Abstract: A rack and system for cooling computing devices such as in a data center is disclosed. In one embodiment, the rack supports a plurality of computing devices and comprises a plurality of planar annular sector or trapezoidal shelves, each having one or more positions for holding computing devices. A number of vertical supports may hold the shelves in a vertically spaced arrangement, and an air barrier may be affixed to the rack and have openings that permit exhaust air to flow from the computing devices through the air barrier into a hot aisle. The rack may be configured to be connected to other similar racks to form a vertical annular cylinder, which may be tapered, and the computing devices may be installed to discharge exhaust at an angle relative to a centerline of the vertical annular cylinder to improve airflow.

Abstract: A rack and system for cooling computing devices such as in a data center is disclosed. In one embodiment, the rack supports computing devices and comprises planar annular sector or trapezoidal shelves, each having one or more positions for holding computing devices. The rack may be configured to be connected to other similar racks to form a vertical geometric prism or annular cylinder, which may be tapered, and the computing devices may be installed to discharge exhaust at an angle. A number of vertical supports may hold the shelves in a vertically spaced arrangement to from a helix within the prism or cylinder. An air barrier may be affixed to the rack and have openings permitting exhaust air to flow from the computing devices through the air barrier. The helix formed by the shelves may channel the airflow generated by the computing devices into a vortex to improve cooling.

Abstract: A system and method for easily managing a data center with multiple computing devices such as cryptocurrency miners from different manufactures is disclosed. A first computer includes a management application to manage the selected computing devices and periodically read and store status information from them into a database. Controls are presented to enable selection of one or more of the devices and to apply an operating mode, including manual, semi-automatic, automatic, and intelligent modes. Machine learning may be used to determine recommended settings for the selected set of computing devices.

Abstract: A system and method for efficient (e.g., economical) computing in hybrid, plug-in hybrid, and electric vehicles is disclosed. A compute manager is configured to receive and schedule compute tasks for execution on computing cores in the vehicle to increase the usage of recaptured energy that would otherwise be wasted due to battery limitations. Vehicle status information such as current battery charge level and current route may be used to determine whether compute tasks can be beneficially executed.

Abstract: A system and method for managing large numbers of computing devices in a data center are disclosed. The computing devices are configured to flash their indicator lights in a pattern that encodes a device ID, and an image capture device such as a mobile phone or tablet captures the flashes in a series of images/video of the data center. The images/video are processed to create a three-dimensional (3D) model of the data center with computing device IDs positioned therein. The 3D model, including correctly positioned device ID indicators, can be rendered for the user of the mobile device to enable the user to more easily identify computing device locations.

Abstract: Systems and methods for cooling large numbers of computing devices in a data center are disclosed. The devices are positioned on shelves in racks and are connected via network switches. The computing devices are oriented so that their cooling fans all exhaust waste heat to one side of the rack into a hot aisle, and each position is offset from positions on neighboring shelves above and below the current shelf. The racks can be offset, or the positions within the racks can be offset. Each computing device on the rack can also be angled horizontally and or vertically to improve airflow. Multiple racks can be configured together into sloped regular polygons, with the interior forming the hot aisle, and deflectors can be installed to further improve airflow.

Abstract: An improved system and method for characterizing application performance are disclosed. The system may comprise a profiling module and a web service module. The profiling module may be configured to prompt the user to select a public mode or a private mode and specify software and hardware targets for profiling. Test results from profiling may be combined with historical data obtained from a web service module providing access to a database of historical profiling test results to create recommendations for improving performance. The profiling module may upload the test-generated data in public mode to the web service module for use in future execution cycles or keep them private if in private mode.

Abstract: A management device for managing a plurality of computing devices in a data center may comprise a network interface, a first module that periodically sends health status queries to the computing devices via the network interface, a second module configured to receive responses to the health status queries and collect and store health status data for the computing devices, a third module configured to create support tickets, and/or a fourth module configured to (i) create and periodically update a Cox proportional hazards (CPH) model based on the health status data; (ii) apply a deep neural network (DNN) to the input of the CPH model; (iii) determine a probability of failure for each computing device; (iv) compare each probability of failure with a threshold; and (v) cause the third module to generate a pre-failure support ticket for each computing device having determined probabilities of failure above the threshold.

Abstract: Systems and methods for cooling large numbers of computing devices in a data center are disclosed. The computing devices have cooling fans that can have their fan speed set by management instructions. The devices are mounted in racks in a two-dimensional array and connected via network switches with ports corresponding to their location in the racks. The computer devices are oriented so that their cooling fans all exhaust waste heat to one side of the rack. Instructions are sent to the computing devices to set one or more attributes such as fan speed, operating frequency and voltage according to one ore more patterns. The patterns can be linear or nonlinear and can be shifted, rotated, or changed over time periodically or based on temperature or other performance measurements from the computing devices.

Abstract: A system and method for managing large numbers of computing devices such as cryptocurrency miners in a data center are disclosed. A three-dimensional (3D) model of the data center is created using machine-readable codes. The 3D model includes device and bin location information. Status data is captured from the computing devices, associated with location, stored in a database, and used to populate the 3D model, which is rendered in various two-dimensional and 3D views to provide the user with information helpful in managing the data center.

