Abstract: A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

Abstract: A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

Abstract: Examples of techniques for enabling a field programmable device on demand are disclosed. In one example implementation according to aspects of the present disclosure, a method may include: determining, by a processing device, whether to enable a disabled field programmable device; responsive to determining to enable the disabled field programmable device, identifying, by the processing device, the field programmable device from a plurality of disabled FPDs; sending an authorization request to an authorization authority to request an authorization to enable the disabled field programmable device; responsive to receiving the authorization from the authorization authority, enabling the disabled field programmable device as an enabled field programmable device; loading computer readable instructions to the enabled field programmable device; and bringing the enabled field programmable device online.

Abstract: Examples of techniques for resource sharing management of a field programmable device are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: selecting a job belonging to one of a plurality of tenants based on resource control; dispatching a job to the field programmable device, wherein the job is received at a processing device, and wherein the job comprises dispatchable units; performing, by the field programmable device, the dispatchable units belonging to the job; and tracking, by the processing device, processing statistics related to each of the plurality of virtual processing devices based on performing the dispatchable units belong to the job.

Abstract: Examples of techniques for service level management of a workload defined environment are disclosed. In one example implementation according to aspects of the present disclosure, a method may include: transmitting runtime workload data, a service level agreement, and workload metadata for a workload from the workload defined environment to a workload-to-hardware adapter; subsequent to transmitting the runtime workload data, the service level agreement, and the workload metadata for the workload to the workload-to-hardware adapter, performing, by a processing device, a determination of whether the workload satisfies the service level agreement; and responsive to the determination that the workload does not satisfy the service level agreement, initiating a performance adjustment to a processing system.

Abstract: Examples of techniques for utilizing a field programmable device binary to perform a workload are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: calling an application program interface to perform a workload; determining, by a processing device, using dynamic characteristics of the workload and a workload environment, whether the workload should be processed by a field programmable device or a software library running on the general purpose processing device; responsive to determining to process the job by the field programmable device, deploying the job to the field programmable device; and responsive to determining to process the job by a software library running on the general purpose processing device, deploying the job to the software library.

Abstract: Examples of techniques for reprogramming a field programmable device on demand are disclosed. According to aspects of the present disclosure, a computer-implemented method may include: identifying a first field programmable device as being over utilized; responsive to identifying the first field programmable device that is over utilized, identifying a second field programmable device that is underutilized; determining whether to reprogram the second field programmable device; responsive to determining to reconfigure the second field programmable device, stopping the second field programmable device from performing a workload; moving the workload to another field programmable device configured to perform the workload; and reprogramming the second field programmable device.

Abstract: Examples of techniques for enabling a field programmable device on demand are disclosed. In one example implementation according to aspects of the present disclosure, a method may include: determining, by a processing device, whether to enable a disabled field programmable device; responsive to determining to enable the disabled field programmable device, identifying, by the processing device, the field programmable device from a plurality of disabled FPDs; sending an authorization request to an authorization authority to request an authorization to enable the disabled field programmable device; responsive to receiving the authorization from the authorization authority, enabling the disabled field programmable device as an enabled field programmable device; loading computer readable instructions to the enabled field programmable device; and bringing the enabled field programmable device online.

Abstract: Examples of techniques for managing workload distribution based on field programmable devices are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: determining, by a processor, a first workload performance for a first general purpose processor and a first field programmable device for a first processing system; determining, by the processor, a second workload performance for a second general purpose processor and a second field programmable device for a second processing system; determining whether the first processing system is likely to outperform the second processing system for execution of a workload; and responsive to determining that the first processing system is likely to outperform the second processing system for the workload, deploying the workload to the first processing system.

Abstract: Examples of techniques for deploying a software library and a corresponding field programmable device binary are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: determining whether the software library and the field programmable device binary are available; determining whether to deploy the field programmable device binary to a field programmable device; determining whether to install the software library for use on a general purpose processor; responsive to determining to install the field programmable device binary to the field programmable device, deploying the field programmable device binary to the field programmable device; and responsive to determining to install the software library for use on the general purpose processor, installing the software library for use the general purpose processor.

