or board are used to mitigate the PSR peaking. This methodology is demonstrated using printed circuit board test vehicles with off-the-shelf components. When compared to conventional approaches, the PTL solution showed ˜80% lower power supply noise.

Abstract: Power supply rejection (PSR) peaking in Low Dropout (LDO) voltage regulators can lead to reduced bandwidth and efficiency. This paper presents a new design method by combining power transmission lines (PTL) with LDOs for enhancing its bandwidth and efficiency. This approach is applicable for LDOs regulating high speed I/O drivers. The PTL combined with decoupling capacitors on the package or board are used to mitigate the PSR peaking. This methodology is demonstrated using printed circuit board test vehicles with off-the-shelf components. When compared to conventional approaches, the PTL solution showed ˜80% lower power supply noise.

Abstract: Described is an apparatus which comprises: a first oscillator to generate a first clock signal a second oscillator to generate a second clock signal; a phase frequency detector to detect phase difference between the first and second clock signals, and to generate a phase difference; and an output stage, coupled to a load, to generate a power supply for the load according to the phase difference.

Abstract: Described is an apparatus which comprises: a clamp coupled between a first power supply and a second power supply, the clamp including a plurality of transistors, a circuit to operate with the second power supply; and a control unit to turn on and off the plurality of transistors to adjust the second power supply when the apparatus enters a low power mode. The control unit includes a first comparator to compare the second power supply with a first reference, a second comparator to compare the second power supply with a second reference, and a counter. The counter counts up when the second power supply is higher than the first reference and counts down when the second power supply is lower than the second reference.

Abstract: Methods of enabling voice processing with minimal power consumption includes recording time-domain audio signal at a first clock frequency and a first voltage, and performing Fast Fourier Transform (FFT) operations on the time-domain audio signal at a second clock frequency to generate frequency-domain audio signal. The frequency domain audio signal may be enhanced to obtain better signal to noise ratio, through one or multiple filtering and enhancing techniques. The enhanced audio signal may be used to generate the total signal energy and estimate the background noise energy. Decision logic may determine from the signal energy and the background noise, the presence or absence of the human voice. The first clock frequency may be different from the second clock frequency.

Abstract: Disclosed herein are semiconductor device arrays, such as, Field Programmable Gate Arrays (FPGAs) and Complex Programmable Logic Arrays (CPLAs) that use high-density Spin Transfer Torque (STT)-based memory elements. STT-based memory elements can either be stand-alone FPGAs/CPLAs, or can be embedded in microprocessors and/or digital signal processing (DSP) system-on-chip (SoC) to provide design flexibility for implementing low power, scalable, secure and reconfigurable hardware architecture. Because the configuration is stored on the FPGA/CPLA die itself, the need for loading the configuration from external storage every time is eliminated when the device is powered on. In addition to instant startup, eliminating configuration I/O traffic results in power savings and possible pin count reduction. Security is greatly improved by eliminating the need to store configuration data in an external memory.

Abstract: Described is an apparatus which comprises: a clamp coupled between a first power supply and a second power supply, the clamp including a plurality of transistors, a circuit to operate with the second power supply; and a control unit to turn on and off the plurality of transistors to adjust the second power supply when the apparatus enters a low power mode. The control unit includes a first comparator to compare the second power supply with a first reference, a second comparator to compare the second power supply with a second reference, and a counter. The counter counts up when the second power supply is higher than the first reference and counts down when the second power supply is lower than the second reference.

Abstract: Described is an apparatus which comprises: a clamp coupled between a first power supply and a second power supply; and a circuit to operate with the second power supply, wherein the clamp is operable to adjust the second power supply when the apparatus enters a low power mode.

Abstract: Techniques are disclosed for enhancing performance of a perpendicular magnetic tunnel junction (MTJ) by implementing an additional ferromagnetic layer therein. The additional ferromagnetic layer can be implemented, for example, in or otherwise proximate either the fixed ferromagnetic layer or the free ferromagnetic layer of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is implemented with a non-magnetic spacer, wherein the thickness of the additional ferromagnetic layer and/or spacer can be adjusted to sufficiently balance the energy barrier between parallel and anti-parallel states of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is configured such that its magnetization is opposite that of the fixed ferromagnetic layer.

Abstract: Methods and systems to read a logic value stored in a magnetic tunnel junction (MTJ)-based memory cell based on a pulsed read current, with time between pulses to permit the MTJ to relax towards the magnetization orientation between the pulses, which may reduce build-up of momentum within the MTJ, and which may reduce and/or eliminate inadvertent re-alignment of a magnetization orientation. A sequence of symmetric and/or non-symmetric pulses may be applied to a wordline (WL) to cause a pre-charged bit line (BL) capacitance to discharge a pulsed read current through the MTJ, resulting in a corresponding sequence of voltage changes on the BL. The BL voltage changes may be integrated over the sequence of read current pulses, and a stored logic value may be determined based on the integrated voltage changes. The pre-charged BL capacitance may also serve as the voltage integrator.

