Abstract: Various implementations described herein are directed to a device having a bank of bitcells split into a plurality of portions including a first row slice of the bitcells and a second row slice of the bitcells. Also, the device may have control circuitry configured to access and repair a first bitcell in the first row slice with a first row address and a second bitcell in the second row slice with a second row address that is different than the first row address.

Abstract: A peripheral device, for use with a host, comprises one or more compute elements a security module and at least one encryption unit. The security module is configured to form a trusted execution environment on the peripheral device for processing sensitive data using sensitive code. The sensitive data and sensitive code are provided by a trusted computing entity which is in communication with the host computing device. The at least one encryption unit is configured to encrypt and decrypt data transferred between the trusted execution environment and the trusted computing entity via the host computing device. The security module is configured to compute and send an attestation to the trusted computing entity to attest that the sensitive code is in the trusted execution environment.

Abstract: A peripheral device, for use with a host, comprises one or more compute elements a security module and at least one encryption unit. The security module is configured to form a trusted execution environment on the peripheral device for processing sensitive data using sensitive code. The sensitive data and sensitive code are provided by a trusted computing entity which is in communication with the host computing device. The at least one encryption unit is configured to encrypt and decrypt data transferred between the trusted execution environment and the trusted computing entity via the host computing device. The security module is configured to compute and send an attestation to the trusted computing entity to attest that the sensitive code is in the trusted execution environment.

Abstract: Embodiments of the present disclosure include a method for token-position handling comprising: processing a first sequence of tokens to produce a second sequence of tokens, wherein the second sequence of tokens has a smaller number of tokens than the first sequence of tokens; masking at least some tokens in the second sequence to produce masked tokens; moving the masked tokens to the beginning of the second sequence to produce a third sequence; encoding tokens in the third sequence into a set of numeric vectors in a first array; and processing the first array in a transformer neural network to determine correlations among the third sequence, the processing the first array producing a second array.

Abstract: Techniques for training neural networks are provided. According to one set of embodiments, a first array is processed in a spreading component to produce a second array, where a first dimension of the first array corresponds to at least one sequence of approximately orthogonal numeric vectors representing tokens, and where the spreading component combines values along the first dimension. The second array is processed in a transformer neural network to determine correlations between the sequence, which produces a third array. One or more batches of the third array are processed in a de-spreading component to produce a fourth array.

Abstract: A peripheral device, for use with a host, comprises one or more compute elements a security module and at least one encryption unit. The security module is configured to form a trusted execution environment on the peripheral device for processing sensitive data using sensitive code. The sensitive data and sensitive code are provided by a trusted computing entity which is in communication with the host computing device. The at least one encryption unit is configured to encrypt and decrypt data transferred between the trusted execution environment and the trusted computing entity via the host computing device. The security module is configured to compute and send an attestation to the trusted computing entity to attest that the sensitive code is in the trusted execution environment.

Abstract: Techniques for training neural networks are provided. According to one set of embodiments, a first array is processed in a spreading component to produce a second array, where a first dimension of the first array corresponds to at least one sequence of approximately orthogonal numeric vectors representing tokens, and where the spreading component combines values along the first dimension. The second array is processed in a transformer neural network to determine correlations between the sequence, which produces a third array. One or more batches of the third array are processed in a de-spreading component to produce a fourth array.

Abstract: Embodiments of the present disclosure include a method for token-position handling comprising: processing a first sequence of tokens to produce a second sequence of tokens, wherein the second sequence of tokens has a smaller number of tokens than the first sequence of tokens; masking at least some tokens in the second sequence to produce masked tokens; moving the masked tokens to the beginning of the second sequence to produce a third sequence; encoding tokens in the third sequence into a set of numeric vectors in a first array; and processing the first array in a transformer neural network to determine correlations among the third sequence, the processing the first array producing a second array.

Abstract: A peripheral device, for use with a host, comprises one or more compute elements a security module and at least one encryption unit. The security module is configured to form a trusted execution environment on the peripheral device for processing sensitive data using sensitive code. The sensitive data and sensitive code are provided by a trusted computing entity which is in communication with the host computing device. The at least one encryption unit is configured to encrypt and decrypt data transferred between the trusted execution environment and the trusted computing entity via the host computing device. The security module is configured to compute and send an attestation to the trusted computing entity to attest that the sensitive code is in the trusted execution environment.

Abstract: A peripheral device, for use with a host, comprises one or more compute elements a security module and at least one encryption unit. The security module is configured to form a trusted execution environment on the peripheral device for processing sensitive data using sensitive code. The sensitive data and sensitive code are provided by a trusted computing entity which is in communication with the host computing device. The at least one encryption unit is configured to encrypt and decrypt data transferred between the trusted execution environment and the trusted computing entity via the host computing device. The security module is configured to compute and send an attestation to the trusted computing entity to attest that the sensitive code is in the trusted execution environment.

Abstract: Reduced precision computer number formats inherently limit the quantity of discrete numeric values that can be represented. Therefore, the solution values of an arithmetic function, for each numeric value that is individually and uniquely expressible utilizing such a reduced precision computer number format, can be precomputed since the quantity of unique solution values can be limited to a quantity that can be conveniently stored, such as in an array. Subsequently, rather than computing the solution value of such an arithmetic function, for a given input value, the precomputed array can be referenced and a solution value corresponding to the given input value can be read from the array. Reading numeric values from an array can be substantially faster than computing solution values of a computationally-expensive arithmetic function.

