Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.

Abstract: A method of controlling a storage device and a random access memory includes, when a size of write-requested data is greater than a threshold, writing the write-requested data in the storage device and writing an address of the storage device in which the write-requested data is written in the random access memory. When the size of the write-requested data is smaller than or equal to the threshold, the write-requested data is written in the random access memory. The threshold is correlated to a size greater than a size of an area allocated to store the address in the random access memory.

Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.

Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.

Abstract: A cache management apparatus includes an access pattern analysis unit configured to analyze an access pattern of each of one or more pages present in a first cache by monitoring data input/output (I/O) requests, a page class management unit configured to determine a class of each of the pages based on results of the analysis performed by the access pattern analysis unit, and a page transfer management unit configured to transfer one or more pages classified into a first class including pages to be transferred, to a second cache based on results of the determination performed by the page class management unit.

Abstract: A method of controlling a storage device and a random access memory includes, when a size of write-requested data is greater than a threshold, writing the write-requested data in the storage device and writing an address of the storage device in which the write-requested data is written in the random access memory. When the size of the write-requested data is smaller than or equal to the threshold, the write-requested data is written in the random access memory. The threshold is correlated to a size greater than a size of an area allocated to store the address in the random access memory.

Abstract: A storage device includes an interface circuit configured to communicate with an external device, nonvolatile memory devices forming a plurality of partitions, and a processing circuit configured to receive a write request, a key, and a value from the interface circuit, to generate a partition identifier and a sort identifier from the received key, to select one of the partitions using the partition identifier, and to sort indexes of accumulated keys corresponding to the selected partition using sort identifiers included in the indexes.

Abstract: A distributed data processing apparatus and method through hardware acceleration are provided. The data processing apparatus includes a mapping node including mapping units configured to process input data in parallel to generate and output mapping results. The data processing apparatus further includes a shuffle node including shuffle units and a memory buffer, the shuffle units configured to process the mapping results output from the mapping units in parallel to generate and output shuffle results, and the shuffle node configured to write the shuffle results output from the shuffle units in the memory buffer. The data processing apparatus further includes a merge node including merge units configured to merge the shuffle results written in the memory buffer to generate merging results.

Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.

Abstract: An apparatus and method for analyzing bottlenecks in a data distributed processing system. The apparatus includes a learning unit mining and learning bottleneck-feature association rules based on hardware information related to a bottleneck node, job configuration information related to a bottleneck causing job, and/or I/O information regarding a bottleneck causing task. Based on the bottleneck-feature association rules, a bottleneck cause analyzing unit detects a bottleneck node among multiple nodes performing tasks in the data distributed processing system, and analyzes the bottleneck cause.

Abstract: A cache management apparatus includes an access pattern analysis unit configured to analyze an access pattern of each of one or more pages present in a first cache by monitoring data input/output (I/O) requests, a page class management unit configured to determine a class of each of the pages based on results of the analysis performed by the access pattern analysis unit, and a page transfer management unit configured to transfer one or more pages classified into a first class including pages to be transferred, to a second cache based on results of the determination performed by the page class management unit.

Abstract: A technique for reducing a size of a snapshot boot image by adjusting a structure of the snapshot boot image based on an analysis of a computing system. In addition, according to the technique, the overriding portions of a snapshot based boot image may be loaded first in consideration of a time of use of the system, and therefore a boot time can be reduced.

Abstract: A workload-aware distributed data processing apparatus and method for processing large data based on hardware acceleration are provided. The data processing apparatus includes a memory buffer including partitions. The data processing apparatus further includes a partition unit configured to distribute a mapping result to the partitions based on a partition proportion scheme. The data processing apparatus further includes a reduce node configured to receive content of a corresponding one of the partitions, and perform a reduction operation on the content to generate a reduce result.

Abstract: Provided is a method of booting a computing system which performs boot image transmission and device initialization in parallel. For example, using an Internal RAM and direct memory access (DMA), hardware initialization and loading of boot image from a main storage medium to a main memory are performed in parallel, thereby reducing time spent on booting.

Abstract: Provided are a booting apparatus and method using a snapshot image. A snapshot image may be divided into a plurality of blocks. Each of the blocks may be stored in a nonvolatile memory in a compressed or non-compressed format. The snapshot image may be incrementally loaded in units of the blocks during booting. The loading and decompression of the blocks may be performed in parallel.

Abstract: Provided are a booting apparatus and method using a snapshot image. A snapshot image may be divided into a plurality of blocks. Each of the blocks may be stored in a nonvolatile memory in a compressed or non-compressed format. The snapshot image may be incrementally loaded in units of the blocks during booting. The loading and decompression of the blocks may be performed in parallel.

Abstract: Provided is a parallel I/O computing apparatus that includes a plurality of computing devices that may have different response characteristics depending on a number of parallel I/Os that are processed by the computing devices. The computing apparatus also includes an I/O dispatcher that distributes a different number of I/Os to one or more of the computing devices based on characteristics of the computing devices.

Abstract: An electronic apparatus in which a virtual machine (VM) runs like a physical device, a VM providing apparatus, and a method of transmitting and receiving a VM service using the electronic apparatus and the VM providing apparatus are provided. The electronic apparatus creates, when a VM is executed, a first domain zone having one or more VMs embedded in the electronic apparatus and a second domain zone having one or more VMs downloaded from a VM providing apparatus, and the control unit controls the first and second domain zones.

Abstract: A workload-aware distributed data processing apparatus and method for processing large data based on hardware acceleration are provided. The data processing apparatus includes a memory buffer including partitions. The data processing apparatus further includes a partition unit configured to distribute a mapping result to the partitions based on a partition proportion scheme. The data processing apparatus further includes a reduce node configured to receive content of a corresponding one of the partitions, and perform a reduction operation on the content to generate a reduce result.

Abstract: A distributed data processing apparatus and method through hardware acceleration are provided. The data processing apparatus includes a mapping node including mapping units configured to process input data in parallel to generate and output mapping results. The data processing apparatus further includes a shuffle node including shuffle units and a memory buffer, the shuffle units configured to process the mapping results output from the mapping units in parallel to generate and output shuffle results, and the shuffle node configured to write the shuffle results output from the shuffle units in the memory buffer. The data processing apparatus further includes a merge node including merge units configured to merge the shuffle results written in the memory buffer to generate merging results.