Abstract: An eight-cell memory cell for static random access memory, the memory cell comprising cross-coupled inverters to store the information bit, two access nMOSFETs connected to local bit lines to access the stored information bit, and two nMOSFETs each having a gate connected to ground and coupled to the local bit lines and the cross-coupled inverters so that sub-threshold leakage currents to and from the local bit lines for a memory cell not being read are balanced.

Abstract: A pipelined four-to-two compressor includes sequential elements with embedded logic. One sequential element is a flip flop with complementary outputs that includes a master stage with embedded logic, a sensing stage, and one or more slave stages. The flip flop operates in a pre-charge state and an evaluate state. During the pre-charge state when a clock signal is low, the flip flop pre-charges internal keeper nodes to a high value. When the clock signal transitions high, the flip flop enters an evaluation state and one of the internal keeper nodes evaluates to a low value. Keeper nodes can also be dynamic flip flop outputs that pre-charge each clock cycle. Another flip flop with embedded logic receives the dynamic output, applies further logic, and provides a static output.

Abstract: An apparatus is described having a plurality of storage cells coupled between a first bit line and a second bit line. The apparatus also has a first transistor that pre-charges the first bit line and provides a first supply of current for one or more leakage currents drawn from the first bit line by any of the plurality of storage cells. The apparatus also has a second transistor that pre-charges the second bit line and provides a second supply of current for one or more leakage currents drawn from the second bit line by any of the plurality of storage cells.

Abstract: A power management device and static random access memory (SRAM) architecture with dynamic supply voltages reduce active power leakage in SRAM cells. When a cell is inactive, a low level supply voltage is applied to the source line connected to the cell to maintain the data stored in the cell. However, before a cell is accessed (e.g., during a read or write operation), the source line is raised to a high level supply voltage.

Abstract: An apparatus is described having a plurality of storage cells coupled between a first bit line and a second bit line. The apparatus also has a first transistor that pre-charges the first bit line and provides a first supply of current for one or more leakage currents drawn from the first bit line by any of the plurality of storage cells. The apparatus also has a second transistor that pre-charges the second bit line and provides a second supply of current for one or more leakage currents drawn from the second bit line by any of the plurality of storage cells.

Abstract: A dual rail flip flop with complementary outputs includes a master stage with embedded logic, a sensing stage, and one or more slave stages. The flip flop operates in a pre-charge state and an evaluate state. During the pre-charge state when a clock signal is low, the flip flop pre-charges internal keeper nodes to a high value. When the clock signal transitions high, the flip flop enters an evaluation state and one of the internal keeper nodes evaluates to a low value. The sense stage senses which of the internal keeper nodes is evaluating to zero, and drives it to zero faster. The slave stages reflect the state of the internal keeper nodes during the evaluate state, and maintain their states during the pre-charge state.

Abstract: The word-lines and/or bit-lines in a memory are physically arranged to reduce capacitive coupling between signal lines and reference lines. In one embodiment the two bit lines connected to a single sense amplifier are physically separated from each other by bit lines connected to other sense amplifiers. In another embodiment the word-lines are separated from each other by placing them in different metallization layers. In a particular embodiment a single word-line has different portions disposed in different metallization layers.

Abstract: An open bit line dynamic random access memory (DRAM) architecture uses a multiple layer bit line configuration to reduce coupling between switching bit lines in the device. In one approach, each successive cell within a row of DRAM cells is coupled to a bit line segment that is on a different metallization layer than a previous cell in the row. Shielding members are also provided between adjacent bit lines on a common metallization layer to further reduce noise coupling. Functionality is also provided for reducing the effect of word line to bit line coupling in the DRAM device using dummy signal injection techniques. In this manner, common mode noise that could otherwise saturate one or more sense amplifiers within the DRAM device is reduced or eliminated before such saturation can take place. In one approach, dummy cells and reference cells are provided for use in performing the signal injection.

Abstract: The present invention is in the field of memory architecture and management. More particularly, the present invention provides a method, apparatus, system, and machine-readable medium to hide refresh cycles of a memory array such as dynamic random access memory.

Abstract: The present invention is in the field of memory device architecture. More particularly, the present invention provides a method, apparatus, system, and machine-readable medium to use a set of word-lines to access a row of memory cells.

Abstract: A multiply-accumulate circuit includes a compressor tree to generate a product with a binary exponent and a mantissa in carry-save format. The product is converted into a number having a three bit exponent and a fifty-seven bit mantissa in carry-save format for accumulation. An adder circuit accumulates the converted products in carry-save format. Because the products being summed are in carry-save format, post-normalization is avoided within the adder feedback loop. The adder operates on floating point number representations having exponents with a least significant bit weight of thirty-two, and exponent comparisons within the adder exponent path are limited in size. Variable shifters are avoided in the adder mantissa path. A single mantissa shift of thirty-two bits is provided by a conditional shifter.

