Abstract: A processor-implemented method includes allocating a user buffer and performing data read when starting data transmission in response to an application start signal, determining whether a memory usage pattern to occur in the data transmission is secured, providing a transmission order and memory information based on a result of the determination and the memory usage pattern, and transmitting data based on the transmission order and the memory information.

Abstract: An electronic device and method with task allocation are provided. The electronic device includes one or more processors configured to determine a target computing node to which a task is to be allocated among a plurality of computing nodes, based on a degradation degree of the plurality of computing nodes, and allocate the task to the target computing node, in which the plurality of computing nodes includes processing units of different types configured to execute the task.

Abstract: An electronic device includes: a host processor configured to: generate a memory group allocated to an expanded virtual memory in response to receiving memory usage information; determine a target memory group comprising a page on which a page fault has occurred among memory groups allocated to the expanded virtual memory, based on the memory usage information; and migrate the target memory group from one of a host memory, an accelerator memory, and a storage device, which comprises the target memory group, to either one of the host memory and the accelerator memory in which the page fault has occurred; and an accelerator configured to perform an operation using the accelerator memory, wherein the expanded virtual memory is a virtual single address space using the host memory, the accelerator memory, and the storage device.

Abstract: A processor-implemented method includes allocating tensors to a memory to perform an initial iteration of training of a deep learning application, wherein the initial iteration is performed through execution of a plurality of kernels and, in response to each kernel being executed, tensors corresponding to the each kernel are used to execute the kernels, storing pattern information for allocating the tensors and the kernels to the memory in the initial iteration, and prefetching the tensors based on the pattern information to perform a next iteration of training of the deep learning application.

Abstract: An apparatus includes a memory configured to store data, and a processor. The processor configured to determine whether an access to the data is a local memory access; determine, based on a result of the determination of whether the access to the data is the local memory access, whether a page fault of the access occurred; determine, based on a result of the determination of whether the page fault occurred, whether the access is a remote access outside a socket; and perform, based on a result of the determination of whether the access is the remote access, the access to the data by copying the data onto a local memory.

Abstract: A processor-implemented method includes receiving a mapping instruction to map target data onto a process address space, in response to reception of the mapping instruction, marking an unused node in a tree that manages the process address space as a use node to reuse, and mapping the target data onto a virtual area in the process address space, wherein the tree manages the virtual area onto which the target data is mapped as the use node.

Abstract: An electronic device includes: a host processor configured to: generate a memory group allocated to an expanded virtual memory in response to receiving memory usage information; determine a target memory group comprising a page on which a page fault has occurred among memory groups allocated to the expanded virtual memory, based on the memory usage information; and migrate the target memory group from one of a host memory, an accelerator memory, and a storage device, which comprises the target memory group, to either one of the host memory and the accelerator memory in which the page fault has occurred; and an accelerator configured to perform an operation using the accelerator memory, wherein the expanded virtual memory is a virtual single address space using the host memory, the accelerator memory, and the storage device.

Abstract: An apparatus includes a memory configured to store data, and a processor. The processor configured to determine whether an access to the data is a local memory access; determine, based on a result of the determination of whether the access to the data is the local memory access, whether a page fault of the access occurred; determine, based on a result of the determination of whether the page fault occurred, whether the access is a remote access outside a socket; and perform, based on a result of the determination of whether the access is the remote access, the access to the data by copying the data onto a local memory.