Nvidia Corporation

Other

Ge Yang

Hwong-Kwo Lin

Charles Chew-Yuen Young

Xi Zhang

Ilyas Elkin

Jiani Yu

Haiyan Gong

Ethan A Frazier

Hwong-Kwo (Hank) Lin

Jonah Matthew Alben

Beibei Ren

Lingfei Deng

Ting-Hsiang Chu

Hank Lin

Guoqing Ning

William James Dally

John Wood Poulton

Jun Yang

Lei Wang

Stephen Felix

Spencer Montgomery Gold

Hua Chen

Jing Guo

Eric H Voelkel

Andreas J Gotterba

Charles R Young

Karthik Natarajan

Jason Golbus

Zhenye Jiang

Ying Huang

Fei Song

An adder circuit that includes an operand input and a second operand input to an XNOR cell. The XNOR cell is configured to provide the operand input and the second operand input to both a NAND gate and a first OAI cell. A second OAI cell transforms the output of the XNOR cell into a carry out signal.

Full adder cell with improved power efficiency

An adder circuit provides a first operand input and a second operand input to an XNOR cell. The XNOR cell transforms these inputs to a propagate signal that is applied to an OAT cell to produce a carry out signal. A third OAT cell transforms a third operand input and the propagate signal into a sum output signal.

A flip-flop element is configured to gate the clock inversions within a master-slave flip-flop element. The flip-flop element reduces the number of circuit elements within the flip-flop element by collapsing elements with common functionality into a single circuit element. Further, by making the actions of judiciously selected circuit elements conditional upon the state of the input data, the flip-flop element circuit reduces the number of internal transitions. In this manner, by reducing the number of circuit elements as well as the number of transitions, the flip-flop element achieves substantial reduction in overall system power consumption, resulting in a more efficient system.

Low power flip-flop element with gated clock

A flip-flop element is configured to include FinFET technology transistors with a mix of threshold voltage levels. The data input path includes FinFET transistors configured with high voltage thresholds (HVT). The clock input path includes transistors configured with standard voltage thresholds (SVT). By including FinFET transistors with SVT thresholds in the clock signal path, the Miller capacitance of the clock signal path is reduced relative to HVT FinFET transistors, leading to lower rise time and correspondingly lower hold time. By including HVT threshold devices in the data input path, the flip-flop element attains high speed and low power operation. By including SVT threshold devices in the clock signal path, the flip-flop element achieves faster switching times in the clock signal path.

Mixed threshold flip-flop element to mitigate hold time penalty due to clock distortion

Systems and methods for latches are presented. In one embodiment a system includes scan in propagation component, data propagation component, and control component. The scan in propagation component is operable to select between a scan in value and a recirculation value. The data propagation component is operable to select between a data value and results forwarded from the scan in propagation component, wherein results of the data propagation component are forwarded as the recirculation value to the scan in propagation component. The control component is operable to control an indication of a selection by the scan in propagation component and the data propagation component.

Efficient scan latch systems and methods

Mitigating external influences on long signal lines. In accordance with an embodiment of the present invention, a column of a memory array includes first and second transistors configured to pull up the bit line of the column. The column includes a third transistor configured to selectively pull up the bit line of the column responsive to a level of the inverted bit line of the column and a fourth transistor configured to selectively pull up the inverted bit line of the column responsive to a level of the bit line of the column. The column further includes fifth and sixth transistors configured to selectively pull up the bit line and inverted bit line of the column responsive to the clamp signal and a seventh transistor configured to selectively couple the bit line of the column and the inverted bit line of the column responsive to the clamp signal.

Mitigating external influences on long signal lines

A static random access memory (SRAM) cell includes a storage unit configured to store a data bit in a storage node. The SRAM cell further includes an access unit coupled to the storage unit. The access unit is configured to transfer current to the storage node when a word line is asserted. The SRAM cell further includes a row header configured to provide current from a power supply when the word line is not asserted, and to not provide current from the power supply when the word line is asserted. The SRAM cell further includes a column header configured to provide current from a power supply when a write column line is not asserted, and to not provide current from the power supply when the write column line is asserted.

