Abstract: Described is a packaging technology to improve performance of an AI processing system. An IC package is provided which comprises: a substrate; a first die on the substrate, and a second die stacked over the first die. The first die includes memory and the second die includes computational logic. The first die comprises a ferroelectric RAM (FeRAM) having bit-cells. Each bit-cell comprises an access transistor and a capacitor including ferroelectric material. The access transistor is coupled to the ferroelectric material. The FeRAM can be FeDRAM or FeSRAM. The memory of the first die may store input data and weight factors. The computational logic of the second die is coupled to the memory of the first die. The second die is an inference die that applies fixed weights for a trained model to an input data to generate an output. In one example, the second die is a training die that enables learning of the weights.

Abstract: A method of fabricating a device comprises forming a multi-layer stack above a first substrate, where multi-layer stack includes a non-linear polar material. In at least one embodiment, method further includes forming a first conductive layer on multi-layer stack and annealing multi-layer stack. A transistor is formed above a second substrate. In at least one embodiment, method also includes forming a second conductive layer above electrode structure and bonding first conductive layer with second conductive layer. After bonding, method includes removing at least a portion of first substrate patterning multi-layer stack to form a memory device.

Abstract: Matrix multiplication process is segregated between two separate dies—a memory die and a compute die to achieve low latency and high bandwidth artificial intelligence (AI) processor. The blocked matrix-multiplication scheme maps computations across multiple processor elements (PE) or matrix-multiplication units. The AI architecture for inference and training includes one or more PEs, where each PE includes memory (e.g., ferroelectric (FE) memory, FE-RAM, SRAM, DRAM, MRAM, etc.) to store weights and input/output I/O data. Each PE also includes a ring or mesh interconnect network to couple the PEs for fast access of information.

Abstract: A device structure comprises a first conductive interconnect, an electrode structure on the first conductive interconnect, an etch stop layer laterally surrounding the electrode structure; a plurality of memory devices above the electrode structure, where individual ones of the plurality of memory devices comprise a dielectric layer comprising a perovskite material. The device structure further comprises a plate electrode coupled between the plurality of memory devices and the electrode structure, where the plate electrode is in direct contact with a respective lower most conductive layer of the individual ones of the plurality of memory devices. The device structure further includes an insulative hydrogen barrier layer on at least a sidewall of the individual ones of the plurality of memory devices; and a plurality of via electrodes, wherein individual ones of the plurality of via electrodes are on a respective one of the individual ones of the plurality of memory devices.

Abstract: Non lead-based perovskite ferroelectric devices for high density memory and logic applications and methods of fabrication are described. While various embodiments are described with reference to FeRAM, capacitive structures formed herein can be used for any application where a capacitor is desired. For example, the capacitive structure can be used for fabricating ferroelectric based or paraelectric based majority gate, minority gate, and/or threshold gate.

Abstract: A packaging technology to improve performance of an AI processing system resulting in an ultra-high bandwidth system. An IC package is provided which comprises: a substrate; a first die on the substrate, and a second die stacked over the first die. The first die can be a first logic die (e.g., a compute chip, CPU, GPU, etc.) while the second die can be a compute chiplet comprising ferroelectric or paraelectric logic. Both dies can include ferroelectric or paraelectric logic. The ferroelectric/paraelectric logic may include AND gates, OR gates, complex gates, majority, minority, and/or threshold gates, sequential logic, etc. The IC package can be in a 3D or 2.5D configuration that implements logic-on-logic stacking configuration. The 3D or 2.5D packaging configurations have chips or chiplets designed to have time distributed or spatially distributed processing. The logic of chips or chiplets is segregated so that one chip in a 3D or 2.5D stacking arrangement is hot at a time.

Abstract: A process integration and patterning flow used to pattern a memory array area for an embedded memory without perturbing a fabricating process for logic circuitries. The fabrication process uses a pocket mask (e.g., a hard mask) to decouple the etching process of a memory array area and non-memory area. Such decoupling allows for a simpler fabrication process with little to no impact on the current fabrication process. The fabrication process may use multiple pocket masks to decouple the etching process of the memory array area and the non-memory area. This fabrication process (using multiple pocket masks) allows to avoid exposure of memory material into a second pocket etch chamber. The process of etching memory material is decoupled from the process of etching an encapsulation material. Examples of embedded memory include dynamic random-access memory and ferroelectric random-access memory.

