Abstract: A modular pod for performing a brazing process includes a housing defining an interior thereof, a vacuum device in selective fluid communication with the interior of the housing with the vacuum device configured to selectively form a vacuum within the interior of the housing, a first energy source disposed external to the interior of the housing, and a first energy access feature provided through the housing. The first energy access feature forms a pathway for transferring energy from the first energy source to the interior of the housing for heating a workpiece disposed therein in accordance with the brazing process. A heat conductive gas is selectively fluidly communicated to the interior of the housing following formation of the vacuum therein with the heat conductive gas aiding in transferring heat energy to the workpiece during the brazing process.

Abstract: Provided is a disaggregated memory server, which in some examples is a rack-mounted hardware appliance comprising a pool of memory for allocation to memory clients. Examples of memory clients may include one or more rack-mounted computing devices co-located on a rack with the disaggregated memory server. The disaggregated memory server may be optimized for high-speed dynamic memory allocation to the other computing devices in the rack.

Abstract: A modular pod for performing a brazing process includes a housing defining an interior thereof, a vacuum device in selective fluid communication with the interior of the housing with the vacuum device configured to selectively form a vacuum within the interior of the housing, a first energy source disposed external to the interior of the housing, and a first energy access feature provided through the housing. The first energy access feature forms a pathway for transferring energy from the first energy source to the interior of the housing for heating a workpiece disposed therein in accordance with the brazing process. A heat conductive gas is selectively fluidly communicated to the interior of the housing following formation of the vacuum therein with the heat conductive gas aiding in transferring heat energy to the workpiece during the brazing process.

Abstract: Provided is a rack, comprising: a plurality of rack units; and a plurality of lockers each housing a different respective subset of the rack units, wherein respective lockers among the plurality comprise: a first respective barrier disposed between a respective pair of the rack units; a second respective barrier disposed between another respective pair of the rack units; a third respective barrier that is orthogonal to the first barrier and the second barrier, the third respective barrier being moveably or removably coupled to the rack; a respective volume configured to receive one or more computing devices; and a respective lock configured to secure the third respective barrier to the rack in the closed position when in a locked state.

Abstract: A high-density memory system includes at least one memory-dense compute unit with a printed circuit board (“PCB”) having a half-width one rack unit (“1U”) form factor, more than 20 memory module slots arranged depth-wise from a front to a rear of the PCB with a horizontal orientation that is parallel to the half-width 1U form factor, at least one processor positioned in between the memory module slots, a dripless connector with a first port that receives a cooling solution from a manifold of a cooling unit and a second port that returns the cooling solution into the manifold, tubing that extends the full length of the PCB from the first port past the memory module slots and the at least one processor and back to the second port, and cooling blocks that are located in between the memory module slots and that are connected to the tubing.

Abstract: Provided is a disaggregated memory server, which in some examples is a rack-mounted hardware appliance comprising a pool of memory for allocation to memory clients. Examples of memory clients may include one or more rack-mounted computing devices co-located on a rack with the disaggregated memory server. The disaggregated memory server may be optimized for high-speed dynamic memory allocation to the other computing devices in the rack.

Abstract: A vehicle, electric machine, and method of manufacturing an electric machine include a stator having teeth extending from a yoke portion toward a rotor and defining slots between adjacent teeth with windings positioned within the slots, wherein the slots are coated with an electrically insulating material having an arcuate surface exiting the slots and extending at least partially over the teeth on at least one end face of the stator to form a winding guide for bending/positioning the windings. The winding guide may be formed by a molded epoxy that replaces insulating paper slot liners while providing a template for forming the hairpin bends of end windings.

Abstract: A high-density memory system includes at least one memory-dense compute unit with a printed circuit board (“PCB”) having a half-width one rack unit (“1 U”) form factor, more than 20 memory module slots arranged depth-wise from a front to a rear of the PCB with a horizontal orientation that is parallel to the half-width 1 U form factor, at least one processor positioned in between the memory module slots, a dripless connector with a first port that receives a cooling solution from a manifold of a cooling unit and a second port that returns the cooling solution into the manifold, tubing that extends the full length of the PCB from the first port past the memory module slots and the at least one processor and back to the second port, and cooling blocks that are located in between the memory module slots and that are connected to the tubing.

Abstract: Provided is a rack, comprising: a plurality of rack units; and a plurality of lockers each housing a different respective subset of the rack units, wherein respective lockers among the plurality comprise: a first respective barrier disposed between a respective pair of the rack units; a second respective barrier disposed between another respective pair of the rack units; a third respective barrier that is orthogonal to the first barrier and the second barrier, the third respective barrier being moveably or removably coupled to the rack; a respective volume configured to receive one or more computing devices; and a respective lock configured to secure the third respective barrier to the rack in the closed position when in a locked state.

