-
公开(公告)号:US20190228344A1
公开(公告)日:2019-07-25
申请号:US16013847
申请日:2018-06-20
Inventor: Seung-Tae HONG , Young-Joo KIM , Jeong-Si KIM , Jin-Ho SEOL
Abstract: Disclosed herein are an apparatus and method for adaptively accelerating a BLAS operation based on a GPU. The apparatus for adaptively accelerating a BLAS operation based on a GPU includes a BLAS operation acceleration unit for setting optimal OpenCL parameters using machine-learning data attribute information and OpenCL device information and for creating a kernel in a binary format by compiling kernel source code; an OpenCL execution unit for creating an OpenCL buffer for a BLAS operation using information about an OpenCL execution environment and the optimal OpenCL parameters and for accelerating machine learning in an embedded system in such a way that a GPU that is capable of accessing the created OpenCL buffer performs the BLAS operation using the kernel, and an accelerator application unit for returning the result of the BLAS operation to a machine-learning algorithm.
-
公开(公告)号:US20180275742A1
公开(公告)日:2018-09-27
申请号:US15690164
申请日:2017-08-29
Inventor: Jin-Ho SEOL , Jeong-Si KIM , Gap-Joo NA , Chae-Deok LIM , Yung-Joon JUNG
CPC classification number: G06F1/3293 , G06F1/3206 , G06F1/324 , G06F1/3296 , G06F9/4893 , G06F9/5094
Abstract: Disclosed herein are an apparatus and method for controlling a governor based on a heterogeneous multicore system. The apparatus includes a heterogeneous core cluster unit for running any one of a first core cluster for high-performance operation and a second core cluster for low-power operation by switching therebetween; a governor-setting unit for generating operation setting information of a governor for controlling operation of the first core cluster and second core cluster; and a governor control unit for controlling operation of one or more governors based on the operation setting information.
-