Abstract: A system and method for efficiently creating and managing application instances in distributed computing systems is disclosed. Controls are presented for specifying an application for instantiation, a data file for use with the application, and a destination for results from the application. Based on user input, graphical representations of available system resources in the distributed computing system are presented along with a logical topology for application instance creation to permit efficient user mapping of application primitives to available system resources. To further improve the user's ability to map, a hierarchical presentation of nodes illustrating resource and interconnection attributes may also be presented, and an error checking process may be performed to detect problems and offer suggested corrections based on application requirements and performance data collected from prior application executions.

Abstract: Systems and methods for managing airflow for cooling computing devices (e.g. in a data center) in normal and cold environments are disclosed. In one embodiment, the method comprises positioning the computing devices on a plurality of racks with air barriers to create hot and cold aisles. The computing devices may be configured in a first mode to draw in cool air the cold aisles and exhaust heated air into the hot aisles. Temperatures in the cold aisles may be periodically measured. In response to temperatures below a predetermined threshold, one or more of the cold aisles may be converted into a temporary hot aisle by adjusting ventilation openings and configuring a subset of the computing devices to temporarily draw in warm air from the temporary hot aisle.

Abstract: A method for measuring airflow for a plurality of computing devices may include characterizing the fan performance of a selected computing device of the plurality of computing devices to provide characterized RPM information. Each of the computing devices may include a cooling fan configured to exhaust heat into a hot aisle. Each cooling fan may include a rotor and a tachometer. The method may also include connecting the computing devices via a network, distributing computing workloads to the plurality of computing devices, and/or performing work on the computing workloads on the plurality of computing devices. Additionally, the method may include reading RPM information from the selected computing device's fan's tachometer and/or comparing the read RPM information with the characterized RPM information to determine a backpressure value for the selected computing device. The power to the selected computing device's fan may be reduced prior to reading the RPM information.

Abstract: Systems, methods and apparatuses are disclosed for implementation and management of a dynamic compute and application marketplace. The dynamic computer marketplace system can coordinate access to one or more other computing resources, including on-premises computing resources, external (or off-premises) computing resources or a combination thereof. In various embodiments, the dynamic computer marketplace system advantageously can be used to facilitate inter-provider migration, transparent pricing, and/or competitive pricing, among other things.

Abstract: Systems and methods for managing airflow for cooling computing devices (e.g. in a data center) in normal and cold environments are disclosed. In one embodiment, the method comprises positioning the computing devices on a plurality of racks with air barriers to create hot and cold aisles. The computing devices may be configured in a first mode to draw in cool air the cold aisles and exhaust heated air into the hot aisles. Temperatures in the cold aisles may be periodically measured. In response to temperatures below a predetermined threshold, one or more of the cold aisles may be converted into a temporary hot aisle by adjusting ventilation openings and configuring a subset of the computing devices to temporarily draw in warm air from the temporary hot aisle.

Abstract: Systems and methods for cooling computing devices in a data center and measuring airflow are disclosed. The computing devices have cooling fans that can have their fan speed set by management instructions. The devices are mounted in racks between cold aisles and hot aisles and are connected via network switches. The computing devices are oriented so that their cooling fans operate to exhaust waste heat to one side of the rack. Measurement instructions are sent to selected computing devices to cause them to go into a lower power state that reduces or stops computational work and reduces electrical power to the cooling fan so that the fan does not spin based on the electromotive force and can instead spin in an opposite direction based on ambient airflow caused by the difference in air pressure from the hot aisle to the cold aisle.

Abstract: A system for cooling computing devices may include at least one facility, at least one cool air aisle disposed within the at least one facility, at least one hot air aisle, at least one air inlet, and at least one exhaust outlet. The system may also include a plurality of computing devices including a plurality of computing device fans arranged within the at least one cool air aisle. An internal air pressure within the at least one cool air aisle provided via the plurality of computing device fans may be lower than an external air pressure of the external environment. The plurality of computing device fans may be configured to provide sufficient airflow of outside air through the at least one facility to cool the plurality of computing devices.

Abstract: A system for cooling computing devices within a facility includes an air inlet that delivers cool air to a supply air space within the facility, an exhaust air damper that is configured to exhaust heated air from an exhaust air space within the facility, and computing devices that are arranged within the facility to at least partially partition the supply air space from the exhaust air space. The system also includes an air filter that is configured to filter the cool air and a mixing damper that is positioned within the interior space of the facility and that is operable to control an amount of exhaust air that is mixed with the cool air. The cool air and/or a portion of the exhaust air are used to cool the computing devices and airflow through the system is substantially driven by fans of the computing devices.

Abstract: A system and method for managing large numbers of computing devices in a data center are disclosed. The computing devices are configured to flash their indicator lights in a pattern that encodes a device ID, and an image capture device such as a mobile phone or tablet captures the flashes in a series of images/video of the data center. The images/video are processed to create a three-dimensional (3D) model of the data center with computing device IDs positioned therein. The 3D model, including correctly positioned device ID indicators, can be rendered for the user of the mobile device to enable the user to more easily identify computing device locations.