Samsung Electronics Co., Ltd.

Youngwoo Ahn

Inchoon Yeo

Ilho Lee

Jeongig Song

Kwonsik Kim

Changsung Lee

A resource allocation method and apparatus utilize the GPU resource efficiently by sorting the tasks using General Purpose GPU (GPGPU) into operations and combining the same operations into a request. The resource allocation method of a Graphic Processing Unit (GPU) according to the present disclosure includes receiving a task including at least one operation; storing the at least one operation in unit of request; merging data of same operations per request; and allocating GPU resource according to an execution order the request.

Resource allocation method and apparatus of GPU

A method of processing data using a Graphic Processing Unit (GPU) is provided. The method includes obtaining operand data and operator information to be applied to the operand data, partitioning the operand data by a channel element size unit of a texel of the GPU, transmitting an instruction which controls the GPU to return an operation result by performing an operation for the partitioned data and transmitting the partitioned data, and obtaining an operation result value from the GPU.

Method and apparatus for data processing using graphic processing unit

A terminal equipped with a central processing unit (CPU) and a graphics processing unit (GPU) performs a method for executing applications in adaptation to the load of the CPU and GPU. The application execution method of the present invention includes checking, when a code of application to be executed is input, workloads of a central processing unit and a graphics processing unit. The method also includes comparing the workloads of the central processing unit and the graphics processing unit with respective workload threshold values, and compiling the code according to comparison result. The method further includes generating a binary for executing the application at one of the central processing unit and the graphics processing unit using the compiled code, and executing the application with the generated binary. The method reduces application execution time by adjusting the workloads of the CPU and GPU according to the total workload, thereby saving power.

Growing community of inventors

Seoul, South Korea

Youngwoo Ahn