Abstract: An open bit line dynamic random access memory (DRAM) architecture uses a multiple layer bit line configuration to reduce coupling between switching bit lines in the device. In one approach, each successive cell within a row of DRAM cells is coupled to a bit line segment that is on a different metallization layer than a previous cell in the row. Shielding members are also provided between adjacent bit lines on a common metallization layer to further reduce noise coupling. Functionality is also provided for reducing the effect of word line to bit line coupling in the DRAM device using dummy signal injection techniques. In this manner, common mode noise that could otherwise saturate one or more sense amplifiers within the DRAM device is reduced or eliminated before such saturation can take place. In one approach, dummy cells and reference cells are provided for use in performing the signal injection.

Abstract: A floating point adder circuit includes an exponent path and a mantissa path. The exponent path includes a comparator to compare two three-bit exponents. The two exponents are each incremented, and a resultant exponent is chosen from one of the two original exponents or one of the incremented exponents. The mantissa path includes an adder to add mantissas, and an adder bypass path to select one of the mantissas in lieu of performing an addition. The mantissa path also includes constant shifters that conditionally shift the mantissas right by thirty-two bit positions.

Abstract: A dual rail flip flop with complementary outputs includes a master stage with embedded logic, a sensing stage, and one or more slave stages. The flip flop operates in a pre-charge state and an evaluate state. During the pre-charge state when a clock signal is low, the flip flop pre-charges internal keeper nodes to a high value. When the clock signal transitions high, the flip flop enters an evaluation state and one of the internal keeper nodes evaluates to a low value. The sense stage senses which of the internal keeper nodes is evaluating to zero, and drives it to zero faster. The slave stages reflect the state of the internal keeper nodes during the evaluate state, and maintain their states during the pre-charge state.

Abstract: An apparatus is described having a plurality of storage cells coupled between a first bit line and a second bit line. The apparatus also has a first transistor that pre-charges the first bit line and provides a first supply of current for one or more leakage currents drawn from the first bit line by any of the plurality of storage cells. The apparatus also has a second transistor that pre-charges the second bit line and provides a second supply of current for one or more leakage currents drawn from the second bit line by any of the plurality of storage cells.

Abstract: A dual rail flip flop with complementary outputs includes a master stage with embedded logic, a sensing stage, and one or more slave stages. The flip flop operates in a pre-charge state and an evaluate state. During the pre-charge state when a clock signal is low, the flip flop pre-charges internal keeper nodes to a high value. When the clock signal transitions high, the flip flop enters an evaluation state and one of the internal keeper nodes evaluates to a low value. The sense stage senses which of the internal keeper nodes is evaluating to zero, and drives it to zero faster. The slave stages reflect the state of the internal keeper nodes during the evaluate state, and maintain their states during the pre-charge state.

Abstract: A multiplexer includes a first stage that has tri-state buffers each of which has split outputs and a final stage that has a tri-state buffer with an output. The multiplexer includes circuitry configured to enable or disable a signal at an input of a selected one of the first-stage buffers to propagate to the output of the final-stage buffer.

Abstract: A planar capacitor for use within a dynamic random access memory (DRAM) cell is operated within semiconductor depletion during normal storage operations to increase the charge retention time of the capacitor. Operation within semiconductor depletion allows a significant increase in charge retention time in a capacitor for which gate oxide leakage is the predominant leakage mechanism. The voltages that are applied to the storage cell during DRAM operation are controlled so that the storage capacitor within the cell remains in depletion during storage of both a logic zero and a logic one. Although the capacitance of the cell is decreased by operating in depletion, the charge retention time of the cell can be increased by multiple orders of magnitude. In one application, the inventive structures and techniques are implemented within a DRAM device that is embedded within logic circuitry.

Abstract: In one embodiment, a method comprises splitting a first data line into two or more first data line segments, wherein each of the first data line segments is connected to one transfer gate of a plurality of first data line transfer gates and to a first group of one or more sense amplifiers of a plurality of sense amplifiers; splitting a second data line into two or more second data line segments, wherein each of the second data line segments is connected to one transfer gate of a plurality of second data line transfer gates and to a second group of one or more sense amplifiers of the plurality of sense amplifiers; and providing voltage differences between each of the sense amplifiers of the first and second groups, wherein at least one of the voltage differences is an incorrect voltage difference that is corrected by the other voltage differences.

Abstract: A pipelined four-to-two compressor includes sequential elements with embedded logic. One sequential element is a flip flop with complementary outputs that includes a master stage with embedded logic, a sensing stage, and one or more slave stages. The flip flop operates in a pre-charge state and an evaluate state. During the pre-charge state when a clock signal is low, the flip flop pre-charges internal keeper nodes to a high value. When the clock signal transitions high, the flip flop enters an evaluation state and one of the internal keeper nodes evaluates to a low value. Keeper nodes can also be dynamic flip flop outputs that pre-charge each clock cycle. Another flip flop with embedded logic receives the dynamic output, applies further logic, and provides a static output.