Abstract: The presented systems enable efficient and effective network communications. The presented systems enable efficient and effective network communications. In one embodiment a memory device includes a memory module, including a plurality of memory chips configured to store information; and an inter-chip network (ICN)/shared smart memory extension (SMX) memory interface controller (ICN/SMX memory interface controller) configured to interface between the memory module and an inter-chip network (ICN), wherein the ICN is configured to communicatively couple the memory device to a parallel processing unit (PPU). In one exemplary implementation, the ICN/SMX memory controller includes a plurality of package buffers, an ICN physical layer interface, a PRC/MAC interface, and a switch. The memory device and be a memory card including memory module (e.g., DDR DIMM, etc.).

Abstract: An optical imaging lens assembly is provided, along an optical axis from an object side to an image side, sequentially includes: a first lens having refractive power; an autofocus assembly; a second lens having refractive power, and an image-side surface of the second lens being a concave surface; a third lens having refractive power, and an image-side surface of the third lens being a convex surface; a fourth lens having refractive power, an object-side surface of the fourth lens being a concave surface, and an image-side surface of the fourth lens being a convex surface; and at least one subsequent lens having refractive power. A radius of curvature of an object-side surface of the autofocus assembly being variable.

Abstract: An optical imaging lens assembly sequentially includes, from an object side to an image side along an optical axis, a first lens (E1), second lens (E2), third lens (E3), fourth lens (E4), fifth lens (E5) and sixth lens (E6) with refractive power. The first lens (E1) has a positive refractive power, and an image-side surface (S2) of the first lens is a concave surface. The second lens (E2) has a negative refractive power. The fifth lens (E5) has a negative refractive power, and an object-side surface (S9) of the fifth lens is a concave surface. A distance TTL from an object-side surface (S1) of the first lens (E1) to an imaging surface (S15) of the optical imaging lens assembly and a total effective focal length f of the optical imaging lens assembly satisfy TTL/f?0.85.

Abstract: Embodiments of the disclosure provide methods and systems for processing a neural network associated with an input matrix having a first number of elements. The method can include: dividing the input matrix into a plurality of vectors, each vector having a second number of elements; grouping the plurality of vectors into a first group of vectors and a second group of vectors; and pruning the first group of vectors and the second group of vectors.

Abstract: The maximum capacity of a very fast memory in a system that requires very fast memory access times is increased by adding a memory with remote access times that are slower than required, and then moving infrequently accessed data from the memory with the very fast access times to the memory with the slow access times.

Abstract: An electrode active material includes a layered metal oxide. The layered metal oxide has the following general formula: NaxM1aM2bMn1-a-bO2-zFz; where 0.55?x?0.85, a?0, b?0, 0.1?a+b?0.33, and 0.06?z/(1?a?b)?0.13; M1 is selected from one or more of alkali metal elements other than Na and alkaline earth metal elements; and M2 is selected from one or more of transition metal elements other than Mn.

Abstract: An optical imaging lens assembly includes a first lens, a second lens, a third lens, a fourth lens, a fifth lens, a sixth lens and a seventh lens, which have refractive power and are sequentially arranged from an object side to an image side of the optical imaging lens assembly along an optical axis. The first lens and the third lens both have positive refractive power. The fifth lens has negative refractive power. A total effective focal length f of the optical imaging lens assembly and an entrance pupil diameter EPD of the optical imaging lens assembly satisfy f/EPD<1.3.

Abstract: The present application provides a positive electrode active material and the preparation thereof, a secondary battery, a battery module, a battery pack, and electrical device. The positive electrode active material of the present application comprises a layered sodium composite oxide containing antimony having a chemical formula of Formula I, NaxMnaFebNicSbdLeO2 (I), in which 0.7<x?1, 0<a, 0?b, 0.1<c?0.3, 0<d?0.1, 0?e, a+b+c+d+e=1, (b+c)/(a+d+e)?1, and L is one or more selected from Cu, Li, Ti, Zr, K, Nb, Mg, Ca, Mo, Zn, Cr, W, Bi, Sn, Ge, Al, Si, La, Ta, P, and B. The layered sodium composite oxide containing antimony of the present application, by being doped with specific metal Sb, has high stability to water.

Abstract: A positive electrode material includes a sodium-containing positive electrode material substrate and a coating layer covering at least a part of a surface of the sodium-containing positive electrode material substrate. The coating layer includes NaxMyO2, where M includes at least one of B, Si, or P, x>0, and y>0.

Abstract: An electrode active material is provided. The electrode active material includes a layered metal oxide having a general formula NaxZnaNibMncM1dO2M2e, where 0.6?x?0.85, 0.95?a+b+c+d?1.05, 0?d?0.05, and 0?e?0.067, and where 0.04?a/c?0.1 and 0.23?b/c?0.45. M1 is selected from at least one of alkaline earth metal elements, transition metal elements, and alkali metal elements other than Zn, Ni, and Mn, and M2 is selected from non-metallic elements other than O.

