Abstract: A reconfigurable processor which merges an inner loop and an outer loop which are included in a nested loop and allocates the merged loop to processing elements in parallel, thereby reducing processing time to process the nested loop. The reconfigurable processor may extract loop execution frequency information from the inner loop and the outer loop of the nested loop, and may merge the inner loop and the outer loop based on the extracted loop execution frequency information.

Abstract: Provided is a processor with a heterogeneous clustered architecture. The processor comprises a first cluster comprising a first functional unit configured to process a first type of instruction, and a register whose I/O ports are connected to I/O ports of the functional unit; and a second cluster comprising a second functional unit configured to process the first type of instruction and second type of instruction, and a second register whose I/O ports are connected to I/O ports of the second functional unit.

Abstract: An apparatus and method for dynamically determining the execution mode of a reconfigurable array are provided. Performance information of a loop may be obtained before and/or during the execution of the loop. The performance information may be used to determine whether to operate the apparatus in a very long instruction word (VLIW) mode or in a coarse grained array (CGA) mode.

Abstract: An apparatus for detecting a source code error location in a mixed-mode program is disclosed. The apparatus may include a compiler, a mapping table generator, a simulator, a comparison data generator and an error location detector. The apparatus extracts low-level data while simulating a verification program and while simulating a reference program. The low-level data is mapped to mapping tables for a verification program and a reference program, and by comparing the tables it is determined if there is an error in the mixed-mode program and if so, where.

Abstract: Provided is a technique for improving the transfer latency of vector register file data when an interrupt is generated. According to an aspect, when interrupt occurs, a core determines whether to store vector register file data currently being executed in a first memory or in a second memory based on whether or not the first memory can store the vector register file data therein. In response to not being able to store the vector register file data in the first memory, a data transfer unit, which is implemented as hardware, is provided to store vector register file data in the second memory.

Abstract: A technique for minimizing overhead caused by copying or moving a value from one cluster to another cluster is provided. A number of operations, for example, a mov operation for moving or copying a value from one cluster to another cluster and a normal operation may be executed concurrently. Accordingly, access to a register file outside of the cluster may be reduced and the performance of code may be improved.

Abstract: A technology for executing an external operation from a software-pipelined loop is provided. Code performance efficiency can be improved by overlapping the execution of the external operations of the loop and the iterations of the loop.

Abstract: Provided is an apparatus and method capable of processing code to which a software pipelining is not applicable, in a CGA mode. The apparatus may include a processing unit that has a very long instruction word (VLIW) mode and a coarse-grained array (CGA) mode, and an adjusting unit configured to detect a target region to which software pipelining is not applicable, in code to be executed by the processing unit. The adjusting unit may selectively map the detected target region to one of the VLIW mode and the CGA mode according to a schedule length of the detected target region.

Abstract: An apparatus and method for dynamically determining the execution mode of a reconfigurable array are provided. Performance information of a loop may be obtained before and/or during the execution of the loop. The performance information may be used to determine whether to operate the apparatus in a very long instruction word (VLIW) mode or in a coarse grained array (CGA) mode.

Abstract: A reconfigurable processor which merges an inner loop and an outer loop which are included in a nested loop and allocates the merged loop to processing elements in parallel, thereby reducing processing time to process the nested loop. The reconfigurable processor may extract loop execution frequency information from the inner loop and the outer loop of the nested loop, and may merge the inner loop and the outer loop based on the extracted loop execution frequency information.

Abstract: Provided are a reconfigurable processor, which is capable of reducing the probability of an incorrect computation by analyzing the dependence between memory access instructions and allocating the memory access instructions between a plurality of processing elements (PEs) based on the results of the analysis, and a method of controlling the reconfigurable processor. The reconfigurable processor extracts an execution trace from simulation results, and analyzes the memory dependence between instructions included in different iterations based on parts of the execution trace of memory access instructions.

Abstract: A method to transfer a plurality of data stored in a memory using one instruction. In a memory including at least two regions to which the addresses are assigned respectively, data are allocated to the addresses in sequence, and the allocated data are transferred using one instruction. At least one block is generated, which transfers data using one instruction, and it is instructed to include the data in the at least one block. The data in the block are linked with each other, and the number of paths linking two data is calculated with respect to the at least one block. The data are linked using shortest paths in consideration of the number of the linking paths, and the data are allocated by the addresses using the shortest paths.

Abstract: A method to transfer a plurality of data stored in a memory using one instruction. In a memory including at least two regions to which the addresses are assigned respectively, data are allocated to the addresses in sequence, and the allocated data are transferred using one instruction. At least one block is generated, which transfers data using one instruction, and it is instructed to include the data in the at least one block. The data in the block are linked with each other, and the number of paths linking two data is calculated with respect to the at least one block. The data are linked using shortest paths in consideration of the number of the linking paths, and the data are allocated by the addresses using the shortest paths.