Gsi Technology, Inc.

Sony Electronics Inc

Sony Corporation

Sony Corporation of Japan

Other

Patrick Chuang

Mu-Hsiang Huang

Atul V Ghia

Pradip Banerjee

Robert Haig

Chih Tseng

Lee-Lean Shu

Chao-Hung Chang

Bob Haig

Jae-Hyeong Kim

Eli Ehrman

Yu-Chi Cheng

Dan Ilan

Kuoyuan Hsu

Jae Hyeong Kim

Hisanobu Tsukazaki

Chih-Chiang Tseng

Hsin-Ley Suzanne Chen

Simon Lau

Kookhwan Kwon

Michelle Huang

Gary Chang

Yoshifumi Miyazima

Chungji Lu

A device and method for facilitating orthogonal data transposition during data transfers to/from a processing array and a storage memory since the data words processed by the processing array (using computational memory cells) are stored orthogonally to how the data words are stored in storage memory. Thus, when data words are transferred between storage memory and the processing array, a mechanism orthogonally transposes the data words.

Orthogonal data transposition system and method during data transfers to/from a processing array

A read and write data processing apparatus and method associated with computational memory cells formed as a memory/processing array (having a plurality of bit line sections) provides a mechanism to logically combine the computation results across multiple bit line sections in a section and across multiple sections, and transmit the combined result as an output of the processing array and/or store the combined result into one or more of those multiple bit line sections.

Results processing circuits and methods associated with computational memory cells

An ultra low VDD memory cell has a ratioless write port. In some embodiments, the VDD operation level can be as low as the threshold voltage of NMOS and PMOS transistors of the cell.

Ultra low VDD memory cell with ratioless write port

A computational memory cell and processing array have a ratioless write port so that a write to the memory cell does not need to overcome the drive strength of a PMOS transistor that is part of the storage cell of the memory cell. The computational memory cell also may have a second read port that has an isolation circuit.

Computational memory cell and processing array device with ratioless write port

A read and write data processing apparatus and method associated with computational memory cells formed as a memory/processing array provides the ability to inhibit writes in selective bit line sections on per-write operation basis to enhance the computational capability of the bl-sects. The read and write data processing apparatus and method also provides a mechanism to inhibit the read bit line pre-charge in selective bit line sections for an extended period of time to save power when pre-charge circuitry is implemented on the read bit line. The read and write data processing apparatus and method also provides a mechanism to inhibit writes to memory cells in selective bl-sects for an extended period of time, to save power.

Read and write data processing circuits and methods associated with computational memory cells that provides write inhibits and read bit line pre-charge inhibits

Multi-bank, dual-pipe SRAM systems, methods, processes of operating such SRAMs, and/or methods of fabricating multi-bank, dual-pipe SRAM are disclosed. For example, one illustrative multi-bank, dual-pipe SRAM may comprise features for capturing read and write addresses, splitting and/or combining them via one or more splitting/combining processes, and/or bussing them to the SRAM memory banks, where they may be read and written to a particular bank. Illustrative multi-bank, dual-pipe SRAMs and methods herein may also comprise features for capturing two beats of write data, splitting and/or combining them via one or more splitting/combining processes, and bussing them to each SRAM bank, where they may be split/combined/recombined via one or more processes to write data to particular memory bank(s).

Systems and methods involving multi-bank, dual-pipe memory circuitry

A system, method and circuits are described that pertain to locked loop circuits, distributed duty cycle correction loop circuitry. In some embodiments, the system and circuit may involve or be configured for coupling with lock loop circuitry such as phase locked loop (PLL) circuitry and/or a delay locked loop (DLL) circuitry. For example, one illustrative implementation may include or involve a phase locked loop (PLL) with distributed duty cycle correction loop/circuitry.

Systems and methods involving lock loop circuits, distributed duty cycle correction loop circuitry

Systems and methods associated with reducing clock skew are disclosed. In some exemplary embodiments, there is provided circuitry associated with lock loop circuits such as a phase lock loop (PLL). Such circuitry may comprise output clock tree circuitry and phase averaging circuitry. In other exemplary embodiments, there is provided circuitry associated with delay lock loop (DLL) circuits. Such circuitry may comprise output clock tree circuitry and/or phase averaging circuitry.

Systems and methods involving lock-loop circuits, clock signal alignment, phase-averaging feedback clock circuitry

A system may include a first inverter configured to invert a first data signal and a second inverter configured to invert a second data signal. A pull-up element may be coupled to an output of the first inverter on a first terminal and a power source on a second terminal, wherein the power source is also coupled to a pull-up element of a main output buffer. A pull-down element may be coupled to an output of the second inverter on a first terminal and a ground on a second terminal, wherein the ground is also coupled to a pull-down element of the main output buffer.

Systems and methods involving pseudo complementary output buffer circuitry/schemes, power noise reduction and/or other features

Systems and methods are disclosed for increasing the performance of static random access memory (SRAM). Various systems herein, for example, may include or involve dual- or multi-pipe, multi-bank SRAMs, such as Quad-B2 SRAMs. In one illustrative implementation, there is provided an SRAM memory device including a memory array comprising a plurality of SRAM banks and pairs of separate and distinct pipes associated with each of the SRAM banks, wherein each pair of pipes may provide independent access to its associated SRAM bank.

Systems and methods involving multi-bank, dual- or multi-pipe SRAMs

Systems and methods of memory and memory operation are disclosed, such as providing a circuit including a local address driver voltage source for memory decoding. In one exemplary implementation, an illustrative circuit may comprise a first buffer and a capacitor. The first buffer may comprise a power input and a ground input. The capacitor may comprise a first terminal connected to the power input of the first buffer and a second terminal connected to the ground input of the first buffer. When the first buffer draws a current from the power input, at least a portion of the current may be supplied by the capacitor.

Memory systems and methods involving high speed local address circuitry

Systems and methods of data inversion, circuitry, detection and/or schemes are disclosed. According to illustrative implementations, exemplary circuitry may include static detection or detection circuitry such as those involving static current sources to detect a threshold for data inversion, pre-conditioning of detection circuitry, and/or active detection circuitry or schemes. In some implementations, exemplary memory or data inversion circuitry may comprise a transistor array, a bias generator, and a sense amplifier, wherein the transistor array may comprise at least one pair of transistor circuits arranged so that an output of the transistor array is provided as a sum or function of signal/current outputs of at least some of the transistor circuits in the array. As set forth, various systems, methods and circuitry herein may posses only a 3 static gate delay, such that very high speed and/or fast flow-through is achieved.

Growing community of inventors

Cupertino, CA, United States of America

Patrick Chuang