A method is described, which includes receiving, by a memory subsystem, a memory command targeted at a memory array; determining, by the memory subsystem, if the memory command is a high priority memory command; and determining if the memory subsystem is processing any non-high priority memory commands. The memory subsystem enables a read page cache mode for processing the memory command in response to determining that (1) the memory command is a high priority memory command and (2) the memory subsystem is not processing any non-high priority memory commands Thereafter, the memory subsystem processes the memory command using the read page cache mode.

Systems and methods relate to a bus adapter for a storage network. The bus adaptor includes a context memory comprising a first storage for uncacheable exchange resource indicators (XRI) and a second storage for cacheable XRI. The bus adapter also includes a host backing store unit configured to provide access to the different tier memories present locally or externally in the host memory extension using several caching sub-units and with the capability of an optional pinning operation for the cacheable XRI based upon at least one of input/output phase, first in line up to a limit, a region of a virtual context address associated with the cacheable XRI indicators, a protocol associated with the cacheable XRI, a size of a transaction, or work queue information.

Systems and methods relate to a bus adapter for a storage network. The bus adaptor includes a context memory comprising a first storage for uncacheable exchange resource indicators (XRI) and a second storage for cacheable XRI. The bus adapter also includes a host backing store unit configured to provide access to the different tier memories present locally or externally in the host memory extension using several caching sub-units and with the capability of an optional pinning operation for the cacheable XRI based upon at least one of input/output phase, first in line up to a limit, a region of a virtual context address associated with the cacheable XRI indicators, a protocol associated with the cacheable XRI, a size of a transaction, or work queue information.

The present disclosure relates to a tensor-based optimization method for GPU memory management of deep learning, at least comprising steps of: executing at least one computing operation, which gets tensors as input and generates tensors as output; when one said computing operation is executed, tracking access information of the tensors, and setting up a memory management optimization decision based on the access information, during a first iteration of training, performing memory swapping operations passively between a CPU memory and a GPU memory so as to obtain the access information about the tensors regarding a complete iteration; according to the obtained access information about the tensors regarding the complete iteration, setting up a memory management optimization decision; and in a successive iteration, dynamically adjusting the set optimization decision of memory management according to operational feedbacks.

The present disclosure relates to a tensor-based optimization method for GPU memory management of deep learning, at least comprising steps of: executing at least one computing operation, which gets tensors as input and generates tensors as output; when one said computing operation is executed, tracking access information of the tensors, and setting up a memory management optimization decision based on the access information, during a first iteration of training, performing memory swapping operations passively between a CPU memory and a GPU memory so as to obtain the access information about the tensors regarding a complete iteration; according to the obtained access information about the tensors regarding the complete iteration, setting up a memory management optimization decision; and in a successive iteration, dynamically adjusting the set optimization decision of memory management according to operational feedbacks.

Methods, apparatus, systems and articles of manufacture are disclosed facilitate read-modify-write support in a coherent victim cache with parallel data paths. An example apparatus includes a random-access memory configured to be coupled to a central processing unit via a first interface and a second interface, the random-access memory configured to obtain a read request indicating a first address to read via a snoop interface, an address encoder coupled to the random-access memory, the address encoder to, when the random-access memory indicates a hit of the read request, generate a second address corresponding to a victim cache based on the first address, and a multiplexer coupled to the victim cache to transmit a response including data obtained from the second address of the victim cache.

Methods, apparatus, systems and articles of manufacture are disclosed facilitate read-modify-write support in a coherent victim cache with parallel data paths. An example apparatus includes a random-access memory configured to be coupled to a central processing unit via a first interface and a second interface, the random-access memory configured to obtain a read request indicating a first address to read via a snoop interface, an address encoder coupled to the random-access memory, the address encoder to, when the random-access memory indicates a hit of the read request, generate a second address corresponding to a victim cache based on the first address, and a multiplexer coupled to the victim cache to transmit a response including data obtained from the second address of the victim cache.

Techniques are disclosed for tracking memory page accesses in a unified virtual memory system. An access tracking unit detects a memory page access generated by a first processor for accessing a memory page in a memory system of a second processor. The access tracking unit determines whether a cache memory includes an entry for the memory page. If so, then the access tracking unit increments an associated access counter. Otherwise, the access tracking unit attempts to find an unused entry in the cache memory that is available for allocation. If so, then the access tracking unit associates the second entry with the memory page, and sets an access counter associated with the second entry to an initial value. Otherwise, the access tracking unit selects a valid entry in the cache memory; clears an associated valid bit; associates the entry with the memory page; and initializes an associated access counter.

A cache device may include a first cache including a first set and a plurality of ways corresponding to the first set, and a second cache including a second set and a plurality of ways corresponding to the second set. The second set is related with the first set depending on a vacancy of the ways of the first set.

A cache device may include a first cache including a first set and a plurality of ways corresponding to the first set, and a second cache including a second set and a plurality of ways corresponding to the second set. The second set is related with the first set depending on a vacancy of the ways of the first set.