Abstract: In an embodiment, a method includes configuring a specialized circuit for floating point computations using numbers represented by a hybrid format, wherein the hybrid format includes a first format and a second format. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a numeric value in the first format during a forward pass for training a deep learning network. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a second numeric value in the second format during a backward pass for training the deep learning network.

Abstract: An on-chip magnetic structure includes a magnetic material comprising cobalt in a range from about 80 to about 90 atomic % (at. %) based on the total number of atoms of the magnetic material, tungsten in a range from about 4 to about 9 at. % based on the total number of atoms of the magnetic material, phosphorous in a range from about 7 to about 15 at. % based on the total number of atoms of the magnetic material, and palladium substantially dispersed throughout the magnetic material.

Abstract: In an embodiment, a method includes configuring a specialized circuit for floating point computations using numbers represented by a hybrid format, wherein the hybrid format includes a first format and a second format. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a numeric value in the first format during a forward pass for training a deep learning network. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a second numeric value in the second format during a backward pass for training the deep learning network.

Abstract: A magnetic material stack comprises a first dielectric layer, a first magnetic material layer on the first dielectric layer, at least a second dielectric layer on the first magnetic material layer and at least a second magnetic material layer on the second dielectric layer. One or more surfaces of the layers are smoothed to remove at least a portion of surface roughness on the respective layers.

Abstract: An apparatus includes circuitry for a neural network that is configured to perform forward propagation neural network operations on floating point numbers having a first n-bit floating point format. The first n-bit floating point format has a configuration consisting of a sign bit, m exponent bits and p mantissa bits where m is greater than p. The circuitry is further configured to perform backward propagation neural network operations on floating point numbers having a second n-bit floating point format that is different than the first n-bit floating point format. The second n-bit floating point format has a configuration consisting of a sign bit, q exponent bits and r mantissa bits where q is greater than m and r is less than p.

Abstract: An apparatus for training and inferencing a neural network includes circuitry that is configured to generate a first weight having a first format including a first number of bits based at least in part on a second weight having a second format including a second number of bits and a residual having a third format including a third number of bits. The second number of bits and the third number of bits are each less than the first number of bits. The circuitry is further configured to update the second weight based at least in part on the first weight and to update the residual based at least in part on the updated second weight and the first weight. The circuitry is further configured to update the first weight based at least in part on the updated second weight and the updated residual.

Abstract: An apparatus includes a memory and a processor coupled to the memory. The processor includes first and second sets of arithmetic units having first and second precision for floating-point computations, the second precision being lower than the first precision. The processor is configured to obtain a machine learning model trained in the first precision, to utilize the second set of arithmetic units to perform inference on input data, to utilize the first set of arithmetic units to generate feedback for updating parameters of the second set of arithmetic units based on the inference performed on the input data by the second set of arithmetic units, to tune parameters of the second set of arithmetic units based at least in part on the feedback generated by the first set of arithmetic units, and to utilize the second set of arithmetic units with the tuned parameters to generate inference results.

Abstract: A magnetic laminating structure and process for preventing substrate bowing include a first magnetic layer, at least one additional magnetic layer, and a dielectric spacer disposed between the first and at least one additional magnetic layers. The magnetic layers are characterized by defined tensile strength. To balance the tensile strength of the magnetic layer, the dielectric layer is selected to provide compressive strength so as to counteract the tendency of the wafer to bow as a consequence of the tensile strength imparted by the magnetic layer(s).

Abstract: Semiconductor devices and methods relating to the semiconductor devices are provided. A semiconductor device includes a resonant clock circuit. The semiconductor device further includes an inductor. The semiconductor device also includes a magnetic layer formed of a magnetic material disposed in between a portion of the resonant clock circuit and the inductor. Clock signals of the resonant clock circuit are utilized by the magnetic layer.

Abstract: A technique relates to a method of forming a laminated multilayer magnetic structure. An adhesion layer is deposited on a substrate. A magnetic seed layer is deposited on top of the adhesion layer. Magnetic layers and non-magnetic spacer layers are alternatingly deposited such that an even number of the magnetic layers is deposited while an odd number of the non-magnetic spacer layers is deposited. The odd number is one less than the even number. Every two of the magnetic layers is separated by one of the non-magnetic spacer layers. The first of the magnetic layers is deposited on the magnetic seed layer, and the magnetic layers each have a thickness less than 500 nanometers.

