Other

Mosaid Technologies Corporation

Duncan George Elliott

W Martin Snelgrove

Kristopher Breen

Raymond Jit-Hung Sung

Leendert Jan Van Den Berg

Tyler Lee Brandon

John Conrad Koob

Daniel Arie Leder

Tyler L Brandon

A level shifter circuit for integrated circuits has one or more inputs that operate in a first voltage domain, and a signal output that operates in a second voltage domain. In some embodiments, the level shifter circuit receives two complementary input signals. The level shifter uses cross-coupled PMOS transistors with drain-bulk breakdown voltage less than the gate-oxide breakdown voltage of high-voltage PMOS transistors to prevent gate-oxide breakdown caused by sub-threshold leakage of auxiliary high-voltage PMOS transistors in the off state. Permanent gate-oxide breakdown is prevented through non-permanent sub-nanoamp drain-bulk junction breakdown. The level shifter circuit has the advantages of small circuit size and low static power consumption.

Level shifter circuits for integrated circuits

A high-density dynamic memory device with compact sense amplifier circuit is described. The memory device achieves high density through the use of a compact sense amplifier circuit that employs a single transistor to sense stored dynamic data. Functionality of the device is enabled by an architecture and method of operation that support a compact sense amplifier circuit. Enabling techniques include sequential sensing of memory columns, a two-pass write operation, a two-step refresh operation, a reference scheme that uses reference data stored in regular memory cells, and the application of digital signal processing to determine sensed data and cancel crosstalk noise.

Memory sensing with secondary buffer

Method and apparatus for a dynamic semiconductor memory with compact sense amplifier circuit

A frequency synthesis phase-locked loop architecture using a regenerative sampling latch is described. The frequency divider typically employed in the feedback path of a frequency synthesis phase-locked loop is replaced by a regenerative sampling latch with a binary output. The regenerative sampling latch subsamples the frequency synthesizer output to produce a low-frequency aliased signal that can be processed further or directly used to lock the phase-locked loop. This architecture is referred to as an alias-locked loop. The relaxed constraints on the regenerative sampling latch make it possible to create high-speed frequency synthesizer phase-locked loops without the suffering the limitations imposed by traditional dividers connected directly to the oscillator output.

Alias-locked loop frequency synthesizer using a regenerative sampling latch

A high-density memory device and design method that utilizes some or all of the existing stacked process conductor layers provided by a manufacturing process to enhance the number of available bitlines and/or wordlines within the memory device. The memory device includes a plurality of memory cells arranged in columns and rows, a plurality of wordlines, a plurality of bitlines, at least one via-stack, wherein said existing stacked process conductor layers are used to implement at least one additional wordline or bitline. The via-stacks consist of a plurality of vias, are located close to a memory cell, and adapted to electrically connect the memory cell to multiple bitlines or multiple wordlines or both0. This design method increases the number of possible connections to or from each individual memory cell. When this design method is combined with varied configurations of basic underlying ROM cell types, even further increased cell density can be achieved.

Multi-layered memory cell structure

A method of operating a digital computer includes the steps of addressing a memory, reading a row of data from the memory, providing the same computational instruction simultaneously to each processor element of a plurality of processor elements, where each of the processor elements is selectively coupled to a corresponding bit position of the memory row of data, performing the same computational operation on a selected plurality of data bits in parallel, and writing the result into the memory at the same row as the data was read from.

Method and apparatus for an energy efficient operation of multiple processors in a memory

A systematic method for single-rail domino logic circuits is provided, in which inverting and non-monotonic logic functions can be integrated into a pipelined system with almost zero overhead. This logic family, called Clock Logic (CL)-domino is functionally complete while tolerating skew and minimizing the number of clock phases that must be distributed. Simulation results for a CL-domino ALU at 1-GHz under high skew (1-FO4) conditions, shows a power reduction of 41% over the same ALU implemented in dual-rail skew-tolerant domino logic. This power reduction incurs no performance penalty over dual-rail techniques, although in some cases additional design effort is required.

Clock logic domino circuits for high-speed and energy efficient microprocessor pipelines

The design methods described enable three-dimensional integrated circuit systems in which all of the dies, in a vertically bonded stack of dies, are identical. Only one mask set and wafer type is required since a single circuit design is produced for one die in the stack and reused for all the dies with little or no modification. The system scales directly as the level of stacking is increased while incurring no extra design effort, beyond that required for the initial design.

Method for scalable architectures in stackable three-dimensional integrated circuits and electronics

A method of operating a digital computer includes the steps of addressing a memory, reading a row of data from the memory, providing the same computational instruction simultaneously to each processor element of a plurality of processor elements, where each of the processor elements is selectively coupled to a corresponding bit position of the memory row of data, performing the same computational operation on a selected plurality of data bits in parallel, and writing the result into the memory at the same row from which the data was read.

A digital computer performs read-modify-write (RMW) processing on each bit of a row of memory in parallel, in one operation cycle, comprising: (a) addressing a memory, (b) reading each bit of a row of data from the memory in parallel, (c) performing the same computational operation on each bit of the data in parallel, using an arithmetic logic unit (ALU) in a dedicated processing element, and (d) writing the result of the operation back into the original memory location for each bit in the row.

Memory device with multiple processors having parallel access to the same memory area

A random access memory chip comprising static random access storage elements, word lines and bit lines connected to the storage elements, a sense amplifier connected to each of the bit lines, a separate processor element connected to each of the sense amplifiers, apparatus for addressing a word line, and apparatus for applying a single instruction to the processor elements, whereby the instructed processor elements are enabled to carry out a processing instruction in parallel on separate bits stored in the storage elements of the addressed word line. A method of operating a digital computer comprising in one operation cycle, addressing a memory, reading each of a row of data from the memory in parallel, and performing an operation function on each bit of the data in parallel to provide a result.

Growing community of inventors

Edmonton, Canada

Duncan George Elliott