Abstract: Various embodiments include methods and devices for implementing decompression of compressed high dynamic ratio fields. Various embodiments may include receiving compressed first and second sets of data fields, decompressing the first and second compressed sets of data fields to generate first and second decompressed sets of data fields, receiving a mapping for mapping the first and second decompressed sets of data fields to a set of data units, aggregating the first and second decompressed sets of data fields using the mapping to generate a compression block comprising the set of data units.

Abstract: Various embodiments include methods and devices for implementing decompression of compressed high dynamic ratio fields. Various embodiments may include receiving compressed first and second sets of data fields, decompressing the first and second compressed sets of data fields to generate first and second decompressed sets of data fields, receiving a mapping for mapping the first and second decompressed sets of data fields to a set of data units, aggregating the first and second decompressed sets of data fields using the mapping to generate a compression block comprising the set of data units.

Abstract: Systems and methods are disclosed method for controlling instantaneous current changes in parallel processors with arrays of parallel computing elements, such as neural processors. An exemplary method comprises monitoring the array of computing elements and determining a transition from a first activity level of the array to a second activity level of the array, such as an idle-to-active or active-to-idle transition. Once a transition is determined, the array is selectively controlled to minimize the instantaneous current change from the transition from the first activity level to the second activity level.

Abstract: Various embodiments include methods and devices for implementing compression of high dynamic ratio fields. Various embodiments may include receiving a compression block having data units, receiving a mapping for the compression block, wherein the mapping is configured to map bits of each data unit to two or more data fields to generate a first set of data fields and a second set of data fields, compressing the first set of data fields together to generate a compressed first set of data fields, and compressing the second set of data fields together to generate a compressed second set of data fields.

Abstract: Various embodiments include methods and devices for implementing compression of high dynamic ratio fields. Various embodiments may include receiving a compression block having data units, receiving a mapping for the compression block, wherein the mapping is configured to map bits of each data unit to two or more data fields to generate a first set of data fields and a second set of data fields, compressing the first set of data fields together to generate a compressed first set of data fields, and compressing the second set of data fields together to generate a compressed second set of data fields.

Abstract: Systems and methods are disclosed method for controlling instantaneous current changes in parallel processors with arrays of parallel computing elements, such as neural processors. An exemplary method comprises monitoring the array of computing elements and determining a transition from a first activity level of the array to a second activity level of the array, such as an idle-to-active or active-to-idle transition. Once a transition is determined, the array is selectively controlled to minimize the instantaneous current change from the transition from the first activity level to the second activity level.

Abstract: Methods and systems are disclosed for full-hardware management of power and clock domains related to a distributed virtual memory (DVM) network. An aspect includes transmitting, from a DVM initiator to a DVM network, a DVM operation, broadcasting, by the DVM network to a plurality of DVM targets, the DVM operation, and, based on the DVM operation being broadcasted to the plurality of DVM targets by the DVM network, performing one or more hardware optimizations comprising: turning on a clock domain coupled to the DVM network or a DVM target of the plurality of DVM targets that is a target of the DVM operation, increasing a frequency of the clock domain, turning on a power domain coupled to the DVM target based on the power domain being turned off, or terminating the DVM operation to the DVM target based on the DVM target being turned off.

Abstract: Methods and systems are disclosed for full-hardware management of power and clock domains related to a distributed virtual memory (DVM) network. An aspect includes transmitting, from a DVM initiator to a DVM network, a DVM operation, broadcasting, by the DVM network to a plurality of DVM targets, the DVM operation, and, based on the DVM operation being broadcasted to the plurality of DVM targets by the DVM network, performing one or more hardware optimizations comprising: turning on a clock domain coupled to the DVM network or a DVM target of the plurality of DVM targets that is a target of the DVM operation, increasing a frequency of the clock domain, turning on a power domain coupled to the DVM target based on the power domain being turned off, or terminating the DVM operation to the DVM target based on the DVM target being turned off.

Abstract: A method and system for dynamic control of shared memory resources within a portable computing device (“PCD”) are disclosed. A limit request of an unacceptable deadline miss (“UDM”) engine of the portable computing device may be determined with a limit request sensor within the UDM element. Next, a memory management unit modifies a shared memory resource arbitration policy in view of the limit request. By modifying the shared memory resource arbitration policy, the memory management unit may smartly allocate resources to service translation requests separately queued based on having emanated from either a flooding engine or a non-flooding engine.

Abstract: A method and system for dynamic control of shared memory resources within a portable computing device (“PCD”) are disclosed. A limit request of an unacceptable deadline miss (“UDM”) engine of the portable computing device may be determined with a limit request sensor within the UDM element. Next, a memory management unit modifies a shared memory resource arbitration policy in view of the limit request. By modifying the shared memory resource arbitration policy, the memory management unit may smartly allocate resources to service translation requests separately queued based on having emanated from either a flooding engine or a non-flooding engine.

Abstract: Systems and methods for pre-fetching address translations in a memory management unit (MMU) are disclosed. The MMU detects a triggering condition related to one or more translation caches associated with the MMU, the triggering condition associated with a trigger address, generates a sequence descriptor describing a sequence of address translations to pre-fetch into the one or more translation caches, the sequence of address translations comprising a plurality of address translations corresponding to a plurality of address ranges adjacent to an address range containing the trigger address, and issues an address translation request to the one or more translation caches for each of the plurality of address translations, wherein the one or more translation caches pre-fetch at least one address translation of the plurality of address translations into the one or more translation caches when the at least one address translation is not present in the one or more translation caches.