Abstract: Disclosed herein are semiconductor device arrays, such as, Field Programmable Gate Arrays (FPGAs) and Complex Programmable Logic Arrays (CPLAs) that use high-density Spin Transfer Torque (STT)-based memory elements. STT-based memory elements can either be stand-alone FPGAs/CPLAs, or can be embedded in microprocessors and/or digital signal processing (DSP) system-on-chip (SoC) to provide design flexibility for implementing low power, scalable, secure and reconfigurable hardware architecture. Because the configuration is stored on the FPGA/CPLA die itself, the need for loading the configuration from external storage every time is eliminated when the device is powered on. In addition to instant startup, eliminating configuration I/O traffic results in power savings and possible pin count reduction. Security is greatly improved by eliminating the need to store configuration data in an external memory.

Abstract: Techniques are disclosed for enhancing performance of a perpendicular magnetic tunnel junction (MTJ) by implementing an additional ferromagnetic layer therein. The additional ferromagnetic layer can be implemented, for example, in or otherwise proximate either the fixed ferromagnetic layer or the free ferromagnetic layer of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is implemented with a non-magnetic spacer, wherein the thickness of the additional ferromagnetic layer and/or spacer can be adjusted to sufficiently balance the energy barrier between parallel and anti-parallel states of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is configured such that its magnetization is opposite that of the fixed ferromagnetic layer.

Abstract: Disclosed herein are semiconductor device arrays, such as, Field Programmable Gate Arrays (FPGAs) and Complex Programmable Logic Arrays (CPLAs) that use high-density Spin Transfer Torque (STT)-based memory elements. STT-based memory elements can either be stand-alone FPGAs/CPLAs, or can be embedded in microprocessors and/or digital signal processing (DSP) system-on-chip (SoC) to provide design flexibility for implementing low power, scalable, secure and reconfigurable hardware architecture. Because the configuration is stored on the FPGA/CPLA die itself, the need for loading the configuration from external storage every time is eliminated when the device is powered on. In addition to instant startup, eliminating configuration I/O traffic results in power savings and possible pin count reduction. Security is greatly improved by eliminating the need to store configuration data in an external memory.

Abstract: Techniques are disclosed for enhancing performance of a perpendicular magnetic tunnel junction (MTJ) by implementing an additional ferromagnetic layer therein. The additional ferromagnetic layer can be implemented, for example, in or otherwise proximate either the fixed ferromagnetic layer or the free ferromagnetic layer of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is implemented with a non-magnetic spacer, wherein the thickness of the additional ferromagnetic layer and/or spacer can be adjusted to sufficiently balance the energy barrier between parallel and anti-parallel states of the perpendicular MTJ. In some embodiments, the additional ferromagnetic layer is configured such that its magnetization is opposite that of the fixed ferromagnetic layer.

Abstract: A thermal sensor is provided that includes a front-end component, an analog-to-digital converter and a digital backend. The front-end component including an array of current sources, a dynamic element matching (DEM) device, an analog chopper and two diodes to sense temperatures on the die. The front-end component to provide analog signals at two output nodes based on currents through the two diodes. The analog-to-digital converter to receive the analog signals from the front-end component and to provide an output signal. The digital backend to receive the output signal from the analog-to-digital converter and to provide a calculated temperature.

Abstract: Described is an apparatus which comprises: a first oscillator to generate a first clock signal a second oscillator to generate a second clock signal; a phase frequency detector to detect phase difference between the first and second clock signals, and to generate a phase difference; and an output stage, coupled to a load, to generate a power supply for the load according to the phase difference.

Abstract: Methods and systems to read a logic value stored in a magnetic tunnel junction (MTJ)-based memory cell based on a pulsed read current, with time between pulses to permit the MTJ to relax towards the magnetization orientation between the pulses, which may reduce build-up of momentum within the MTJ, and which may reduce and/or eliminate inadvertent re-alignment of a magnetization orientation. A sequence of symmetric and/or non-symmetric pulses may be applied to a wordline (WL) to cause a pre-charged bit line (BL) capacitance to discharge a pulsed read current through the MTJ, resulting in a corresponding sequence of voltage changes on the BL. The BL voltage changes may be integrated over the sequence of read current pulses, and a stored logic value may be determined based on the integrated voltage changes. The pre-charged BL capacitance may also serve as the voltage integrator.

Abstract: Described herein are apparatus, method, and system for reducing clock-to-output delay of a sequential logic unit in a processor. The apparatus comprises a sequential unit including: a data path, to receive an input signal, including logic gates to operate on a first power supply level, the data path to generate an output signal; and a clock path including logic gates to operate on a second power supply level, the logic gates of the clock path to sample the input signal using a sampling signal to generate the output signal, wherein the second power supply level is higher than the first power supply level. The apparatus improves (i.e. reduces) setup time of the sequential unit and allows the processor to operate at minimum operating voltage (Vmin) without degrading performance of the sequential unit.