Abstract: Examples of techniques for service level management of a workload defined environment are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: collecting runtime workload data for a workload executing within a container; performing, by a processing device, a determination of whether the runtime workload data satisfies a goal set forth in a service level agreement; responsive to determining that the runtime workload data does not satisfy the goal, providing data from within the container in a format utilized by an application program interface; and accessing the data from within the container through the application program interface from outside of the container.

Abstract: Examples of techniques for enabling a field programmable device on demand are disclosed. In one example implementation according to aspects of the present disclosure, a method may include: determining, by a processing device, whether to enable a disabled field programmable device; responsive to determining to enable the disabled field programmable device, identifying, by the processing device, the field programmable device from a plurality of disabled FPDs; sending an authorization request to an authorization authority to request an authorization to enable the disabled field programmable device; responsive to receiving the authorization from the authorization authority, enabling the disabled field programmable device as an enabled field programmable device; loading computer readable instructions to the enabled field programmable device; and bringing the enabled field programmable device online.

Abstract: Embodiments relate to facilitating a plurality of heterogeneous hosts to use a range of priority values. A method of facilitating a plurality of heterogeneous hosts to use a range of priority values is provided. The method retrieves a plurality of priority ranges from a plurality of network forwarding elements shared by a plurality of heterogeneous hosts. The network forwarding elements provide access to a set of storage devices that stores data for the plurality of heterogeneous hosts. The method generates, by a computer that comprises one of the heterogeneous hosts, a universal priority range from the plurality of priority ranges. The method maps a plurality of workloads performed by the computer to priority values in the universal priority range. The method sends the universal priority range to at least one other host of the heterogeneous hosts.

Abstract: A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

Abstract: A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

Abstract: Embodiments of the disclosure include systems for performing a data manipulation function. The method includes receiving, by a processor, a request from an application to perform the data manipulation function and based on determining that a specialized hardware device configured to perform the data manipulation function is available, the method includes determining if executing the request on the specialized hardware device is viable. Based on determining that the request is viable to execute on the specialized hardware device, the method includes executing the request on the specialized hardware device.

Abstract: Embodiments of the disclosure include methods, systems and computer program products for performing a data manipulation function. The method includes receiving, by a processor, a request from an application to perform the data manipulation function and based on determining that a specialized hardware device configured to perform the data manipulation function is available, the method includes determining if executing the request on the specialized hardware device is viable. Based on determining that the request is viable to execute on the specialized hardware device, the method includes executing the request on the specialized hardware device.

Abstract: Embodiments of the disclosure relate to testing a software interface for a streaming hardware device through simulation. Methods include receiving, by a processor, a data manipulation request and a data segment associated with the data manipulation request and generating, by the software interface, an input data stream comprising control information and the data segment. The method also includes transmitting the input data stream to a simulation device and generating, by the simulation device, an output data stream in response to the input data stream, the output data stream including a delineator, control data, a manipulated data segment and a trailing delineator. The simulation device is configured to simulate the operation of the streaming hardware device by performing the data manipulation request.

Abstract: Embodiments of the disclosure relate to testing a software interface for a streaming hardware device through simulation. Methods include receiving, by a processor, a data manipulation request and a data segment associated with the data manipulation request and generating, by the software interface, an input data stream comprising control information and the data segment. The method also includes transmitting the input data stream to a simulation device and generating, by the simulation device, an output data stream in response to the input data stream, the output data stream including a delineator, control data, a manipulated data segment and a trailing delineator. The simulation device is configured to simulate the operation of the streaming hardware device by performing the data manipulation request.

Abstract: Embodiments relate to providing a data stream interface for offloading the inflation/deflation processing of data to a stateless compression accelerator. An aspect includes transmitting a request to inflate or deflate a data stream to a compression accelerator. The request may include references to an input buffer for storing input data from the data stream, an output buffer for storing processed input data, and a state data control block for storing a stream state. The stream state is provided to the compression accelerator to continue processing the data stream responsive to the request being a subsequent request. The compression accelerator is instructed to store a current stream state in the state data control block responsive to the request being a non-final request. Accordingly, the current stream state is received from the compression accelerator responsive to the request being a non-final request. The processed input data is received from the compression accelerator.