SRAM core cell design with write assist

Low clocking power flip-flop. In accordance with a first embodiment of the present invention, a flip-flop electronic circuit includes a master latch coupled to a slave latch in a flip-flop configuration. The flip-flop electronic circuit also includes a clock control circuit for comparing an input to the master latch with an output of the slave latch, and responsive to the comparing, blocking a clock signal to the master latch and the slave latch when the flip-flop electronic circuit is in a quiescent condition.

Low clocking power flip-flop

A subsystem configured to select the power supply to a static random access memory cell compares the level of a dedicated memory supply voltage to the primary system supply voltage. The subsystem then switches the primary system supply to the SRAM cell when the system voltage is higher than the memory supply voltage with some margin. When the system voltage is lower than the memory supply voltage, with margin, the subsystem switches the memory supply to the SRAM cell. When the system voltage is comparable to the memory supply, the subsystem switches the system voltage to the SRAM cell if performance is a prioritized consideration, but switches the memory supply to the SRAM cell if power reduction is a prioritized consideration. In this manner, the system achieves optimum performance without incurring steady state power losses and avoids timing issues in accessing memory.

Power savings via selection of SRAM power source

A flip-flop circuit may include a master latch and a slave latch. Each latch may have a transparent mode and a storage mode. The slave latch may be in storage mode when the master latch is in transparent mode; and vice-versa. A clock signal may control the mode of each latch through a pair of clock-gated pull-up transistors and a pair clock-gated of pull-down transistors, for a total of four clock-gated transistors. The clock-gated transistors may be shared by the master latch and the slave latch. Fewer clock-gated transistors may be required when they are shared, as opposed to not being shared. Clock-gated transistors may have parasitic capacitance and consume power when subjected to a varying clock signal, due to the charging and discharging of the parasitic capacitance. Having fewer clock-gated transistors thus may reduce the power consumed by the flip-flop circuit.

Low power master-slave flip-flop

A flip-flop and a method of receiving a digital signal from an asynchronous domain. In one embodiment, the flip-flop includes: (1) a first loop coupled to a flip-flop input and having first and second stable states and (2) a second loop coupled to the first loop and having the first and second stable states, properties of cross-coupled inverters in the first and second loops creating a metastable state skewed toward the first stable state in the first loop and skewed toward the second stable state in the second loop. Certain embodiments of the flip-flop have lower time constant and thus a higher Mean Time Between Failure (MTBF).

Low tau synchronizer flip-flop with dual loop feedback approach to improve mean time between failure

A scan flip-flop circuit comprises a scan input sub-circuit and a selection sub-circuit. The scan input sub-circuit is configured to receive a scan input signal and a scan enable signal and, when the scan enable signal is activated, generate complementary scan input signals representing the scan input signal that are delayed relative to a transition of a clock input signal between two different logic levels. The selection sub-circuit is coupled to the scan input sub-circuit and configured to receive the complementary scan input signals and, based on the scan enable signal, output an inverted version of either the scan input signal or a data signal as a first selected input signal.

Flip-flop circuit having a reduced hold time requirement for a scan input

Provided herein is a voltage level shifter, an apparatus including a voltage level shifter and a method of converting voltages between input and output power domains. In one embodiment, the voltage level shifter includes: (1) an input circuit configured to receive a data signal from an input power domain and a power down signal from a output power domain and (2) a transition circuit coupled to the input circuit and configured to receive the data signal and an inverted signal of the power down signal, wherein the input circuit and the transition circuit are both configured to connect to a supply voltage of the output power domain as a power source.

Low power, single-rail level shifters employing power down signal from output power domain and a method of converting a data signal between power domains

Growing community of inventors

Pleasanton, CA, United States of America

Ge Yang