Abstract: Designs for enabling safe insertion and removal of computing components from a live motherboard are presented herein. In one example, a method includes maintaining a slot power connection and an auxiliary power connection for a peripheral card slot in a powered-off state, and sensing insertion of a peripheral card into the peripheral card slot and responsively detecting whether the auxiliary power connection is employed by the peripheral card. Based on detecting the auxiliary power connection is employed by the peripheral card, the method further includes applying current limits selected for the peripheral card to the slot power connection and the auxiliary power connection and concurrently enabling the slot power connection and the auxiliary power connection for the peripheral card.

Abstract: Peer-to-peer arrangements between graphics processing units (GPUs) are provided herein. A method includes establishing synthetic devices representing GPUs in an address domain associated with a host processor, where the GPUs have a different address domain than the host processor. The method also includes forming a peer arrangement between the GPUs such that data transfers between the GPUs in the different address domain can be initiated by the host processor interfacing with the synthetic devices.

Abstract: Computing architectures, platforms, and systems are provided herein. In one example, system is provided. The system includes a first processor configured to initiate a communication arrangement between a first peripheral component interconnect express (PCIe) device and a second PCIe device. The communication arrangement is configured to detect transfers from the first PCIe device to one or more addresses corresponding to an address range of the second PCIe device, and redirect the transfers to the second PCIe device without passing the transfers through a second processor that initiates the transfers.

Abstract: Deployment of arrangements of physical computing components coupled over a communication fabric are presented herein. In one example, a method includes coupling into a communication fabric a plurality of communication interfaces provided by a baseboard hosting a plurality data processing devices. The method includes establishing a one-hop latency in the communication fabric between the plurality of data processing devices and peripheral card slots, and establishing a two-hop latency in the communication fabric between the plurality of data processing devices and additional peripheral card slots. The method also includes establishing interconnect pathways between a plurality of communication switches that provide the one-hop latency through one or more cross-connect communication switches that provide the two-hop latency.

Abstract: Software configuration deployment techniques for disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method includes presenting a user interface configured to receive instructions related to deployment of software to compute units, and receiving user selections of a software element for deployment to a compute unit comprising a processing element and a storage element.

Abstract: Designs for a rackmount chassis having multiple card slots are presented herein. In one example, an apparatus includes a chassis configured to mount into a server rack, including a plurality of peripheral card slots, and a plurality of status lights configured to provide indications of operational status for an associated slot. The chassis further includes switch circuitry, including at least three switch elements, configured to couple the slots, wherein a first portion of ports on each of the switch elements is coupled to corresponding slots, a second portion of the ports on each of the switch elements is coupled to external ports of the chassis, and a third portion of the ports on each of the switch elements is coupled to at least another among the switch elements. The chassis may further include a plurality of external ports on the chassis communicatively coupled to the slots through the switch circuitry.

Abstract: Deployment of arrangements of physical computing components coupled over a communication fabric are presented herein. In one example, a method includes receiving execution jobs directed to a computing cluster comprising a pool of computing components coupled to at least a communication fabric. Based on properties of the execution jobs, the method includes determining resource scheduling for handling the execution jobs, the resource scheduling indicating timewise allocations of resources of the computing cluster, and initiating the execution jobs on the computing cluster according to the resource scheduling by at least instructing the communication fabric to compose compute units comprising sets of computing components selected from among the pool of computing components to handle the execution jobs. Responsive to completions of the execution jobs, the compute units are decomposed back into the pool of computing components.

Abstract: Deployment of arrangements of physical computing components coupled over a communication fabric are presented herein. In one example, a method includes coupling into a communication fabric a plurality of communication interfaces provided by a baseboard hosting a plurality data processing devices. The method includes establishing a one-hop latency in the communication fabric between the plurality of data processing devices and peripheral card slots, and establishing a two-hop latency in the communication fabric between the plurality of data processing devices and additional peripheral card slots. The method also includes establishing interconnect pathways between a plurality of communication switches that provide the one-hop latency through one or more cross-connect communication switches that provide the two-hop latency.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating a data processing system is provided. The method includes instructing a PCIe fabric communicatively coupling a plurality of physical computing components including PCIe devices and one or more PCIe switches to establish a first PCIe communication path between the management processor and a target PCIe device. The method also includes directing at least configuration data to the target PCIe device using the first PCIe communication path and instructing the PCIe fabric to remove the first PCIe communication path between the management processor and the target PCIe device. The method also includes instructing the PCIe fabric to establish a second PCIe communication path between a selected PCIe device and the target PCIe device configured according to the configuration data.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method includes instructing a communication fabric to establish a first logical partition in the communication fabric that includes a first processing device and a memory device, and directing transfer of configuration data for storage by the memory device over the first logical partition. After transfer of the configuration data, the method includes instructing the communication fabric to remove the first logical partition in the communication fabric, where the configuration data remains stored by the memory device after removal of the first logical partition. The method also includes instructing the communication fabric to establish a second logical partition in the communication fabric that includes at least a second processing device and the memory device comprising the configuration data, where the second processing device is operated using the configuration data.