Abstract: A technique relates to a method of forming a laminated multilayer magnetic structure. An adhesion layer is deposited on a substrate. A magnetic seed layer is deposited on top of the adhesion layer. Magnetic layers and non-magnetic spacer layers are alternatingly deposited such that an even number of the magnetic layers is deposited while an odd number of the non-magnetic spacer layers is deposited. The odd number is one less than the even number. Every two of the magnetic layers is separated by one of the non-magnetic spacer layers. The first of the magnetic layers is deposited on the magnetic seed layer, and the magnetic layers each have a thickness less than 500 nanometers.

Abstract: An inductor device includes a conductive coil formed within a dielectric material and having a central core area within the coil. Particles are dispersed within the central core region to reduce eddy current loss and increase energy storage. The particles include magnetic properties.

Abstract: In an embodiment, a method includes configuring a specialized circuit for floating point computations using numbers represented by a hybrid format, wherein the hybrid format includes a first format and a second format. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a numeric value in the first format during a forward pass for training a deep learning network. In the embodiment, the method includes operating the further configured specialized circuit to store an approximation of a second numeric value in the second format during a backward pass for training the deep learning network.

Abstract: Embodiments are directed to a method of forming a laminated magnetic inductor and resulting structures having multiple magnetic layer thicknesses. A first magnetic stack having one or more magnetic layers alternating with one or more insulating layers is formed in a first inner region of the laminated magnetic inductor. A second magnetic stack is formed opposite a major surface of the first magnetic stack in an outer region of the laminated magnetic inductor. A third magnetic stack is formed opposite a major surface of the second magnetic stack in a second inner region of the laminated magnetic inductor. The magnetic layers are formed such that a thickness of a magnetic layer in each of the first and third magnetic stacks is less than a thickness of a magnetic layer in the second magnetic stack.

Abstract: A compute matrix is configured to include a set of compute units, each compute unit including a multiplier and an accumulator, each of the multiplier and the accumulator formed using at least one floating point unit (FPU). An accumulator array is configured to include a set of external accumulators. The compute matrix is operated to produce a chunk dot-product using a first chunk of a first input vector and a first chunk of a second input vector. The accumulator array is operated to output a dot-product of the first input vector and the second input vector using the chunk dot-product.

Abstract: A first material is filled during a semiconductor fabrication process in a space bound on at least one side by a fence formation created as a result of an etching operation. A solvent-removable material is deposited such that the solvent-removable material encapsulates at least that portion of the fence formation which is protruding from the structure such that a height of the fence formation exceeds a height of the structure. The portion of the fence formation which is protruding from the structure and a first portion of the solvent-removable material are removed by planarization. A second portion of the solvent-removable material is removed by dissolving in a solvent, the second portion remaining after removal by the planarization of the first portion of the solvent-removable material.

Abstract: Techniques regarding autonomous identification of aged circuits are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an identification component, operatively coupled to the processor, that can identify an aged circuit by analyzing a current-voltage characteristic curve for a distortion in a sub-threshold quiescent current signature of the aged circuit.

Abstract: A multi-phase buck switching converter having grouped pairs of phases, each phase using two magnetically coupled air-core inductors. For each group, a first driver circuit controlling switching of a first power transistor switching circuit coupled to a first air-core inductor output for driving an output load at the first phase. A second driver circuit controlling switching of a second power transistor switching circuit coupled to a second air-core inductor output for driving said output load at the second phase. The first and second phases are spaced 180° apart. The coupled air-core inductors per group of such orientation, separation distance and mutual inductance polarity relative to each other such that magnetic coupling between the two or more inductors at each phase results in a net increase in effective inductance per unit volume. Each air-core inductor is a metal slab of defined length, height and thickness formed using back-end-of-line semiconductor manufacturing process.

Abstract: Embodiments are directed to a method of forming a laminated magnetic inductor and resulting structures having anisotropic magnetic layers. A first magnetic stack is formed having one or more magnetic layers alternating with one or more insulating layers. A trench is formed in the first magnetic stack oriented such that an axis of the trench is perpendicular to a hard axis of the magnetic inductor. The trench is filled with a dielectric material.

Abstract: Embodiments are directed to a method of forming a magnetic stack arrangement of a laminated magnetic inductor having a high frequency peak quality factor (Q). A first magnetic stack is formed having one or more magnetic layers alternating with one or more insulating layers in a first inner region of a laminated magnetic inductor. A second magnetic stack is formed opposite a surface of the first magnetic stack in an outer region of the laminated magnetic inductor. A third magnetic stack is formed opposite a surface of the second magnetic stack in a second inner region of the laminated magnetic inductor. The insulating layers are formed such that a thickness of an insulating layer in the second magnetic stack is greater than a thickness of an insulating layer in the first magnetic stack.