Abstract: Reduced precision computer number formats inherently limit the quantity of discrete numeric values that can be represented. Therefore, the solution values of an arithmetic function, for each numeric value that is individually and uniquely expressible utilizing such a reduced precision computer number format, can be precomputed since the quantity of unique solution values can be limited to a quantity that can be conveniently stored, such as in an array. Subsequently, rather than computing the solution value of such an arithmetic function, for a given input value, the precomputed array can be referenced and a solution value corresponding to the given input value can be read from the array. Reading numeric values from an array can be substantially faster than computing solution values of a computationally-expensive arithmetic function.

Abstract: Compositions of nanoparticles functionalized with at least one zwitterionic moiety, methods for making a plurality of nanoparticles, and methods of their use as diagnostic agents are provided. The nanoparticles have characteristics that result in minimal retention of the particles in the body compared to other nanoparticles. The nanoparticle comprising a nanoparticulate transition metal oxide covalently functionalized with a silane-functionalized non-targeting zwitterionic moiety.

Abstract: The present invention is generally directed to core/shell nanoparticles, wherein such core/shell nanoparticles comprise a nanoparticle core and a nanoshell disposed about the nanoparticle core such that, in the aggregate, they form a core/shell nanoparticle that is operable for use as an imaging agent in X-ray/computed tomography (CT). Typically, such core/shell nanoparticle-based X-ray CT imaging agents further comprise a targeting species for targeting the imaging agent to diseased sites. Included herein are methods for forming such agents, comprising forming an ensemble of core/shell nanoparticles, wherein the mean diameter of the ensemble of core/shell nanoparticles is selected so as to render the nanoparticles in the ensemble substantially clearable by a mammalian kidney.

Abstract: A reinforced pipeline liner designed to facilitate installation and systems and methods for producing and installing a reinforced pipeline liner. A reinforced pipeline liner can comprise a body portion having a layer of matrix material, the layer having an inner surface and an outer surface, and a plurality of interspersed reinforcement structures embedded within the body portion. The reinforcement structures are positioned between the inner surface and outer surface of the layer and circumferentially offset from the other reinforcement structures. Additionally, the body portion may have multiple thicknesses.

Abstract: Compositions of nanoparticles functionalized with at least one zwitterionic moiety, methods for making a plurality of nanoparticles, and methods of their use as diagnostic agents are provided. The nanoparticles have characteristics that result in minimal retention of the particles in the body compared to other nanoparticles. The nanoparticle comprises a core, having a core surface essentially free of silica, and a shell attached to the core surface. The shell comprises at least one silane-functionalized zwitterionic moiety.

Abstract: Compositions of nanoparticles functionalized with at least one zwitterionic moiety, methods for making a plurality of nanoparticles, and methods of their use as diagnostic agents are provided. The nanoparticles have characteristics that result in minimal retention of the particles in the body compared to other nanoparticles. The nanoparticle comprises a core, having a core surface essentially free of silica, and a shell attached to the core surface. The shell comprises at least one silane-functionalized zwitterionic moiety.

Abstract: A scannable integrated circuit (100) including a functional integrated circuit (P1, P2) having scan chains, multiple scan decompressors (120.1, 120.2), each operable to supply scan bits to some of the scan chains (101.k, 102.k), a shared scan-programmable control circuit (110, 300), a tree circuit (400) coupled with the functional integrated circuit (P1, P2), the shared scan-programmable control circuit (110, 300) coupled to control the tree circuit (400), and a selective coupling circuit (180) operable to provide selective coupling with the shared scan-programmable control circuit (110, 300) for scan programming through any of the multiple scan decompressors (120.1, 120.2). Other circuits, devices, systems, and processes of operation and manufacture are disclosed.

Abstract: Composition of non-radioactive traceable metal isotope-enriched nanoparticles, and methods of their use for determining in-vivo biodistribution are provided. The methods comprise the steps of: (a) introducing the nanoparticles into the biological material, wherein the nanoparticles comprise at least one inorganic core, and the inorganic core comprises at least two metal isotopes in a predetermined ratio; wherein at least one metal isotope is enriched non-radioactive traceable metal isotope and (b) determining the distribution of the nanoparticles in the biological material based on the predetermined ratio of the metal isotopes.

Abstract: A scannable integrated circuit (100) including a functional integrated circuit (P1, P2) having scan chains, multiple scan decompressors (120.1, 120.2), each operable to supply scan bits to some of the scan chains (101.k, 102.k), a shared scan-programmable control circuit (110, 300), a tree circuit (400) coupled with the functional integrated circuit (P1, P2), the shared scan-programmable control circuit (110, 300) coupled to control the tree circuit (400), and a selective coupling circuit (180) operable to provide selective coupling with the shared scan-programmable control circuit (110, 300) for scan programming through any of the multiple scan decompressors (120.1, 120.2). Other circuits, devices, systems, and processes of operation and manufacture are disclosed.