Abstract: The embodiments of methods and structures disclosed herein provide mechanisms of forming and programming a non-salicided polysilicon fuse. The non-salicided polysilicon fuse and a programming transistor form a one-time programmable (OTP) memory cell, which can be programmed with a low programming voltage.

Abstract: A memory circuit includes at least one memory cell for storing a charge representative of a datum. The memory cell is coupled with a word line and a first bit line. At least one bit line equalization transistor is coupled between the first bit line and a second bit line. A bit line equalization circuit is coupled with the bit line equalization transistor. The bit line equalization circuit is configured for providing a pulse to the bit line equalization transistor to substantially equalize voltages of the first bit line and the second bit line during a standby period before an access cycle of the memory cell.

Abstract: An OTP memory array includes a bit line coupled to a plurality of memory banks. Each memory bank includes a plurality of memory cells, a footer, and a bias device, and is associated with a current mirror. When a memory cell is activated (e.g., for reading) the memory bank including the activated memory cell is referred to as an activated memory bank and other banks are referred to as deactivated memory banks. A current tracking device serves to compensate for bit line leakage current in deactivated memory cells in the activated memory bank. Further, footers and bias devices in deactivated memory banks and associated current mirrors are configured to reduce/eliminate bit line current leakage through deactivated memory cells in deactivated memory banks.

Abstract: A one time programming (OTP) memory cell includes a first transistor and a second transistor. The first transistor has a first drain, a first source, a first gate, and a first normal operational voltage value higher that a second normal operational voltage value of the second transistor. The second transistor has a second drain, a second source, and a second gate. The first source is coupled to the second drain. The second source is configured to detect data stored in the OTP memory cell.

Abstract: A memory has a tracking circuit for a read tracking operation. The memory includes a memory bit cell array, a tracking column, a tracking row, a sense amplifier row coupled to the memory bit cell array and the tracking row, and a sense amplifier enable logic. The memory further includes a tracking bit line coupled to the tracking column and the sense amplifier enable logic, and a tracking word line coupled to the tracking row and the sense amplifier enable logic. The tracking circuit is configured to track a column time delay along the tracking column before a row time delay along the tracking row.

Abstract: A circuit includes a first node; a second node; a first PMOS transistor having a source coupled to the first node, a drain coupled to a first control transistor, and a gate driven by a first voltage; and a first NMOS transistor having a source coupled to the second node, a drain coupled to the first control transistor, and a gate driven by a second voltage. The first PMOS transistor is configured to automatically turn off based on the first voltage and a first node voltage at the first node. The first NMOS transistor is configured to automatically turn off based on the second voltage and a second node voltage at the second node. When the first PMOS transistor, the control transistor, and the first NMOS transistor are on, the first node voltage is lowered while the second voltage is raised.

Abstract: A method of operating a memory circuit includes providing the memory circuit. The memory circuit includes a memory cell; a word line connected to the memory cell; a first local bit line and a second local bit line connected to the memory cell; and a first global bit line and a second global bit line coupled to the first and the second local bit lines, respectively. The method further includes starting an equalization to equalize voltages on the first and the second local bit lines; stopping the equalization; and after the step of starting the equalization and before the step of stopping the equalization, writing values from the first and the second global bit lines to the first and the second local bit lines.

Abstract: Some embodiments regard a memory array that has a plurality of eFuse memory cells arranged in rows and columns, a plurality of bit lines, and a plurality of word lines. A column includes a bit line selector, a bit line coupled to the bit line selector, and a plurality of eFuse memory cells. An eFuse memory cell of the column includes a PMOS transistor and an eFuse. A drain of the PMOS transistor is coupled to a first end of the eFuse. A gate of the PMOS transistor is coupled to a word line. A source of the PMOS transistor is coupled to the bit line of the column.

Abstract: A circuit includes a memory cell having a ground reference node, a switch coupled to the ground reference node, and a mode changing circuit having an output coupled to the switch. The mode changing circuit is configured to change a logic state of the output between a first output logic state and a second output logic state in response to a change in an operational voltage and/or temperature, thereby set the memory cell in a first mode in which the ground reference node is at first reference level or in a second mode in which the ground reference node is at a second reference level different from the first reference level.

Abstract: A system for performing data-parallel operations and task-parallel operations. A first switch fabric node (SFN) includes first and second lane processing engines (LPEs). The first LPE includes a first set of lane processing units (LPUs) configured to perform data-parallel operations, where each LPU performs a set of operations, and each LPU uses a different set of data for the set of operations, and each LPU within the first set of LPUs uses a different set of data for the set of operations. The second LPE includes a second set of LPUs configured to perform task-parallel operations, where each LPU performs a different set of operations. A processing control engine (PCE) is configured to distribute instructions and data to the first LPE and the second LPE. Advantageously, data parallel operations and task parallel operations are able to be performed on the same processor simultaneously.

