Abstract:
Systems, methods, and apparatus related to memory devices that use multi-pillar memory cells for performing multiplication and other operations. In one approach, a memory cell array has memory cells used to perform matrix vector multiplication based on summing output currents from the memory cells. The memory cells are arranged in pillars of memory cells connected in series. Each memory cell uses at least one transistor from two or more different pillars. A bitline is formed overlying the pillars. The bitline is electrically connected to the pillars and accumulates output currents from the pillars when performing the matrix vector multiplication.
Abstract:
Systems, methods, and apparatus related to memory devices that perform multiplication using memory cells programmed to have different thresholds based on bit significance. In one approach, a memory cell array has memory cells that are each programmed to store one bit of a multi-bit weight. Voltage drivers apply voltages to the memory cells. The applied voltages represent inputs to be multiplied by the weights. A common line is coupled each of the memory cells to accumulate output currents from the cells. The output currents each have a magnitude corresponding to the significance of the bit stored by the respective memory cell. A digitizer uses the summed output currents as an input and provides a digital result as an output.
Abstract:
Methods, systems, and devices for buried lines and related fabrication techniques are described. An electronic device (e.g., an integrated circuit) may include multiple buried lines at multiple layers of a stack. For example, a first layer of the stack may include multiple buried lines formed based on a pattern of vias formed at an upper layer of the stack. The pattern of vias may be formed in a wide variety of spatial configurations, and may allow for conductive material to be deposited at a buried target layer. In some cases, buried lines may be formed at multiple layers of the stack concurrently.
Abstract:
Methods and structures for accessing memory cells in parallel in a cross-point array include accessing in parallel a first memory cell disposed between a first selected column and a first selected row and a second memory cell disposed between a second selected column different from the first selected column and a second selected row different from the first selected row. Accessing in parallel includes simultaneously applying access biases between the first selected column and the first selected row and between the second selected column and the second selected row. The accessing in parallel is conducted while the cells are in a thresholded condition or while the cells are in a post-threshold recovery period.
Abstract:
A memory circuit, including a memory array (such as a cross-point array), may include circuit elements that may function both as selection elements/drivers and de-selection elements/drivers. A selection/de-selection driver may be used to provide both a selection function as well as an operation function. The operation function may include providing sufficient currents and voltages for WRITE and/or READ operations in the memory array. When the de-selection path is used for providing the operation function, highly efficient cross-point implementations can be achieved. The operation function may be accomplished by circuit manipulation of a de-selection supply and/or de-selection elements.
Abstract:
Methods, systems, and devices for buried lines and related fabrication techniques are described. An electronic device (e.g., an integrated circuit) may include multiple buried lines at multiple layers of a stack. For example, a first layer of the stack may include multiple buried lines formed based on a pattern of vias formed at an upper layer of the stack. The pattern of vias may be formed in a wide variety of spatial configurations, and may allow for conductive material to be deposited at a buried target layer. In some cases, buried lines may be formed at multiple layers of the stack concurrently.
Abstract:
Systems, methods, and apparatus related to memory devices that perform multiplication using memory cells. In one approach, a memory cell array has memory cells stacked vertically above a semiconductor substrate. Each memory cell stores a weight. Local digit lines connect to terminals of the memory cells. The local digit lines extend vertically above the substrate. Select transistors connect to the local digit lines. Select lines control the select transistors, and are used to encode an input pattern to multiply by the stored weights. Accumulation circuitry sums output currents from the memory cells. In one example, each memory cell is formed using a transistor that includes a semiconductor layer to provide a horizontal channel. A gate layer (e.g., a gate stack layer) wraps around a circumference of the semiconductor layer. Wordlines apply gate voltages to the transistors. Each wordline has a respective portion that wraps around a circumference of the gate layer of each transistor.
Abstract:
Systems, methods, and apparatus related to memory devices that perform multiplication using sets of memory cells. In one approach, memory cells in the sets are programmed so that each set stores a signed weight. Voltage drivers apply voltages to the memory cells in each set. The voltages correspond to signed inputs to multiply by the signed weights in the sets. One or more common lines (e.g., bitlines) are coupled to each set for summing output currents from the sets. A digitizer provides a signed result based on summing the output currents from the sets.
Abstract:
Embodiments disclosed herein may relate to applying verify or read pulses for phase change memory and switch (PCMS) devices. The read pulses may be applied at a first voltage for a first period of time. A threshold event for the phase change memory cell may be detected during a sense window. The sense window may close after the expiration of the first period of time for which the read pulses are applied.
Abstract:
Systems, methods, and apparatus related to memory devices that perform signed multiplication using logical states of memory cells. In one approach, a memory device has a memory array including sets of memory cells programmed to store a signed weight in each set (e.g., four cells in a set store a signed weight of +1, 0, or −1). Voltages that represent signed inputs (e.g., +1, 0, or −1) are applied to the memory cells to perform the multiplication. A result from the multiplication is determined based on summing of output currents from the memory cells.