According to one embodiment, a semiconductor storage device includes a memory cell, a bit line connected to the memory cell, and a sense circuit connected to the bit line, wherein the sense circuit includes a first transistor with a first end connected to the bit line, a second transistor with a first end connected to a second end of the first transistor, a third transistor with a first end connected to the bit line, a fourth transistor with a first end connected to a second end of the third transistor, and an amplifier connected to a second end of the second transistor and to a second end of the fourth transistor.

A multi-chip package includes a field-programmable-gate-array (FPGA) integrated-circuit (IC) chip configured to perform a logic function based on a truth table, wherein the field-programmable-gate-array (FPGA) integrated-circuit (IC) chip comprises multiple non-volatile memory cells therein configured to store multiple resulting values of the truth table, and a programmable logic block therein configured to select, in accordance with one of the combinations of its inputs, one from the resulting values into its output; and a memory chip coupling to the field-programmable-gate-array (FPGA) integrated-circuit (IC) chip, wherein a data bit width between the field-programmable-gate-array (FPGA) integrated-circuit (IC) chip and the memory chip is greater than or equal to 64.

A circuit includes an operational amplifier including an inverting input terminal capacitively coupled to each of an OTP cell array and an NVM cell array and first and second output terminals, an ADC coupled to the first and second output terminals, thereby configured to receive a differential output voltage from the operational amplifier, and a comparator coupled to the ADC and configured to output a data bit responsive to a digital output signal received from the ADC. The circuit is configured to cause the operational amplifier to generate the differential output voltage based on each of a current received from an OTP cell of the OTP cell array and a voltage received from an NVM cell of the NVM cell array.

1. The present disclosure is drawn to, among other things, a method for accessing memory using dual standby modes, the method including receiving a first standby mode indication selecting a first standby mode from a first standby mode or a second standby mode, configuring a read bias system to provide a read bias voltage and a write bias system to provide approximately no voltage, or any voltage outside the necessary range for write operation, based on the first standby mode, receiving a second standby mode indication selecting the second standby mode, and configuring the read bias system to provide at least the read bias voltage and the write bias system to provide a write bias voltage based on the second standby mode, the read bias voltage being lower than the write bias voltage.

In a memory array with a cross-point structure, at each cross-point junction a programmable resistive memory element, such as an MRAM memory cell, is connected in series with a threshold switching selector, such as an ovonic threshold switch. The threshold switching selector switches to a conducting state when a voltage above a threshold voltage is applied. When powered down for extended periods, the threshold voltage can drift upward. If the drift is excessive, this can make the memory cell difficult to access and can disturb stored data values when accessed. Techniques are presented to determine whether excessive voltage threshold drift may have occurred, including a read based test and a time based test.

Concurrent access of multiple memory cells in a cross-point memory array is disclosed. In one aspect, a forced current approach is used in which, while a select voltage is applied to a selected bit line, an access current is driven separately through each selected word line to concurrently drive the access current separately through each selected memory cell. Hence, multiple memory cells are concurrently accessed. In some aspects, the memory cells are accessed using a self-referenced read (SRR), which improves read margin. Concurrently accessing more than one memory cell in a cross-point memory array improves bandwidth. Moreover, such concurrent accessing allows the memory system to be constructed with fewer, but larger cross-point arrays, which increases array efficiency. Moreover, concurrent access as disclosed herein is compatible with memory cells such as MRAM which require bipolar operation.

A computing device includes one or more processors, random access memory (RAM), and a non-transitory computer-readable storage medium storing instructions for execution by the one or more processors. The computing device receives first data and classifies the first data using a neural network that includes at least one quantized layer. The classifying includes reading values from the random access memory for a set of weights of the at least one quantized layer of the neural network using first read parameters corresponding to a first error rate.

A method of testing a non-volatile memory (NVM) array includes obtaining a current distribution of a subset of NVM cells of the NVM array, the current distribution including first and second portions corresponding to respective logically high and low states of the subset of NVM cells, programming an entirety of the NVM cells of the NVM array to one of the logically high or low states, determining an initial bit error rate (BER) by performing first and second pass/fail (P/F) tests on each NVM cell of the NVM array, and using the current distribution to adjust the initial BER rate. Each of obtaining the current distribution, programming the entirety of the NVM cells, and performing the first and second P/F tests is performed while the NVM array is heated to a target temperature.

A magnetic multilayer film for a magnetic memory element includes an amorphous heavy metal layer having a multilayer structure in which a plurality of first layers containing Hf alternate repeatedly with a plurality of second layers containing a heavy metal excluding Hf; and a recording layer that includes a ferromagnetic layer and that is adjacent to the heavy metal layer, the ferromagnetic layer having a variable magnetization direction.

A memory device includes a spin-orbit-transfer (SOT) bottom electrode, an SOT ferromagnetic free layer, a first tunnel barrier layer, a spin-transfer-torque (STT) ferromagnetic free layer, a second tunnel barrier layer and a reference layer. The SOT ferromagnetic free layer is over the SOT bottom electrode. The SOT ferromagnetic free layer has a magnetic orientation switchable by the SOT bottom electrode using a spin Hall effect or Rashba effect. The first tunnel barrier layer is over the SOT ferromagnetic free layer. The STT ferromagnetic free layer is over the first tunnel barrier layer and has a magnetic orientation switchable using an STT effect. The second tunnel barrier layer is over the STT ferromagnetic free layer. The second tunnel barrier layer has a thickness different from a thickness of the first tunnel barrier layer. The reference layer is over the second tunnel barrier layer and has a fixed magnetic orientation.