Abstract: Described herein is a network fabric including a plurality of graphical processing unit (GPU) clusters that are communicatively coupled with one another via a plurality of switches arranged in a hierarchical structure including a first tier of switches, a second tier of switches, and a third tier of switches. One or more switches are selected from the third tier of switches to form a set of target switches, where each target switch receives address information of each GPU included in the plurality of GPU clusters. Each target switch generates, a plurality of sets of address information by filtering received address information based on a condition and transmits the plurality of sets of address information to each switch included in the first tier of switches, wherein the switch stores a subset of the plurality of sets of address information in accordance with the condition.

Abstract: Each host machine of a plurality of host machines stores hierarchical locality information for the host machine that identifies at least a rack comprising the host machine, and a block of a plurality of blocks hosting the rack. The host machine is associated with one or more graphical processing units (GPUs), and wherein GPUs included in a first block operate at a first speed and GPUs included in a second block operate at a second speed that is different than the first speed. Responsive to receiving a request requesting execution of a workload, one or more host machines are identified as being available for executing the workload, and the hierarchical locality information and linkage information of the one or more host machines is provided in response to the request.

Abstract: Methods and systems are provided for controlling fueling and mitigating knock in internal combustion engines, such as multi-fuel engines. In one example, a method may include monitoring a frequency of knock events corresponding to one or more engine cylinders, and dynamically increasing a substitution ratio while the frequency of knock events is less than a maximum action threshold. In some examples, the method may further include actively adjusting one or more engine operating conditions to decrease the substitution ratio responsive to a severity of knocking in the one or more engine cylinders being greater than or equal to a threshold severity.

Abstract: A plurality of GPU clusters are communicatively coupled with one another via a plurality of network devices arranged in a hierarchical structure, wherein the GPU clusters includes at least a first GPU cluster operating at a first speed and a second GPU cluster operating at a second speed that is different than the first speed. A routing policy is configured for each network device, wherein the configuring includes establishing a mapping of each incoming port-link of the network device to a unique outgoing port-link of the network device. For a packet transmitted by a GPU of a host machine and received by a first network device, an incoming port-link of the first network device is determined on which the packet was received and based on the configuring, an outgoing port-link is identified that corresponds to the incoming port-link. The packet is forwarded on the outgoing port-link of the network device.

Abstract: Described herein is a network fabric including a plurality of graphical processing unit (GPU) clusters. The plurality of GPU clusters includes at least a first GPU cluster operating at a first speed and a second GPU cluster operating at a second speed that is different than the first speed. The network fabric includes a plurality of blocks, wherein each block includes: (a) one or more racks that host a GPU cluster, and (b) a plurality of switches arranged in a hierarchical structure that communicatively couple the block to other blocks included in the network fabric. Responsive to receiving a request to execute a workload, allocating one or more GPUs from the plurality of GPU clusters to execute the workload.

Abstract: Provided is a system and method for stake-prioritized serving of utility in a network of a plurality of servers, with stake verification on a proof-of-stake blockchain. For stake-controlled inflation the utility may be validated in a plurality of validators that set stake-weighted utility assessment values for each utility server registered on the blockchain, where a consensus calculator may determine a relative utility measure and level of agreement and adjusts the next block reward so that servers obtain inflation in proportion to their level of agreed utility. New servers and validators may register and may thereby activate stake in the utility network by solving a proof-of-work challenge verified on the blockchain, after which servers can serve utility and validators can validate utility and influence blockchain inflation distribution.

Abstract: A panel system includes a chassis holding one or more tray arrangements, which are each configured to receive one or more cassettes at two or more bays. The tray arrangements and cassettes cooperate to define a cassette sensor arrangement and a port occupancy sensor arrangement having separate interface points. The cassette sensor arrangement may include electronic memory storing physical layer information about the cassette. All active components of the port occupancy sensor arrangement are disposed on the tray while the electronic memories of the cassette sensor arrangement are stored on the cassettes.

Abstract: The present invention provides a system for retailers to monitor and track customer interaction with a product in a retail environment. The system of the present invention utilizes RFID tagged products and communicating with near field communication in an Internet of Things environment for a more comprehensive relationship between customers and the products of interest. Where the products are not so connected, the system of the present invention alerts the need for same.

Abstract: A rotary impact tool includes a motor housing, an electric motor supported in the motor housing, and a drive assembly for converting a continuous torque input from the motor to consecutive rotational impacts upon a workpiece. The drive assembly includes an anvil including an anvil lug and a hammer that is both rotationally and axially movable relative to the anvil. The hammer includes a hammer lug for imparting the consecutive rotational impacts upon the anvil lug. The rotary impact tool further comprises a printed circuit board assembly including a sensor that is configured to detect rotation of the anvil. The printed circuit board assembly is spaced from the anvil to define an axial gap therebetween.

Abstract: The presently disclosed subject matter relates to multi-material electrical contacts, and methods of making multi-material electrical contact comprising a functionally graded monolithic structure, having a first metal and a second metal, an amount of the second metal as compared to an amount of the first metal increases with distance in the structure from a first surface to a second opposing surface of the structure such that the second metal content increases continuously or incrementally throughout the height of the electrical contact.

