13 results about "Supercomputer" patented technology

An extension for a supercomputer rack, the extension including a reinforcement frame, defining a rectangular through-opening, and at least one fluidic connection support mounted to the reinforcement frame. The at least one fluidic connection support includes an upstream circuit, configured to convey a refrigerant liquid to a plurality of connectors configured to be each connected via a cold flexible manifold to a cooling circuit of a compute blade of a server, and a downstream circuit, configured to collect the heated refrigerant liquid having passed through a compute blade of a server via a hot flexible manifold and a plurality of collection connectors. The extension is configured to be positioned at a rear end of the rack.

Systems and methods for intelligent processing of requests in an artificial intelligence system, including receiving an incoming request at an AI broker, evaluating the incoming request to determine routing characteristics, selecting selected specialized language models from a plurality of specialized language models based on the routing characteristics, computing performance metrics for the one or more selected specialized language models, routing the incoming request to the selected specialized language models based on the performance metrics, and generating a final result by receiving and processing results from the selected specialized language models.

The ever increasing number of orbiting bodies in low Earth orbit has made it infeasible to calculate potential conjunctions between orbiting bodies more than a few days in advance, even with the aid of supercomputers. Disclosed embodiments utilize machine learning to predict potential conjunctions between orbiting bodies faster than state-of-the art systems by orders of magnitude. This enables potential conjunctions to be identified well in advance (e.g., 30 days or more), so that they may be prioritized (e.g., for fine calculations), visualized, and remediated (e.g., via control of the impacted satellites).

The application relates to a method and system for improving the speed of writing shared main memory critical resources in parallel by a new generation Shenwei many-core processor, which comprises the following steps: a slave core applies for a data space on its private local data memory; critical resource data in the main memory is copied to the respective private local data memory; each slave core performs read-write operation; each slave core initiates a reduction operation through a remote memory access (RMA) channel, wherein the reduction operation refers to performing certain aggregation function operation on the critical resource data in the private local data memory of the plurality of slave cores to obtain a final result; and the critical resource data in the private local data memory after the reduction operation is written back to the main memory through a direct memory access (DMA) channel. The method can effectively improve the speed of reading and writing the shared main memory critical resources by the slave core of the Shenwei many-core processor, and improve the performance and efficiency of the supercomputer.

The application relates to a big data quality control method, a system, a supercomputer and a computer readable storage medium, wherein the method comprises the following steps: a source data acquisition step of acquiring source data from a plurality of preset data sources; a knowledge graph construction step of constructing a knowledge graph based on the source data through knowledge extraction and data alignment, wherein the knowledge graph comprises entity data, relationship data, triple data and subgraph data; a quality control model construction step of configuring quality control parameters, constructing a quality evaluation dataset based on the quality control parameters and the knowledge graph, constructing a multi-modal end-to-end big data quality control model, training the quality control model by using the quality evaluation dataset, and using the trained quality control model to calculate and output a data confidence value based on input entity data, subgraph data and / or triple data. Through the application, big data quality control based on graph data is realized, and the domain expansion of the quality control method is improved.

The utility model discloses a supercomputer water cooling plate structure relates to water cooling plate field, including bottom frame and mainboard, bottom frame and mainboard are connected through the friction stir welding, the top of mainboard is installed with the mounting block, and the one side of mounting block is provided with the liquid inlet pipe, the both sides of mounting block are provided with the liquid outlet pipe, and the inside of mounting block is provided with two groups of through -hole, the inside of mainboard is provided with solution groove, the top of mainboard is provided with two groups of liquid hole. The utility model solves the higher cost problem of current bottom frame and mainboard when welding, and the bottom frame and mainboard are fixed through the friction stir welding mode, and the working efficiency of this mode is high, stable, low cost and environmental protection, replaces the fixing mode of traditional brazing, and through the solution groove and fin of setting, the coolant enters into the solution groove, and the contact area with liquid can be increased through the fin of setting, thereby better heat dissipation can be carried out, and the water cooling plate main body heat dissipation effect is better.