Abstract: A high-density memory system includes at least one memory-dense compute unit with a printed circuit board (“PCB”) having a half-width one rack unit (“1U”) form factor, more than 20 memory module slots arranged depth-wise from a front to a rear of the PCB with a horizontal orientation that is parallel to the half-width 1U form factor, at least one processor positioned in between the memory module slots, a dripless connector with a first port that receives a cooling solution from a manifold of a cooling unit and a second port that returns the cooling solution into the manifold, tubing that extends the full length of the PCB from the first port past the memory module slots and the at least one processor and back to the second port, and cooling blocks that are located in between the memory module slots and that are connected to the tubing.

Abstract: Provided is a rack, comprising: a plurality of rack units; and a plurality of lockers each housing a different respective subset of the rack units, wherein respective lockers among the plurality comprise: a first respective barrier disposed between a respective pair of the rack units; a second respective barrier disposed between another respective pair of the rack units; a third respective barrier that is orthogonal to the first barrier and the second barrier, the third respective barrier being moveably or removably coupled to the rack; a respective volume configured to receive one or more computing devices; and a respective lock configured to secure the third respective barrier to the rack in the closed position when in a locked state.

Abstract: A high-density memory system includes at least one memory-dense compute unit with a printed circuit board (“PCB”) having a half-width one rack unit (“1U”) form factor, more than 20 memory module slots arranged depth-wise from a front to a rear of the PCB with a horizontal orientation that is parallel to the half-width 1U form factor, at least one processor positioned in between the memory module slots, a dripless connector with a first port that receives a cooling solution from a manifold of a cooling unit and a second port that returns the cooling solution into the manifold, tubing that extends the full length of the PCB from the first port past the memory module slots and the at least one processor and back to the second port, and cooling blocks that are located in between the memory module slots and that are connected to the tubing.

Abstract: Provided is a process of managing rack-mounted computing devices in a data center with a distributed peer-to-peer management system, the process including: determining roles of data-center management computing devices in a distributed peer-to-peer data-center management system; receiving, via an out-of-band network, a data-center management command at a given data-center management computing device; distributing, based on at least some of the roles, via the out-of-band network, the data-center management command.

Abstract: The present disclosure relates to a system and method for reducing stabilization times. The system includes at least a device-under-test (DUT), a flow generator, and optionally a heat exchanger to accelerate the thermal stabilization of fluid in the DUT during and after it has been filled with test gas. This rapidly equilibrates the temperature of the fluid in the DUT to the heat exchange medium, thereby reducing temperature differentials. The reduced magnitude of the temperature differential reduces the flows associated with temperature change of the fluid due to this thermal stabilization. As a result, this allows the leak test measurement to be made in less time, or for more of the cycle time to be used for leak measurement and, thus increase the accuracy of the test measurement.

Abstract: Provided is a rack, comprising: a plurality of rack units; and a plurality of lockers each housing a different respective subset of the rack units, wherein respective lockers among the plurality comprise: a first respective barrier disposed between a respective pair of the rack units; a second respective barrier disposed between another respective pair of the rack units; a third respective barrier that is orthogonal to the first barrier and the second barrier, the third respective barrier being moveably or removeably coupled to the rack; a respective volume configured to receive one or more computing devices; and a respective lock configured to secure the third respective barrier to the rack in the closed position when in a locked state.

Abstract: Provided is a disaggregated memory server, which in some examples is a rack-mounted hardware appliance comprising a pool of memory for allocation to memory clients. Examples of memory clients may include one or more rack-mounted computing devices co-located on a rack with the disaggregated memory server. The disaggregated memory server may be optimized for high-speed dynamic memory allocation to the other computing devices in the rack.

Abstract: Provided is a process of managing rack-mounted computing devices in a data center with a distributed peer-to-peer management system, the process including: determining roles of data-center management computing devices in a distributed peer-to-peer data-center management system; receiving, via an out-of-band network, a data-center management command at a given data-center management computing device; distributing, based on at least some of the roles, via the out-of-band network, the data-center management command.

Abstract: A vehicle, electric machine, and method of manufacturing an electric machine include a stator having teeth extending from a yoke portion toward a rotor and defining slots between adjacent teeth with windings positioned within the slots, wherein the slots are coated with an electrically insulating material having an arcuate surface exiting the slots and extending at least partially over the teeth on at least one end face of the stator to form a winding guide for bending/positioning the windings. The winding guide may be formed by a molded epoxy that replaces insulating paper slot liners while providing a template for forming the hairpin bends of end windings.

Abstract: Provided is a disaggregated memory server, which in some examples is a rack-mounted hardware appliance comprising a pool of memory for allocation to memory clients. Examples of memory clients may include one or more rack-mounted computing devices co-located on a rack with the disaggregated memory server. The disaggregated memory server may be optimized for high-speed dynamic memory allocation to the other computing devices in the rack.

Abstract: Disclosed is a controller for a disaggregated memory device. The controller may receive a request to allocate memory of a specific size from the disaggregated memory device to a computing device, and may generate a memory block device in the specific size from a memory pool formed from physical memory modules configured on the disaggregated memory device. The controller may expose the memory block device to the computing device as a Non-Volatile Memory Express (“NVMe”) target device, and may control access to the memory block device by converting NVMe access requests in a first format from the computing device to access requests in a different second format supported by the memory block device.