A data access system including a processor and a storage system including a main memory and a cache module. The cache module includes a FLC controller and a cache. The cache is configured as a FLC to be accessed prior to accessing the main memory. The processor is coupled to levels of cache separate from the FLC. The processor generates, in response to data required by the processor not being in the levels of cache, a physical address corresponding to a physical location in the storage system. The FLC controller generates a virtual address based on the physical address. The virtual address corresponds to a physical location within the FLC or the main memory. The cache module causes, in response to the virtual address not corresponding to the physical location within the FLC, the data required by the processor to be retrieved from the main memory.

Aspects of a storage device including a memory and a controller are provided which simplify controller management of logical and physical meta-dies and meta-blocks by allowing a logical meta-die to be mapped to multiple physical meta-dies. The memory includes first dies grouped in a first physical meta-die and second dies grouped in a second physical meta-die. The physical meta-dies each include physical meta-blocks. The controller maps a logical meta-die to the first physical meta-die and the second physical meta-die. The controller may also map logical meta-blocks of the logical meta-die to the physical meta-blocks. For instance, the controller may associate a first logical metablock of the logical meta-die to the first physical meta-die and a second logical metablock of the logical meta-die to the second physical meta-die. As a result, firmware complexity in managing meta-dies and meta-blocks may be reduced compared to one-to-one logical-to-physical meta-die mapping approaches.

In accordance with an embodiment, a communication method includes: receiving, by a first host, a memory access address sent by a network device, wherein the memory access address points to a memory unit in a first memory pool, the network device is connected to the first host, the network device is configured to switch and forward a service of the first host, and the network device is further configured to manage the first memory pool; and in response to memory of the first host satisfying a preset condition, accessing, by the first host, the memory unit based on the memory access address.

Apparatuses, systems, and techniques to execute one or more application programming interface (API) functions to facilitate parallel computing. In at least one embodiment, one or more APIs are to indicate whether one or more storage locations can be shared during performance of software using various novel techniques described herein.

Input data for a layer of a convolutional neural network (CNN) is provided by receiving input data values to be processed in a layer of the CNN. Addresses in banked memory of a buffer are determined in which the received data values are to be stored based upon format data indicating a format parameter of the input data in the layer and indicating a format parameter of a filter which is to be used to process the input data in the layer. The received input data values are stored at the determined addresses in the buffer for retrieval for processing in the layer.

A system and method for machine learning, with a processing circuit executing an operating system, the processing circuit being connected to a first memory and to a second memory. In some embodiments, the method includes: requesting, by a user level process, from the operating system, a first memory allocation from the first memory, the first memory allocation including a plurality of first segments, a first segment of the plurality of first segments having a size sufficient to store a data object of a first kind; determining, by the user level process, that a result of a first calculation will be a data object of the first kind; and in response to determining that the result of the first calculation will be a data object of the first kind: determining, by the user level process, that none of the first segments are unused.

An information processing apparatus including a memory and a memory controller writing data to the memory in response to a write for writing the data to the memory, in which the memory executes error correction processing for each data of a predetermined data length, and the memory controller executes, in place of the memory, read modify write processing in a case where a data length of the data related to the write instruction is smaller than the predetermined data length.

A high-bandwidth memory (HBM) includes a memory and a controller. The controller receives a data write request from a processor external to the HBM and the controller stores an entry in the memory indicating at least one address of data of the data write request and generates an indication that a data bus is available for an operation during a cycle time of the data write request based on the data write request comprising sparse data or data-value similarity. Sparse data includes a predetermined percentage of data values equal to zero, and data-value similarity includes a predetermined amount of spatial value locality of the data values. The predetermined percentage of data values equal to zero of sparse data and the predetermined amount of spatial value locality of the special-value pattern are both based on a predetermined data granularity.

Aspects of a storage device including a memory and a controller are provided which simplify controller management of logical and physical meta-dies and meta-blocks by allowing a logical meta-die to be mapped to multiple physical meta-dies. The memory includes first dies grouped in a first physical meta-die and second dies grouped in a second physical meta-die. The physical meta-dies each include physical meta-blocks. The controller maps a logical meta-die to the first physical meta-die and the second physical meta-die. The controller may also map logical meta-blocks of the logical meta-die to the physical meta-blocks. For instance, the controller may associate a first logical metablock of the logical meta-die to the first physical meta-die and a second logical metablock of the logical meta-die to the second physical meta-die. As a result, firmware complexity in managing meta-dies and meta-blocks may be reduced compared to one-to-one logical-to-physical meta-die mapping approaches.

A method for communicating between motorized power tools includes establishing, using a physical interface of a first power tool, a wireless radio link between the first power tool and a second power tool. The first power tool has a first motor and the second power tool has a second motor. A signal is received over the wireless radio link, via the physical interface, at the first power tool from the second power tool using a first wireless communication protocol. The signal includes an identifier. The second power tool is verified as authorized to send the signal to the first power tool based on the identifier. A tool component of the first power tool is controlled responsive to the signal.