Abstract: Described is a low power, high-density non-volatile differential memory bit-cell. The transistors of the differential memory bit-cell can be planar or non-planer and can be fabricated in the frontend or backend of a die. A bit-cell of the non-volatile differential memory bit-cell comprises first transistor first non-volatile structure that are controlled to store data of a first value. Another bit-cell of the non-volatile differential memory bit-cell comprises second transistor and second non-volatile structure that are controlled to store data of a second value, wherein the first value is an inverse of the second value. The first and second volatile structures comprise ferroelectric material (e.g., perovskite, hexagonal ferroelectric, improper ferroelectric).

Abstract: An apparatus and configuring scheme where a capacitive input circuit can be programmed to perform different logic functions by adjusting the switching threshold of the capacitive input circuit. Digital inputs are received by respective capacitors on first terminals of those capacitors. The second terminals of the capacitors are connected to a summing node. A pull-up and pull-down device are coupled to the summing node. The pull-up and pull-down devices are controlled separately. During a reset phase, the pull-up and/or pull-down devices are turned on or off in a sequence, and inputs to the capacitors are set to condition the voltage on node n1. As such, a threshold for the capacitive input circuit is set. After the reset phase, an evaluation phase follows. In the evaluation phase, the output of the capacitive input circuit is determined based on the inputs and the logic function configured during the reset phase.

Abstract: Approaches for integrating FE memory arrays into a processor, and the resulting structures are described. Simultaneous integrations of regions with ferroelectric (FE) cells and regions with standard interconnects are also described. FE cells include FE capacitors that include a FE stack of layers, which is encapsulated with a protection material. The protection material protects the FE stack of layers as structures for regular logic are fabricated in the same die.

Abstract: A low power sequential circuit (e.g., latch) uses a non-linear polar capacitor to retain charge with fewer transistors than traditional CMOS sequential circuits. In one example, a sequential circuit includes pass-gates and inverters, but without a feedback mechanism or memory element. In another example, a sequential uses load capacitors (e.g., capacitors coupled to a storage node and a reference supply). The load capacitors are implemented using ferroelectric material, paraelectric material, or linear dielectric. In one example, a sequential uses minority, majority, or threshold gates with ferroelectric or paraelectric capacitors. In one example, a sequential circuit uses minority, majority, or threshold gates configured as NAND gates.

Abstract: Described herein is a memory bit-cell that results in lower leakage and higher sensing margin. In at least one embodiment, a memory bit-cell comprises a plurality of capacitors, wherein an individual capacitor is coupled to a node and an individual plate-line. In at least one embodiment, memory bit-cell comprises a first transistor coupled to the node. In at least one embodiment, memory bit-cell comprises a second transistor coupled in series with the first transistor, wherein the second transistor is coupled to a bit-line, wherein the first transistor or the second transistor is controllable by a word-line, and wherein the word-line is parallel to the individual plate-line.

Abstract: The memory bit-cell formed using the ferroelectric capacitor results in a taller and narrower bit-cell compared to traditional memory bit-cells. As such, more bit-cells can be packed in a die resulting in a higher density memory that can operate at lower voltages than traditional memories while providing the much sought after non-volatility behavior. The pillar capacitor includes a plug that assists in fabricating a narrow pillar.

Abstract: Described herein is a memory bit-cell that results in lower leakage and higher sensing margin. In at least one embodiment, a memory bit-cell comprises a plurality of capacitors, wherein an individual capacitor is coupled to a node and an individual plate-line. In at least one embodiment, memory bit-cell comprises a first transistor coupled to the node. In at least one embodiment, memory bit-cell comprises a second transistor coupled in series with the first transistor, wherein the second transistor is coupled to a bit-line, wherein the first transistor or the second transistor is controllable by a word-line, and wherein the word-line is parallel to the individual plate-line.