This utility model relates to the field of supercomputer cooling equipment technology, and more particularly to a single-phase liquid cooler cabinet, comprising: a cabinet body, the cabinet body having a primary chamber and at least one secondary chamber isolated from each other, the primary chamber being used to hold coolant and immerse a heat source; a heat exchange mechanism disposed in the secondary chamber, the heat exchange mechanism having an inlet pipe communicating with the primary chamber, an outlet pipe communicating with the primary chamber, and a heat exchanger and a liquid driving device connecting the inlet pipe and the outlet pipe; and a cover connected to the cabinet body, the cabinet body having an opening in at least one of the primary chambers, the cover being used for a sealed connection with the opening of the cover; wherein, the heat exchange mechanism is used to drive the coolant in the primary chamber to the heat exchanger for heat exchange before injecting it back into the primary chamber, thereby forming a cooling circulation loop. This utility model, through the above-described configuration, ensures the safe and long-term reliable operation of the liquid cooler cabinet.

A system and method for enhancing performance of h-LLMs including providing specialized h-LLMs specialized for different tasks and trained on a training dataset specific to the specific task to be performed by the specialized h-LLM, generating synthetic data by processing input prompts through the h-LLMs to produce synthetic outputs, feeding the synthetic data back to the specialize h-LLMs through a feedback loop process implemented in a cloud container environment, and performing model refinement on the specialized h-LLMs by retraining at least one specialized h-LLM using the synthetic data.

Systems, methods, and computer-readable media for using full waveform inversion for imaging surveyed media are provided. The full waveform inversion uses a Sifrian functional to fully leverage Hessian information and update a model by augmenting and assembling data derived from the Sifrian functional when equilibrated. The Sifrian inversion produces high resolution images of the surveyed medium typically only seen with full Hessian inversions and can produce such images without requiring supercomputer computation power or extremely long computation time

The application discloses a kind of based on supercomputer's full electromagnetic transient simulation batch impedance calculation method and system, belong to electric power system technical field.The method of the present application, including: the full electromagnetic transient simulation model of the power system to be measured is established, and according to example configuration batched calculation fault card, and generate fault card list;The fault card list is imported to supercomputer task call system, based on the supercomputer task call system, the fault card in the fault card list is parsed, generates simulation task, based on the simulation task, control the full electromagnetic transient simulation model carries out simulation, generates impedance calculation configuration file and simulation result file;The impedance calculation configuration file is parsed, and the simulation result file is read, generates zscoutput.txt file, the zscoutput.txt file is parsed, and the calculation result is output.The application ensures the accuracy of data extraction.

The application discloses a kind of server customization system and method based on supercomputer and AI cluster technology, it is related to server customization technical field, the application includes information acquisition module, hardware selection module, topology customization module and database, first according to the type of each hardware currently owned, the flowability of data under the combination of different types of each hardware and different connection relations, obtain the required type of each hardware of server, then analyze the best physical topology of different supercomputer and AI cluster load ratio, build physical topology matching table, then customize the physical topology of server, and real-time monitoring the load ratio of supercomputer and AI cluster in server during running, according to monitoring result and physical topology matching table, re-customize physical topology and adjust, guarantee the adjustability of physical topology, also guarantee the core performance and the stability of operation of server.

The application discloses a heterogeneous computing system and method of a computer, and relates to the technical field of supercomputers, wherein the heterogeneous computing system of the computer comprises: a register unit, which is used for determining a computing core and a target configuration register corresponding to the computing core based on a physical address of to-be-computed data corresponding to a heterogeneous computing task of a processor device, and allocating the to-be-computed data to the target configuration register; and a data read-write unit, which is used for allocating the to-be-computed data to a corresponding memory layer in a plurality of memory layers through a first cross switch based on the target configuration register, so as to drive a computing unit to execute a computing task according to the to-be-computed data corresponding to the plurality of memory layers. The problems of large data transmission delay and low memory utilization of a heterogeneous acceleration system in the prior art are solved, the technical effects of fully utilizing memory resources in a heterogeneous platform, improving the performance of data transmission between different computing units, and reducing the delay of data movement are achieved.