Abstract: A circuit includes a first node; a second node; a first PMOS transistor having a source coupled to the first node, a drain coupled to a first control transistor, and a gate driven by a first voltage; and a first NMOS transistor having a source coupled to the second node, a drain coupled to the first control transistor, and a gate driven by a second voltage. The first PMOS transistor is configured to automatically turn off based on the first voltage and a first node voltage at the first node. The first NMOS transistor is configured to automatically turn off based on the second voltage and a second node voltage at the second node. When the first PMOS transistor, the control transistor, and the first NMOS transistor are on, the first node voltage is lowered while the second voltage is raised.

Abstract: An input of a first inverter is configured to serve as an input node. An output of the first inverter is coupled to an input of a second inverter. An output of the second inverter is configured to serve as an output node. An input of a third inverter is coupled to an input of the first inverter. A gate of a first NMOS transistor is coupled to an output of the third inverter. A drain of the first NMOS transistor is coupled to the second inverter. A source of the first NMOS transistor is configured to serve as a level input node. When the input node is configured to receive a low logic level, the output node is configured to receive a voltage level provided by a voltage level at the level input node.

Abstract: Some embodiments regard a memory array that has a plurality of eFuse memory cells arranged in rows and columns, a plurality of bit lines, and a plurality of word lines. A column includes a bit line selector, a bit line coupled to the bit line selector, and a plurality of eFuse memory cells. An eFuse memory cell of the column includes a PMOS transistor and an eFuse. A drain of the PMOS transistor is coupled to a first end of the eFuse. A gate of the PMOS transistor is coupled to a word line. A source of the PMOS transistor is coupled to the bit line of the column.

Abstract: A circuit includes a first node; a second node; a first PMOS transistor having a source coupled to the first node, a drain coupled to a first control transistor, and a gate driven by a first voltage; and a first NMOS transistor having a source coupled to the second node, a drain coupled to the first control transistor, and a gate driven by a second voltage. The first PMOS transistor is configured to automatically turn off based on the first voltage and a first node voltage at the first node. The first NMOS transistor is configured to automatically turn off based on the second voltage and a second node voltage at the second node. When the first PMOS transistor, the control transistor, and the first NMOS transistor are on, the first node voltage is lowered while the second voltage is raised.

Abstract: Some embodiments regard a memory array that has a plurality of rows and columns. A column includes a program control device, a plurality of eFuse memory cells in the column, a sense amplifier, and a bit line coupling the program control device, the plurality of memory cells in the column, and the sense amplifier. A row includes a plurality of eFuse memory cells in the row, a word line coupling the plurality of eFuse memory cells in the row, and a footer configured as a current path for the plurality of eFuse memory cells in the row.

Abstract: A Static Random Access Memory (SRAM) includes at least two memory cells sharing a read bit line (RBL) and a write bit line (WBL). Each memory cell is coupled to a respective read word line (RWL) and a respective write word line (WWL). A write tracking control circuit is coupled to the memory cells for determining a write time of the memory cells. The write tracking control circuit is capable of receiving an input voltage and providing an output voltage. The respective RWL and the respective WWL of each memory cell are asserted during a write tracking operation.

Abstract: A memory comprising: a plurality of memory cells arranged in a plurality of rows and a plurality of columns. A column of the plurality of columns including a first power supply node configured to provide a first voltage, a second power supply node configured to provide a second voltage, a plurality of internal supply nodes electrically coupled together and configured to receive the first voltage or the second voltage for a plurality of memory cells in the column and a plurality of internal ground nodes. The internal ground nodes electrically coupled together and configured to provide at least two current paths for the plurality of memory cells in the column.

Abstract: Some embodiments regard a memory array comprising: a plurality of memory cells arranged in a plurality of rows and a plurality of columns; wherein a column of the plurality of columns includes a column ground node; at least two voltage sources configured to be selectively coupled to the column ground node; and a plurality of memory cells having a plurality of internal ground nodes electrically coupled together and to the column ground node.

Abstract: The present invention provides extended precision in SIMD arithmetic operations in a processor having a register file and an accumulator. A first set of data elements and a second set of data elements are loaded into first and second vector registers, respectively. Each data element comprises N bits. Next, an arithmetic instruction is fetched from memory. The arithmetic instruction is decoded. Then, the first vector register and the second vector register are read from the register file. The present invention executes the arithmetic instruction on corresponding data elements in the first and second vector registers. The resulting element of the execution is then written into the accumulator. Then, the resulting element is transformed into an N-bit width element and written into a third register for further operation or storage in memory. The transformation of the resulting element can include, for example, rounding, clamping, and/or shifting the element.

Abstract: A circuit with leakage and data retention control includes at least one memory cell in a first memory array. The at least one memory cell is coupled to a first power supply voltage and a virtual ground. The circuit includes a current source and an NMOS transistor. The drain of the NMOS transistor is coupled to the virtual ground and the gate of the NMOS transistor is coupled to the current source.