Abstract: A mechanism and method for maintaining a consistent state in a non-volatile random access memory system without constraining normal computer operation is provided, thereby enabling a computer system to recover from faults, power loss, or other computer system failure without a loss of data or processing continuity. In a typical computer system, checkpointing data is either very slow, very inefficient or would not survive a power failure. In embodiments of the present invention, a non-volatile random access memory system is used to capture checkpointed data, and can later be used to rollback the computer system to a previous checkpoint. This structure and protocol can efficiently and quickly enable a computer system to recover from faults, power loss, or other computer system failure.

Abstract: A mechanism and method for maintaining a consistent state in a non-volatile random access memory system without constraining normal computer operation is provided, thereby enabling a computer system to recover from faults, power loss, or other computer system failure without a loss of data or processing continuity. In a typical computer system, checkpointing data is either very slow, very inefficient or would not survive a power failure. In embodiments of the present invention, a non-volatile random access memory system is used to capture checkpointed data, and can later be used to rollback the computer system to a previous checkpoint. This structure and protocol can efficiently and quickly enable a computer system to recover from faults, power loss, or other computer system failure.

Abstract: A mechanism and method for maintaining a consistent state in a non-volatile random access memory system without constraining normal computer operation is provided, thereby enabling a computer system to recover from faults, power loss, or other computer system failure without a loss of data or processing continuity. In a typical computer system, checkpointing data is either very slow, very inefficient or would not survive a power failure. In embodiments of the present invention, a non-volatile random access memory system is used to capture checkpointed data, and can later be used to rollback the computer system to a previous checkpoint. This structure and protocol can efficiently and quickly enable a computer system to recover from faults, power loss, or other computer system failure.

Abstract: A buffer circuit is used to provide hysteresis, which can reduce the negative effects of noise in digital circuits. Reducing the number of transistors in the buffer circuit reduces the amount of space the circuit occupies and reduces power consumption. By connecting a voltage-coupling element between the body of a transistor in a first inverter and an output of a second inverter, the voltage-coupling element can control the hysteresis of the buffer circuit.

Abstract: A buffer circuit is used to provide hysteresis, which can reduce the negative effects of noise in digital circuits. Reducing the number of transistors in the buffer circuit reduces the amount of space the circuit occupies and reduces power consumption. By connecting a voltage-coupling element between the body of a transistor in a first inverter and an output of a second inverter, the voltage-coupling element can control the hysteresis of the buffer circuit.

Abstract: A mechanism and method for maintaining a consistent state in a non-volatile random access memory system without constraining normal computer operation is provided, thereby enabling a computer system to recover from faults, power loss, or other computer system failure without a loss of data or processing continuity. In a typical computer system, checkpointing data is either very slow, very inefficient or would not survive a power failure. In embodiments of the present invention, a non-volatile random access memory system is used to capture checkpointed data, and can later be used to rollback the computer system to a previous checkpoint. This structure and protocol can efficiently and quickly enable a computer system to recover from faults, power loss, or other computer system failure.

Abstract: A glitch removal circuit is disclosed that removes negative glitches from those signals that are provided to circuit elements that are turned-on by negative glitches (e.g., p-channel transistors), and/or removes positive glitches from those signals that are provided to circuit elements that are turned on by positive glitches (e.g., n-channel transistors). The positive glitches need not be removed from those signals that are provided to the circuit elements that are turned-off by positive glitches (e.g., p-channel transistors), and the negative glitches need not be removed from those signals that are provided to circuit elements that are turned-off by negative glitches (e.g., n-channel transistors). An advantage of the present invention is that both positive and negative glitches can be removed in parallel, rather then serially. This can significantly increase the performance of some circuits, and may reduce the amount of glitch removal circuitry required.

Abstract: A semiconductor device is disclosed that eliminates at least one of the channel/dielectric interfaces along the side walls of an SOI/SOS transistor channel, but does not require the use of a dedicated body tie contact. Because a dedicated body contact is not required, the packing density of the device may be significantly improved over conventional T-gate and H-gate configurations. The present invention may also reduce the overall gate area, which may increase both the speed and overall yield of the device.