Abstract: Provided are a layered oxide and a preparation method thereof, a positive electrode sheet, a secondary battery, a battery module, a battery pack and an electrical apparatus. The layered oxide includes an oxide with the general formula NaxMnyAaQbCcO2, where A is one or two of Fe and Ni; Q is one or more of transition metal elements containing 3d or 4d orbital electrons except Fe and Ni; C is one or two of Al and B, 0.66<x?1, 0.2?y?0.6, 0.3?a?0.6, 0<b?0.2, 0<c?0.1, and 1?b/c?100. The A element undergoes valence changes to provide charge compensation in a charge and discharge process, thereby improving the specific capacity of the layered oxide; the Q element and oxygen form a hybrid orbital, inhibiting irreversible oxygen losses and structure collapse of oxygen under a high voltage; the C element has a high ionic potential so as to effectively inhibit oxygen losses; and 1?b/c?100.

Abstract: The present disclosure discloses an optical imaging system including, sequentially from an object side to an image side along an optical axis, a first lens having refractive power; a second lens having negative refractive power; a third lens having negative refractive power; a fourth lens having refractive power, a convex object-side surface and a concave image-side surface; and a fifth lens having refractive power. A distance TTL along the optical axis from an object-side surface of the first lens to an imaging plane of the optical imaging system and half of a diagonal length ImgH of an effective pixel area on the imaging plane of the optical imaging system satisfy: 1.0<TTL/ImgH<1.5.

Abstract: Provided are a positive active material for use in a sodium-ion battery, a method for preparing same, a positive electrode plate containing same, a sodium-ion battery, and an electrical device. The method for preparing a positive active material for use in a sodium-ion battery includes the following steps: mixing a positive active material for use in a sodium-ion battery with, and causing the positive active material to react with, a washing solution at a temperature of T1, and filtering and drying a product of the reaction to obtain a washed positive active material for use in a sodium-ion battery, where the washing solution is deionized water or an acidic solution with a pH value lower than 7.0, and 0° C.?T1<20° C.

Abstract: This application describes systems and methods for facilitating memory access for graph neural network (GNN) processing. An example method includes fetching, by an access engine circuitry implemented on a circuitry board, a portion of structure data of a graph from a pinned memory in a host memory of a host via a first peripheral component interconnect express (PCIe) connection; performing node sampling using the fetched portion of the structure data of the graph to select one or more sampled nodes; fetching, by the access engine circuitry, a portion of attribute data of the graph from the pinned memory via the first PCIe connection; sending the fetched portion of the attribute data of the graph to one or more processors; and performing, by the one or more processors, GNN processing for the graph using the fetched portion of the attribute data of the graph.

Abstract: The total memory space that is logically available to a processor in a general-purpose graphics processing unit (GPGPU) module is increased to accommodate terabyte-sized amounts of data by utilizing the memory space in an external memory module, and by further utilizing a portion of the memory space in a number of other external memory modules.

Abstract: A number of domain specific accelerators (DSA1-DSAn) are integrated into a conventional processing system (100) to operate on the same chip by adding additional instructions to a conventional instruction set architecture (ISA), and further adding an accelerator interface unit (130) to the processing system (100) to respond to the additional instructions and interact with the DSAs.

Abstract: An input weight pattern of a machine learning model may be received. The input weight pattern may be pruned to produce an output weight pattern based on a predetermined pruning algorithm. The pruning algorithm may include partitioning the input weight pattern into a plurality of sub-patterns, each row of the input weight pattern including sub-rows of a first number of sub-patterns, and each column of the input weight pattern including sub-columns of a second number of sub-patterns; and pruning sub-columns and sub-rows from the plurality of sub-patterns to achieve predetermined column and row sparsities respectively, with a constraint that at least one sub-row in each row of the input weight pattern is not pruned. The output weight pattern may further be compressed to produce a compact weight pattern. The compact weight pattern has lower memory and computational overheads as compared to the input weight pattern for the machine learning model.

Abstract: Aspects of the present technology are directed toward three-dimensional (3D) stacked processing systems characterized by high memory capacity, high memory bandwidth, low power consumption and small form factor. The 3D stacked processing systems include a plurality of processor chiplets and input/output circuits directly coupled to each of the plurality of processor chiplets.

Abstract: A layered-oxide positive electrode active material may have a molecular formula of NaxMnaFebNicMdNeO2-?Qf, where a doping element M is selected from at least one of Cu, Li, Ti, Zr, K, Sb, Nb, Mg, Ca, Mo, Zn, Cr, W, Bi, Sn, Ge, or Al, a doping element N is selected from at least one of Si, P, B, S, or Se, a doping element Q is selected from at least one of F, Cl, or N, 0.66?x?1, 0<a?0.70, 0<b?0.70, 0<c?0.23, 0?d<0.30, 0?e?0.30, 0?f?0.30, 0???0.30, a+b+c+d+e=1, 0<e+f?0.30, 0<(e+f)/a?0.30, 0.20?d+e+f?0.30, and (b+c)/a?1.5.

Abstract: A system-in-package architecture in accordance with aspects includes a logic die and one or more memory dice coupled together in a three-dimensional slack. The logic die can include one or more global building blocks and a plurality of local building blocks. The number of local building blocks can be scalable. The local building blocks can include a plurality of engines and memory controllers. The memory controllers can be configured to directly couple one or more of the engines to the one or more memory dice. The number and type of local building blocks, and the number and types of engines and memory controllers can be scalable.