Abstract: Providing memory management functionality using aggregated memory management units (MMUs), and related apparatuses and methods are disclosed. In one aspect, an aggregated MMU is provided, comprising a plurality of input data paths including each including plurality of input transaction buffers, and a plurality of output paths each including a plurality of output transaction buffers. Some aspects of the aggregated MMU additionally provide one or more translation caches and/or one or more hardware page table walkers The aggregated MMU further includes an MMU management circuit configured to retrieve a memory address translation request (MATR) from an input transaction buffer, perform a memory address translation operation based on the MATR to generate a translated memory address field (TMAF), and provide the TMAF to an output transaction buffer. The aggregated MMU also provides a plurality of output data paths, each configured to output transactions with resulting memory address translations.

Abstract: Systems and methods relate to performing address translations in a multithreaded memory management unit (MMU). Two or more address translation requests can be received by the multithreaded MMU and processed in parallel to retrieve address translations to addresses of a system memory. If the address translations are present in a translation cache of the multithreaded MMU, the address translations can be received from the translation cache and scheduled for access of the system memory using the translated addresses. If there is a miss in the translation cache, two or more address translation requests can be scheduled in two or more translation table walks in parallel.

Abstract: Aspects include computing devices, apparatus, and methods for accelerating distributive virtual memory (DVM) message processing in a computing device. DVM message interceptors may be positioned in various locations within a DVM network of a computing device so that DVM messages may be intercepted before reaching certain DVM destinations. A DVM message interceptor may receive a broadcast DVM message from first DVM source. The DVM message interceptor may determine whether a preemptive DVM message response should be returned to the DVM source on behalf of the DVM destination. When certain criteria are met, the DVM message interceptor may generate a preemptive DVM message response to the broadcast DVM message, and send the preemptive DVM message response to the DVM source.

Abstract: A comparand that includes a virtual address is received. Upon determining a match of the comparand to a burst entry tag, a candidate matching translation data unit is selected. The selecting is from a plurality of translation data units associated with the burst entry tag, and is based at least in part on at least one bit of the virtual address. Content of the candidate matching translation data unit is compared to at least a portion of the comparand. Upon a match, a hit is generated.

Abstract: Providing memory management unit (MMU) partitioned translation caches, and related apparatuses, methods, and computer-readable media. In this regard, an apparatus comprising an MMU is provided. The MMU comprises a translation cache providing a plurality of translation cache entries defining address translation mappings. The MMU further comprises a partition descriptor table providing a plurality of partition descriptors defining a corresponding plurality of partitions each comprising one or more translation cache entries of the plurality of translation cache entries. The MMU also comprises a partition translation circuit configured to receive a memory access request from a requestor. The partition translation circuit is further configured to determine a translation cache partition identifier (TCPID) of the memory access request, identify one or more partitions of the plurality of partitions based on the TCPID, and perform the memory access request on a translation cache entry of the one or more partitions.

Abstract: Methods and systems for pre-fetching address translations in a memory management unit (MMU) of a device are disclosed. In an embodiment, the MMU receives a pre-fetch command from an upstream component of the device, the pre-fetch command including an address of an instruction, pre-fetches a translation of the instruction from a translation table in a memory of the device, and stores the translation of the instruction in a translation cache associated with the MMU.

Abstract: Providing memory management unit (MMU) partitioned translation caches, and related apparatuses, methods, and computer-readable media. In this regard, an apparatus comprising an MMU is provided. The MMU comprises a translation cache providing a plurality of translation cache entries defining address translation mappings. The MMU further comprises a partition descriptor table providing a plurality of partition descriptors defining a corresponding plurality of partitions each comprising one or more translation cache entries of the plurality of translation cache entries. The MMU also comprises a partition translation circuit configured to receive a memory access request from a requestor. The partition translation circuit is further configured to determine a translation cache partition identifier (TCPID) of the memory access request, identify one or more partitions of the plurality of partitions based on the TCPID, and perform the memory access request on a translation cache entry of the one or more partitions.

Abstract: Methods and systems are disclosed for full-hardware management of power and clock domains related to a distributed virtual memory (DVM) network. An aspect includes transmitting, from a DVM initiator to a DVM network, a DVM operation, broadcasting, by the DVM network to a plurality of DVM targets, the DVM operation, and, based on the DVM operation being broadcasted to the plurality of DVM targets by the DVM network, performing one or more hardware optimizations comprising: turning on a clock domain coupled to the DVM network or a DVM target of the plurality of DVM targets that is a target of the DVM operation, increasing a frequency of the clock domain, turning on a power domain coupled to the DVM target based on the power domain being turned off, or terminating the DVM operation to the DVM target based on the DVM target being turned off.

Abstract: Aspects include computing devices, apparatus, and methods for accelerating distributive virtual memory (DVM) message processing in a computing device. DVM message interceptors may be positioned in various locations within a DVM network of a computing device so that DVM messages may be intercepted before reaching certain DVM destinations. A DVM message interceptor may receive a broadcast DVM message from first DVM source. The DVM message interceptor may determine whether a preemptive DVM message response should be returned to the DVM source on behalf of the DVM destination. When certain criteria are met, the DVM message interceptor may generate a preemptive DVM message response to the broadcast DVM message, and send the preemptive DVM message response to the DVM source.