Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: The present disclosure relates to a method of managing requests to a key-value database. A non-limiting example of the method includes receiving a request that includes a number of keys. The number of keys can be compared with a first threshold number and second threshold number. If the number of keys exceeds the first threshold number, the request can be split. If the number of keys is smaller than the second threshold number, the request can be merged with at least one previous or subsequent request. Requests resulting from the splitting and merging steps can be submitted to the key-value database for further processing of the submitted requests.

Abstract: A method for adjusting machine learning models in a system including a plurality of devices is suggested. The method includes providing a system including a plurality of devices, wherein the devices have computational resource capacities; providing one or more machine learning tasks; providing a repository of ML models for the one or more tasks, wherein a plurality of the ML models of a single task solve the same task with different computational resources requirements and different quality metrics; selecting a device of the plurality of devices of the system to execute a task, wherein the selected device has available computational resource capacities; and selecting, from the repository of ML models of the task to be executed, one of the ML models, wherein the computational resources requirements of the selected ML model do not exceed the available computational resource capacities of the selected device. Systems configured to perform the methods as disclosed herein are also suggested.

Abstract: A method for allocating fog applications in a fog network with a plurality of fog nodes is suggested. The method includes: providing an application model; providing a fog network image that reflects the properties of the fog network; performing a resource usage test of the application model on the fog network image, and receiving resource requirements for the fog network; creating a concrete application model based on the application model, wherein the concrete application model contains the received resource requirements; and performing allocation of the concrete application model on one or more of the fog nodes of the fog network.

Abstract: A method for detecting system problems in a distributed control system including a plurality of computational devices is suggested. The method includes:—deploying one or more software agents on one or more devices of the system;—monitoring, via the one or more software agents, a system configuration and/or a system functionality;—detecting a problem in the monitored system configuration and/or a system functionality;—adding one or more new software agents and deploying the one or more new software agents on one or more devices of the system associated with the problem;—collecting data associated with the problem, via the added software agents.

Abstract: Embodiments include pre-processing work items to be processed by computerized processing elements. Aspects include accessing a performance index, which relates to (dynamic) processing performances of work items as processed by the computerized processing elements. Aspects also include determining a time interval (during which the receiver may group queued work items into a block, according to the accessed performance index. Aspects further includes setting a timer to the determined time interval, to allow the receiver to group work items being queued until that time interval has elapsed, according to the timer set. As a result, a block of grouped work items will be obtained, which can then be passed to a scheduler for subsequent processing by computerized processing elements.

Abstract: Embodiments of the invention provide a computer-implemented method for managing cryptographic objects in a key management system. This system comprises a set of one or more hardware security modules (HSMs), as well as clients interacting with the HSMs on behalf of users who interact with the clients. The method comprises monitoring, for each HSM of the set, an entropy pool and/or a load at each HSM. The entropy pool of a HSM is the entropy that is available at this HSM for generating cryptographic objects. The load induced at a HSM is the load due to the users interacting with the clients to obtain cryptographic objects. Cryptographic objects are generated, at each HSM, according to the monitored entropy pool and/or load. The extent to which such objects are generated depends on the monitored entropy pool and/or load.

Abstract: Embodiments include pre-processing work items to be processed by computerized processing elements. Aspects include accessing a performance index, which relates to (dynamic) processing performances of work items as processed by the computerized processing elements. Aspects also include determining a time interval (during which the receiver may group queued work items into a block, according to the accessed performance index. Aspects further includes setting a timer to the determined time interval, to allow the receiver to group work items being queued until that time interval has elapsed, according to the timer set. As a result, a block of grouped work items will be obtained, which can then be passed to a scheduler for subsequent processing by computerized processing elements.

Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: Embodiments include pre-processing work items to be processed by computerized processing elements. Aspects include accessing a performance index, which relates to (dynamic) processing performances of work items as processed by the computerized processing elements. Aspects also include determining a time interval (during which the receiver may group queued work items into a block), according to the accessed performance index. Aspects further includes setting a timer to the determined time interval, to allow the receiver to group work items being queued until that time interval has elapsed, according to the timer set. As a result, a block of grouped work items will be obtained, which can then be passed to a scheduler for subsequent processing by computerized processing elements.

Abstract: A plurality of requests are received for computing processing. At least some of the plurality of requests are replicated. The requests are replicated based on a fractional replication factor. Each received request and each replicated request are transmitted to a computer resource for processing. At least some embodiments provide the capability for meeting tail latency targets with improved performance and reduced cost.

Abstract: The present disclosure relates to a method of managing requests to a key-value database. A non-limiting example of the method includes receiving a request that includes a number of keys. The number of keys can be compared with a first threshold number and second threshold number. If the number of keys exceeds the first threshold number, the request can be split. If the number of keys is smaller than the second threshold number, the request can be merged with at least one previous or subsequent request. Requests resulting from the splitting and merging steps can be submitted to the key-value database for further processing of the submitted requests.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: Embodiments of the invention provide a computer-implemented method for managing cryptographic objects in a key management system. This system comprises a set of one or more hardware security modules (HSMs), as well as clients interacting with the HSMs on behalf of users who interact with the clients. The method comprises monitoring, for each HSM of the set, an entropy pool and/or a load at each HSM. The entropy pool of a HSM is the entropy that is available at this HSM for generating cryptographic objects. The load induced at a HSM is the load due to the users interacting with the clients to obtain cryptographic objects. Cryptographic objects are generated, at each HSM, according to the monitored entropy pool and/or load. The extent to which such objects are generated depends on the monitored entropy pool and/or load.

Abstract: A method for coordinating cache and memory reservation in a computerized system includes identifying at least one running application, recognizing the at least one application as a latency-critical application, monitoring information associated with a current cache access rate and a required memory bandwidth of the at least one application, allocating a cache partition, a size of the cache partition corresponds to the cache access rate and the required memory bandwidth of the at least one application, defining a threshold value including a number of cache misses per time unit, determining a reduction of cache misses per time unit, in response to the reduction of cache misses per time unit being above the threshold value, retaining the cache partition, assigning a priority of scheduling memory request including a medium priority level, and assigning a memory channel to the at least one application to avoid memory channel contention.

Abstract: Congestion management for data traffic in a virtual domain identifies a congestion source and sends a message to the source to adjust data traffic rates. The source may be a virtual machine hosted by a physical server with one or more virtual servers incorporated. A congestion manager may identify the source and send the message to the source without affecting other data sources hosted by the physical server or the virtual servers. In some embodiments, information about the congestion source may be encapsulated in a packet payload readable only by the congestion source so only the congestion source receives the instruction to adjust the transmission rate.