Abstract: A data system includes a plurality of storage drives each comprising a multi-lane serial drive interface. The data system also includes a control system configured to receive, over a host link, a write operation for storage of data, process a storage address of the write operation against storage allocation information to apportion the data for storage among more than one target storage drive, and transfer corresponding portions of the data to the target storage drives.

Abstract: Systems, methods, apparatuses, and software for computing systems are provided herein. In one example, a system includes processing modules each having a communication interface and a processor, and additional modules each having a communication interface. Communication switch circuitry is coupled to the communication interfaces of the processing modules and the communication interfaces of the additional modules, wherein the communication switch circuitry is configured to establish isolation among ports in the communication switch circuitry for one or more processing modules and one or more additional modules. At least one processor instantiates access to the one or more additional modules for the one or more processing modules over at least the isolation.

Abstract: Machine templates are described herein that provide for configuration and deployment of arrangements of physical computing components coupled over a communication fabric. A method includes presenting a user interface having indications of computing component types includable in a new template specifying at least an arrangement of physical computing components for inclusion in compute units. The method includes receiving selections made by a user for inclusion of selected physical computing component types within the new template, and determining properties of the selections to generalize an arrangement of the selected physical computing component types into a specification for the new template. The method includes storing the specification of the new template for subsequent usage in creation of a target compute unit based at least on the arrangement indicated by the new template.

Abstract: Deployment of arrangements of computing components coupled over communication fabrics are presented herein. In one example, a method includes forming a compute unit to include at least a selected disaggregated computing component and at least a selected converged computing element. The selected disaggregated computing component is added to the compute unit from a pool of disaggregated computing components having a granularity comprising the disaggregated computing components arbitrarily and separately coupled to a communication fabric. The selected converged computing element is added to the compute unit from a pool of converged computing elements having a granularity comprising sets of computing components with fixed relationships to associated processors.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method includes receiving user input to establish a compute unit comprising a host processor and at least two graphics processing units (GPUs) having a peer-to-peer capability. The method also includes instructing a management element for a communication fabric to form the compute unit and communicatively couple the host processor and the at least two GPUs over the communication fabric. The method also includes instructing the management element to establish an isolation function to form the peer arrangement between the at least two GPUs in the communication fabric, where the isolation function isolates a first address domain associated with the at least two GPUs from at least a second address domain associated with the host processor by at least establishing synthetic devices representing the at least two GPUs in the second address domain.

Abstract: Disaggregated computing architectures, platforms, and systems are provided herein. In one example, a method of operating compute units is presented that includes forming compute units among a plurality of physical computing components coupled over a Peripheral Component Interconnect Express (PCIe) fabric configured to communicatively couple the plurality of physical computing components and isolate the compute unit using logical partitioning within the PCIe fabric. The method also includes initiating a software component deployed to at least associated CPUs within the compute units, reporting telemetry to the management processor related to operation of the compute unit, and emulating operation of at least one among an Ethernet and InfiniBand interface to an operating system of the associated CPU for transfer of communications comprising at least the telemetry to the management processor over the PCIe fabric.

Abstract: Systems, methods, apparatuses, and software for computing systems are provided herein. In one example, a system includes a plurality of first modules each having a Peripheral Component Interconnect Express (PCIe) interface and a processor, and a plurality of second modules each having a PCIe interface. PCIe switch circuitry is coupled to the PCIe interfaces of the first modules and the PCIe interfaces of the second modules, wherein the PCIe switch circuitry is configured to establish logical isolation in the PCIe switch circuitry between one or more first modules and one or more second modules. At least one processor instantiates access to the one or more second modules for the one or more first modules over at least the logical isolation in the PCIe switch circuitry.

Abstract: Deployment of arrangements of physical computing components coupled over a communication fabric are presented herein. In one example, a method includes detecting disaggregated computing components communicatively coupled to at least a first communication fabric, and detecting converged computing components communicatively coupled to a second communication fabric. The method includes forming a free pool of computing components comprising the disaggregated computing components and the converged computing components, and receiving user commands to form compute units from among computing components included in the free pool of computing components. Based at least on the user commands, the method includes forming the compute units for use by one or more users.

Abstract: Machine templates are described herein that provide for enhanced configuration and deployment of arrangements of physical computing components coupled over a communication fabric. In one example, a method includes presenting a user interface indicating a plurality of templates each specifying at least a predefined arrangement of physical computing components for inclusion in compute units, and receiving a user selection indicating a selected template among the plurality of templates to form a target compute unit. The method includes allocating to the target compute unit a set of physical computing components according to the selected template, and instructing a management entity to establish the target compute unit based at least on logical partitioning within a communication fabric communicatively coupling the set of physical computing components of the target compute unit.

Abstract: Computing architectures, platforms, and systems are provided herein. In one example, system is provided. The system includes a first processor configured to initiate a communication arrangement between a first peripheral component interconnect express (PCIe) device and a second PCIe device. The communication arrangement is configured to detect transfers from the first PCIe device to one or more addresses corresponding to an address range of the second PCIe device, and redirect the transfers to the second PCIe device without passing the transfers through a second processor that initiates the transfers.