David E. Weekly

To reduce machine-to-machine latency, data centers are increasingly specified to have a high machine density. Per current practices, rack spacing is designed such that any machine in any rack can be serviced by humans. This limits the size and performance of a machine cluster. This disclosure describes data center configurations of high machine density, formed by arranging racks in tight two-dimensional or three-dimensional arrays. Provision is made to enable the lateral movement of racks… Show more

To reduce machine-to-machine latency, data centers are increasingly specified to have a high machine density. Per current practices, rack spacing is designed such that any machine in any rack can be serviced by humans. This limits the size and performance of a machine cluster. This disclosure describes data center configurations of high machine density, formed by arranging racks in tight two-dimensional or three-dimensional arrays. Provision is made to enable the lateral movement of racks. Machines are serviced by moving one or more racks up, down, or to the side, such that a temporary aisle is created leading to the rack under repair. A human or autonomous operator can reach the rack under repair via the temporary aisle. Once repair is completed, the aisle is closed. Show less

This disclosure addresses the problem of ranging or imaging a remote environment, e.g., a remote conference room, using audio equipment present at the remote location. Ultrasonic waves are transmitted, e.g., via standard telecommunication channels, from the near end to the remote location, and their reflections off objects at the remote location are received at the near end. The reflections are used to reconstruct the remote environment and form an ultrasonic signature. The techniques of this… Show more

This disclosure addresses the problem of ranging or imaging a remote environment, e.g., a remote conference room, using audio equipment present at the remote location. Ultrasonic waves are transmitted, e.g., via standard telecommunication channels, from the near end to the remote location, and their reflections off objects at the remote location are received at the near end. The reflections are used to reconstruct the remote environment and form an ultrasonic signature. The techniques of this disclosure can be used to secure a phone call, e.g., to verify the identity of the remote party; verify the remote location; differentiate humans from bots at the remote location; verify the number of individuals present at the remote location; verify the identity of the devices being used at the remote location; etc. In addition to ultrasonic waves, devices are remotely vibrated to characterize the surface on which the device rests. Show less

As Moore's law slows down, CPUs offer less annual incremental performance per watt, while demand continues to increase. To maintain economic computational performance in the face of increasing demand, data centers are deploying hardware accelerators specialized for particular tasks, e.g., machine vision, video compression, etc. Creating custom application specific integrated circuits (ASICs) for specialized tasks is expensive and requires a highly skilled team.

The techniques of this… Show more

As Moore's law slows down, CPUs offer less annual incremental performance per watt, while demand continues to increase. To maintain economic computational performance in the face of increasing demand, data centers are deploying hardware accelerators specialized for particular tasks, e.g., machine vision, video compression, etc. Creating custom application specific integrated circuits (ASICs) for specialized tasks is expensive and requires a highly skilled team.

The techniques of this disclosure describe a workload-identifying process that automatically identifies computational hotspots amenable to hardware acceleration. FPGA designs for such workloads may be machine generated. The FPGA design is tested, and if found worthy by the measure of economic return-on-investment (RoI), taped out as an ASIC. The RoI is fed back to the workload-identifying process, which uses such feedback to improve identification of economically relevant computational hotspots. Show less

This disclosure describes a system of ceiling mounted laser projectors that can display bright visual indications, e.g., arrows, of a path to direct users to a next work location. The techniques of this disclosure can be implemented in various ways. For example, the projected arrow can move as the user moves; a visual path is projected for the next few seconds of transit time or the whole of the path going to the next task; different shapes or colors are projected to indicate different workers… Show more

This disclosure describes a system of ceiling mounted laser projectors that can display bright visual indications, e.g., arrows, of a path to direct users to a next work location. The techniques of this disclosure can be implemented in various ways. For example, the projected arrow can move as the user moves; a visual path is projected for the next few seconds of transit time or the whole of the path going to the next task; different shapes or colors are projected to indicate different workers or tasks; etc. For different spaces, with different aspect ratios, different numbers of laser projectors may be installed. The techniques of this disclosure can also be used to illuminate the paths of Automated Guided Vehicles (AGV) or robots. Show less

This disclosure describes a rack transporter for relocating data center racks. The rack transporter includes a power source and provides network connectivity to a rack in active use during relocation of the rack. The rack transporter is moved to a current location of the rack and the rack is mounted onto the rack transporter. Electrical and network connections are established between the rack transporter and the rack. Upon successful verification of the electrical and network connections to the… Show more

This disclosure describes a rack transporter for relocating data center racks. The rack transporter includes a power source and provides network connectivity to a rack in active use during relocation of the rack. The rack transporter is moved to a current location of the rack and the rack is mounted onto the rack transporter. Electrical and network connections are established between the rack transporter and the rack. Upon successful verification of the electrical and network connections to the rack transporter, the rack is decoupled from local power and network connections. The rack transporter and mounted rack are moved to the target location. The rack is physically moved into place and connected to local power and network connections at the target location. Upon verification of local power and network connections at the target location, the power and network connections from the rack transporter are decoupled and the rack is unmounted from the rack transporter. Show less

A system is described that improves performance in processes that are resumed by providing a cache that stores information that can immediately be used by the process when the process resumes. A processor may store a snapshot of a cache for a process to memory when the process yields to another process. When performance of the process is later resumed on the processor, the processor may retrieve the cache for the process from the memory and then resume the process.

A hypervisor provides secure separation of multiple virtual machines on a device, thus removing conflicts when using the device for multiple purposes, including business and personal use. The hypervisor ensures security and privacy amongst the multiple virtual machines and prevents malicious attacks on one virtual machine from threatening another virtual machine. A switch provides a dedicated interface to the hypervisor, enabling secure switching between the multiple virtual machines. In… Show more

A hypervisor provides secure separation of multiple virtual machines on a device, thus removing conflicts when using the device for multiple purposes, including business and personal use. The hypervisor ensures security and privacy amongst the multiple virtual machines and prevents malicious attacks on one virtual machine from threatening another virtual machine. A switch provides a dedicated interface to the hypervisor, enabling secure switching between the multiple virtual machines. In addition, an indicator enables the hypervisor to identify an active virtual machine. Furthermore, the hypervisor hibernates inactive virtual machines in order to conserve power and provide another layer of protection against malicious attacks. Show less