Abstract: A disturb mitigation scheme is described for a 1TnC or multi-element ferroelectric gain bit-cell where after writing to a selected capacitor of the bit-cell, a cure phase is initiated. Between the cure phase and the write phase, there may be zero or more cycles where the selected word-line, bit-line, and plate-lines are pulled-down to ground. The cure phase may occur immediately before the write phase. In the cure phase, the word-line is asserted again just like in the write phase. In the cure phase, the voltage on bit-line is inverted compared to the voltage on the bit-line in the write phase. By programming a value in a selected capacitor to be opposite of the value written in the write phase of that selected capacitor, time accumulation of disturb is negated. This allows to substantially zero out disturb field on the unselected capacitors of the same bit-cell and/or other unselected bit-cells.

Abstract: A configuration for efficiently placing a group of capacitors with one terminal connected to a common node is described. The capacitors are stacked and folded along the common node. In a stack and fold configuration, devices are stacked vertically (directly or with a horizontal offset) with one terminal of the devices being shared to a common node, and further the capacitors are placed along both sides of the common node. The common node is a point of fold. In one example, the devices are capacitors. N number of capacitors can be divided in L number of stack layers such that there are N/L capacitors in each stacked layer. The N/L capacitors are shorted together with an electrode (e.g., bottom electrode). The electrode can be metal, a conducting oxide, or a combination of a conducting oxide and a barrier material. The capacitors can be planar, non-planar or replaced by memory elements.

Abstract: Described is a packaging technology to improve performance of an AI processing system. An IC package is provided which comprises: a substrate; a first die on the substrate, and a second die stacked over the first die. The first die includes memory and the second die includes computational logic. The first die comprises DRAM having bit-cells. The memory of the first die may store input data and weight factors. The computational logic of the second die is coupled to the memory of the first die. In one example, the second die is an inference die that applies fixed weights for a trained model to an input data to generate an output. In one example, the second die is a training die that enables learning of the weights. Ultra high-bandwidth is changed by placing the first die below the second die. The two dies are wafer-to-wafer bonded or coupled via micro-bumps.

Abstract: A ferroelectric memory chiplet in a multi-dimensional packaging. The multi-dimensional packaging includes a first die comprising a switch and a first plurality of input-output transceivers. The multi-dimensional packaging includes a second die comprising a processor, wherein the second die includes a second plurality of input-output transceivers coupled to the first plurality of input-output transceivers. The multi-dimensional packaging includes a third die comprising a coherent cache or memory-side buffer, wherein the coherent cache or memory-side buffer comprises ferroelectric memory cells, wherein the coherent cache or memory-side buffer is coupled to the second die via I/Os. The dies are wafer-to-wafer bonded or coupled via micro-bumps, copper-to-copper hybrid bond, or wire bond, Flip-chip ball grid array routing, chip-on-wafer substrate, or embedded multi-die interconnect bridge.

Abstract: A multiplier cell is derived from a 1-bit full adder and an AND gate. The 1-bit full adder is derived from majority and/or minority gates. The majority and/or minority gates include non-linear polar material (e.g., ferroelectric or paraelectric material). A reset mechanism is provided to reset the nodes across the non-linear polar material. The multiplier cell is a hybrid of majority and/or minority gates and complementary metal oxide semiconductor (CMOS) based inverters and/or buffers. The adder uses a non-linear polar capacitor to retain charge with fewer transistors than traditional CMOS sequential circuits. The non-linear polar capacitor includes ferroelectric material, paraelectric material, or non-linear dielectric. Input signals are received by respective terminals of capacitors having non-linear polar material. The other terminals of these capacitors are coupled to a node where the majority function takes place for the inputs.

Abstract: A computer-aided design (CAD) tool is provided for logic optimization and synthesis. The CAD tool executes a process that involves optimizing power, performance, and area (PPA) of a logic circuit by minimizing a number of CMOS gates, and majority and/or minority gates in the circuit and its depth. The CAD tool implements a methodology of optimizing logic synthesis based on a mix of standard cell libraries (such as AND, OR, NAND, NOR, XOR, Multiplexer, full adder, half adder, etc.) and varying input majority and minority gates (where the number of inputs in the minority and majority gates could vary as odd numbers from 3 and above). The standard cell libraries cells may contain minority and/or majority gates.