Abstract: Discussed herein is a framework that provisions for customized processing for different classes of traffic. A network device in a communication path between a source host machine and a destination host machine extracts a tag from a packet received by the network device. The packet originates at a source executing on the source host machine and whose destination is the destination host machine. The tag set by the source and indicative of a first traffic class to be associated with the packet, the first traffic class being selected by the source from a plurality of traffic classes. The network device determines, based on the tag, that the first traffic class corresponds to a latency sensitive traffic and processes the packet using one or more settings configured at the network device for processing packets associated with the first traffic class.

Abstract: Technologies are described for cost based management of cache entries stored in a computer memory. In one example, a plurality of cache entries may be stored at a cache in a computer memory and the cache entries may have a cost measure associated with individual cache entries. A cost measure may represent a computing cost of an application to generate a cache entry. An incoming cache entry may be received at the cache, where the incoming cache entry has a cost measure associated with the incoming cache entry. In response to receiving the incoming cache entry, a cache entry that has a lower cost measure than the cost measure for other cache entries may be identified for eviction from the cache. The cache entry identified for eviction may be evicted from the cache, and the incoming cache entry may be written into the cache stored in the computer memory.

Abstract: A service engine determines whether there is a potential lack of transaction tax compliance in a plurality of jurisdictions for a plurality of entities. The service engine generates and/or transmits tax compliance data which may include information about potential lack of tax compliance of an entity in various jurisdictions based on rules about establishing nexus for purposes of remitting transaction tax in the jurisdictions. The tax compliance data may include a notification about the generation of the information, such as a notification to the entity that there exists a potential lack of tax compliance of that entity in specific jurisdictions. The service engine may update the tax compliance data dynamically and send corresponding notifications, automatically in real time or near real time for the applicable entity as sales of the entity change and/or rules for establishing nexus change for various jurisdictions.

Abstract: A microscope mounting system includes a sample holder shaped and configured to fit a particular horizontal microscope stage and fix one end of a soft material sample. A blade holder configured to position a cutting blade and connect directly or eventually to the particular microscope or a frame of the particular microscope. A load measurement device is configured to determine a load applied to the cutting blade. A precision adjustment assembly sets positioning of the cutting blade in the horizontal x-y plane and the z vertical plane such that a cutting edge of the cutting blade can be positioned at a focal point of the particular microscope. At least two grips are configured to grip a second end of the soft material sample at at least two discrete locations on opposite sides of the cutting blade when the blade contacts the soft material sample at the focal point. A tension mechanism can apply tension in the x-y plane to each of the at least two grips.

Abstract: Discussed herein is a framework that provisions for customized processing for different classes of traffic. A network device in a communication path between a source host machine and a destination host machine extracts a tag from a packet received by the network device. The packet originates at a source executing on the source host machine and whose destination is the destination host machine. The tag set by the source and indicative of a first traffic class to be associated with the packet, the first traffic class being selected by the source from a plurality of traffic classes. The network device determines, based on the tag, that the first traffic class corresponds to a bandwidth sensitive traffic and processes the packet using one or more settings configured at the network device for processing packets associated with the first traffic class.

Abstract: Discussed herein is a framework that provisions for customized processing for different classes of traffic. A network device in a communication path between a source host machine and 5 a destination host machine extracts a tag from a packet received by the network device. The packet originates at a source executing on the source host machine and whose destination is the destination host machine. The tag set by the source and indicative of a first traffic class to be associated with the packet, the first traffic class being selected by the source from a plurality of traffic classes. The network device determines the first traffic class based on the tag extracted from the packet and 10 processes the packet based on the first traffic class.

Abstract: An apparatus for producing pozzolanic material from consumer waste includes a glass separator unit to remove glass material from the waste and a size reduction unit downstream the glass separator unit. The glass separator unit includes a tubular outer member and an inner helical member extending inwardly from the inner surface of the tubular outer member and defining an open central bore. The tubular outer member and the open central bore define respective coaxial longitudinal axes that are disposed at an angle relative to a horizontal reference plane, with the inlet higher than the outlet. Non-glass/non-ceramic material is output through the open outlet end of tubular outer member utilizing a flow of water. The glass/ceramic material is output to the size reduction unit through the open inlet end of the tubular outer member utilizing the rotating inner helical member of the glass separator unit.

Abstract: A unique design is provided that increases the strength and extends the life of an asphalt saw blade. The asphalt saw blade may include a main body, outer plates and cutter assemblies that are secured to the main body and outer plates. The cutter assemblies can include a front cutter component and a rear cutter component that interlock. The front cutter component may include cutting elements and a plate that reinforces the cutting elements while also shielding the front cutter component's main body from wear. The rear cutter component may also include cutting elements.

Abstract: Discussed herein is a routing mechanism for graphical processing units (GPUs) that are hosted on several host machines in a cloud environment. For a packet transmitted by a GPU of a host machine and received by a network device, the network device determines an incoming port-link of the network device on which the packet was received. The network device obtains a flow information associated with the packet, and computes, based on the flow information, an outgoing port-link of the network device in accordance with a hashing algorithm. The hashing algorithm is configured to hash packets received on a particular incoming port-link of the network device to be transmitted on a same outgoing port-link of the network device. The network device forwards the packet on the outgoing port-link of the network device.